Patrick Godau , Piotr Kalinowski , Evangelia Christodoulou , Annika Reinke , Minu Tizabi , Luciana Ferrer , Paul Jäger , Lena Maier-Hein
{"title":"Navigating prevalence shifts in image analysis algorithm deployment","authors":"Patrick Godau , Piotr Kalinowski , Evangelia Christodoulou , Annika Reinke , Minu Tizabi , Luciana Ferrer , Paul Jäger , Lena Maier-Hein","doi":"10.1016/j.media.2025.103504","DOIUrl":"10.1016/j.media.2025.103504","url":null,"abstract":"<div><div>Domain gaps are significant obstacles to the clinical implementation of machine learning (ML) solutions for medical image analysis. Although current research emphasizes new training methods and network architectures, the specific impact of prevalence shifts on algorithms in real-world applications is often overlooked. Differences in class frequencies between development and deployment data are crucial, particularly for the widespread adoption of artificial intelligence (AI), as disease prevalence can vary greatly across different times and locations. Our contribution is threefold. Based on a diverse set of 30 medical classification tasks (1) we demonstrate that lack of prevalence shift handling can have severe consequences on the quality of calibration, decision threshold, and performance assessment. Furthermore, (2) we show that prevalences can be accurately and reliably estimated in a data-driven manner. Finally, (3) we propose a new workflow for prevalence-aware image classification that uses estimated deployment prevalences to adjust a trained classifier to a new environment, without requiring additional annotated deployment data. Comprehensive experiments indicate that our proposed approach could contribute to generating better classifier decisions and more reliable performance estimates compared to current practice.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"102 ","pages":"Article 103504"},"PeriodicalIF":10.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haorui He , Abhirup Banerjee , Robin P. Choudhury , Vicente Grau
{"title":"Deep learning based coronary vessels segmentation in X-ray angiography using temporal information","authors":"Haorui He , Abhirup Banerjee , Robin P. Choudhury , Vicente Grau","doi":"10.1016/j.media.2025.103496","DOIUrl":"10.1016/j.media.2025.103496","url":null,"abstract":"<div><div>Invasive coronary angiography (ICA) is the gold standard imaging modality during cardiac interventions. Accurate segmentation of coronary vessels in ICA is required for aiding diagnosis and creating treatment plans. Current automated algorithms for vessel segmentation face task-specific challenges, including motion artifacts and unevenly distributed contrast, as well as the general challenge inherent to X-ray imaging, which is the presence of shadows from overlapping organs in the background. To address these issues, we present Temporal Vessel Segmentation Network (TVS-Net) model that fuses sequential ICA information into a novel densely connected 3D encoder-2D decoder structure with a loss function based on elastic interaction. We develop our model using an ICA dataset comprising 323 samples, split into 173 for training, 82 for validation, and 68 for testing, with a relatively relaxed annotation protocol that produced coarse-grained samples, and achieve 83.4% Dice and 84.3% recall on the test dataset. We additionally perform an external evaluation over 60 images from a local hospital, achieving 78.5% Dice and 82.4% recall and outperforming the state-of-the-art approaches. We also conduct a detailed manual re-segmentation for evaluation only on a subset of the first dataset under strict annotation protocol, achieving a Dice score of 86.2% and recall of 86.3% and surpassing even the coarse-grained gold standard used in training. The results indicate our TVS-Net is effective for multi-frame ICA segmentation, highlights the network’s generalizability and robustness across diverse settings, and showcases the feasibility of weak supervision in ICA segmentation.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"102 ","pages":"Article 103496"},"PeriodicalIF":10.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MedIAnomaly: A comparative study of anomaly detection in medical images","authors":"Yu Cai , Weiwen Zhang , Hao Chen , Kwang-Ting Cheng","doi":"10.1016/j.media.2025.103500","DOIUrl":"10.1016/j.media.2025.103500","url":null,"abstract":"<div><div>Anomaly detection (AD) aims at detecting abnormal samples that deviate from the expected normal patterns. Generally, it can be trained merely on normal data, without a requirement for abnormal samples, and thereby plays an important role in rare disease recognition and health screening in the medical domain. Despite the emergence of numerous methods for medical AD, the lack of a fair and comprehensive evaluation causes ambiguous conclusions and hinders the development of this field. To address this problem, this paper builds a benchmark with unified comparison. Seven medical datasets with five image modalities, including chest X-rays, brain MRIs, retinal fundus images, dermatoscopic images, and histopathology images, are curated for extensive evaluation. Thirty typical AD methods, including reconstruction and self-supervised learning-based methods, are involved in comparison of image-level anomaly classification and pixel-level anomaly segmentation. Furthermore, for the first time, we systematically investigate the effect of key components in existing methods, revealing unresolved challenges and potential future directions. The datasets and code are available at <span><span>https://github.com/caiyu6666/MedIAnomaly</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"102 ","pages":"Article 103500"},"PeriodicalIF":10.7,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Balamurali Murugesan , Sukesh Adiga Vasudeva , Bingyuan Liu , Herve Lombaert , Ismail Ben Ayed , Jose Dolz
{"title":"Neighbor-aware calibration of segmentation networks with penalty-based constraints","authors":"Balamurali Murugesan , Sukesh Adiga Vasudeva , Bingyuan Liu , Herve Lombaert , Ismail Ben Ayed , Jose Dolz","doi":"10.1016/j.media.2025.103501","DOIUrl":"10.1016/j.media.2025.103501","url":null,"abstract":"<div><div>Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly in real-world domains such as healthcare. Recent literature on calibrating deep segmentation networks has resulted in substantial progress. Nevertheless, these approaches are strongly inspired by the advancements in classification tasks, and thus their uncertainty is usually modeled by leveraging the information of individual pixels, disregarding the local structure of the object of interest. Indeed, only the recent <em>Spatially Varying Label Smoothing (SVLS)</em> approach considers pixel spatial relationships across classes, by softening the pixel label assignments with a discrete spatial Gaussian kernel. In this work, we first present a constrained optimization perspective of SVLS and demonstrate that it enforces an implicit constraint on soft class proportions of surrounding pixels. Furthermore, our analysis shows that SVLS lacks a mechanism to balance the contribution of the constraint with the primary objective, potentially hindering the optimization process. Based on these observations, we propose NACL (Neighbor Aware CaLibration), a principled and simple solution based on equality constraints on the logit values, which enables to control explicitly both the enforced constraint and the weight of the penalty, offering more flexibility. Comprehensive experiments on a wide variety of well-known segmentation benchmarks demonstrate the superior calibration performance of the proposed approach, without affecting its discriminative power. Furthermore, ablation studies empirically show the model agnostic nature of our approach, which can be used to train a wide span of deep segmentation networks. The code is available at <span><span>https://github.com/Bala93/MarginLoss</span><svg><path></path></svg></span></div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103501"},"PeriodicalIF":10.7,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ziyan Huang , Zhongying Deng , Jin Ye , Haoyu Wang , Yanzhou Su , Tianbin Li , Hui Sun , Junlong Cheng , Jianpin Chen , Junjun He , Yun Gu , Shaoting Zhang , Lixu Gu , Yu Qiao
{"title":"A-Eval: A benchmark for cross-dataset and cross-modality evaluation of abdominal multi-organ segmentation","authors":"Ziyan Huang , Zhongying Deng , Jin Ye , Haoyu Wang , Yanzhou Su , Tianbin Li , Hui Sun , Junlong Cheng , Jianpin Chen , Junjun He , Yun Gu , Shaoting Zhang , Lixu Gu , Yu Qiao","doi":"10.1016/j.media.2025.103499","DOIUrl":"10.1016/j.media.2025.103499","url":null,"abstract":"<div><div>Although deep learning has revolutionized abdominal multi-organ segmentation, its models often struggle with generalization due to training on small-scale, specific datasets and modalities. The recent emergence of large-scale datasets may mitigate this issue, but some important questions remain unsolved: <strong>Can models trained on these large datasets generalize well across different datasets and imaging modalities? If yes/no, how can we further improve their generalizability?</strong> To address these questions, we introduce A-Eval, a benchmark for the cross-dataset and cross-modality Evaluation (’Eval’) of Abdominal (’A’) multi-organ segmentation, integrating seven datasets across CT and MRI modalities. Our evaluations indicate that significant domain gaps persist despite larger data scales. While increased datasets improve generalization, model performance on unseen data remains inconsistent. Joint training across multiple datasets and modalities enhances generalization, though annotation inconsistencies pose challenges. These findings highlight the need for diverse and well-curated training data across various clinical scenarios and modalities to develop robust medical imaging models. The code and pre-trained models are available at <span><span>https://github.com/uni-medical/A-Eval</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103499"},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ming Li , Pengcheng Xu , Junjie Hu , Zeyu Tang , Guang Yang
{"title":"From challenges and pitfalls to recommendations and opportunities: Implementing federated learning in healthcare","authors":"Ming Li , Pengcheng Xu , Junjie Hu , Zeyu Tang , Guang Yang","doi":"10.1016/j.media.2025.103497","DOIUrl":"10.1016/j.media.2025.103497","url":null,"abstract":"<div><div>Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centers while ensuring data privacy and security are not compromised. Although numerous recent studies suggest or utilize federated learning based methods in healthcare, it remains unclear which ones have potential clinical utility. This review paper considers and analyzes the most recent studies up to May 2024 that describe federated learning based methods in healthcare. After a thorough review, we find that the vast majority are not appropriate for clinical use due to their methodological flaws and/or underlying biases which include but are not limited to privacy concerns, generalization issues, and communication costs. As a result, the effectiveness of federated learning in healthcare is significantly compromised. To overcome these challenges, we provide recommendations and promising opportunities that might be implemented to resolve these problems and improve the quality of model development in federated learning with healthcare.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103497"},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143418562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei-Chan Hsu , Monique Meuschke , Alejandro F. Frangi , Bernhard Preim , Kai Lawonn
{"title":"A survey of intracranial aneurysm detection and segmentation","authors":"Wei-Chan Hsu , Monique Meuschke , Alejandro F. Frangi , Bernhard Preim , Kai Lawonn","doi":"10.1016/j.media.2025.103493","DOIUrl":"10.1016/j.media.2025.103493","url":null,"abstract":"<div><div>Intracranial aneurysms (IAs) are a critical public health concern: they are asymptomatic and can lead to fatal subarachnoid hemorrhage in case of rupture. Neuroradiologists rely on advanced imaging techniques to identify aneurysms in a patient and consider the characteristics of IAs along with several other patient-related factors for rupture risk assessment and treatment decision-making. The process of diagnostic image reading is time-intensive and prone to inter- and intra-individual variations, so researchers have proposed many computer-aided diagnosis (CAD) systems for aneurysm detection and segmentation. This paper provides a comprehensive literature survey of semi-automated and automated approaches for IA detection and segmentation and proposes a taxonomy to classify the approaches. We also discuss the current issues and give some insight into the future direction of CAD systems for IA detection and segmentation.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103493"},"PeriodicalIF":10.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yifeng Wang , Luyang Luo , Mingxiang Wu , Qiong Wang , Hao Chen
{"title":"Learning robust medical image segmentation from multi-source annotations","authors":"Yifeng Wang , Luyang Luo , Mingxiang Wu , Qiong Wang , Hao Chen","doi":"10.1016/j.media.2025.103489","DOIUrl":"10.1016/j.media.2025.103489","url":null,"abstract":"<div><div>Collecting annotations from multiple independent sources could mitigate the impact of potential noises and biases from a single source, which is a common practice in medical image segmentation. However, learning segmentation networks from multi-source annotations remains a challenge due to the uncertainties brought by the variance of the annotations. In this paper, we proposed an Uncertainty-guided Multi-source Annotation Network (UMA-Net), which guided the training process by uncertainty estimation at both the pixel and the image levels. First, we developed an annotation uncertainty estimation module (AUEM) to estimate the pixel-wise uncertainty of each annotation, which then guided the network to learn from reliable pixels by a weighted segmentation loss. Second, a quality assessment module (QAM) was proposed to assess the image-level quality of the input samples based on the former estimated annotation uncertainties. Furthermore, instead of discarding the low-quality samples, we introduced an auxiliary predictor to learn from them and thus ensured the preservation of their representation knowledge in the backbone without directly accumulating errors within the primary predictor. Extensive experiments demonstrated the effectiveness and feasibility of our proposed UMA-Net on various datasets, including 2D chest X-ray segmentation dataset, 2D fundus image segmentation dataset, 3D breast DCE-MRI segmentation dataset, and the QUBIQ multi-task segmentation dataset. Code will be released at <span><span>https://github.com/wangjin2945/UMA-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103489"},"PeriodicalIF":10.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Piotr Keller , Muhammad Dawood , Brinder Singh Chohan , Fayyaz ul Amir Afsar Minhas
{"title":"HistoKernel: Whole slide image level Maximum Mean Discrepancy kernels for pan-cancer predictive modelling","authors":"Piotr Keller , Muhammad Dawood , Brinder Singh Chohan , Fayyaz ul Amir Afsar Minhas","doi":"10.1016/j.media.2025.103491","DOIUrl":"10.1016/j.media.2025.103491","url":null,"abstract":"<div><div>In computational pathology, labels are typically available only at the whole slide image (WSI) or patient level, necessitating weakly supervised learning methods that aggregate patch-level features or predictions to produce WSI-level scores for clinically significant tasks such as cancer subtype classification or survival analysis. However, existing approaches lack a theoretically grounded framework to capture the holistic distributional differences between the patch sets within WSIs, limiting their ability to accurately and comprehensively model the underlying pathology. To address this limitation, we introduce HistoKernel, a novel WSI-level Maximum Mean Discrepancy (MMD) kernel designed to quantify distributional similarity between WSIs using their local feature representation. HistoKernel enables a wide range of applications, including classification, regression, retrieval, clustering, survival analysis, multimodal data integration, and visualization of large WSI datasets. Additionally, HistoKernel offers a novel perturbation-based method for patch-level explainability. Our analysis over large pan-cancer datasets shows that HistoKernel achieves performance that typically matches or exceeds existing state-of-the-art methods across diverse tasks, including WSI retrieval (n = 9324), drug sensitivity regression (n = 551), point mutation classification (n = 3419), and survival analysis (n = 2291). By pioneering the use of kernel-based methods for a diverse range of WSI-level predictive tasks, HistoKernel opens new avenues for computational pathology research especially in terms of rapid prototyping on large and complex computational pathology datasets. Code and interactive visualization are available at: <span><span>https://histokernel.dcs.warwick.ac.uk/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103491"},"PeriodicalIF":10.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuanzhuo Zhu , Xianjun Li , Chen Niu , Fan Wang , Jianhua Ma
{"title":"Geometric deep learning with adaptive full-band spatial diffusion for accurate, efficient, and robust cortical parcellation","authors":"Yuanzhuo Zhu , Xianjun Li , Chen Niu , Fan Wang , Jianhua Ma","doi":"10.1016/j.media.2025.103492","DOIUrl":"10.1016/j.media.2025.103492","url":null,"abstract":"<div><div>Cortical parcellation delineates the cerebral cortex into distinct regions according to their distinctiveness in anatomy and/or function, which is a fundamental preprocess in brain cortex analysis and can influence the accuracy and specificity of subsequent neuroscientific research and clinical diagnosis. Conventional methods for cortical parcellation involve spherical mapping and multiple morphological feature computation, which are time-consuming and prone to error due to the spherical mapping process. Recent geometric learning approaches have attempted to automate this process by replacing the registration-based parcellation with deep learning-based methods. However, they have not fully addressed spherical mapping and cortical features quantification, making them sensitive to variations in mesh structures. In this work, to directly parcellate original surfaces in individual space with minimal preprocessing, we present a full-band spectral-accelerated spatial diffusion strategy for stable information propagation on highly folded cortical surfaces, contributing to adaptive learning of fine-grained geometric representations and the construction of a compact deep network (termed Cortex-Diffusion) for fully automatic parcellation. Using only raw 3D vertex coordinates and having merely 0.49 MB of learnable parameters, it demonstrates state-of-the-art parcellation accuracy, efficiency, and superior robustness to mesh resolutions and discretization patterns in both the cases of infant and adult brain imaging datasets.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"101 ","pages":"Article 103492"},"PeriodicalIF":10.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143418559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}