深度学习在医学应用中已取得显著进展，可辅助基于胸部X光图像的疾病诊断。然而，利用新数据扩展模型能力仍是一项挑战，持续学习（CL）旨在解决这一问题。以往研究主要基于分类性能来评估持续学习策略；但在医疗保健等敏感领域，评估模型在社会显著群体上的表现以检测潜在偏见至关重要。本研究利用领域特定的公平性指标，考察偏见如何随任务演化，以及不同持续学习策略如何影响这一演化过程。我们的结果表明，无遗忘学习（Learning without Forgetting）和伪标签（Pseudo-Label）方法取得了最优的分类性能，但伪标签方法的偏见更小。
英文摘要：
Deep Learning has advanced significantly in medical applications, aiding disease diagnosis in Chest X-ray images. However, expanding model capabilities with new data remains a challenge, which Continual Learning (CL) aims to address. Previous studies have evaluated CL strategies based on classification performance; however, in sensitive domains such as healthcare, it is crucial to assess performance across socially salient groups to detect potential biases. This study examines how bias evolves across tasks using domain-specific fairness metrics and how different CL strategies impact this evolution. Our results show that Learning without Forgetting and Pseudo-Label achieve optimal classification performance, but Pseudo-Label is less biased.
FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification
Center for Artificial Intelligence and Robotics, New York University Abu Dhabi（纽约大学阿布扎比分校人工智能与机器人中心）；New York University（纽约大学）；Harvard University（哈佛大学）
Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects
Faculty of Informatics and Data Science, University of Regensburg（雷根斯堡大学信息学与数据科学学院）；University of California, Davis（加州大学戴维斯分校）；Motilal Nehru National Institute of Technology Allahabad（莫蒂拉尔·尼赫鲁国立阿拉哈巴德技术学院）；Faculty of Electrical Engineering and Information Technology, RWTH Aachen University（亚琛工业大学电气工程与信息技术学院）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
This work investigates continual learning of two segmentation tasks in brain MRI with neural networks. To explore in this context the capabilities of current methods for countering catastrophic forgetting of the first task when a new one is learned, we investigate elastic weight consolidation, a recently proposed method based on Fisher information, originally evaluated on reinforcement learning of Atari games. We use it to sequentially learn segmentation of normal brain structures and then segmentation of white matter lesions. Our findings show this recent method reduces catastrophic forgettin…
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
The University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（矢量研究所）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）
Centre for Intelligent Machines, McGill University（麦吉尔大学智能机器中心）
Although deep learning (DL) models have shown great success in many medical image analysis tasks, deployment of the resulting models into real clinical contexts requires: (1) that they exhibit robustness and fairness across different sub-populations, and (2) that the confidence in DL model predictions be accurately expressed in the form of uncertainties. Unfortunately, recent studies have indeed shown significant biases in DL models across demographic subgroups (e.g., race, sex, age) in the context of medical image analysis, indicating a lack of fairness in the models. Although several methods…
Distribution-Aware Replay for Continual MRI Segmentation
Technical University of Darmstadt（达姆施塔特工业大学）；Stanford University（斯坦福大学）；The Hessian Center for Artificial Intelligence: hessian.AI（黑森人工智能中心（hessian.AI））
FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA
Harvard AI and Robotics Lab（哈佛人工智能与机器人实验室）；Harvard University（哈佛大学）；Harvard Ophthalmology AI lab（哈佛眼科人工智能实验室）；University of Central Florida（佛罗里达中央大学）；University of Louisiana at Lafayette（路易斯安那州立大学拉斐特分校）；New York University（纽约大学）；NYUAD Center for Artificial Intelligence and Robotics（纽约大学阿布扎克人工智能与机器人中心）
Fairness in Multi-modal Medical Diagnosis with Demonstration Selection
Arizona State University（亚利桑那州立大学）；University of Rochester（罗切斯特大学）；University of Virginia（弗吉尼亚大学）；UCL（伦敦大学学院）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Central Florida（佛罗里达中央大学）
Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Review
Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州研究院）；Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院计算技术研究所中国科学院智能信息处理重点实验室）
Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance
Department of Data Science, Dana-Farber Cancer Institute（丹娜-法伯癌症研究所数据科学系）；AI in Medicine, Technical University of Munich（慕尼黑工业大学医学人工智能）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Department of Computing, Imperial College London（伦敦帝国理工学院计算系）；Harvard Medical School（哈佛医学院）
Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial static training set, model performance and reliability suffer from changes of acquisition characteristics as data and targets may become inconsistent. Continual learning can help to adapt models to the changing environment by training on a continuous data stream. However, continual manual expert labelling of medical imaging requires substantial effort. Thus, ways…
Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans
Queen Mary University of London（伦敦玛丽女王大学）；National Technical University of Athens（雅典国家技术大学）；National Infrastructures for Research and Technology（国家研究与技术基础设施机构）
The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
Department of Computer Science and Engineering, The Ohio State University（计算机科学与工程系，俄亥俄州立大学）；Department of Biomedical Informatics, The Ohio State University（生物医学信息学系，俄亥俄州立大学）；Department of Ophthalmology and Visual Sciences, The Ohio State University（眼科学与视觉科学系，俄亥俄州立大学）
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious, laborious, and time consuming, but it also demands costly, specialty-oriented skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method to naturally integrate active learning and transfer learning (fine-tuning) into a si…
InvCoSS: Inversion-driven Continual Self-supervised Learning in Medical Multi-modal Image Pre-training
University of Electronic Science and Technology of China（电子科技大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Brain-Computer Interface & Brain-Inspired Intelligence Key Laboratory of Sichuan Province（四川省脑机接口与脑启发智能重点实验室）
The University of British Columbia（不列颠哥伦比亚大学）；The Chinese University of Hong Kong（香港中文大学）
Mitigating the discrimination of machine learning models has gained increasing attention in medical image analysis. However, rare works focus on fair treatments for patients with multiple sensitive demographic ones, which is a crucial yet challenging problem for real-world clinical applications. In this paper, we propose a novel method for fair representation learning with respect to multi-sensitive attributes. We pursue the independence between target and multi-sensitive representations by achieving orthogonality in the representation space. Concretely, we enforce the column space orthogonali…
Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matching
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Lassonde School of Engineering, York University（约克大学拉萨onde工程学院）
Stanford University（斯坦福大学）；Duke University（杜克大学）；Arizona State University（亚利桑那州立大学）
Despite the routine use of electronic health record (EHR) data by radiologists to contextualize clinical history and inform image interpretation, the majority of deep learning architectures for medical imaging are unimodal, i.e., they only learn features from pixel-level information. Recent research revealing how race can be recovered from pixel data alone highlights the potential for serious biases in models which fail to account for demographics and other key patient attributes. Yet the lack of imaging datasets which capture clinical context, inclusive of demographics and longitudinal medica…
Arizona State University（亚利桑那州立大学）；Stanford University（斯坦福大学）；Mayo Clinic（梅奥诊所）
Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image analysis, leaving several important questions unanswered. As the first step in this direction, we conduct a systematic study on the transferability of models pre-trained on iNat2021, the most recent large-scale fine-grained dataset, and 14 top self-supervised ImageNet models on 7 diverse medical tasks in comparison with the supervised ImageNet model. Furtherm…
Intersectional Fairness in Vision-Language Models for Medical Image Disease Classification
Biomedical Data Analysis and Visualisation (BDAV) Lab, School of Computer Science（生物医学数据分析与可视化实验室，计算机科学学院）；Sydney School of Public Health（悉尼公共卫生学院）；School of Computing（计算学院）
Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distribution
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（A*STAR））；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Princeton University（普林斯顿大学）；Shanghai Jiaotong University（上海交通大学）；University of Pennsylvania（宾夕法尼亚大学）；RIKEN AIP（理化学研究所先进智能项目中心）；University of Tokyo（东京大学）
Fairness and accountability are two essential pillars for trustworthy Artificial Intelligence (AI) in healthcare. However, the existing AI model may be biased in its decision marking. To tackle this issue, we propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system. Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model. We further impose an orthogonality regularization to force the two modules to be ind…
Towards unraveling calibration biases in medical image analysis
Hospital Italiano de Buenos Aires（布宜诺斯艾利斯意大利医院）；Universidad Tecnológica Nacional（国立技术大学）；Research Institute for Signals, Systems and Computational Intelligence sinc(i) (FICH-UNL/CONICET)（信号、系统与计算智能研究所sinc(i)（FICH-UNL/阿根廷国家科学与技术研究理事会））
Towards Fair Medical AI: Adversarial Debiasing of 3D CT Foundation Embeddings
Rice University（莱斯大学）；The Johns Hopkins University（约翰斯·霍普金斯大学）；McGovern Medical School, UTHealth Houston（德克萨斯大学健康科学中心休斯顿分校麦戈文医学院）；The Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）；Sidney Kimmel Comprehensive Cancer Center, The Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院西德尼·基梅尔综合癌症中心）；Google Research（谷歌研究院）；Department of Neurosurgery, The Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院神经外科）
Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and targets become inconsistent with their initial static training set. Continual learning can adapt to a continuous data stream of a changing imaging environment. Here, we propose a method for continual active learning on a data stream of medical images. It recognizes shifts or additions of new imaging sources - domains -, adapts training accordingly, and selects …
Massachusetts Institute of Technology（麻省理工学院）；University of Toronto（多伦多大学）；University of Tübingen（蒂宾根大学）；University of Adelaide（阿德莱德大学）；Stanford University（斯坦福大学）
Deep learning models have reached or surpassed human-level performance in the field of medical imaging, especially in disease diagnosis using chest x-rays. However, prior work has found that such classifiers can exhibit biases in the form of gaps in predictive performance across protected groups. In this paper, we question whether striving to achieve zero disparities in predictive performance (i.e. group fairness) is the appropriate fairness definition in the clinical setting, over minimax fairness, which focuses on maximizing the performance of the worst-case group. We benchmark the performan…
TU Dresden（德累斯顿工业大学）；Carl Zeiss Meditec AG（卡尔蔡司医疗技术股份公司）
The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware regularization losses based on batch estimates of Demographic Parity, Equalized Odds, and a novel Intersection-over-Union measure. The experiments performed on facial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanoma classification challenge show the effectiveness of our proposed fairness losses for bias mitigation as they improve model fairness wh…
Continual atlas-based segmentation of prostate MRI
Technical University of Darmstadt（达姆施塔特工业大学）；Stanford University（斯坦福大学）；University of Cologne（科隆大学）；University of Frankfurt（法兰克福大学）；University Medical Center Mainz（美因茨大学医学中心）
