Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
Department of Computer Science, University of Rochester, NY, USA（罗切斯特大学计算机科学系）；Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN, USA（印第安纳大学医学院生物统计学与健康数据科学系）；Department of Computer Science, University of Central Florida, FL, USA（佛罗里达州立大学计算机科学系）
Vision-language models achieve expert-level performance on medical imaging tasks but exhibit significant diagnostic accuracy disparities across demographic groups. We introduce fairness-aware Low-Rank Adaptation for medical VLMs, combining parameter efficiency with explicit fairness optimization. Our key algorithmic contribution is a differentiable MaxAccGap loss that enables end-to-end optimization of accuracy parity across demographic groups. We propose three methods: FR-LoRA integrates MaxAccGap regularization into the training objective, GR-LoRA applies inverse frequency weighting to balance gradient contributions, and Hybrid-LoRA combines both mechanisms. Evaluated on 10,000 glaucoma fundus images, GR-LoRA reduces diagnostic accuracy disparities by 69% while maintaining 53.15% overall accuracy. Ablation studies reveal that strong regularization strength achieves optimal fairness with minimal accuracy trade-off, and race-specific optimization yields 60% disparity reduction. Our approach requires only 0.24% trainable parameters, enabling practical deployment of fair medical AI in resource-constrained healthcare settings.
Instituto de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València（瓦伦西亚理工大学生物工程研究与创新研究所）；Universidad Politécnica de Cartagena（卡塔赫纳理工大学）
Glaucoma is one of the leading causes of blindness worldwide and Optical Coherence Tomography (OCT) is the quintessential imaging technique for its detection. Unlike most of the state-of-the-art studies focused on glaucoma detection, in this paper, we propose, for the first time, a novel framework for glaucoma grading using raw circumpapillary B-scans. In particular, we set out a new OCT-based hybrid network which combines hand-driven and deep learning algorithms. An OCT-specific descriptor is proposed to extract hand-crafted features related to the retinal nerve fibre layer (RNFL). In paralle…
Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization
Harvard Medical School（哈佛医学院）；Massachusetts Eye and Ear（麻省眼耳医院）；Schepens Eye Research Institute（谢彭斯眼科研究所）；Eye and Vision Research Institute（眼科与视觉研究所）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）
Muroran Institute of Technology（室兰工业大学）；Niigata University of Healthcare and Welfare（新潟医疗福祉大学）；Konica Minolta, Inc.（柯尼卡美能达公司）
Artificial Intelligence for RObust Glaucoma Screening (AIROGS) Challenge is held for developing solutions for glaucoma screening from color fundus photography that are robust to real-world scenarios. This report describes our method submitted to the AIROGS challenge. Our method employs convolutional neural networks to classify input images to "referable glaucoma" or "no referable glaucoma". In addition, we introduce an inference-time out-of-distribution (OOD) detection method to identify ungradable images. Our OOD detection is based on an energy-based method combined with activation rectificat…
Ghent University Global Campus（根特大学全球校区）；Ghent University（根特大学）
Glaucoma is a major eye disease, leading to vision loss in the absence of proper medical treatment. Current diagnosis of glaucoma is performed by ophthalmologists who are often analyzing several types of medical images generated by different types of medical equipment. Capturing and analyzing these medical images is labor-intensive and expensive. In this paper, we present a novel computational approach towards glaucoma diagnosis and localization, only making use of eye fundus images that are analyzed by state-of-the-art deep learning techniques. Specifically, our approach leverages Convolution…
Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡全国眼科中心）；Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工学院研究与技术联盟）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）；National University of Singapore（新加坡国立大学）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学医学院）；Vilnius University（维尔纽斯大学）；Vilnius University Hospital Santaros Klinikos（维尔纽斯大学圣罗克利什科斯医院）；Massachusetts Institute of Technology（麻省理工学院）；Institute for Molecular and Clinical Ophthalmology（分子与临床眼科研究所）
Purpose: The optic nerve head (ONH) undergoes complex and deep 3D morphological changes during the development and progression of glaucoma. Optical coherence tomography (OCT) is the current gold standard to visualize and quantify these changes, however the resulting 3D deep-tissue information has not yet been fully exploited for the diagnosis and prognosis of glaucoma. To this end, we aimed: (1) To compare the performance of two relatively recent geometric deep learning techniques in diagnosing glaucoma from a single OCT scan of the ONH; and (2) To identify the 3D structural features of the ON…
National University of Singapore（新加坡国立大学）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；Yong Loo Lin School of Medicine（杨潞龄医学院）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学医学院）；Institute for Molecular and Clinical Ophthalmology, Basel（巴塞尔分子与临床眼科研究所）
Purpose: (1) To assess the performance of geometric deep learning (PointNet) in diagnosing glaucoma from a single optical coherence tomography (OCT) 3D scan of the optic nerve head (ONH); (2) To compare its performance to that obtained with a standard 3D convolutional neural network (CNN), and with a gold-standard glaucoma parameter, i.e. retinal nerve fiber layer (RNFL) thickness. Methods: 3D raster scans of the ONH were acquired with Spectralis OCT for 477 glaucoma and 2,296 non-glaucoma subjects at the Singapore National Eye Centre. All volumes were automatically segmented using deep learni…
With the advancement of deep learning techniques, an increasing number of methods have been proposed for optic disc and cup (OD/OC) segmentation from the fundus images. Clinically, OD/OC segmentation is often annotated by multiple clinical experts to mitigate the personal bias. However, it is hard to train the automated deep learning models on multiple labels. A common practice to tackle the issue is majority vote, e.g., taking the average of multiple labels. However such a strategy ignores the different expertness of medical experts. Motivated by the observation that OD/OC segmentation is oft…
Joint Segmentation and Grading with Iterative Optimization for Multimodal Glaucoma Diagnosis
Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China（香港大学电子与电气工程系）；College of Information Engineering, Zhejiang University of Technology, Hangzhou, China（浙江工业大学信息工程学院）
Glaucoma is a disease in which the optic nerve is chronically damaged by the elevation of the intra-ocular pressure, resulting in visual field defect. Therefore, it is important to monitor and treat suspected patients before they are confirmed with glaucoma. In this paper, we propose a 2-stage ranking-CNN that classifies fundus images as normal, suspicious, and glaucoma. Furthermore, we propose a method of using the class activation map as a mask filter and combining it with the original fundus image as an intermediate input. Our results have improved the average accuracy by about 10% over the…
Technical University of Munich（慕尼黑工业大学）；Heritage Institute of Technology（印度传统理工学院）
Automatic evaluation of the retinal fundus image is emerging as one of the most important tools for early detection and treatment of progressive eye diseases like Glaucoma. Glaucoma results to a progressive degeneration of vision and is characterized by the deformation of the shape of optic cup and the degeneration of the blood vessels resulting in the formation of a notch along the neuroretinal rim. In this paper, we propose a deep learning-based pipeline for automatic segmentation of optic disc (OD) and optic cup (OC) regions from Digital Fundus Images (DFIs), thereby extracting distinct fea…
Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心）；Opthalmology Clinic（眼科诊所）；National University of Science and Technology (NUST)（国立科技大学）；National Center of Artificial Intelligence（国家人工智能中心）；Smart Data and Knowledge Services（智能数据与知识服务部）
Scarcity of large publicly available retinal fundus image datasets for automated glaucoma detection has been the bottleneck for successful application of artificial intelligence towards practical Computer-Aided Diagnosis (CAD). A few small datasets that are available for research community usually suffer from impractical image capturing conditions and stringent inclusion criteria. These shortcomings in already limited choice of existing datasets make it challenging to mature a CAD system so that it can perform in real-world environment. In this paper we present a large publicly available retin…
Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；National University of Singapore（新加坡国立大学）；Aravind Eye Care Systems（阿拉温德眼科护理系统）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）
The optic nerve head (ONH) typically experiences complex neural- and connective-tissue structural changes with the development and progression of glaucoma, and monitoring these changes could be critical for improved diagnosis and prognosis in the glaucoma clinic. The gold-standard technique to assess structural changes of the ONH clinically is optical coherence tomography (OCT). However, OCT is limited to the measurement of a few hand-engineered parameters, such as the thickness of the retinal nerve fiber layer (RNFL), and has not yet been qualified as a stand-alone device for glaucoma diagnos…
Baidu Inc.（百度公司）；Zhongshan Ophthalmic Center, Sun Yat-sen University（中山大学中山眼科中心）；Xiamen University（厦门大学）
Color fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both two modalities of images have prominent biomarkers to indicate glaucoma suspected. Clinically, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment. Inspired by the success of Retinal Fundus Glaucoma Challenge (REFU…
Adaptive Multiscale Retinal Diagnosis: A Hybrid Trio-Model Approach for Comprehensive Fundus Multi-Disease Detection Leveraging Transfer Learning and Siamese Networks
Weill Cornell Medicine（威尔康奈尔医学院）；University of Pennsylvania（宾夕法尼亚大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
In the United States, primary open-angle glaucoma (POAG) is the leading cause of blindness, especially among African American and Hispanic individuals. Deep learning has been widely used to detect POAG using fundus images as its performance is comparable to or even surpasses diagnosis by clinicians. However, human bias in clinical diagnosis may be reflected and amplified in the widely-used deep learning models, thus impacting their performance. Biases may cause (1) underdiagnosis, increasing the risks of delayed or inadequate treatment, and (2) overdiagnosis, which may increase individuals' st…
Shanghai Jiao Tong University（上海交通大学）；the Second Affiliated Hospital of Zhejiang University, College of Medicine（浙江大学医学院附属第二医院）
The early diagnosis and screening of glaucoma are important for patients to receive treatment in time and maintain eyesight. Nowadays, deep learning (DL) based models have been successfully used for computer-aided diagnosis (CAD) of glaucoma from retina fundus images. However, a DL model pre-trained using a dataset from one hospital center may have poor performance on a dataset from another new hospital center and therefore its applications in the real scene are limited. In this paper, we propose a self-adaptive transfer learning (SATL) strategy to fill the domain gap between multicenter datas…
National Tsing Hua University（国立清华大学）；Massachusetts Institute of Technology（麻省理工学院）；Emory University（埃默里大学）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Emory University School of Medicine（埃默里大学医学院）
Chronic obstructive pulmonary disease (COPD) is one of the most common chronic illnesses in the world and the third leading cause of mortality worldwide. It is often underdiagnosed or not diagnosed until later in the disease course. Spirometry tests are the gold standard for diagnosing COPD but can be difficult to obtain, especially in resource-poor countries. Chest X-rays (CXRs), however, are readily available and may serve as a screening tool to identify patients with COPD who should undergo further testing. Currently, no research applies deep learning (DL) algorithms that use large multi-si…
Deep learning models have the capacity to fundamentally revolutionize medical imaging analysis, and they have particularly interesting applications in computer-aided diagnosis. We attempt to use deep learning neural networks to diagnose funduscopic images, visual representations of the interior of the eye. Recently, a few robust deep learning approaches have performed binary classification to infer the presence of a specific ocular disease, such as glaucoma or diabetic retinopathy. In an effort to broaden the applications of computer-aided ocular disease diagnosis, we propose a unifying model …
Opening the black box of deep learning: Validating the statistical association between explainable artificial intelligence (XAI) and clinical domain knowledge in fundus image-based glaucoma diagnosis
Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Singapore National Eye Centre（新加坡国家眼科中心）
3D Structural Phenotype of the Optic Nerve Head at the Intersection of Glaucoma and Myopia -- A Key to Improving Glaucoma Diagnosis in Myopic Populations
Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工研究与技术联盟）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学医学院）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）；Emory University School of Medicine（埃默里大学医学院）；National University of Singapore（新加坡国立大学）；Georgia Institute of Technology（佐治亚理工学院）；Emory Empathetic AI for Health Institute（埃默里大学共情健康人工智能研究所）；Emory Eye Center（埃默里眼科中心）；Emory School of Medicine（埃默里医学院）；Emory Clinic（埃默里诊所）；Abyss Processing Pte Ltd（Abyss Processing私人有限公司）
Singapore Eye Research Institute, Singapore National Eye Centre（新加坡眼科研究所，新加坡国家眼科中心）；National University of Singapore（新加坡国立大学）；Vilnius University（维尔纽斯大学）；Vilnius University Hospital Santaros Klinikos（维尔纽斯大学桑塔罗斯诊所医院）；Aravind Eye Care Systems（阿拉文眼科医疗系统）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Institute for Molecular and Clinical Ophthalmology（分子与临床眼科研究所）
Purpose: To assess whether the three-dimensional (3D) structural configuration of the central retinal vessel trunk and its branches (CRVT&B) could be used as a diagnostic marker for glaucoma. Method: We trained a deep learning network to automatically segment the CRVT&B from the B-scans of the optical coherence tomography (OCT) volume of the optic nerve head (ONH). Subsequently, two different approaches were used for glaucoma diagnosis using the structural configuration of the CRVT&B as extracted from the OCT volumes. In the first approach, we aimed to provide a diagnosis using only 3D CNN and…
Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（集成空天地海大数据应用技术国家工程实验室）；Northwestern Polytechnical University（西北工业大学）；Huiying Medical Technology Company Ltd.（慧影医疗技术有限公司）；The School of Computer Science（计算机学院）；The University of Sydney（悉尼大学）；Department of Computer Science and Engineering（计算机科学与工程系）；The Chinese University of Hong Kong（香港中文大学）
Screening for the diagnosis of glaucoma through a fundus image can be determined by the optic cup to disc diameter ratio (CDR), which requires the segmentation of the cup and disc regions. In this paper, we propose two novel approaches, namely Parameter-Shared Branched Network (PSBN) andWeak Region of Interest Model-based segmentation (WRoIM) to identify disc and cup boundaries. Unlike the previous approaches, the proposed methods are trained end-to-end through a single neural network architecture and use dynamic cropping instead of manual or traditional computer vision-based cropping. We are …
AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Department of Computer Science, Columbia University, New York, NY, USA（计算机科学系，哥伦比亚大学）；Department of Ophthalmology, Columbia University Irving Medical Center, New York, NY, USA（眼科学系，哥伦比亚大学伊万杰琳医疗中心）；Department of Biomedical Engineering, Columbia University, New York, NY, USA（生物医学工程系，哥伦比亚大学）；The Data Science Institute, Columbia University, New York, NY, USA（数据科学学院，哥伦比亚大学）
Guangdong Provincial People’s Hospital（广东省人民医院）；University of Notre Dame（圣母大学）；University of Pittsburgh（匹兹堡大学）
Many works have shown that deep learning-based medical image classification models can exhibit bias toward certain demographic attributes like race, gender, and age. Existing bias mitigation methods primarily focus on learning debiased models, which may not necessarily guarantee all sensitive information can be removed and usually comes with considerable accuracy degradation on both privileged and unprivileged groups. To tackle this issue, we propose a method, FairPrune, that achieves fairness by pruning. Conventionally, pruning is used to reduce the model size for efficient inference. However…
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）
University of Notre Dame（圣母大学）；University of Pittsburgh（匹兹堡大学）
Dermatological diseases pose a major threat to the global health, affecting almost one-third of the world's population. Various studies have demonstrated that early diagnosis and intervention are often critical to prognosis and outcome. To this end, the past decade has witnessed the rapid evolvement of deep learning based smartphone apps, which allow users to conveniently and timely identify issues that have emerged around their skins. In order to collect sufficient data needed by deep learning and at the same time protect patient privacy, federated learning is often used, where individual cli…
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）
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）；National University of Singapore（新加坡国立大学）
Deep learning approaches often require huge datasets to achieve good generalization. This complicates its use in tasks like image-based medical diagnosis, where the small training datasets are usually insufficient to learn appropriate data representations. For such sensitive tasks it is also important to provide the confidence in the predictions. Here, we propose a way to learn and use probabilistic labels to train accurate and calibrated deep networks from relatively small datasets. We observe gains of up to 22% in the accuracy of models trained with these labels, as compared with traditional…
