Ronald M. Summers

Lena Maier-Hein, Annika Reinke, Patrick Godau et al. · utoronto

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, our large international expert consortium created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool, which also provides a point of access to explore weaknesses, strengths and specific recommendations for the most common validation metrics. The broad applicability of our framework across domains is demonstrated by an instantiation for various biological and medical image analysis use cases.

Gregory Holste, Song Wang, Ziyu Jiang et al.

Imaging exams, such as chest radiography, will yield a small set of common findings and a much larger set of uncommon findings. While a trained radiologist can learn the visual presentation of rare conditions by studying a few representative examples, teaching a machine to learn from such a "long-tailed" distribution is much more difficult, as standard methods would be easily biased toward the most frequent classes. In this paper, we present a comprehensive benchmark study of the long-tailed learning problem in the specific domain of thorax diseases on chest X-rays. We focus on learning from naturally distributed chest X-ray data, optimizing classification accuracy over not only the common "head" classes, but also the rare yet critical "tail" classes. To accomplish this, we introduce a challenging new long-tailed chest X-ray benchmark to facilitate research on developing long-tailed learning methods for medical image classification. The benchmark consists of two chest X-ray datasets for 19- and 20-way thorax disease classification, containing classes with as many as 53,000 and as few as 7 labeled training images. We evaluate both standard and state-of-the-art long-tailed learning methods on this new benchmark, analyzing which aspects of these methods are most beneficial for long-tailed medical image classification and summarizing insights for future algorithm design. The datasets, trained models, and code are available at https://github.com/VITA-Group/LongTailCXR.

Qingqing Zhu, Tejas Sudharshan Mathai, Pritam Mukherjee et al.

Despite the reduction in turn-around times in radiology reports with the use of speech recognition software, persistent communication errors can significantly impact the interpretation of the radiology report. Pre-filling a radiology report holds promise in mitigating reporting errors, and despite efforts in the literature to generate medical reports, there exists a lack of approaches that exploit the longitudinal nature of patient visit records in the MIMIC-CXR dataset. To address this gap, we propose to use longitudinal multi-modal data, i.e., previous patient visit CXR, current visit CXR, and previous visit report, to pre-fill the 'findings' section of a current patient visit report. We first gathered the longitudinal visit information for 26,625 patients from the MIMIC-CXR dataset and created a new dataset called Longitudinal-MIMIC. With this new dataset, a transformer-based model was trained to capture the information from longitudinal patient visit records containing multi-modal data (CXR images + reports) via a cross-attention-based multi-modal fusion module and a hierarchical memory-driven decoder. In contrast to previous work that only uses current visit data as input to train a model, our work exploits the longitudinal information available to pre-fill the 'findings' section of radiology reports. Experiments show that our approach outperforms several recent approaches. Code will be published at https://github.com/CelestialShine/Longitudinal-Chest-X-Ray.

Xinyue Hu, Lin Gu, Qiyuan An et al.

To contribute to automating the medical vision-language model, we propose a novel Chest-Xray Difference Visual Question Answering (VQA) task. Given a pair of main and reference images, this task attempts to answer several questions on both diseases and, more importantly, the differences between them. This is consistent with the radiologist's diagnosis practice that compares the current image with the reference before concluding the report. We collect a new dataset, namely MIMIC-Diff-VQA, including 700,703 QA pairs from 164,324 pairs of main and reference images. Compared to existing medical VQA datasets, our questions are tailored to the Assessment-Diagnosis-Intervention-Evaluation treatment procedure used by clinical professionals. Meanwhile, we also propose a novel expert knowledge-aware graph representation learning model to address this task. The proposed baseline model leverages expert knowledge such as anatomical structure prior, semantic, and spatial knowledge to construct a multi-relationship graph, representing the image differences between two images for the image difference VQA task. The dataset and code can be found at https://github.com/Holipori/MIMIC-Diff-VQA. We believe this work would further push forward the medical vision language model.

Annika Reinke, Minu D. Tizabi, Michael Baumgartner et al.

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.

Gregory Holste, Ziyu Jiang, Ajay Jaiswal et al.

Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. However, the nuanced ways in which pruning impacts model behavior are not well understood, particularly for long-tailed, multi-label datasets commonly found in clinical settings. This knowledge gap could have dangerous implications when deploying a pruned model for diagnosis, where unexpected model behavior could impact patient well-being. To fill this gap, we perform the first analysis of pruning's effect on neural networks trained to diagnose thorax diseases from chest X-rays (CXRs). On two large CXR datasets, we examine which diseases are most affected by pruning and characterize class "forgettability" based on disease frequency and co-occurrence behavior. Further, we identify individual CXRs where uncompressed and heavily pruned models disagree, known as pruning-identified exemplars (PIEs), and conduct a human reader study to evaluate their unifying qualities. We find that radiologists perceive PIEs as having more label noise, lower image quality, and higher diagnosis difficulty. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification. All code, model weights, and data access instructions can be found at https://github.com/VITA-Group/PruneCXR.

Boah Kim, Yujin Oh, Bradford J. Wood et al.

Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.

Seung Yeon Shin, Thomas C. Shen, Stephen A. Wank et al.

Finding small lesions is very challenging due to lack of noticeable features, severe class imbalance, as well as the size itself. One approach to improve small lesion segmentation is to reduce the region of interest and inspect it at a higher sensitivity rather than performing it for the entire region. It is usually implemented as sequential or joint segmentation of organ and lesion, which requires additional supervision on organ segmentation. Instead, we propose to utilize an intensity distribution of a target lesion at no additional labeling cost to effectively separate regions where the lesions are possibly located from the background. It is incorporated into network training as an auxiliary task. We applied the proposed method to segmentation of small bowel carcinoid tumors in CT scans. We observed improvements for all metrics (33.5% $\rightarrow$ 38.2%, 41.3% $\rightarrow$ 47.8%, 30.0% $\rightarrow$ 35.9% for the global, per case, and per tumor Dice scores, respectively.) compared to the baseline method, which proves the validity of our idea. Our method can be one option for explicitly incorporating intensity distribution information of a target in network training.

M. Jorge Cardoso, Julia Moosbauer, Tessa S. Cook et al.

The integration of AI into radiology introduces opportunities for improved clinical care provision and efficiency but it demands a meticulous approach to mitigate potential risks as with any other new technology. Beginning with rigorous pre-deployment evaluation and validation, the focus should be on ensuring models meet the highest standards of safety, effectiveness and efficacy for their intended applications. Input and output guardrails implemented during production usage act as an additional layer of protection, identifying and addressing individual failures as they occur. Continuous post-deployment monitoring allows for tracking population-level performance (data drift), fairness, and value delivery over time. Scheduling reviews of post-deployment model performance and educating radiologists about new algorithmic-driven findings is critical for AI to be effective in clinical practice. Recognizing that no single AI solution can provide absolute assurance even when limited to its intended use, the synergistic application of quality assurance at multiple levels - regulatory, clinical, technical, and ethical - is emphasized. Collaborative efforts between stakeholders spanning healthcare systems, industry, academia, and government are imperative to address the multifaceted challenges involved. Trust in AI is an earned privilege, contingent on a broad set of goals, among them transparently demonstrating that the AI adheres to the same rigorous safety, effectiveness and efficacy standards as other established medical technologies. By doing so, developers can instil confidence among providers and patients alike, enabling the responsible scaling of AI and the realization of its potential benefits. The roadmap presented herein aims to expedite the achievement of deployable, reliable, and safe AI in radiology.

Mengliang Zhang, Xinyue Hu, Lin Gu et al.

Patients undergoing chest X-rays (CXR) often endure multiple lung diseases. When evaluating a patient's condition, due to the complex pathologies, subtle texture changes of different lung lesions in images, and patient condition differences, radiologists may make uncertain even when they have experienced long-term clinical training and professional guidance, which makes much noise in extracting disease labels based on CXR reports. In this paper, we re-extract disease labels from CXR reports to make them more realistic by considering disease severity and uncertainty in classification. Our contributions are as follows: 1. We re-extracted the disease labels with severity and uncertainty by a rule-based approach with keywords discussed with clinical experts. 2. To further improve the explainability of chest X-ray diagnosis, we designed a multi-relationship graph learning method with an expert uncertainty-aware loss function. 3. Our multi-relationship graph learning method can also interpret the disease classification results. Our experimental results show that models considering disease severity and uncertainty outperform previous state-of-the-art methods.

Gregory Holste, Yiliang Zhou, Song Wang et al.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Seung Yeon Shin, Ronald M. Summers

Small bowel path tracking is a challenging problem considering its many folds and contact along its course. For the same reason, it is very costly to achieve the ground-truth (GT) path of the small bowel in 3D. In this work, we propose to train a deep reinforcement learning tracker using datasets with different types of annotations. Specifically, we utilize CT scans that have only GT small bowel segmentation as well as ones with the GT path. It is enabled by designing a unique environment that is compatible for both, including a reward definable even without the GT path. The performed experiments proved the validity of the proposed method. The proposed method holds a high degree of usability in this problem by being able to utilize the scans with weak annotations, and thus by possibly reducing the required annotation cost.

Seung Yeon Shin, Thomas C. Shen, Ronald M. Summers

We propose a method to incorporate the intensity information of a target lesion on CT scans in training segmentation and detection networks. We first build an intensity-based lesion probability (ILP) function from an intensity histogram of the target lesion. It is used to compute the probability of being the lesion for each voxel based on its intensity. Finally, the computed ILP map of each input CT scan is provided as additional supervision for network training, which aims to inform the network about possible lesion locations in terms of intensity values at no additional labeling cost. The method was applied to improve the segmentation of three different lesion types, namely, small bowel carcinoid tumor, kidney tumor, and lung nodule. The effectiveness of the proposed method on a detection task was also investigated. We observed improvements of 41.3% -> 47.8%, 74.2% -> 76.0%, and 26.4% -> 32.7% in segmenting small bowel carcinoid tumor, kidney tumor, and lung nodule, respectively, in terms of per case Dice scores. An improvement of 64.6% -> 75.5% was achieved in detecting kidney tumors in terms of average precision. The results of different usages of the ILP map and the effect of varied amount of training data are also presented.

Seung Yeon Shin, Sungwon Lee, Ronald M. Summers

We present a new graph-based method for small bowel path tracking based on cylindrical constraints. A distinctive characteristic of the small bowel compared to other organs is the contact between parts of itself along its course, which makes the path tracking difficult together with the indistinct appearance of the wall. It causes the tracked path to easily cross over the walls when relying on low-level features like the wall detection. To circumvent this, a series of cylinders that are fitted along the course of the small bowel are used to guide the tracking to more reliable directions. It is implemented as soft constraints using a new cost function. The proposed method is evaluated against ground-truth paths that are all connected from start to end of the small bowel for 10 abdominal CT scans. The proposed method showed clear improvements compared to the baseline method in tracking the path without making an error. Improvements of 6.6% and 17.0%, in terms of the tracked length, were observed for two different settings related to the small bowel segmentation.

Hexin Dong, Yi Lin, Pengyu Zhou et al.

Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing benchmarks often rely on closed-set classes from a single institution, failing to capture the prevalence of rare diseases or the appearance of novel findings. To address this, we present the CXR-LT challenge. The first event, CXR-LT 2023, established a large-scale benchmark for long-tailed multi-label CXR classification and identified key challenges in rare disease recognition. CXR-LT 2024 further expanded the label space and introduced a zero-shot task to study generalization to unseen findings. Building on the success of CXR-LT 2023 and 2024, this third iteration of the benchmark introduces a multi-center dataset comprising over 145,000 images from PadChest and NIH Chest X-ray datasets. Additionally, all development and test sets in CXR-LT 2026 are annotated by radiologists, providing a more reliable and clinically grounded evaluation than report-derived labels. The challenge defines two core tasks this year: (1) Robust Multi-Label Classification on 30 known classes and (2) Open-World Generalization to 6 unseen (out-of-distribution) rare disease classes. This paper summarizes the overview of the CXR-LT 2026 challenge. We describe the data collection and annotation procedures, analyze solution strategies adopted by participating teams, and evaluate head-versus-tail performance, calibration, and cross-center generalization gaps. Our results show that vision-language foundation models improve both in-distribution and zero-shot performance, but detecting rare findings under multi-center shift remains challenging. Our study provides a foundation for developing and evaluating AI systems in realistic long-tailed and open-world clinical conditions.

Andrew M. Nguyen, Tejas Sudharshan Mathai, Liangchen Liu et al.

Pericoronary adipose tissue (PCAT) is the deposition of fat in the vicinity of the coronary arteries. It is an indicator of coronary inflammation and associated with coronary artery disease. Non-invasive coronary CT angiography (CCTA) is presently used to obtain measures of the thickness, volume, and attenuation of fat deposition. However, prior works solely focus on measuring PCAT using semi-automated approaches at the right coronary artery (RCA) over the left coronary artery (LCA). In this pilot work, we developed a fully automated approach for the measurement of PCAT mean attenuation and volume in the region around both coronary arteries. First, we used a large subset of patients from the public ImageCAS dataset (n = 735) to train a 3D full resolution nnUNet to segment LCA and RCA. Then, we automatically measured PCAT in the surrounding arterial regions. We evaluated our method on a held-out test set of patients (n = 183) from the same dataset. A mean Dice score of 83% and PCAT attenuation of -73.81 $\pm$ 12.69 HU was calculated for the RCA, while a mean Dice score of 81% and PCAT attenuation of -77.51 $\pm$ 7.94 HU was computed for the LCA. To the best of our knowledge, we are the first to develop a fully automated method to measure PCAT attenuation and volume at both the RCA and LCA. Our work underscores how automated PCAT measurement holds promise as a biomarker for identification of inflammation and cardiac disease.

Qingqing Zhu, Qiao Jin, Tejas S. Mathai et al.

Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited by the scarcity of publicly available CT datasets with lesion-level annotations. To bridge this gap, we introduce CT-Bench, a first-of-its-kind benchmark dataset comprising two components: a Lesion Image and Metadata Set containing 20,335 lesions from 7,795 CT studies with bounding boxes, descriptions, and size information, and a multitask visual question answering benchmark with 2,850 QA pairs covering lesion localization, description, size estimation, and attribute categorization. Hard negative examples are included to reflect real-world diagnostic challenges. We evaluate multiple state-of-the-art multimodal models, including vision-language and medical CLIP variants, by comparing their performance to radiologist assessments, demonstrating the value of CT-Bench as a comprehensive benchmark for lesion analysis. Moreover, fine-tuning models on the Lesion Image and Metadata Set yields significant performance gains across both components, underscoring the clinical utility of CT-Bench.

Tejas Sudharshan Mathai, Anisa V. Prasad, Xinya Wang et al.

Type 2 Diabetes Mellitus (T2DM) is a chronic metabolic disease that affects millions of people worldwide. Early detection is crucial as it can alter pancreas function through morphological changes and increased deposition of ectopic fat, eventually leading to organ damage. While studies have shown an association between T2DM and pancreas volume and fat content, the role of increased pancreatic surface lobularity (PSL) in patients with T2DM has not been fully investigated. In this pilot work, we propose a fully automated approach to delineate the pancreas and other abdominal structures, derive CT imaging biomarkers, and opportunistically screen for T2DM. Four deep learning-based models were used to segment the pancreas in an internal dataset of 584 patients (297 males, 437 non-diabetic, age: 45$\pm$15 years). PSL was automatically detected and it was higher for diabetic patients (p=0.01) at 4.26 $\pm$ 8.32 compared to 3.19 $\pm$ 3.62 for non-diabetic patients. The PancAP model achieved the highest Dice score of 0.79 $\pm$ 0.17 and lowest ASSD error of 1.94 $\pm$ 2.63 mm (p$<$0.05). For predicting T2DM, a multivariate model trained with CT biomarkers attained 0.90 AUC, 66.7\% sensitivity, and 91.9\% specificity. Our results suggest that PSL is useful for T2DM screening and could potentially help predict the early onset of T2DM.

Ruida Cheng, Tejas Sudharshan Mathai, Pritam Mukherjee et al.

Segmentation of lesions on CT enables automatic measurement for clinical assessment of chronic diseases (e.g., lymphoma). Integrating large language models (LLMs) into the lesion segmentation workflow offers the potential to combine imaging features with descriptions of lesion characteristics from the radiology reports. In this study, we investigate the feasibility of integrating text into the Swin-UMamba architecture for the task of lesion segmentation. The publicly available ULS23 DeepLesion dataset was used along with short-form descriptions of the findings from the reports. On the test dataset, a high Dice Score of 82% and low Hausdorff distance of 6.58 (pixels) was obtained for lesion segmentation. The proposed Text-Swin-UMamba model outperformed prior approaches: 37% improvement over the LLM-driven LanGuideMedSeg model (p < 0.001),and surpassed the purely image-based xLSTM-UNet and nnUNet models by 1.74% and 0.22%, respectively. The dataset and code can be accessed at https://github.com/ruida/LLM-Swin-UMamba

Ricardo Bigolin Lanfredi, Yan Zhuang, Mark Finkelstein et al.

Extracting structured labels from radiology reports has been employed to create vision models to simultaneously detect several types of abnormalities. However, existing works focus mainly on the chest region. Few works have been investigated on abdominal radiology reports due to more complex anatomy and a wider range of pathologies in the abdomen. We propose LEAVS (Large language model Extractor for Abdominal Vision Supervision). This labeler can annotate the certainty of presence and the urgency of seven types of abnormalities for nine abdominal organs on CT radiology reports. To ensure broad coverage, we chose abnormalities that encompass most of the finding types from CT reports. Our approach employs a specialized chain-of-thought prompting strategy for a locally-run LLM using sentence extraction and multiple-choice questions in a tree-based decision system. We demonstrate that the LLM can extract several abnormality types across abdominal organs with an average F1 score of 0.89, significantly outperforming competing labelers and humans. Additionally, we show that extraction of urgency labels achieved performance comparable to human annotations. Finally, we demonstrate that the abnormality labels contain valuable information for training a single vision model that classifies several organs as normal or abnormal. We release our code and structured annotations for a public CT dataset containing over 1,000 CT volumes.

Benjamin Hou, Qingqing Zhu, Tejas Sudarshan Mathai et al.

In this paper, we introduce DRR-RATE, a large-scale synthetic chest X-ray dataset derived from the recently released CT-RATE dataset. DRR-RATE comprises of 50,188 frontal Digitally Reconstructed Radiographs (DRRs) from 21,304 unique patients. Each image is paired with a corresponding radiology text report and binary labels for 18 pathology classes. Given the controllable nature of DRR generation, it facilitates the inclusion of lateral view images and images from any desired viewing position. This opens up avenues for research into new and novel multimodal applications involving paired CT, X-ray images from various views, text, and binary labels. We demonstrate the applicability of DRR-RATE alongside existing large-scale chest X-ray resources, notably the CheXpert dataset and CheXnet model. Experiments demonstrate that CheXnet, when trained and tested on the DRR-RATE dataset, achieves sufficient to high AUC scores for the six common pathologies cited in common literature: Atelectasis, Cardiomegaly, Consolidation, Lung Lesion, Lung Opacity, and Pleural Effusion. Additionally, CheXnet trained on the CheXpert dataset can accurately identify several pathologies, even when operating out of distribution. This confirms that the generated DRR images effectively capture the essential pathology features from CT images. The dataset and labels are publicly accessible at https://huggingface.co/datasets/farrell236/DRR-RATE.

Yifan Peng, Yu-Xing Tang, Sungwon Lee et al.

The latest threat to global health is the COVID-19 outbreak. Although there exist large datasets of chest X-rays (CXR) and computed tomography (CT) scans, few COVID-19 image collections are currently available due to patient privacy. At the same time, there is a rapid growth of COVID-19-relevant articles in the biomedical literature. Here, we present COVID-19-CT-CXR, a public database of COVID-19 CXR and CT images, which are automatically extracted from COVID-19-relevant articles from the PubMed Central Open Access (PMC-OA) Subset. We extracted figures, associated captions, and relevant figure descriptions in the article and separated compound figures into subfigures. We also designed a deep-learning model to distinguish them from other figure types and to classify them accordingly. The final database includes 1,327 CT and 263 CXR images (as of May 9, 2020) with their relevant text. To demonstrate the utility of COVID-19-CT-CXR, we conducted four case studies. (1) We show that COVID-19-CT-CXR, when used as additional training data, is able to contribute to improved DL performance for the classification of COVID-19 and non-COVID-19 CT. (2) We collected CT images of influenza and trained a DL baseline to distinguish a diagnosis of COVID-19, influenza, or normal or other types of diseases on CT. (3) We trained an unsupervised one-class classifier from non-COVID-19 CXR and performed anomaly detection to detect COVID-19 CXR. (4) From text-mined captions and figure descriptions, we compared clinical symptoms and clinical findings of COVID-19 vs. those of influenza to demonstrate the disease differences in the scientific publications. We believe that our work is complementary to existing resources and hope that it will contribute to medical image analysis of the COVID-19 pandemic. The dataset, code, and DL models are publicly available at https://github.com/ncbi-nlp/COVID-19-CT-CXR.

Kerstin Hammernik, Jo Schlemper, Chen Qin et al.

Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $Σ$-net, for accelerated parallel MR image reconstruction using deep learning. Theory and Methods: MR image reconstruction is formulated as learned unrolled optimization scheme with a Down-Up network as regularization and varying data consistency layers. The different architectures are split into sensitivity networks, which rely on explicit coil sensitivity maps, and parallel coil networks, which learn the combination of coils implicitly. Different content and adversarial losses, a semi-supervised fine-tuning scheme and model ensembling are investigated. Results: Evaluated on the fastMRI multicoil validation set, architectures involving raw k-space data outperform image enhancement methods significantly. Semi-supervised fine-tuning adapts to new k-space data and provides, together with reconstructions based on adversarial training, the visually most appealing results although quantitative quality metrics are reduced. The $Σ$-net ensembles the benefits from different models and achieves similar scores compared to the single state-of-the-art approaches. Conclusion: This work provides an open-source framework to perform a systematic wide-range comparison of state-of-the-art reconstruction approaches for parallel MR image reconstruction on the fastMRI knee dataset and explores the importance of data consistency. A suitable trade-off between perceptual image quality and quantitative scores are achieved with the ensembled $Σ$-net.

Youbao Tang, Yuxing Tang, Jing Xiao et al.

This paper proposes a novel framework for lung segmentation in chest X-rays. It consists of two key contributions, a criss-cross attention based segmentation network and radiorealistic chest X-ray image synthesis (i.e. a synthesized radiograph that appears anatomically realistic) for data augmentation. The criss-cross attention modules capture rich global contextual information in both horizontal and vertical directions for all the pixels thus facilitating accurate lung segmentation. To reduce the manual annotation burden and to train a robust lung segmentor that can be adapted to pathological lungs with hazy lung boundaries, an image-to-image translation module is employed to synthesize radiorealistic abnormal CXRs from the source of normal ones for data augmentation. The lung masks of synthetic abnormal CXRs are propagated from the segmentation results of their normal counterparts, and then serve as pseudo masks for robust segmentor training. In addition, we annotate 100 CXRs with lung masks on a more challenging NIH Chest X-ray dataset containing both posterioranterior and anteroposterior views for evaluation. Extensive experiments validate the robustness and effectiveness of the proposed framework. The code and data can be found from https://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor .

Amber L. Simpson, Michela Antonelli, Spyridon Bakas et al.

Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community.

Ke Yan, Mohammadhadi Bagheri, Ronald M. Summers

Detecting lesions from computed tomography (CT) scans is an important but difficult problem because non-lesions and true lesions can appear similar. 3D context is known to be helpful in this differentiation task. However, existing end-to-end detection frameworks of convolutional neural networks (CNNs) are mostly designed for 2D images. In this paper, we propose 3D context enhanced region-based CNN (3DCE) to incorporate 3D context information efficiently by aggregating feature maps of 2D images. 3DCE is easy to train and end-to-end in training and inference. A universal lesion detector is developed to detect all kinds of lesions in one algorithm using the DeepLesion dataset. Experimental results on this challenging task prove the effectiveness of 3DCE. We have released the code of 3DCE in https://github.com/rsummers11/CADLab/tree/master/lesion_detector_3DCE.

Yan Zhuang, Benjamin Hou, Tejas Sudharshan Mathai et al.

As a new emerging and promising type of generative models, diffusion models have proven to outperform Generative Adversarial Networks (GANs) in multiple tasks, including image synthesis. In this work, we explore semantic image synthesis for abdominal CT using conditional diffusion models, which can be used for downstream applications such as data augmentation. We systematically evaluated the performance of three diffusion models, as well as to other state-of-the-art GAN-based approaches, and studied the different conditioning scenarios for the semantic mask. Experimental results demonstrated that diffusion models were able to synthesize abdominal CT images with better quality. Additionally, encoding the mask and the input separately is more effective than naïve concatenating.

Tejas Sudharshan Mathai, Bohan Liu, Ronald M. Summers

Purpose: Lymph nodes (LNs) in the chest have a tendency to enlarge due to various pathologies, such as lung cancer or pneumonia. Clinicians routinely measure nodal size to monitor disease progression, confirm metastatic cancer, and assess treatment response. However, variations in their shapes and appearances make it cumbersome to identify LNs, which reside outside of most organs. Methods: We propose to segment LNs in the mediastinum by leveraging the anatomical priors of 28 different structures (e.g., lung, trachea etc.) generated by the public TotalSegmentator tool. The CT volumes from 89 patients available in the public NIH CT Lymph Node dataset were used to train three 3D nnUNet models to segment LNs. The public St. Olavs dataset containing 15 patients (out-of-training-distribution) was used to evaluate the segmentation performance. Results: For the 15 test patients, the 3D cascade nnUNet model obtained the highest Dice score of 72.2 +- 22.3 for mediastinal LNs with short axis diameter $\geq$ 8mm and 54.8 +- 23.8 for all LNs respectively. These results represent an improvement of 10 points over a current approach that was evaluated on the same test dataset. Conclusion: To our knowledge, we are the first to harness 28 distinct anatomical priors to segment mediastinal LNs, and our work can be extended to other nodal zones in the body. The proposed method has immense potential for improved patient outcomes through the identification of enlarged nodes in initial staging CT scans.

Qiao Jin, Nicholas Wan, Robert Leaman et al.

Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.

Kimberly Helm, Tejas Sudharshan Mathai, Boah Kim et al.

Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide variations in imaging practice at institutions and myriad MRI scanners from various manufacturers being used for imaging. The intensity distributions of MRI sequences differ widely as a result, and there also exists information conflicts related to the sequence type in the DICOM headers. At present, clinician oversight is necessary to ensure that the correct sequence is being read and used for diagnosis. This poses a challenge when specific series need to be considered for building a cohort for a large clinical study or for developing AI algorithms. In order to reduce clinician oversight and ensure the validity of the DICOM headers, we propose an automated method to classify the 3D MRI sequence acquired at the levels of the chest, abdomen, and pelvis. In our pilot work, our 3D DenseNet-121 model achieved an F1 score of 99.5% at differentiating 5 common MRI sequences obtained by three Siemens scanners (Aera, Verio, Biograph mMR). To the best of our knowledge, we are the first to develop an automated method for the 3D classification of MRI sequences in the chest, abdomen, and pelvis, and our work has outperformed the previous state-of-the-art MRI series classifiers.

Peter D. Erickson, Tejas Sudharshan Mathai, Ronald M. Summers

Radiologists routinely detect and size lesions in CT to stage cancer and assess tumor burden. To potentially aid their efforts, multiple lesion detection algorithms have been developed with a large public dataset called DeepLesion (32,735 lesions, 32,120 CT slices, 10,594 studies, 4,427 patients, 8 body part labels). However, this dataset contains missing measurements and lesion tags, and exhibits a severe imbalance in the number of lesions per label category. In this work, we utilize a limited subset of DeepLesion (6\%, 1331 lesions, 1309 slices) containing lesion annotations and body part label tags to train a VFNet model to detect lesions and tag them. We address the class imbalance by conducting three experiments: 1) Balancing data by the body part labels, 2) Balancing data by the number of lesions per patient, and 3) Balancing data by the lesion size. In contrast to a randomly sampled (unbalanced) data subset, our results indicated that balancing the body part labels always increased sensitivity for lesions >= 1cm for classes with low data quantities (Bone: 80\% vs. 46\%, Kidney: 77\% vs. 61\%, Soft Tissue: 70\% vs. 60\%, Pelvis: 83\% vs. 76\%). Similar trends were seen for three other models tested (FasterRCNN, RetinaNet, FoveaBox). Balancing data by lesion size also helped the VFNet model improve recalls for all classes in contrast to an unbalanced dataset. We also provide a structured reporting guideline for a ``Lesions'' subsection to be entered into the ``Findings'' section of a radiology report. To our knowledge, we are the first to report the class imbalance in DeepLesion, and have taken data-driven steps to address it in the context of joint lesion detection and tagging.

Benjamin Hou, Tejas Sudharshan Mathai, Jianfei Liu et al.

Purpose: Body composition measurements from routine abdominal CT can yield personalized risk assessments for asymptomatic and diseased patients. In particular, attenuation and volume measures of muscle and fat are associated with important clinical outcomes, such as cardiovascular events, fractures, and death. This study evaluates the reliability of an Internal tool for the segmentation of muscle and fat (subcutaneous and visceral) as compared to the well-established public TotalSegmentator tool. Methods: We assessed the tools across 900 CT series from the publicly available SAROS dataset, focusing on muscle, subcutaneous fat, and visceral fat. The Dice score was employed to assess accuracy in subcutaneous fat and muscle segmentation. Due to the lack of ground truth segmentations for visceral fat, Cohen's Kappa was utilized to assess segmentation agreement between the tools. Results: Our Internal tool achieved a 3% higher Dice (83.8 vs. 80.8) for subcutaneous fat and a 5% improvement (87.6 vs. 83.2) for muscle segmentation respectively. A Wilcoxon signed-rank test revealed that our results were statistically different with p<0.01. For visceral fat, the Cohen's kappa score of 0.856 indicated near-perfect agreement between the two tools. Our internal tool also showed very strong correlations for muscle volume (R^2=0.99), muscle attenuation (R^2=0.93), and subcutaneous fat volume (R^2=0.99) with a moderate correlation for subcutaneous fat attenuation (R^2=0.45). Conclusion: Our findings indicated that our Internal tool outperformed TotalSegmentator in measuring subcutaneous fat and muscle. The high Cohen's Kappa score for visceral fat suggests a reliable level of agreement between the two tools. These results demonstrate the potential of our tool in advancing the accuracy of body composition analysis.

Boah Kim, Tejas Sudharshan Mathai, Kimberly Helm et al.

Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently. Using mpMRI data from various institutions, multiple deep learning-based classifiers of ResNet, EfficientNet, and DenseNet are trained to classify 8 different MRI series, and their performance is compared. Then, the best-performing classifier is identified, and its classification capability under the setting of different training data quantities is studied. Also, the model is evaluated on the out-of-training-distribution datasets. Moreover, the model is trained using mpMRI exams obtained from different scanners in two training strategies, and its performance is tested. Experimental results show that the DenseNet-121 model achieves the highest F1-score and accuracy of 0.966 and 0.972 over the other classification models with p-value$<$0.05. The model shows greater than 0.95 accuracy when trained with over 729 studies of the training data, whose performance improves as the training data quantities grew larger. On the external data with the DLDS and CPTAC-UCEC datasets, the model yields 0.872 and 0.810 accuracy for each. These results indicate that in both the internal and external datasets, the DenseNet-121 model attains high accuracy for the task of classifying 8 body MRI series types.

Anisa V. Prasad, Tejas Sudharshan Mathai, Pritam Mukherjee et al.

An accurate segmentation of the pancreas on CT is crucial to identify pancreatic pathologies and extract imaging-based biomarkers. However, prior research on pancreas segmentation has primarily focused on modifying the segmentation model architecture or utilizing pre- and post-processing techniques. In this article, we investigate the utility of anatomical priors to enhance the segmentation performance of the pancreas. Two 3D full-resolution nnU-Net models were trained, one with 8 refined labels from the public PANORAMA dataset, and another that combined them with labels derived from the public TotalSegmentator (TS) tool. The addition of anatomical priors resulted in a 6\% increase in Dice score ($p < .001$) and a 36.5 mm decrease in Hausdorff distance for pancreas segmentation ($p < .001$). Moreover, the pancreas was always detected when anatomy priors were used, whereas there were 8 instances of failed detections without their use. The use of anatomy priors shows promise for pancreas segmentation and subsequent derivation of imaging biomarkers.

Boah Kim, Tejas Sudharshan Mathai, Kimberly Helm et al.

Multi-parametric MRI (mpMRI) studies are widely available in clinical practice for the diagnosis of various diseases. As the volume of mpMRI exams increases yearly, there are concomitant inaccuracies that exist within the DICOM header fields of these exams. This precludes the use of the header information for the arrangement of the different series as part of the radiologist's hanging protocol, and clinician oversight is needed for correction. In this pilot work, we propose an automated framework to classify the type of 8 different series in mpMRI studies. We used 1,363 studies acquired by three Siemens scanners to train a DenseNet-121 model with 5-fold cross-validation. Then, we evaluated the performance of the DenseNet-121 ensemble on a held-out test set of 313 mpMRI studies. Our method achieved an average precision of 96.6%, sensitivity of 96.6%, specificity of 99.6%, and F1 score of 96.6% for the MRI series classification task. To the best of our knowledge, we are the first to develop a method to classify the series type in mpMRI studies acquired at the level of the chest, abdomen, and pelvis. Our method has the capability for robust automation of hanging protocols in modern radiology practice.

Tejas Sudharshan Mathai, Benjamin Hou, Ronald M. Summers

In the U.S., lung cancer is the second major cause of death. Early detection of suspicious lung nodules is crucial for patient treatment planning, management, and improving outcomes. Many approaches for lung nodule segmentation and volumetric analysis have been proposed, but few have looked at longitudinal changes in total lung tumor burden. In this work, we trained two 3D models (nnUNet) with and without anatomical priors to automatically segment lung lesions and quantified total lesion burden for each patient. The 3D model without priors significantly outperformed ($p < .001$) the model trained with anatomy priors. For detecting clinically significant lesions $>$ 1cm, a precision of 71.3\%, sensitivity of 68.4\%, and F1-score of 69.8\% was achieved. For segmentation, a Dice score of 77.1 $\pm$ 20.3 and Hausdorff distance error of 11.7 $\pm$ 24.1 mm was obtained. The median lesion burden was 6.4 cc (IQR: 2.1, 18.1) and the median volume difference between manual and automated measurements was 0.02 cc (IQR: -2.8, 1.2). Agreements were also evaluated with linear regression and Bland-Altman plots. The proposed approach can produce a personalized evaluation of the total tumor burden for a patient and facilitate interval change tracking over time.

Alexander Shieh, Tejas Sudharshan Mathai, Jianfei Liu et al.

Universal lesion detection and tagging (ULDT) in CT studies is critical for tumor burden assessment and tracking the progression of lesion status (growth/shrinkage) over time. However, a lack of fully annotated data hinders the development of effective ULDT approaches. Prior work used the DeepLesion dataset (4,427 patients, 10,594 studies, 32,120 CT slices, 32,735 lesions, 8 body part labels) for algorithmic development, but this dataset is not completely annotated and contains class imbalances. To address these issues, in this work, we developed a self-training pipeline for ULDT. A VFNet model was trained on a limited 11.5\% subset of DeepLesion (bounding boxes + tags) to detect and classify lesions in CT studies. Then, it identified and incorporated novel lesion candidates from a larger unseen data subset into its training set, and self-trained itself over multiple rounds. Multiple self-training experiments were conducted with different threshold policies to select predicted lesions with higher quality and cover the class imbalances. We discovered that direct self-training improved the sensitivities of over-represented lesion classes at the expense of under-represented classes. However, upsampling the lesions mined during self-training along with a variable threshold policy yielded a 6.5\% increase in sensitivity at 4 FP in contrast to self-training without class balancing (72\% vs 78.5\%) and a 11.7\% increase compared to the same self-training policy without upsampling (66.8\% vs 78.5\%). Furthermore, we show that our results either improved or maintained the sensitivity at 4FP for all 8 lesion classes.

Qingqing Zhu, Benjamin Hou, Tejas S. Mathai et al.

Automatically interpreting CT scans can ease the workload of radiologists. However, this is challenging mainly due to the scarcity of adequate datasets and reference standards for evaluation. This study aims to bridge this gap by introducing a novel evaluation framework, named ``GPTRadScore''. This framework assesses the capabilities of multi-modal LLMs, such as GPT-4 with Vision (GPT-4V), Gemini Pro Vision, LLaVA-Med, and RadFM, in generating descriptions for prospectively-identified findings. By employing a decomposition technique based on GPT-4, GPTRadScore compares these generated descriptions with gold-standard report sentences, analyzing their accuracy in terms of body part, location, and type of finding. Evaluations demonstrated a high correlation with clinician assessments and highlighted its potential over traditional metrics, such as BLEU, METEOR, and ROUGE. Furthermore, to contribute to future studies, we plan to release a benchmark dataset annotated by clinicians. Using GPTRadScore, we found that while GPT-4V and Gemini Pro Vision fare better, their performance revealed significant areas for improvement, primarily due to limitations in the dataset used for training these models. To demonstrate this potential, RadFM was fine-tuned and it resulted in significant accuracy improvements: location accuracy rose from 3.41\% to 12.8\%, body part accuracy from 29.12\% to 53\%, and type accuracy from 9.24\% to 30\%, thereby validating our hypothesis.

Jianfei Liu, Christopher Parnell, Ronald M. Summers

Accurate training labels are a key component for multi-class medical image segmentation. Their annotation is costly and time-consuming because it requires domain expertise. This work aims to develop a dual-branch network and automatically improve training labels for multi-class image segmentation. Transfer learning is used to train the network and improve inaccurate weak labels sequentially. The dual-branch network is first trained by weak labels alone to initialize model parameters. After the network is stabilized, the shared encoder is frozen, and strong and weak decoders are fine-tuned by strong and weak labels together. The accuracy of weak labels is iteratively improved in the fine-tuning process. The proposed method was applied to a three-class segmentation of muscle, subcutaneous and visceral adipose tissue on abdominal CT scans. Validation results on 11 patients showed that the accuracy of training labels was statistically significantly improved, with the Dice similarity coefficient of muscle, subcutaneous and visceral adipose tissue increased from 74.2% to 91.5%, 91.2% to 95.6%, and 77.6% to 88.5%, respectively (p<0.05). In comparison with our earlier method, the label accuracy was also significantly improved (p<0.05). These experimental results suggested that the combination of the dual-branch network and transfer learning is an efficient means to improve training labels for multi-class segmentation.

David C. Oluigboa, Bikash Santra, Tejas Sudharshan Mathai et al.

Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors which have the potential to metastasize. For the management of patients with PPGLs, CT is the preferred modality of choice for precise localization and estimation of their progression. However, due to the myriad variations in size, morphology, and appearance of the tumors in different anatomical regions, radiologists are posed with the challenge of accurate detection of PPGLs. Since clinicians also need to routinely measure their size and track their changes over time across patient visits, manual demarcation of PPGLs is quite a time-consuming and cumbersome process. To ameliorate the manual effort spent for this task, we propose an automated method to detect PPGLs in CT studies via a proxy segmentation task. As only weak annotations for PPGLs in the form of prospectively marked 2D bounding boxes on an axial slice were available, we extended these 2D boxes into weak 3D annotations and trained a 3D full-resolution nnUNet model to directly segment PPGLs. We evaluated our approach on a dataset consisting of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. We obtained a precision of 70% and sensitivity of 64.1% with our proposed approach when tested on 53 CT studies. Our findings highlight the promising nature of detecting PPGLs via segmentation, and furthers the state-of-the-art in this exciting yet challenging area of rare cancer management.

Tao Sheng, Tejas Sudharshan Mathai, Alexander Shieh et al.

The skeletal region is one of the common sites of metastatic spread of cancer in the breast and prostate. CT is routinely used to measure the size of lesions in the bones. However, they can be difficult to spot due to the wide variations in their sizes, shapes, and appearances. Precise localization of such lesions would enable reliable tracking of interval changes (growth, shrinkage, or unchanged status). To that end, an automated technique to detect bone lesions is highly desirable. In this pilot work, we developed a pipeline to detect bone lesions (lytic, blastic, and mixed) in CT volumes via a proxy segmentation task. First, we used the bone lesions that were prospectively marked by radiologists in a few 2D slices of CT volumes and converted them into weak 3D segmentation masks. Then, we trained a 3D full-resolution nnUNet model using these weak 3D annotations to segment the lesions and thereby detected them. Our automated method detected bone lesions in CT with a precision of 96.7% and recall of 47.3% despite the use of incomplete and partial training data. To the best of our knowledge, we are the first to attempt the direct detection of bone lesions in CT via a proxy segmentation task.

Jared Frazier, Tejas Sudharshan Mathai, Jianfei Liu et al.

Radiologists routinely perform the tedious task of lesion localization, classification, and size measurement in computed tomography (CT) studies. Universal lesion detection and tagging (ULDT) can simultaneously help alleviate the cumbersome nature of lesion measurement and enable tumor burden assessment. Previous ULDT approaches utilize the publicly available DeepLesion dataset, however it does not provide the full volumetric (3D) extent of lesions and also displays a severe class imbalance. In this work, we propose a self-training pipeline to detect 3D lesions and tag them according to the body part they occur in. We used a significantly limited 30\% subset of DeepLesion to train a VFNet model for 2D lesion detection and tagging. Next, the 2D lesion context was expanded into 3D, and the mined 3D lesion proposals were integrated back into the baseline training data in order to retrain the model over multiple rounds. Through the self-training procedure, our VFNet model learned from its own predictions, detected lesions in 3D, and tagged them. Our results indicated that our VFNet model achieved an average sensitivity of 46.9\% at [0.125:8] false positives (FP) with a limited 30\% data subset in comparison to the 46.8\% of an existing approach that used the entire DeepLesion dataset. To our knowledge, we are the first to jointly detect lesions in 3D and tag them according to the body part label.

Mingquan Lin, Gregory Holste, Song Wang et al.

The CXR-LT series is a community-driven initiative designed to enhance lung disease classification using chest X-rays (CXR). It tackles challenges in open long-tailed lung disease classification and enhances the measurability of state-of-the-art techniques. The first event, CXR-LT 2023, aimed to achieve these goals by providing high-quality benchmark CXR data for model development and conducting comprehensive evaluations to identify ongoing issues impacting lung disease classification performance. Building on the success of CXR-LT 2023, the CXR-LT 2024 expands the dataset to 377,110 chest X-rays (CXRs) and 45 disease labels, including 19 new rare disease findings. It also introduces a new focus on zero-shot learning to address limitations identified in the previous event. Specifically, CXR-LT 2024 features three tasks: (i) long-tailed classification on a large, noisy test set, (ii) long-tailed classification on a manually annotated "gold standard" subset, and (iii) zero-shot generalization to five previously unseen disease findings. This paper provides an overview of CXR-LT 2024, detailing the data curation process and consolidating state-of-the-art solutions, including the use of multimodal models for rare disease detection, advanced generative approaches to handle noisy labels, and zero-shot learning strategies for unseen diseases. Additionally, the expanded dataset enhances disease coverage to better represent real-world clinical settings, offering a valuable resource for future research. By synthesizing the insights and innovations of participating teams, we aim to advance the development of clinically realistic and generalizable diagnostic models for chest radiography.

Dazhou Guo, Zhanghexuan Ji, Yanzhou Su et al.

Precision medicine in the quantitative management of chronic diseases and oncology would be greatly improved if the Computed Tomography (CT) scan of any patient could be segmented, parsed and analyzed in a precise and detailed way. However, there is no such fully annotated CT dataset with all anatomies delineated for training because of the exceptionally high manual cost, the need for specialized clinical expertise, and the time required to finish the task. To this end, we proposed a novel continual learning-driven CT model that can segment complete anatomies presented using dozens of previously partially labeled datasets, dynamically expanding its capacity to segment new ones without compromising previously learned organ knowledge. Existing multi-dataset approaches are not able to dynamically segment new anatomies without catastrophic forgetting and would encounter optimization difficulty or infeasibility when segmenting hundreds of anatomies across the whole range of body regions. Our single unified CT segmentation model, CL-Net, can highly accurately segment a clinically comprehensive set of 235 fine-grained whole-body anatomies. Composed of a universal encoder, multiple optimized and pruned decoders, CL-Net is developed using 13,952 CT scans from 20 public and 16 private high-quality partially labeled CT datasets of various vendors, different contrast phases, and pathologies. Extensive evaluation demonstrates that CL-Net consistently outperforms the upper limit of an ensemble of 36 specialist nnUNets trained per dataset with the complexity of 5% model size and significantly surpasses the segmentation accuracy of recent leading Segment Anything-style medical image foundation models by large margins. Our continual learning-driven CL-Net model would lay a solid foundation to facilitate many downstream tasks of oncology and chronic diseases using the most widely adopted CT imaging.

Andrew M. Nguyen, Jianfei Liu, Tejas Sudharshan Mathai et al.

Coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD). However, manual assessment of CAC often requires radiological expertise, time, and invasive imaging techniques. The purpose of this multicenter study is to validate an automated cardiac plaque detection model using a 3D multiclass nnU-Net for gated and non-gated non-contrast chest CT volumes. CT scans were performed at three tertiary care hospitals and collected as three datasets, respectively. Heart, aorta, and lung segmentations were determined using TotalSegmentator, while plaques in the coronary arteries and heart valves were manually labeled for 801 volumes. In this work we demonstrate how the nnU-Net semantic segmentation pipeline may be adapted to detect plaques in the coronary arteries and valves. With a linear correction, nnU-Net deep learning methods may also accurately estimate Agatston scores on chest non-contrast CT scans. Compared to manual Agatson scoring, automated Agatston scoring indicated a slope of the linear regression of 0.841 with an intercept of +16 HU (R2 = 0.97). These results are an improvement over previous work assessing automated Agatston score computation in non-gated CT scans.

Tanjin Taher Toma, Tejas Sudharshan Mathai, Bikash Santra et al.

Accurate segmentation of pheochromocytoma (PCC) in abdominal CT scans is essential for tumor burden estimation, prognosis, and treatment planning. It may also help infer genetic clusters, reducing reliance on expensive testing. This study systematically evaluates anatomical priors to identify configurations that improve deep learning-based PCC segmentation. We employed the nnU-Net framework to evaluate eleven annotation strategies for accurate 3D segmentation of pheochromocytoma, introducing a set of novel multi-class schemes based on organ-specific anatomical priors. These priors were derived from adjacent organs commonly surrounding adrenal tumors (e.g., liver, spleen, kidney, aorta, adrenal gland, and pancreas), and were compared against a broad body-region prior used in previous work. The framework was trained and tested on 105 contrast-enhanced CT scans from 91 patients at the NIH Clinical Center. Performance was measured using Dice Similarity Coefficient (DSC), Normalized Surface Distance (NSD), and instance-wise F1 score. Among all strategies, the Tumor + Kidney + Aorta (TKA) annotation achieved the highest segmentation accuracy, significantly outperforming the previously used Tumor + Body (TB) annotation across DSC (p = 0.0097), NSD (p = 0.0110), and F1 score (25.84% improvement at an IoU threshold of 0.5), measured on a 70-30 train-test split. The TKA model also showed superior tumor burden quantification (R^2 = 0.968) and strong segmentation across all genetic subtypes. In five-fold cross-validation, TKA consistently outperformed TB across IoU thresholds (0.1 to 0.5), reinforcing its robustness and generalizability. These findings highlight the value of incorporating relevant anatomical context into deep learning models to achieve precise PCC segmentation, offering a valuable tool to support clinical assessment and longitudinal disease monitoring in PCC patients.

Nicole Tran, Anisa Prasad, Yan Zhuang et al.

The segmentation of multiple organs in multi-parametric MRI studies is critical for many applications in radiology, such as correlating imaging biomarkers with disease status (e.g., cirrhosis, diabetes). Recently, three publicly available tools, such as MRSegmentator (MRSeg), TotalSegmentator MRI (TS), and TotalVibeSegmentator (VIBE), have been proposed for multi-organ segmentation in MRI. However, the performance of these tools on specific MRI sequence types has not yet been quantified. In this work, a subset of 40 volumes from the public Duke Liver Dataset was curated. The curated dataset contained 10 volumes each from the pre-contrast fat saturated T1, arterial T1w, venous T1w, and delayed T1w phases, respectively. Ten abdominal structures were manually annotated in these volumes. Next, the performance of the three public tools was benchmarked on this curated dataset. The results indicated that MRSeg obtained a Dice score of 80.7 $\pm$ 18.6 and Hausdorff Distance (HD) error of 8.9 $\pm$ 10.4 mm. It fared the best ($p < .05$) across the different sequence types in contrast to TS and VIBE.

Tejas Sudharshan Mathai, Sungwon Lee, Thomas C. Shen et al.

Robust localization of lymph nodes (LNs) in multiparametric MRI (mpMRI) is critical for the assessment of lymphadenopathy. Radiologists routinely measure the size of LN to distinguish benign from malignant nodes, which would require subsequent cancer staging. Sizing is a cumbersome task compounded by the diverse appearances of LNs in mpMRI, which renders their measurement difficult. Furthermore, smaller and potentially metastatic LNs could be missed during a busy clinical day. To alleviate these imaging and workflow problems, we propose a pipeline to universally detect both benign and metastatic nodes in the body for their ensuing measurement. The recently proposed VFNet neural network was employed to identify LN in T2 fat suppressed and diffusion weighted imaging (DWI) sequences acquired by various scanners with a variety of exam protocols. We also use a selective augmentation technique known as Intra-Label LISA (ILL) to diversify the input data samples the model sees during training, such that it improves its robustness during the evaluation phase. We achieved a sensitivity of $\sim$83\% with ILL vs. $\sim$80\% without ILL at 4 FP/vol. Compared with current LN detection approaches evaluated on mpMRI, we show a sensitivity improvement of $\sim$9\% at 4 FP/vol.

Benjamin Hou, Tejas Sudharshan Mathai, Pritam Mukherjee et al.

Purpose: To automate contrast phase classification in CT using organ-specific features extracted from a widely used segmentation tool with a lightweight decision tree classifier. Materials and Methods: This retrospective study utilized three public CT datasets from separate institutions. The phase prediction model was trained on the WAW-TACE (median age: 66 [60,73]; 185 males) dataset, and externally validated on the VinDr-Multiphase (146 males; 63 females; 56 unk) and C4KC-KiTS (median age: 61 [50.68; 123 males) datasets. Contrast phase classification was performed using organ-specific features extracted by TotalSegmentator, followed by prediction using a gradient-boosted decision tree classifier. Results: On the VinDr-Multiphase dataset, the phase prediction model achieved the highest or comparable AUCs across all phases (>0.937), with superior F1-scores in the non-contrast (0.994), arterial (0.937), and delayed (0.718) phases. Statistical testing indicated significant performance differences only in the arterial and delayed phases (p<0.05). On the C4KC-KiTS dataset, the phase prediction model achieved the highest AUCs across all phases (>0.991), with superior F1-scores in arterial/venous (0.968) and delayed (0.935) phases. Statistical testing confirmed significant improvements over all baseline models in these two phases (p<0.05). Performance in the non-contrast class, however, was comparable across all models, with no statistically significant differences observed (p>0.05). Conclusion: The lightweight model demonstrated strong performance relative to all baseline models, and exhibited robust generalizability across datasets from different institutions.

Xinya Wang, Tejas Sudharshan Mathai, Boah Kim et al.

Multiphase CT studies are routinely obtained in clinical practice for diagnosis and management of various diseases, such as cancer. However, the CT studies can be acquired with low radiation doses, different scanners, and are frequently affected by motion and metal artifacts. Prior approaches have targeted the quality improvement of one specific CT phase (e.g., non-contrast CT). In this work, we hypothesized that leveraging multiple CT phases for the quality enhancement of one phase may prove advantageous for downstream tasks, such as segmentation. A 3D progressive fusion and non-local (PFNL) network was developed. It was trained with three degraded (low-quality) phases (non-contrast, arterial, and portal venous) to enhance the quality of the portal venous phase. Then, the effect of scan quality enhancement was evaluated using a proxy task of pancreas segmentation, which is useful for tracking pancreatic cancer. The proposed approach improved the pancreas segmentation by 3% over the corresponding low-quality CT scan. To the best of our knowledge, we are the first to harness multiphase CT for scan quality enhancement and improved pancreas segmentation.