Noel C. F. Codella

Tassilo Wald, Ibrahim Ethem Hamamci, Yuan Gao et al.

Vision-language pre-training, i.e., aligning images with paired text, is a powerful paradigm to create encoders that can be directly used for tasks such as classification and retrieval, and for downstream tasks such as segmentation and report generation. In the 3D medical image domain, these capabilities allow vision-language encoders (VLEs) to support radiologists by retrieving patients with similar abnormalities or predicting likelihoods of abnormality. While the methodology holds promise, data availability limits the capabilities of current 3D VLEs. In this paper, we alleviate the lack of data by injecting additional inductive biases: introducing a report generation objective and pairing vision-language pre-training with vision-only pre-training. This allows us to leverage both image-only and paired image-text 3D datasets, increasing the total amount of data to which our model is exposed. Through these additional inductive biases, paired with best practices of the 3D medical imaging domain, we develop the Comprehensive Language-image Pre-training (COLIPRI) encoder family. Our COLIPRI encoders achieve state-of-the-art performance in report generation, classification probing, and zero-shot classification, and remain competitive for semantic segmentation.

Maximilian Ilse, Harshita Sharma, Anton Schwaighofer et al.

Foundation vision encoders such as CLIP and DINOv2, trained on web-scale data, exhibit strong transfer performance across tasks and datasets. However, medical imaging foundation models remain constrained by smaller datasets, limiting our understanding of how data scale and pretraining paradigms affect performance in this setting. In this work, we systematically study continual pretraining of two vision encoders, MedImageInsight (MI2) and RAD-DINO representing the two major encoder paradigms CLIP and DINOv2, on up to 3.5M chest x-rays from a single institution, holding compute and evaluation protocols constant. We evaluate on classification (radiology findings, lines and tubes), segmentation (lines and tubes), and radiology report generation. While prior work has primarily focused on tasks related to radiology findings, we include lines and tubes tasks to counterbalance this bias and evaluate a model's ability to extract features that preserve continuity along elongated structures. Our experiments show that MI2 scales more effectively for finding-related tasks, while RAD-DINO is stronger on tube-related tasks. Surprisingly, continually pretraining MI2 with both reports and structured labels using UniCL improves performance, underscoring the value of structured supervision at scale. We further show that for some tasks, as few as 30k in-domain samples are sufficient to surpass open-weights foundation models. These results highlight the utility of center-specific continual pretraining, enabling medical institutions to derive significant performance gains by utilizing in-domain data.

Alyssa Unell, Noel C. F. Codella, Sam Preston et al.

The National Comprehensive Cancer Network (NCCN) provides evidence-based guidelines for cancer treatment. Translating complex patient presentations into guideline-compliant treatment recommendations is time-intensive, requires specialized expertise, and is prone to error. Advances in large language model (LLM) capabilities promise to reduce the time required to generate treatment recommendations and improve accuracy. We present an LLM agent-based approach to automatically generate guideline-concordant treatment trajectories for patients with non-small cell lung cancer (NSCLC). Our contributions are threefold. First, we construct a novel longitudinal dataset of 121 cases of NSCLC patients that includes clinical encounters, diagnostic results, and medical histories, each expertly annotated with the corresponding NCCN guideline trajectories by board-certified oncologists. Second, we demonstrate that existing LLMs possess domain-specific knowledge that enables high-quality proxy benchmark generation for both model development and evaluation, achieving strong correlation (Spearman coefficient r=0.88, RMSE = 0.08) with expert-annotated benchmarks. Third, we develop a hybrid approach combining expensive human annotations with model consistency information to create both the agent framework that predicts the relevant guidelines for a patient, as well as a meta-classifier that verifies prediction accuracy with calibrated confidence scores for treatment recommendations (AUROC=0.800), a critical capability for communicating the accuracy of outputs, custom-tailoring tradeoffs in performance, and supporting regulatory compliance. This work establishes a framework for clinically viable LLM-based guideline adherence systems that balance accuracy, interpretability, and regulatory requirements while reducing annotation costs, providing a scalable pathway toward automated clinical decision support.

Shruthi Bannur, Kenza Bouzid, Daniel C. Castro et al.

Radiology reporting is a complex task requiring detailed medical image understanding and precise language generation, for which generative multimodal models offer a promising solution. However, to impact clinical practice, models must achieve a high level of both verifiable performance and utility. We augment the utility of automated report generation by incorporating localisation of individual findings on the image - a task we call grounded report generation - and enhance performance by incorporating realistic reporting context as inputs. We design a novel evaluation framework (RadFact) leveraging the logical inference capabilities of large language models (LLMs) to quantify report correctness and completeness at the level of individual sentences, while supporting the new task of grounded reporting. We develop MAIRA-2, a large radiology-specific multimodal model designed to generate chest X-ray reports with and without grounding. MAIRA-2 achieves state of the art on existing report generation benchmarks and establishes the novel task of grounded report generation.

Newton M. Kinyanjui, Timothy Odonga, Celia Cintas et al.

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5° and 48°, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.

Marc Combalia, Noel C. F. Codella, Veronica Rotemberg et al.

This article summarizes the BCN20000 dataset, composed of 19424 dermoscopic images of skin lesions captured from 2010 to 2016 in the facilities of the Hospital Clínic in Barcelona. With this dataset, we aim to study the problem of unconstrained classification of dermoscopic images of skin cancer, including lesions found in hard-to-diagnose locations (nails and mucosa), large lesions which do not fit in the aperture of the dermoscopy device, and hypo-pigmented lesions. The BCN20000 will be provided to the participants of the ISIC Challenge 2019, where they will be asked to train algorithms to classify dermoscopic images of skin cancer automatically.

Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy et al.

Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes. Recently, a new framework for providing explanations, called TED, has been proposed to provide meaningful explanations for predictions. This framework augments training data to include explanations elicited from domain users, in addition to features and labels. This approach ensures that explanations for predictions are tailored to the complexity expectations and domain knowledge of the consumer. In this paper, we build on this foundational work, by exploring more sophisticated instantiations of the TED framework and empirically evaluate their effectiveness in two diverse domains, chemical odor and skin cancer prediction. Results demonstrate that meaningful explanations can be reliably taught to machine learning algorithms, and in some cases, improving modeling accuracy.

Michael Hind, Dennis Wei, Murray Campbell et al.

Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.

Noel C. F. Codella, Chung-Ching Lin, Allan Halpern et al.

Automated dermoscopic image analysis has witnessed rapid growth in diagnostic performance. Yet adoption faces resistance, in part, because no evidence is provided to support decisions. In this work, an approach for evidence-based classification is presented. A feature embedding is learned with CNNs, triplet-loss, and global average pooling, and used to classify via kNN search. Evidence is provided as both the discovered neighbors, as well as localized image regions most relevant to measuring distance between query and neighbors. To ensure that results are relevant in terms of both label accuracy and human visual similarity for any skill level, a novel hierarchical triplet logic is implemented to jointly learn an embedding according to disease labels and non-expert similarity. Results are improved over baselines trained on disease labels alone, as well as standard multiclass loss. Quantitative relevance of results, according to non-expert similarity, as well as localized image regions, are also significantly improved.

Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy et al.

The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes. In this paper, we propose an approach to generate such explanations in which training data is augmented to include, in addition to features and labels, explanations elicited from domain users. A joint model is then learned to produce both labels and explanations from the input features. This simple idea ensures that explanations are tailored to the complexity expectations and domain knowledge of the consumer. Evaluation spans multiple modeling techniques on a game dataset, a (visual) aesthetics dataset, a chemical odor dataset and a Melanoma dataset showing that our approach is generalizable across domains and algorithms. Results demonstrate that meaningful explanations can be reliably taught to machine learning algorithms, and in some cases, also improve modeling accuracy.

Noel C. F. Codella, Daren Anderson, Tyler Philips et al.

This work presents the first segmentation study of both diseased and healthy skin in standard camera photographs from a clinical environment. Challenges arise from varied lighting conditions, skin types, backgrounds, and pathological states. For study, 400 clinical photographs (with skin segmentation masks) representing various pathological states of skin are retrospectively collected from a primary care network. 100 images are used for training and fine-tuning, and 300 are used for evaluation. This distribution between training and test partitions is chosen to reflect the difficulty in amassing large quantities of labeled data in this domain. A deep learning approach is used, and 3 public segmentation datasets of healthy skin are collected to study the potential benefits of pre-training. Two variants of U-Net are evaluated: U-Net and Dense Residual U-Net. We find that Dense Residual U-Nets have a 7.8% improvement in Jaccard, compared to classical U-Net architectures (0.55 vs. 0.51 Jaccard), for direct transfer, where fine-tuning data is not utilized. However, U-Net outperforms Dense Residual U-Net for both direct training (0.83 vs. 0.80) and fine-tuning (0.89 vs. 0.88). The stark performance improvement with fine-tuning compared to direct transfer and direct training emphasizes both the need for adequate representative data of diseased skin, and the utility of other publicly available data sources for this task.

Noel C. F. Codella, David Gutman, M. Emre Celebi et al.

This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge. The goal is to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. The challenge was divided into 3 tasks: lesion segmentation, feature detection, and disease classification. Participation involved 593 registrations, 81 pre-submissions, 46 finalized submissions (including a 4-page manuscript), and approximately 50 attendees, making this the largest standardized and comparative study in this field to date. While the official challenge duration and ranking of participants has concluded, the dataset snapshots remain available for further research and development.

David Gutman, Noel C. F. Codella, Emre Celebi et al.

In this article, we describe the design and implementation of a publicly accessible dermatology image analysis benchmark challenge. The goal of the challenge is to sup- port research and development of algorithms for automated diagnosis of melanoma, a lethal form of skin cancer, from dermoscopic images. The challenge was divided into sub-challenges for each task involved in image analysis, including lesion segmentation, dermoscopic feature detection within a lesion, and classification of melanoma. Training data included 900 images. A separate test dataset of 379 images was provided to measure resultant performance of systems developed with the training data. Ground truth for both training and test sets was generated by a panel of dermoscopic experts. In total, there were 79 submissions from a group of 38 participants, making this the largest standardized and comparative study for melanoma diagnosis in dermoscopic images to date. While the official challenge duration and ranking of participants has concluded, the datasets remain available for further research and development.