Faisal Mahmood

Paul Pu Liang, Yun Cheng, Xiang Fan et al. · cmu, princeton

The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities. Despite these empirical advances, there remain fundamental research questions: How can we quantify the interactions that are necessary to solve a multimodal task? Subsequently, what are the most suitable multimodal models to capture these interactions? To answer these questions, we propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. We term these three measures as the PID statistics of a multimodal distribution (or PID for short), and introduce two new estimators for these PID statistics that scale to high-dimensional distributions. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks where PID estimations are compared with human annotations. Finally, we demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies engaging with domain experts in pathology, mood prediction, and robotic perception where our framework helps to recommend strong multimodal models for each application.

Guillaume Jaume, Anurag Vaidya, Richard Chen et al.

Integrating whole-slide images (WSIs) and bulk transcriptomics for predicting patient survival can improve our understanding of patient prognosis. However, this multimodal task is particularly challenging due to the different nature of these data: WSIs represent a very high-dimensional spatial description of a tumor, while bulk transcriptomics represent a global description of gene expression levels within that tumor. In this context, our work aims to address two key challenges: (1) how can we tokenize transcriptomics in a semantically meaningful and interpretable way?, and (2) how can we capture dense multimodal interactions between these two modalities? Specifically, we propose to learn biological pathway tokens from transcriptomics that can encode specific cellular functions. Together with histology patch tokens that encode the different morphological patterns in the WSI, we argue that they form appropriate reasoning units for downstream interpretability analyses. We propose fusing both modalities using a memory-efficient multimodal Transformer that can model interactions between pathway and histology patch tokens. Our proposed model, SURVPATH, achieves state-of-the-art performance when evaluated against both unimodal and multimodal baselines on five datasets from The Cancer Genome Atlas. Our interpretability framework identifies key multimodal prognostic factors, and, as such, can provide valuable insights into the interaction between genotype and phenotype, enabling a deeper understanding of the underlying biological mechanisms at play. We make our code public at: https://github.com/ajv012/SurvPath.

Ming Y. Lu, Bowen Chen, Andrew Zhang et al.

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In this paper we present MI-Zero, a simple and intuitive framework for unleashing the zero-shot transfer capabilities of contrastively aligned image and text models on gigapixel histopathology whole slide images, enabling multiple downstream diagnostic tasks to be carried out by pretrained encoders without requiring any additional labels. MI-Zero reformulates zero-shot transfer under the framework of multiple instance learning to overcome the computational challenge of inference on extremely large images. We used over 550k pathology reports and other available in-domain text corpora to pre-train our text encoder. By effectively leveraging strong pre-trained encoders, our best model pretrained on over 33k histopathology image-caption pairs achieves an average median zero-shot accuracy of 70.2% across three different real-world cancer subtyping tasks. Our code is available at: https://github.com/mahmoodlab/MI-Zero.

Arinbjorn Kolbeinsson, Kyle O'Brien, Tianjin Huang et al.

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories -- Knowledge Editing, Model Compression, and Machine Unlearning. Our results from 310 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. All of our code is public: https://github.com/hartvigsen-group/composable-interventions.

Guillaume Jaume, Anurag Vaidya, Andrew Zhang et al.

Developing self-supervised learning (SSL) models that can learn universal and transferable representations of H&E gigapixel whole-slide images (WSIs) is becoming increasingly valuable in computational pathology. These models hold the potential to advance critical tasks such as few-shot classification, slide retrieval, and patient stratification. Existing approaches for slide representation learning extend the principles of SSL from small images (e.g., 224 x 224 patches) to entire slides, usually by aligning two different augmentations (or views) of the slide. Yet the resulting representation remains constrained by the limited clinical and biological diversity of the views. Instead, we postulate that slides stained with multiple markers, such as immunohistochemistry, can be used as different views to form a rich task-agnostic training signal. To this end, we introduce Madeleine, a multimodal pretraining strategy for slide representation learning. Madeleine is trained with a dual global-local cross-stain alignment objective on large cohorts of breast cancer samples (N=4,211 WSIs across five stains) and kidney transplant samples (N=12,070 WSIs across four stains). We demonstrate the quality of slide representations learned by Madeleine on various downstream evaluations, ranging from morphological and molecular classification to prognostic prediction, comprising 21 tasks using 7,299 WSIs from multiple medical centers. Code is available at https://github.com/mahmoodlab/MADELEINE.

Richard J. Chen, Chengkuan Chen, Yicong Li et al.

Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384384). For gigapixel whole-slide imaging (WSI) in computational pathology, WSIs can be as large as 150000x150000 pixels at 20X magnification and exhibit a hierarchical structure of visual tokens across varying resolutions: from 16x16 images capture spatial patterns among cells, to 4096x4096 images characterizing interactions within the tissue microenvironment. We introduce a new ViT architecture called the Hierarchical Image Pyramid Transformer (HIPT), which leverages the natural hierarchical structure inherent in WSIs using two levels of self-supervised learning to learn high-resolution image representations. HIPT is pretrained across 33 cancer types using 10,678 gigapixel WSIs, 408,218 4096x4096 images, and 104M 256x256 images. We benchmark HIPT representations on 9 slide-level tasks, and demonstrate that: 1) HIPT with hierarchical pretraining outperforms current state-of-the-art methods for cancer subtyping and survival prediction, 2) self-supervised ViTs are able to model important inductive biases about the hierarchical structure of phenotypes in the tumor microenvironment.

Anurag J. Vaidya, Felix Meissen, Daniel C. Castro et al.

Digitized histopathology analysis involves complex, time-intensive workflows and specialized expertise, limiting its accessibility. We introduce NOVA, an agentic framework that translates scientific queries into executable analysis pipelines by iteratively generating and running Python code. NOVA integrates 49 domain-specific tools (e.g., nuclei segmentation, whole-slide encoding) built on open-source software, and can also create new tools ad hoc. To evaluate such systems, we present SlideQuest, a 90-question benchmark -- verified by pathologists and biomedical scientists -- spanning data processing, quantitative analysis, and hypothesis testing. Unlike prior biomedical benchmarks focused on knowledge recall or diagnostic QA, SlideQuest demands multi-step reasoning, iterative coding, and computational problem solving. Quantitative evaluation shows NOVA outperforms coding-agent baselines, and a pathologist-verified case study links morphology to prognostically relevant PAM50 subtypes, demonstrating its scalable discovery potential.

Daniel Shao, Joel Runevic, Richard J. Chen et al.

Multiple Instance Learning (MIL) is the predominant framework for classifying gigapixel whole-slide images in computational pathology. MIL follows a sequence of 1) extracting patch features, 2) applying a linear layer to obtain task-specific patch features, and 3) aggregating the patches into a slide feature for classification. While substantial efforts have been devoted to optimizing patch feature extraction and aggregation, none have yet addressed the second point, the critical layer which transforms general-purpose features into task-specific features. We hypothesize that this layer constitutes an overlooked performance bottleneck and that stronger representations can be achieved with a low-rank transformation tailored to each patch's phenotype, yielding synergistic effects with any of the existing MIL approaches. To this end, we introduce MAMMOTH, a parameter-efficient, multi-head mixture of experts module designed to improve the performance of any MIL model with minimal alterations to the total number of parameters. Across eight MIL methods and 19 different classification tasks, we find that such task-specific transformation has a larger effect on performance than the choice of aggregation method. For instance, when equipped with MAMMOTH, even simple methods such as max or mean pooling attain higher average performance than any method with the standard linear layer. Overall, MAMMOTH improves performance in 130 of the 152 examined configurations, with an average $+3.8\%$ change in performance. Code is available at https://github.com/mahmoodlab/mammoth.

Richard J. Chen, Tong Ding, Ming Y. Lu et al.

Tissue phenotyping is a fundamental computational pathology (CPath) task in learning objective characterizations of histopathologic biomarkers in anatomic pathology. However, whole-slide imaging (WSI) poses a complex computer vision problem in which the large-scale image resolutions of WSIs and the enormous diversity of morphological phenotypes preclude large-scale data annotation. Current efforts have proposed using pretrained image encoders with either transfer learning from natural image datasets or self-supervised pretraining on publicly-available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using over 100 million tissue patches from over 100,000 diagnostic haematoxylin and eosin-stained WSIs across 20 major tissue types, and evaluated on 33 representative CPath clinical tasks in CPath of varying diagnostic difficulties. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree code classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient AI models that can generalize and transfer to a gamut of diagnostically-challenging tasks and clinical workflows in anatomic pathology.

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson et al.

The accelerated adoption of digital pathology and advances in deep learning have enabled the development of powerful models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain and the model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text, and notably over 1.17 million image-caption pairs via task-agnostic pretraining. Evaluated on a suite of 13 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving either or both histopathology images and text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.

Iain Carmichael, Andrew H. Song, Richard J. Chen et al.

Supervised learning tasks such as cancer survival prediction from gigapixel whole slide images (WSIs) are a critical challenge in computational pathology that requires modeling complex features of the tumor microenvironment. These learning tasks are often solved with deep multi-instance learning (MIL) models that do not explicitly capture intratumoral heterogeneity. We develop a novel variance pooling architecture that enables a MIL model to incorporate intratumoral heterogeneity into its predictions. Two interpretability tools based on representative patches are illustrated to probe the biological signals captured by these models. An empirical study with 4,479 gigapixel WSIs from the Cancer Genome Atlas shows that adding variance pooling onto MIL frameworks improves survival prediction performance for five cancer types.

Imaad Zaffar, Guillaume Jaume, Nasir Rajpoot et al.

Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs' limited RAM. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. Experiments on the SICAPv2 dataset show that our approach outperforms MIL without augmentation and is on par with traditional patch-level augmentation for MIL training while being substantially faster.

Andrew H. Song, Mane Williams, Drew F. K. Williamson et al.

Human tissue and its constituent cells form a microenvironment that is fundamentally three-dimensional (3D). However, the standard-of-care in pathologic diagnosis involves selecting a few two-dimensional (2D) sections for microscopic evaluation, risking sampling bias and misdiagnosis. Diverse methods for capturing 3D tissue morphologies have been developed, but they have yet had little translation to clinical practice; manual and computational evaluations of such large 3D data have so far been impractical and/or unable to provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy or microcomputed tomography and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting the value of capturing larger extents of heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, MAMBA provides a general and efficient framework for 3D weakly supervised learning for clinical decision support and can help to reveal novel 3D morphological biomarkers for prognosis and therapeutic response.

Andrew Zhang, Tong Ding, Sophia J. Wagner et al.

Modern medicine generates vast multimodal data across siloed systems, yet no existing model integrates the full breadth and temporal depth of the clinical record into a unified patient representation. We introduce Apollo, a multimodal temporal foundation model trained and evaluated on over three decades of longitudinal hospital records from a major US hospital system, composed of 25 billion records from 7.2 million patients, representing 28 distinct medical modalities and 12 major medical specialties. Apollo learns a unified representation space integrating over 100 thousand unique medical events in our clinical vocabulary as well as images and clinical text. This "atlas of medical concepts" forms a computational substrate for modeling entire patient care journeys comprised of sequences of structured and unstructured events, which are compressed by Apollo into virtual patient representations. To assess the potential of these whole-patient representations, we created 322 prognosis and retrieval tasks from a held-out test set of 1.4 million patients. We demonstrate the generalized clinical forecasting potential of Apollo embeddings, including predicting new disease onset risk up to five years in advance (95 tasks), disease progression (78 tasks), treatment response (59 tasks), risk of treatment-related adverse events (17 tasks), and hospital operations endpoints (12 tasks). Using feature attribution techniques, we show that model predictions align with clinically-interpretable multimodal biomarkers. We evaluate semantic similarity search on 61 retrieval tasks, and moreover demonstrate the potential of Apollo as a multimodal medical search engine using text and image queries. Together, these modeling capabilities establish the foundation for computable medicine, where the full context of patient care becomes accessible to computational reasoning.

Guillaume Jaume, Lukas Oldenburg, Anurag Vaidya et al.

Self-supervised learning (SSL) has been successful in building patch embeddings of small histology images (e.g., 224x224 pixels), but scaling these models to learn slide embeddings from the entirety of giga-pixel whole-slide images (WSIs) remains challenging. Here, we leverage complementary information from gene expression profiles to guide slide representation learning using multimodal pre-training. Expression profiles constitute highly detailed molecular descriptions of a tissue that we hypothesize offer a strong task-agnostic training signal for learning slide embeddings. Our slide and expression (S+E) pre-training strategy, called Tangle, employs modality-specific encoders, the outputs of which are aligned via contrastive learning. Tangle was pre-trained on samples from three different organs: liver (n=6,597 S+E pairs), breast (n=1,020), and lung (n=1,012) from two different species (Homo sapiens and Rattus norvegicus). Across three independent test datasets consisting of 1,265 breast WSIs, 1,946 lung WSIs, and 4,584 liver WSIs, Tangle shows significantly better few-shot performance compared to supervised and SSL baselines. When assessed using prototype-based classification and slide retrieval, Tangle also shows a substantial performance improvement over all baselines. Code available at https://github.com/mahmoodlab/TANGLE.

Muhammad Shaban, Yuzhou Chang, Huaying Qiu et al.

Foundation models have begun to transform image analysis by acting as pretrained generalist backbones that can be adapted to many tasks even when post-training data are limited, yet their impact on spatial proteomics, imaging that maps proteins at single-cell resolution, remains limited. Here, we introduce KRONOS, a foundation model built for spatial proteomics. KRONOS was trained in a self-supervised manner on over 47 million image patches covering 175 protein markers, 16 tissue types, and 8 fluorescence-based imaging platforms. We introduce key architectural adaptations to address the high-dimensional, multi-channel, and heterogeneous nature of multiplex imaging. We demonstrate that KRONOS learns biologically meaningful representations across multiple scales, ranging from cellular and microenvironment to tissue levels, enabling it to address diverse downstream tasks, including cell phenotyping, region classification, and patient stratification. Evaluated across 11 independent cohorts, KRONOS achieves state-of-the-art performance across cell phenotyping, treatment response prediction, and retrieval tasks, and is highly data-efficient. KRONOS also introduces the paradigm of segmentation-free patch-level processing for efficient and scalable spatial proteomics analysis, allowing cross-institutional comparisons, and as an image reverse search engine for spatial patterns. Together, these results position KRONOS as a flexible and scalable tool for spatial proteomics. The model is publicly accessible at https://github.com/mahmoodlab/KRONOS.

Daniel Shao, Richard J. Chen, Andrew H. Song et al.

Multiple Instance Learning (MIL) is a cornerstone approach in computational pathology (CPath) for generating clinically meaningful slide-level embeddings from gigapixel tissue images. However, MIL often struggles with small, weakly supervised clinical datasets. In contrast to fields such as NLP and conventional computer vision, where transfer learning is widely used to address data scarcity, the transferability of MIL models remains poorly understood. In this study, we systematically evaluate the transfer learning capabilities of pretrained MIL models by assessing 11 models across 21 pretraining tasks for morphological and molecular subtype prediction. Our results show that pretrained MIL models, even when trained on different organs than the target task, consistently outperform models trained from scratch. Moreover, pretraining on pancancer datasets enables strong generalization across organs and tasks, outperforming slide foundation models while using substantially less pretraining data. These findings highlight the robust adaptability of MIL models and demonstrate the benefits of leveraging transfer learning to boost performance in CPath. Lastly, we provide a resource which standardizes the implementation of MIL models and collection of pretrained model weights on popular CPath tasks, available at https://github.com/mahmoodlab/MIL-Lab

Andrew H. Song, Guillaume Jaume, Drew F. K. Williamson et al.

Advances in digitizing tissue slides and the fast-paced progress in artificial intelligence, including deep learning, have boosted the field of computational pathology. This field holds tremendous potential to automate clinical diagnosis, predict patient prognosis and response to therapy, and discover new morphological biomarkers from tissue images. Some of these artificial intelligence-based systems are now getting approved to assist clinical diagnosis; however, technical barriers remain for their widespread clinical adoption and integration as a research tool. This Review consolidates recent methodological advances in computational pathology for predicting clinical end points in whole-slide images and highlights how these developments enable the automation of clinical practice and the discovery of new biomarkers. We then provide future perspectives as the field expands into a broader range of clinical and research tasks with increasingly diverse modalities of clinical data.

Guillaume Jaume, Paul Doucet, Andrew H. Song et al.

Spatial transcriptomics enables interrogating the molecular composition of tissue with ever-increasing resolution and sensitivity. However, costs, rapidly evolving technology, and lack of standards have constrained computational methods in ST to narrow tasks and small cohorts. In addition, the underlying tissue morphology, as reflected by H&E-stained whole slide images (WSIs), encodes rich information often overlooked in ST studies. Here, we introduce HEST-1k, a collection of 1,229 spatial transcriptomic profiles, each linked to a WSI and extensive metadata. HEST-1k was assembled from 153 public and internal cohorts encompassing 26 organs, two species (Homo Sapiens and Mus Musculus), and 367 cancer samples from 25 cancer types. HEST-1k processing enabled the identification of 2.1 million expression--morphology pairs and over 76 million nuclei. To support its development, we additionally introduce the HEST-Library, a Python package designed to perform a range of actions with HEST samples. We test HEST-1k and Library on three use cases: (1) benchmarking foundation models for pathology (HEST-Benchmark), (2) biomarker exploration, and (3) multimodal representation learning. HEST-1k, HEST-Library, and HEST-Benchmark can be freely accessed at https://github.com/mahmoodlab/hest.

Chengkuan Chen, Ming Y. Lu, Drew F. K. Williamson et al.

The expanding adoption of digital pathology has enabled the curation of large repositories of histology whole slide images (WSIs), which contain a wealth of information. Similar pathology image search offers the opportunity to comb through large historical repositories of gigapixel WSIs to identify cases with similar morphological features and can be particularly useful for diagnosing rare diseases, identifying similar cases for predicting prognosis, treatment outcomes, and potential clinical trial success. A critical challenge in developing a WSI search and retrieval system is scalability, which is uniquely challenging given the need to search a growing number of slides that each can consist of billions of pixels and are several gigabytes in size. Such systems are typically slow and retrieval speed often scales with the size of the repository they search through, making their clinical adoption tedious and are not feasible for repositories that are constantly growing. Here we present Fast Image Search for Histopathology (FISH), a histology image search pipeline that is infinitely scalable and achieves constant search speed that is independent of the image database size while being interpretable and without requiring detailed annotations. FISH uses self-supervised deep learning to encode meaningful representations from WSIs and a Van Emde Boas tree for fast search, followed by an uncertainty-based ranking algorithm to retrieve similar WSIs. We evaluated FISH on multiple tasks and datasets with over 22,000 patient cases spanning 56 disease subtypes. We additionally demonstrate that FISH can be used to assist with the diagnosis of rare cancer types where sufficient cases may not be available to train traditional supervised deep models. FISH is available as an easy-to-use, open-source software package (https://github.com/mahmoodlab/FISH).

Richard J. Chen, Ming Y. Lu, Muhammad Shaban et al.

Cancer prognostication is a challenging task in computational pathology that requires context-aware representations of histology features to adequately infer patient survival. Despite the advancements made in weakly-supervised deep learning, many approaches are not context-aware and are unable to model important morphological feature interactions between cell identities and tissue types that are prognostic for patient survival. In this work, we present Patch-GCN, a context-aware, spatially-resolved patch-based graph convolutional network that hierarchically aggregates instance-level histology features to model local- and global-level topological structures in the tumor microenvironment. We validate Patch-GCN with 4,370 gigapixel WSIs across five different cancer types from the Cancer Genome Atlas (TCGA), and demonstrate that Patch-GCN outperforms all prior weakly-supervised approaches by 3.58-9.46%. Our code and corresponding models are publicly available at https://github.com/mahmoodlab/Patch-GCN.

Kutsev Bengisu Ozyoruk, Guliz Irem Gokceler, Gulfize Coskun et al.

Deep learning techniques hold promise to develop dense topography reconstruction and pose estimation methods for endoscopic videos. However, currently available datasets do not support effective quantitative benchmarking. In this paper, we introduce a comprehensive endoscopic SLAM dataset consisting of 3D point cloud data for six porcine organs, capsule and standard endoscopy recordings as well as synthetically generated data. A Panda robotic arm, two commercially available capsule endoscopes, two conventional endoscopes with different camera properties, and two high precision 3D scanners were employed to collect data from 8 ex-vivo porcine gastrointestinal (GI)-tract organs. In total, 35 sub-datasets are provided with 6D pose ground truth for the ex-vivo part: 18 sub-dataset for colon, 12 sub-datasets for stomach and 5 sub-datasets for small intestine, while four of these contain polyp-mimicking elevations carried out by an expert gastroenterologist. Synthetic capsule endoscopy frames from GI-tract with both depth and pose annotations are included to facilitate the study of simulation-to-real transfer learning algorithms. Additionally, we propound Endo-SfMLearner, an unsupervised monocular depth and pose estimation method that combines residual networks with spatial attention module in order to dictate the network to focus on distinguishable and highly textured tissue regions. The proposed approach makes use of a brightness-aware photometric loss to improve the robustness under fast frame-to-frame illumination changes. To exemplify the use-case of the EndoSLAM dataset, the performance of Endo-SfMLearner is extensively compared with the state-of-the-art. The codes and the link for the dataset are publicly available at https://github.com/CapsuleEndoscope/EndoSLAM. A video demonstrating the experimental setup and procedure is accessible through https://www.youtube.com/watch?v=G_LCe0aWWdQ.

Yasin Almalioglu, Kutsev Bengisu Ozyoruk, Abdulkadir Gokce et al.

Although wireless capsule endoscopy is the preferred modality for diagnosis and assessment of small bowel diseases, the poor camera resolution is a substantial limitation for both subjective and automated diagnostics. Enhanced-resolution endoscopy has shown to improve adenoma detection rate for conventional endoscopy and is likely to do the same for capsule endoscopy. In this work, we propose and quantitatively validate a novel framework to learn a mapping from low-to-high resolution endoscopic images. We combine conditional adversarial networks with a spatial attention block to improve the resolution by up to factors of 8x, 10x, 12x, respectively. Quantitative and qualitative studies performed demonstrate the superiority of EndoL2H over state-of-the-art deep super-resolution methods DBPN, RCAN and SRGAN. MOS tests performed by 30 gastroenterologists qualitatively assess and confirm the clinical relevance of the approach. EndoL2H is generally applicable to any endoscopic capsule system and has the potential to improve diagnosis and better harness computational approaches for polyp detection and characterization. Our code and trained models are available at https://github.com/CapsuleEndoscope/EndoL2H.

Tong Ding, Sophia J. Wagner, Andrew H. Song et al.

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose TITAN, a multimodal whole slide foundation model pretrained using 335,645 WSIs via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative AI copilot for pathology. Without any finetuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that TITAN outperforms both ROI and slide foundation models across machine learning settings such as linear probing, few-shot and zero-shot classification, rare cancer retrieval and cross-modal retrieval, and pathology report generation.

Andrew H. Song, Richard J. Chen, Tong Ding et al.

Representation learning of pathology whole-slide images (WSIs) has been has primarily relied on weak supervision with Multiple Instance Learning (MIL). However, the slide representations resulting from this approach are highly tailored to specific clinical tasks, which limits their expressivity and generalization, particularly in scenarios with limited data. Instead, we hypothesize that morphological redundancy in tissue can be leveraged to build a task-agnostic slide representation in an unsupervised fashion. To this end, we introduce PANTHER, a prototype-based approach rooted in the Gaussian mixture model that summarizes the set of WSI patches into a much smaller set of morphological prototypes. Specifically, each patch is assumed to have been generated from a mixture distribution, where each mixture component represents a morphological exemplar. Utilizing the estimated mixture parameters, we then construct a compact slide representation that can be readily used for a wide range of downstream tasks. By performing an extensive evaluation of PANTHER on subtyping and survival tasks using 13 datasets, we show that 1) PANTHER outperforms or is on par with supervised MIL baselines and 2) the analysis of morphological prototypes brings new qualitative and quantitative insights into model interpretability.

Anurag Vaidya, Andrew Zhang, Guillaume Jaume et al.

Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances, foundation models are still limited in their ability to encode the entire gigapixel whole-slide images without additional training and often lack complementary multimodal data. Here, we introduce Threads, a slide-level foundation model capable of generating universal representations of whole-slide images of any size. Threads was pre-trained using a multimodal learning approach on a diverse cohort of 47,171 hematoxylin and eosin (H&E)-stained tissue sections, paired with corresponding genomic and transcriptomic profiles - the largest such paired dataset to be used for foundation model development to date. This unique training paradigm enables Threads to capture the tissue's underlying molecular composition, yielding powerful representations applicable to a wide array of downstream tasks. In extensive benchmarking across 54 oncology tasks, including clinical subtyping, grading, mutation prediction, immunohistochemistry status determination, treatment response prediction, and survival prediction, Threads outperformed all baselines while demonstrating remarkable generalizability and label efficiency. It is particularly well suited for predicting rare events, further emphasizing its clinical utility. We intend to make the model publicly available for the broader community.

Carlijn Lems, Sander Moonemans, Natálie Klubíčková et al.

Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent benchmarking to assess its potential in assisting pathologists in routine diagnostics. We created DALPHIN, the first multicentric open benchmark for pathology AI copilots, comprising 1236 images from 300 cases, spanning 130 rare to common diagnoses, 6 countries, and 14 subspecialties. The DALPHIN design and dataset are introduced alongside a human performance benchmark of 31 pathologists from 10 countries with varying expertise. We report results for two general-purpose (GPT-5, Gemini 2.5 Pro) and one pathology-specific copilot (PathChat+) for sequential and independent answer generation. We observed no statistically significant difference from expert-level performance in four of six tasks for PathChat, 2/6 tasks for Gemini, and 1/6 tasks for GPT. DALPHIN is publicly released with sequestered, indirectly accessible ground truth to foster robust and enduring benchmarking. Data, methods, and the evaluation platform are accessible through dalphin.grand-challenge.org.

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson et al.

The field of computational pathology has witnessed remarkable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders. However, despite the explosive growth of generative artificial intelligence (AI), there has been limited study on building general purpose, multimodal AI assistants tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology using an in-house developed foundational vision encoder pretrained on 100 million histology images from over 100,000 patient cases and 1.18 million pathology image-caption pairs. The vision encoder is then combined with a pretrained large language model and the whole system is finetuned on over 250,000 diverse disease agnostic visual language instructions. We compare PathChat against several multimodal vision language AI assistants as well as GPT4V, which powers the commercially available multimodal general purpose AI assistant ChatGPT-4. When relevant clinical context is provided with the histology image, PathChat achieved a diagnostic accuracy of 87% on multiple-choice questions based on publicly available cases of diverse tissue origins and disease models. Additionally, using open-ended questions and human expert evaluation, we found that overall PathChat produced more accurate and pathologist-preferable responses to diverse queries related to pathology. As an interactive and general vision language AI assistant that can flexibly handle both visual and natural language inputs, PathChat can potentially find impactful applications in pathology education, research, and human-in-the-loop clinical decision making.

Andrew Zhang, Guillaume Jaume, Anurag Vaidya et al.

Advances in foundation modeling have reshaped computational pathology. However, the increasing number of available models and lack of standardized benchmarks make it increasingly complex to assess their strengths, limitations, and potential for further development. To address these challenges, we introduce a new suite of software tools for whole-slide image processing, foundation model benchmarking, and curated publicly available tasks. We anticipate that these resources will promote transparency, reproducibility, and continued progress in the field.

Chengkuan Chen, Luca L. Weishaupt, Drew F. K. Williamson et al.

Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.

Cristina Almagro-Pérez, Andrew H. Song, Luca Weishaupt et al.

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology-transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://vortex-demo.github.io/

Konstantin Hemker, Andrew H. Song, Cristina Almagro-Pérez et al.

Spatial transcriptomics (ST) provides spatially resolved measurements of gene expression, enabling characterization of the molecular landscape of human tissue beyond histological assessment as well as localized readouts that can be aligned with morphology. Concurrently, the success of multimodal foundation models that integrate vision with complementary modalities suggests that morphomolecular coupling between local expression and morphology can be systematically used to improve histological representations themselves. We introduce Spatial Expression-Aligned Learning (SEAL), a vision-omics self-supervised learning framework that infuses localized molecular information into pathology vision encoders. Rather than training new encoders from scratch, SEAL is designed as a parameter-efficient vision-omics finetuning method that can be flexibly applied to widely used pathology foundation models. We instantiate SEAL by training on over 700,000 paired gene expression spot-tissue region examples spanning tumor and normal samples from 14 organs. Tested across 38 slide-level and 15 patch-level downstream tasks, SEAL provides a drop-in replacement for pathology foundation models that consistently improves performance over widely used vision-only and ST prediction baselines on slide-level molecular status, pathway activity, and treatment response prediction, as well as patch-level gene expression prediction tasks. Additionally, SEAL encoders exhibit robust domain generalization on out-of-distribution evaluations and enable new cross-modal capabilities such as gene-to-image retrieval. Our work proposes a general framework for ST-guided finetuning of pathology foundation models, showing that augmenting existing models with localized molecular supervision is an effective and practical step for improving visual representations and expanding their cross-modal utility.

Rajarshi Ghosh, Abhay Gupta, Hudson McBride et al.

Large language models (LLMs) are increasingly deployed in clinical decision support, yet subtle demographic cues can influence their reasoning. Prior work has documented disparities in outputs across patient groups, but little is known about how internal reasoning shifts under controlled demographic changes. We introduce MEDEQUALQA, a counterfactual benchmark that perturbs only patient pronouns (he/him, she/her, they/them) while holding critical symptoms and conditions (CSCs) constant. Each clinical vignette is expanded into single-CSC ablations, producing three parallel datasets of approximately 23,000 items each (69,000 total). We evaluate a GPT-4.1 model and compute Semantic Textual Similarity (STS) between reasoning traces to measure stability across pronoun variants. Our results show overall high similarity (mean STS >0.80), but reveal consistent localized divergences in cited risk factors, guideline anchors, and differential ordering, even when final diagnoses remain unchanged. Our error analysis highlights certain cases in which the reasoning shifts, underscoring clinically relevant bias loci that may cascade into inequitable care. MEDEQUALQA offers a controlled diagnostic setting for auditing reasoning stability in medical AI.

Andrew H. Song, Richard J. Chen, Guillaume Jaume et al.

Multimodal survival methods combining gigapixel histology whole-slide images (WSIs) and transcriptomic profiles are particularly promising for patient prognostication and stratification. Current approaches involve tokenizing the WSIs into smaller patches (>10,000 patches) and transcriptomics into gene groups, which are then integrated using a Transformer for predicting outcomes. However, this process generates many tokens, which leads to high memory requirements for computing attention and complicates post-hoc interpretability analyses. Instead, we hypothesize that we can: (1) effectively summarize the morphological content of a WSI by condensing its constituting tokens using morphological prototypes, achieving more than 300x compression; and (2) accurately characterize cellular functions by encoding the transcriptomic profile with biological pathway prototypes, all in an unsupervised fashion. The resulting multimodal tokens are then processed by a fusion network, either with a Transformer or an optimal transport cross-alignment, which now operates with a small and fixed number of tokens without approximations. Extensive evaluation on six cancer types shows that our framework outperforms state-of-the-art methods with much less computation while unlocking new interpretability analyses.

Gan Gao, Andrew H. Song, Fiona Wang et al.

Accurate patient diagnoses based on human tissue biopsies are hindered by current clinical practice, where pathologists assess only a limited number of thin 2D tissue slices sectioned from 3D volumetric tissue. Recent advances in non-destructive 3D pathology, such as open-top light-sheet microscopy, enable comprehensive imaging of spatially heterogeneous tissue morphologies, offering the feasibility to improve diagnostic determinations. A potential early route towards clinical adoption for 3D pathology is to rely on pathologists for final diagnosis based on viewing familiar 2D H&E-like image sections from the 3D datasets. However, manual examination of the massive 3D pathology datasets is infeasible. To address this, we present CARP3D, a deep learning triage approach that automatically identifies the highest-risk 2D slices within 3D volumetric biopsy, enabling time-efficient review by pathologists. For a given slice in the biopsy, we estimate its risk by performing attention-based aggregation of 2D patches within each slice, followed by pooling of the neighboring slices to compute a context-aware 2.5D risk score. For prostate cancer risk stratification, CARP3D achieves an area under the curve (AUC) of 90.4% for triaging slices, outperforming methods relying on independent analysis of 2D sections (AUC=81.3%). These results suggest that integrating additional depth context enhances the model's discriminative capabilities. In conclusion, CARP3D has the potential to improve pathologist diagnosis via accurate triage of high-risk slices within large-volume 3D pathology datasets.

Richard J. Chen, Tiffany Y. Chen, Jana Lipkova et al.

In the current development and deployment of many artificial intelligence (AI) systems in healthcare, algorithm fairness is a challenging problem in delivering equitable care. Recent evaluation of AI models stratified across race sub-populations have revealed inequalities in how patients are diagnosed, given treatments, and billed for healthcare costs. In this perspective article, we summarize the intersectional field of fairness in machine learning through the context of current issues in healthcare, outline how algorithmic biases (e.g. - image acquisition, genetic variation, intra-observer labeling variability) arise in current clinical workflows and their resulting healthcare disparities. Lastly, we also review emerging technology for mitigating bias via federated learning, disentanglement, and model explainability, and their role in AI-SaMD development.

Richard J. Chen, Ming Y. Lu, Drew F. K. Williamson et al.

The rapidly emerging field of deep learning-based computational pathology has demonstrated promise in developing objective prognostic models from histology whole slide images. However, most prognostic models are either based on histology or genomics alone and do not address how histology and genomics can be integrated to develop joint image-omic prognostic models. Additionally identifying explainable morphological and molecular descriptors from these models that govern such prognosis is of interest. We used multimodal deep learning to integrate gigapixel whole slide pathology images, RNA-seq abundance, copy number variation, and mutation data from 5,720 patients across 14 major cancer types. Our interpretable, weakly-supervised, multimodal deep learning algorithm is able to fuse these heterogeneous modalities for predicting outcomes and discover prognostic features from these modalities that corroborate with poor and favorable outcomes via multimodal interpretability. We compared our model with unimodal deep learning models trained on histology slides and molecular profiles alone, and demonstrate performance increase in risk stratification on 9 out of 14 cancers. In addition, we analyze morphologic and molecular markers responsible for prognostic predictions across all cancer types. All analyzed data, including morphological and molecular correlates of patient prognosis across the 14 cancer types at a disease and patient level are presented in an interactive open-access database (http://pancancer.mahmoodlab.org) to allow for further exploration and prognostic biomarker discovery. To validate that these model explanations are prognostic, we further analyzed high attention morphological regions in WSIs, which indicates that tumor-infiltrating lymphocyte presence corroborates with favorable cancer prognosis on 9 out of 14 cancer types studied.

Kutsev Bengisu Ozyoruk, Sermet Can, Guliz Irem Gokceler et al.

Frozen sectioning (FS) is the preparation method of choice for microscopic evaluation of tissues during surgical operations. The high speed of the procedure allows pathologists to rapidly assess the key microscopic features, such as tumour margins and malignant status to guide surgical decision-making and minimise disruptions to the course of the operation. However, FS is prone to introducing many misleading artificial structures (histological artefacts), such as nuclear ice crystals, compression, and cutting artefacts, hindering timely and accurate diagnostic judgement of the pathologist. Additional training and prolonged experience is often required to make highly effective and time-critical diagnosis on frozen sections. On the other hand, the gold standard tissue preparation technique of formalin-fixation and paraffin-embedding (FFPE) provides significantly superior image quality, but is a very time-consuming process (12-48 hours), making it unsuitable for intra-operative use. In this paper, we propose an artificial intelligence (AI) method that improves FS image quality by computationally transforming frozen-sectioned whole-slide images (FS-WSIs) into whole-slide FFPE-style images in minutes. AI-FFPE rectifies FS artefacts with the guidance of an attention mechanism that puts a particular emphasis on artefacts while utilising a self-regularization mechanism established between FS input image and synthesized FFPE-style image that preserves clinically relevant features. As a result, AI-FFPE method successfully generates FFPE-style images without significantly extending tissue processing time and consequently improves diagnostic accuracy. We demonstrate the efficacy of AI-FFPE on lung and brain frozen sections using a variety of different qualitative and quantitative metrics including visual Turing tests from 20 board certified pathologists.

Ming Y. Lu, Dehan Kong, Jana Lipkova et al.

Deep Learning-based computational pathology algorithms have demonstrated profound ability to excel in a wide array of tasks that range from characterization of well known morphological phenotypes to predicting non-human-identifiable features from histology such as molecular alterations. However, the development of robust, adaptable, and accurate deep learning-based models often rely on the collection and time-costly curation large high-quality annotated training data that should ideally come from diverse sources and patient populations to cater for the heterogeneity that exists in such datasets. Multi-centric and collaborative integration of medical data across multiple institutions can naturally help overcome this challenge and boost the model performance but is limited by privacy concerns amongst other difficulties that may arise in the complex data sharing process as models scale towards using hundreds of thousands of gigapixel whole slide images. In this paper, we introduce privacy-preserving federated learning for gigapixel whole slide images in computational pathology using weakly-supervised attention multiple instance learning and differential privacy. We evaluated our approach on two different diagnostic problems using thousands of histology whole slide images with only slide-level labels. Additionally, we present a weakly-supervised learning framework for survival prediction and patient stratification from whole slide images and demonstrate its effectiveness in a federated setting. Our results show that using federated learning, we can effectively develop accurate weakly supervised deep learning models from distributed data silos without direct data sharing and its associated complexities, while also preserving differential privacy using randomized noise generation.

Kagan Incetan, Ibrahim Omer Celik, Abdulhamid Obeid et al.

Current capsule endoscopes and next-generation robotic capsules for diagnosis and treatment of gastrointestinal diseases are complex cyber-physical platforms that must orchestrate complex software and hardware functions. The desired tasks for these systems include visual localization, depth estimation, 3D mapping, disease detection and segmentation, automated navigation, active control, path realization and optional therapeutic modules such as targeted drug delivery and biopsy sampling. Data-driven algorithms promise to enable many advanced functionalities for capsule endoscopes, but real-world data is challenging to obtain. Physically-realistic simulations providing synthetic data have emerged as a solution to the development of data-driven algorithms. In this work, we present a comprehensive simulation platform for capsule endoscopy operations and introduce VR-Caps, a virtual active capsule environment that simulates a range of normal and abnormal tissue conditions (e.g., inflated, dry, wet etc.) and varied organ types, capsule endoscope designs (e.g., mono, stereo, dual and 360°camera), and the type, number, strength, and placement of internal and external magnetic sources that enable active locomotion. VR-Caps makes it possible to both independently or jointly develop, optimize, and test medical imaging and analysis software for the current and next-generation endoscopic capsule systems. To validate this approach, we train state-of-the-art deep neural networks to accomplish various medical image analysis tasks using simulated data from VR-Caps and evaluate the performance of these models on real medical data. Results demonstrate the usefulness and effectiveness of the proposed virtual platform in developing algorithms that quantify fractional coverage, camera trajectory, 3D map reconstruction, and disease classification.

Ming Y. Lu, Melissa Zhao, Maha Shady et al.

Cancer of unknown primary (CUP) is an enigmatic group of diagnoses where the primary anatomical site of tumor origin cannot be determined. This poses a significant challenge since modern therapeutics such as chemotherapy regimen and immune checkpoint inhibitors are specific to the primary tumor. Recent work has focused on using genomics and transcriptomics for identification of tumor origins. However, genomic testing is not conducted for every patient and lacks clinical penetration in low resource settings. Herein, to overcome these challenges, we present a deep learning-based computational pathology algorithm-TOAD-that can provide a differential diagnosis for CUP using routinely acquired histology slides. We used 17,486 gigapixel whole slide images with known primaries spread over 18 common origins to train a multi-task deep model to simultaneously identify the tumor as primary or metastatic and predict its site of origin. We tested our model on an internal test set of 4,932 cases with known primaries and achieved a top-1 accuracy of 0.84, a top-3 accuracy of 0.94 while on our external test set of 662 cases from 202 different hospitals, it achieved a top-1 and top-3 accuracy of 0.79 and 0.93 respectively. We further curated a dataset of 717 CUP cases from 151 different medical centers and identified a subset of 290 cases for which a differential diagnosis was assigned. Our model predictions resulted in concordance for 50% of cases (\k{appa}=0.4 when adjusted for agreement by chance) and a top-3 agreement of 75%. Our proposed method can be used as an assistive tool to assign differential diagnosis to complicated metastatic and CUP cases and could be used in conjunction with or in lieu of immunohistochemical analysis and extensive diagnostic work-ups to reduce the occurrence of CUP.

Ming Y. Lu, Drew F. K. Williamson, Tiffany Y. Chen et al.

The rapidly emerging field of computational pathology has the potential to enable objective diagnosis, therapeutic response prediction and identification of new morphological features of clinical relevance. However, deep learning-based computational pathology approaches either require manual annotation of gigapixel whole slide images (WSIs) in fully-supervised settings or thousands of WSIs with slide-level labels in a weakly-supervised setting. Moreover, whole slide level computational pathology methods also suffer from domain adaptation and interpretability issues. These challenges have prevented the broad adaptation of computational pathology for clinical and research purposes. Here we present CLAM - Clustering-constrained attention multiple instance learning, an easy-to-use, high-throughput, and interpretable WSI-level processing and learning method that only requires slide-level labels while being data efficient, adaptable and capable of handling multi-class subtyping problems. CLAM is a deep-learning-based weakly-supervised method that uses attention-based learning to automatically identify sub-regions of high diagnostic value in order to accurately classify the whole slide, while also utilizing instance-level clustering over the representative regions identified to constrain and refine the feature space. In three separate analyses, we demonstrate the data efficiency and adaptability of CLAM and its superior performance over standard weakly-supervised classification. We demonstrate that CLAM models are interpretable and can be used to identify well-known and new morphological features. We further show that models trained using CLAM are adaptable to independent test cohorts, cell phone microscopy images, and biopsies. CLAM is a general-purpose and adaptable method that can be used for a variety of different computational pathology tasks in both clinical and research settings.

Richard J. Chen, Ming Y. Lu, Jingwen Wang et al.

Cancer diagnosis, prognosis, and therapeutic response predictions are based on morphological information from histology slides and molecular profiles from genomic data. However, most deep learning-based objective outcome prediction and grading paradigms are based on histology or genomics alone and do not make use of the complementary information in an intuitive manner. In this work, we propose Pathomic Fusion, an interpretable strategy for end-to-end multimodal fusion of histology image and genomic (mutations, CNV, RNA-Seq) features for survival outcome prediction. Our approach models pairwise feature interactions across modalities by taking the Kronecker product of unimodal feature representations and controls the expressiveness of each representation via a gating-based attention mechanism. Following supervised learning, we are able to interpret and saliently localize features across each modality, and understand how feature importance shifts when conditioning on multimodal input. We validate our approach using glioma and clear cell renal cell carcinoma datasets from the Cancer Genome Atlas (TCGA), which contains paired whole-slide image, genotype, and transcriptome data with ground truth survival and histologic grade labels. In a 15-fold cross-validation, our results demonstrate that the proposed multimodal fusion paradigm improves prognostic determinations from ground truth grading and molecular subtyping, as well as unimodal deep networks trained on histology and genomic data alone. The proposed method establishes insight and theory on how to train deep networks on multimodal biomedical data in an intuitive manner, which will be useful for other problems in medicine that seek to combine heterogeneous data streams for understanding diseases and predicting response and resistance to treatment.

Jingwen Wang, Richard J. Chen, Ming Y. Lu et al.

Histology-based grade classification is clinically important for many cancer types in stratifying patients distinct treatment groups. In prostate cancer, the Gleason score is a grading system used to measure the aggressiveness of prostate cancer from the spatial organization of cells and the distribution of glands. However, the subjective interpretation of Gleason score often suffers from large interobserver and intraobserver variability. Previous work in deep learning-based objective Gleason grading requires manual pixel-level annotation. In this work, we propose a weakly-supervised approach for grade classification in tissue micro-arrays (TMA) using graph convolutional networks (GCNs), in which we model the spatial organization of cells as a graph to better capture the proliferation and community structure of tumor cells. As node-level features in our graph representation, we learn the morphometry of each cell using a contrastive predictive coding (CPC)-based self-supervised approach. We demonstrate that on a five-fold cross validation our method can achieve $0.9659\pm0.0096$ AUC using only TMA-level labels. Our method demonstrates a 39.80\% improvement over standard GCNs with texture features and a 29.27% improvement over GCNs with VGG19 features. Our proposed pipeline can be used to objectively stratify low and high risk cases, reducing inter- and intra-observer variability and pathologist workload.

Ming Y. Lu, Richard J. Chen, Jingwen Wang et al.

Convolutional neural networks can be trained to perform histology slide classification using weak annotations with multiple instance learning (MIL). However, given the paucity of labeled histology data, direct application of MIL can easily suffer from overfitting and the network is unable to learn rich feature representations due to the weak supervisory signal. We propose to overcome such limitations with a two-stage semi-supervised approach that combines the power of data-efficient self-supervised feature learning via contrastive predictive coding (CPC) and the interpretability and flexibility of regularized attention-based MIL. We apply our two-stage CPC + MIL semi-supervised pipeline to the binary classification of breast cancer histology images. Across five random splits, we report state-of-the-art performance with a mean validation accuracy of 95% and an area under the ROC curve of 0.968. We further evaluate the quality of features learned via CPC relative to simple transfer learning and show that strong classification performance using CPC features can be efficiently leveraged under the MIL framework even with the feature encoder frozen.

Richard J. Chen, Taylor L. Bobrow, Thomas Athey et al.

Medical endoscopy remains a challenging application for simultaneous localization and mapping (SLAM) due to the sparsity of image features and size constraints that prevent direct depth-sensing. We present a SLAM approach that incorporates depth predictions made by an adversarially-trained convolutional neural network (CNN) applied to monocular endoscopy images. The depth network is trained with synthetic images of a simple colon model, and then fine-tuned with domain-randomized, photorealistic images rendered from computed tomography measurements of human colons. Each image is paired with an error-free depth map for supervised adversarial learning. Monocular RGB images are then fused with corresponding depth predictions, enabling dense reconstruction and mosaicing as an endoscope is advanced through the gastrointestinal tract. Our preliminary results demonstrate that incorporating monocular depth estimation into a SLAM architecture can enable dense reconstruction of endoscopic scenes.

Mason T. Chen, Faisal Mahmood, Jordan A. Sweer et al.

We present a deep learning framework for wide-field, content-aware estimation of absorption and scattering coefficients of tissues, called Generative Adversarial Network Prediction of Optical Properties (GANPOP). Spatial frequency domain imaging is used to obtain ground-truth optical properties from in vivo human hands, freshly resected human esophagectomy samples and homogeneous tissue phantoms. Images of objects with either flat-field or structured illumination are paired with registered optical property maps and are used to train conditional generative adversarial networks that estimate optical properties from a single input image. We benchmark this approach by comparing GANPOP to a single-snapshot optical property (SSOP) technique, using a normalized mean absolute error (NMAE) metric. In human gastrointestinal specimens, GANPOP estimates both reduced scattering and absorption coefficients at 660 nm from a single 0.2/mm spatial frequency illumination image with 58% higher accuracy than SSOP. When applied to both in vivo and ex vivo swine tissues, a GANPOP model trained solely on human specimens and phantoms estimates optical properties with approximately 43% improvement over SSOP, indicating adaptability to sample variety. Moreover, we demonstrate that GANPOP estimates optical properties from flat-field illumination images with similar error to SSOP, which requires structured-illumination. Given a training set that appropriately spans the target domain, GANPOP has the potential to enable rapid and accurate wide-field measurements of optical properties, even from conventional imaging systems with flat-field illumination.

Faisal Mahmood, Wenhao Xu, Nicholas J. Durr et al.

We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation. Much like commonly used convolutional neural network -- conditional Markov random field (CNN-CRF) models, the proposed method is able to enforce higher-order consistency in the model, but without being limited to a very specific class of potentials. The method is conceptually simple and flexible, and our experimental results demonstrate improvement on several diverse structured prediction tasks.

Faisal Mahmood, Ziyun Yang, Thomas Ashley et al.

Humans make accurate decisions by interpreting complex data from multiple sources. Medical diagnostics, in particular, often hinge on human interpretation of multi-modal information. In order for artificial intelligence to make progress in automated, objective, and accurate diagnosis and prognosis, methods to fuse information from multiple medical imaging modalities are required. However, combining information from multiple data sources has several challenges, as current deep learning architectures lack the ability to extract useful representations from multimodal information, and often simple concatenation is used to fuse such information. In this work, we propose Multimodal DenseNet, a novel architecture for fusing multimodal data. Instead of focusing on concatenation or early and late fusion, our proposed architectures fuses information over several layers and gives the model flexibility in how it combines information from multiple sources. We apply this architecture to the challenge of polyp characterization and landmark identification in endoscopy. Features from white light images are fused with features from narrow band imaging or depth maps. This study demonstrates that Multimodal DenseNet outperforms monomodal classification as well as other multimodal fusion techniques by a significant margin on two different datasets.

Taylor L. Bobrow, Faisal Mahmood, Miguel Inserni et al.

Speckle artifacts degrade image quality in virtually all modalities that utilize coherent energy, including optical coherence tomography, reflectance confocal microscopy, ultrasound, and widefield imaging with laser illumination. We present an adversarial deep learning framework for laser speckle reduction, called DeepLSR (https://durr.jhu.edu/DeepLSR), that transforms images from a source domain of coherent illumination to a target domain of speckle-free, incoherent illumination. We apply this method to widefield images of objects and tissues illuminated with a multi-wavelength laser, using light emitting diode-illuminated images as ground truth. In images of gastrointestinal tissues, DeepLSR reduces laser speckle noise by 6.4 dB, compared to a 2.9 dB reduction from optimized non-local means processing, a 3.0 dB reduction from BM3D, and a 3.7 dB reduction from an optical speckle reducer utilizing an oscillating diffuser. Further, DeepLSR can be combined with optical speckle reduction to reduce speckle noise by 9.4 dB. This dramatic reduction in speckle noise may enable the use of coherent light sources in applications that require small illumination sources and high-quality imaging, including medical endoscopy.