Routine clinical imaging of the retina using optical coherence tomography (OCT) is performed with large slice spacing, resulting in highly anisotropic images and a sparsely scanned retina. Most learning-based methods circumvent the problems arising from the anisotropy by using 2D approaches rather than performing volumetric analyses. These approaches inherently bear the risk of generating inconsistent results for neighboring B-scans. For example, 2D retinal layer segmentations can have irregular surfaces in 3D. Furthermore, the typically used convolutional neural networks are bound to the resolution of the training data, which prevents their usage for images acquired with a different imaging protocol. Implicit neural representations (INRs) have recently emerged as a tool to store voxelized data as a continuous representation. Using coordinates as input, INRs are resolution-agnostic, which allows them to be applied to anisotropic data. In this paper, we propose two frameworks that make use of this characteristic of INRs for dense 3D analyses of retinal OCT volumes. 1) We perform inter-B-scan interpolation by incorporating additional information from en-face modalities, that help retain relevant structures between B-scans. 2) We create a resolution-agnostic retinal atlas that enables general analysis without strict requirements for the data. Both methods leverage generalizable INRs, improving retinal shape representation through population-based training and allowing predictions for unseen cases. Our resolution-independent frameworks facilitate the analysis of OCT images with large B-scan distances, opening up possibilities for the volumetric evaluation of retinal structures and pathologies. Our code is available at <a href='https://github.com/tkepp/ResA-OCT'>https://github.com/tkepp/ResA-OCT</a>

Bone marrow examination has become increasingly important for the diagnosis and treatment of hematologic and other illnesses. The present methods for analyzing bone marrow biopsy samples involve subjective and inaccurate assessments by visual estimation by pathologists. Thus, there is a need to develop automated tools to assist in the analysis of bone marrow samples. However, there is a lack of publicly available standardized and high-quality datasets that can aid in the research and development of automated tools that can provide consistent and objective measurements. In this paper, we present a comprehensive Bone Marrow Biopsy (BaMBo) dataset consisting 185 semantic-segmented bone marrow biopsy images, specifically designed for the automated calculation of bone marrow cellularity. Our dataset comprises high-resolution, generalized images of bone marrow biopsies, each annotated with precise semantic segmentation of different haematological components. These components are divided into 4 classes: Bony trabeculae, adipocytes, cellular region and Background (BG). The annotations were performed with the help of two experienced hematopathologists that were supported by state-of-the-art Deep Learning (DL) models and image processing techniques. We then used our dataset to train a custom U-Net based DL model that performs multi-class semantic segmentation of the images (Dice Score: 0.831± 0.099) and predicts the cellularity of these images with an error of 5.9% ± 8.8%. This shows the applicability of our data for future research in this domain. Our code is available at <a href='https://github.com/AI-in-Medicine-IIT-Ropar/BaMbo-Bone-Marrow-Biopsy'>https://github.com/AI-in-Medicine-IIT-Ropar/BaMbo-Bone-Marrow-Biopsy</a>

Lung cancer is the leading cause of cancer-related mortality in adults worldwide. Screening high-risk individuals with annual low-dose CT (LDCT) can support earlier detection and reduce deaths, but widespread implementation may strain the already limited radiology workforce. Artificial intelligence (AI) models have shown potential in estimating lung cancer risk from LDCT scans. However, high-risk populations for lung cancer are diverse, and these models’ performance across diverse demographic groups remains an open question. In this study, we used the JustEFAB ethical framework to evaluate potential performance disparities and fairness in two AI-based risk estimation models for lung cancer screening: the Sybil lung cancer risk model and the Venkadesh21 nodule risk estimator. We also examined disparities in the PanCan2b logistic regression model recommended in the British Thoracic Society nodule management guideline. Both AI-based models were trained on data from the U.S.-based National Lung Screening Trial (NLST), and assessed on a held-out NLST validation set. We evaluated area under the ROC curve (AUROC), sensitivity, and specificity across demographic subgroups, and explored potential confounding from clinical risk factors. We observed a statistically significant AUROC difference in Sybil’s performance between women (0.88, 95% CI: 0.86, 0.90) and men (0.81, 95% CI: 0.78, 0.84, p < .001). At 90% specificity, Venkadesh21 showed lower sensitivity for Black (0.39, 95% CI: 0.23, 0.59) than White participants (0.69, 95% CI: 0.65, 0.73). These differences were not explained by available clinical confounders and may be classified as unfair biases according to JustEFAB. Our findings highlight the importance of improving and monitoring model performance across underrepresented subgroups in lung cancer screening, as well as further research on algorithmic fairness in this field.

Accurately translating medical images between different modalities, such as Computed Tomography (CT) to Magnetic Resonance Imaging (MRI), has numerous downstream clinical and machine learning applications. While several methods have been proposed to achieve this, they often prioritize perceptual quality with respect to output domain features over preserving anatomical fidelity. However, maintaining anatomy during translation is essential for many tasks, e.g., when leveraging masks from the input domain to develop a segmentation model with images translated to the output domain. To address these challenges, we propose ContourDiff with Spatially Coherent Guided Diffusion (SCGD), a novel framework that leverages domain-invariant anatomical contour representations of images. These representations are simple to extract from images, yet form precise spatial constraints on their anatomical content. We introduce a diffusion model that converts contour representations of images from arbitrary input domains into images in the output domain of interest. By applying the contour as a constraint at every diffusion sampling step, we ensure the preservation of anatomical content. We evaluate our method on challenging lumbar spine and hip-and-thigh CT-to-MRI translation tasks, via (1) the performance of segmentation models trained on translated images applied to real MRIs, and (2) the foreground FID and KID of translated images with respect to real MRIs. Our method outperforms other unpaired image translation methods by a significant margin across almost all metrics and scenarios. Moreover, it achieves this without the need to access any input domain information during training and we further verify its zero-shot capability, showing that a model trained on one anatomical region can be directly applied to unseen regions without retraining. Our code is available at <a href='https://github.com/mazurowski-lab/ContourDiff'>https://github.com/mazurowski-lab/ContourDiff</a>

Artificial Intelligence (AI) models have demonstrated expert-level performance in melanoma detection, yet their clinical adoption is hindered by performance disparities across demographic subgroups such as gender, race, and age. Previous efforts to benchmark the performance of AI models have primarily focused on assessing model performance using group fairness metrics that rely on the Area Under the Receiver Operating Characteristic curve (AUROC), which does not provide insights into a model’s ability to provide accurate estimates. In line with clinical assessments, this paper addresses this gap by incorporating calibration as a complementary benchmarking metric to AUROC-based fairness metrics. Calibration evaluates the alignment between predicted probabilities and observed event rates, offering deeper insights into subgroup biases. We assess the performance of the leading skin cancer detection algorithm of the ISIC 2020 Challenge on the ISIC 2020 Challenge dataset and the PROVE-AI dataset, and compare it with the second- and third-place models, focusing on subgroups defined by sex, race (Fitzpatrick Skin Tone), and age. Our findings reveal that while existing models enhance discriminative accuracy, they often over-diagnose risk and exhibit calibration issues when applied to new datasets. This study underscores the necessity for comprehensive model auditing strategies and extensive metadata collection to achieve equitable AI-driven healthcare solutions.

Deep learning models have recently achieved accuracy comparable to traditional iterative methods for deformable image registration. However, their performance often degrades when test data deviate from the training distribution, for example due to changes in imaging protocols or subject demographics. While data augmentation can improve robustness, it may not account for all types of domain shifts, particularly those that are unpredictable. To address this limitation, recent approaches have explored training on synthetic images with diverse structures and intensities to promote generalization across modalities and anatomical regions. Nevertheless, the robustness of such models to other types of domain shifts, and their adaptability to specific registration tasks, remains unclear.<br>In this study, we investigate whether transfer learning can enhance registration model robustness under unforeseen domain shifts. We first train a generic, weakly supervised model on synthetic data, then fine-tune it on target domains. Specifically, we examine: (1) how design factors in synthetic data influence cross-domain performance (e.g., brain MRI vs. lung CT); (2) the efficiency of fine-tuning compared to training from scratch; and (3) the robustness of fine-tuned models on previously unseen datasets. Our results show that the fine-tuned model achieved the most consistent registration performance across datasets. It also required fewer training epochs and less target domain data than from-scratch training. Furthermore, while the use of random geometric shapes and dynamic contrast in the synthetic data was critical for cross-domain performance, we found that different target domains may benefit from different synthetic data. These findings support transfer learning as a promising strategy to improve robustness to diverse domain shifts in deformable image registration.

Medical image segmentation involves partitioning medical images into meaningful regions, with a focus on identifying anatomical structures and lesions. It has broad applications in healthcare, and deep learning methods have enabled significant advancements in automating this process. Recently, the introduction of the Segmentation Anything Model (SAM), the first foundation model for segmentation task, has prompted researchers to adapt it for the medical domain to improve performance across various tasks. However, SAM’s large model size and high GPU requirements hinder its scalability and development in the medical domain. To address these challenges, research has increasingly focused on lightweight adaptations of SAM to reduce its parameter count, enabling training with limited GPU resources while maintaining competitive segmentation performance. In this work, we propose MCP-MedSAM, a powerful and lightweight medical SAM model designed to be trainable on a single A100 GPU with 40GB of memory within one day while delivering superior segmentation performance. Recognizing the significant internal differences between modalities and the need for direct segmentation target information within bounding boxes, we introduce two kinds of prompts: the modality prompt and the content prompt. After passing through the prompt encoder, their embedding representations can further improve the segmentation performance by incorporating more relevant information without adding significant training overhead. Additionally, we adopt an effective modality-based data sampling strategy to address data imbalance between modalities, ensuring more balanced performance across all modalities. Our method was trained and evaluated using a large-scale challenge dataset, compared to top-ranking methods on the challenge leaderboard, MCP-MedSAM achieved superior performance while requiring only one day of training on a single GPU. The code is publicly available at <a href='https://github.com/dong845/MCP-MedSAM'>https://github.com/dong845/MCP-MedSAM</a>

Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind—Segment Anything Model (SAM)—has been developed only recently and has shown similar promise. However, there are still no sys- tematic analyses or “best-practice” guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and finetuning algorithms across 18 combinations and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameterefficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, and (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at <a href='https://github.com/mazurowski-lab/finetune-SAM'>https://github.com/mazurowskilab/finetune-SAM</a>