APTOS-2024挑战赛报告：从眼底照片生成合成3D OCT图像

基于CLIP的排名感知适应的糖尿病视网膜病变分级：在视网膜图像上的比较研究

Diabetic Retinopathy Grading with CLIP-based Ranking-Aware Adaptation:A Comparative Study on Fundus Image

本文比较了三种基于CLIP的方法用于五类糖尿病视网膜病变严重程度分级，提出排名感知模型在整体准确率和临床关键严重病例召回率上表现最佳，混合FCN-CLIP模型在检测增生性视网膜病变方面表现突出，均优于零样本基线。

面向移动设备的糖尿病视网膜病变自动分诊系统

Mobile-Ready Automated Triage of Diabetic Retinopathy Using Digital Fundus Images

本文提出基于MobileNetV3和CORAL头的轻量级深度学习框架，用于移动设备上高效评估糖尿病视网膜病变严重程度，实现高准确率和可扩展的筛查工具。

From Machine to Machine: An OCT-trained Deep Learning Algorithm for Objective Quantification of Glaucomatous Damage in Fundus Photographs

Previous approaches using deep learning algorithms to classify glaucomatous damage on fundus photographs have been limited by the requirement for human labeling of a reference training set. We propose a new approach using spectral-domain optical coherence tomography (SDOCT) data to train a deep learning algorithm to quantify glaucomatous structural damage on optic disc photographs. The dataset included 32,820 pairs of optic disc photos and SDOCT retinal nerve fiber layer (RNFL) scans from 2,312 eyes of 1,198 subjects. A deep learning convolutional neural network was trained to assess optic dis…

GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges

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…

学习自监督表示以实现糖尿病视网膜病变眼底图像上标签高效的跨域知识迁移

Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images

本文提出一种标签高效的自监督对比表示学习方法，利用无标注源域知识迁移完成跨域DR眼底图像分类，仅需少量标注即达到二分类与多分类SOTA。

ELF：一种用于青光眼分级的端到端局部与全局多模态融合框架

ELF: An End-to-end Local and Global Multimodal Fusion Framework for Glaucoma Grading

针对青光眼分级，提出端到端局部与全局多模态融合框架ELF，充分利用眼底图像与OCT的互补信息及局部和全局相互信息，在GAMMA数据集上验证了其有效性。

基于卷积神经网络并结合SMOTE与CLAHE技术应用于眼底图像的糖尿病视网膜病变检测

Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images

本研究利用SMOTE和CLAHE技术处理眼底图像，结合卷积神经网络对糖尿病视网膜病变进行二分类和多分类检测，在APTOS 2019数据集上分别取得99.55%和95.26%的准确率，证明AI方法优于传统人工分析。

整合非线性Radon变换用于糖尿病视网膜病变分级

Integrating Non-Linear Radon Transformation for Diabetic Retinopathy Grading

本文提出RadFuse框架，融合非线性RadEx变换的sinogram图像与传统眼底图像，增强糖尿病视网膜病变分级，在APTOS-2019和DDR数据集上显著提升性能。

使用同步眼底图像与光学相干断层扫描图像的多尺度颜色引导注意力集成分类器用于年龄相关性黄斑变性

Multiscale Color Guided Attention Ensemble Classifier for Age-Related Macular Degeneration using Concurrent Fundus and Optical Coherence Tomography Images

本文提出MCGAEc方法，通过多尺度颜色空间编码与注意力机制融合眼底和OCT双模态特征，并用随机森林分类AMD，在公开数据集上验证其性能。

COROLLA: An Efficient Multi-Modality Fusion Framework with Supervised Contrastive Learning for Glaucoma Grading

Glaucoma is one of the ophthalmic diseases that may cause blindness, for which early detection and treatment are very important. Fundus images and optical coherence tomography (OCT) images are both widely-used modalities in diagnosing glaucoma. However, existing glaucoma grading approaches mainly utilize a single modality, ignoring the complementary information between fundus and OCT. In this paper, we propose an efficient multi-modality supervised contrastive learning framework, named COROLLA, for glaucoma grading. Through layer segmentation as well as thickness calculation and projection, re…

Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization

This paper studies automated categorization of age-related macular degeneration (AMD) given a multi-modal input, which consists of a color fundus image and an optical coherence tomography (OCT) image from a specific eye. Previous work uses a traditional method, comprised of feature extraction and classifier training that cannot be optimized jointly. By contrast, we propose a two-stream convolutional neural network (CNN) that is end-to-end. The CNN's fusion layer is tailored to the need of fusing information from the fundus and OCT streams. For generating more multi-modal training instances, we…

融合深度学习与眼底照相及光学相干断层扫描用于心血管疾病预测

Integrating Deep Learning with Fundus and Optical Coherence Tomography for Cardiovascular Disease Prediction

本研究提出基于多通道变分自编码器（MCVAE）的二分类网络，融合眼底照片与OCT图像预测未来5年心血管疾病风险，在2,854名受试者上取得AUROC 0.78，展示了视网膜成像作为非侵入性CVD筛查工具的潜力。

Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning

To investigate whether and to what extent central serous chorioretinopathy (CSC) depicted on color fundus photographs can be assessed using deep learning technology. We collected a total of 2,504 fundus images acquired on different subjects. We verified the CSC status of these images using their corresponding optical coherence tomography (OCT) images. A total of 1,329 images depicted CSC. These images were preprocessed and normalized. This resulting dataset was randomly split into three parts in the ratio of 8:1:1 respectively for training, validation, and testing purposes. We used the deep le…

基于标记最优传输的眼科疾病分级与诊断鲁棒不完整模态对齐

Robust Incomplete-Modality Alignment for Ophthalmic Disease Grading and Diagnosis via Labeled Optimal Transport

针对多模态眼科诊断中不完整数据问题，提出基于标记最优传输的鲁棒不完整模态对齐框架，通过类级和特征级对齐及非对称融合，在缺失模态下实现准确诊断，性能优于现有方法。

评估针对糖尿病黄斑水肿检测的眼底专用基础模型

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection

本文对比RETFound、FLAIR两款眼底专用基础模型与EfficientNetB0，在三个数据集上开展DME检测实验，发现轻量级CNN表现更优，基础模型在该任务中无明显优势。

MM-Retinal V2：将精英知识火种迁移至眼底视觉-语言预训练

MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining

针对眼底VLP依赖大规模私有数据且预训练方式受限的问题，提出含CFP等模态的MM-Retinal V2数据集与KeepFIT V2模型，通过整合精英知识、结合对比与生成学习，在多设置下性能媲美顶尖私有数据模型且公开可用。

掩码图像建模用于视网膜OCT理解

Masked Image Modelling for retinal OCT understanding

本文利用掩码自编码器在视网膜OCT图像上自监督预训练，获得通用表示，并在6个下游任务上验证其性能，同时扩展至多模态融合，提升应用效果。

MultiEYE：面向OCT增强的眼底图像视网膜疾病识别的数据集与基准

MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images

本文提出OCT增强的眼底图像疾病识别新设定，构建首个大规模多模态多类别眼病数据集MultiEYE，并设计OCT-CoDA概念蒸馏方法，通过可解释的跨模态知识迁移显著提升仅用眼底图像的诊断性能。

Dataset and Evaluation algorithm design for GOALS Challenge

Glaucoma causes irreversible vision loss due to damage to the optic nerve, and there is no cure for glaucoma.OCT imaging modality is an essential technique for assessing glaucomatous damage since it aids in quantifying fundus structures. To promote the research of AI technology in the field of OCT-assisted diagnosis of glaucoma, we held a Glaucoma OCT Analysis and Layer Segmentation (GOALS) Challenge in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022 to provide data and corresponding annotations for researchers studying …

拓扑签名与梯度直方图：面向医学图像分类的比较研究

Topological Signatures vs. Gradient Histograms: A Comparative Study for Medical Image Classification

本文比较了HOG和TDA在视网膜图像分类中的性能，发现XGBoost在两种特征类型上均表现最佳，展示了结合两种方法提升医学图像分类的潜力。

OCTCube-M：用于视网膜和系统性疾病的3D多模态光学相干断层扫描基础模型，并进行跨队列和跨设备验证

OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation

本文提出3D多模态OCT基础模型OCTCube-M，通过COEP框架整合多模态视网膜成像数据，在视网膜及系统性疾病预测和地理萎缩生长率评估中展现出卓越性能与临床应用价值。

Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning

Diabetic eye disease is one of the fastest growing causes of preventable blindness. With the advent of anti-VEGF (vascular endothelial growth factor) therapies, it has become increasingly important to detect center-involved diabetic macular edema (ci-DME). However, center-involved diabetic macular edema is diagnosed using optical coherence tomography (OCT), which is not generally available at screening sites because of cost and workflow constraints. Instead, screening programs rely on the detection of hard exudates in color fundus photographs as a proxy for DME, often resulting in high false p…

使用扩散模型生成视网膜眼底图像和OCT图像的真实反事实图像

Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models

本文提出结合扩散模型与对抗鲁棒分类器生成视网膜眼底图像和OCT图像的高度真实反事实图像，实验表明其真实感显著优于先前方法，甚至与真实图像难以区分。

VAMPIRE：从 OCTA 图像中挖掘血管方向与形态信息以预测心血管疾病风险因素

VAMPIRE: Uncovering Vessel Directional and Morphological Information from OCTA Images for Cardiovascular Disease Risk Factor Prediction

提出 OCTA-CVD 数据集与 VAMPIRE 模型，通过方向和形态学模块联合预测 CVD 风险及相关血液因子状况，性能优于多种现有方法。

Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding

Convolutional Neural Network models have successfully detected retinal illness from optical coherence tomography (OCT) and fundus images. These CNN models frequently rely on vast amounts of labeled data for training, difficult to obtain, especially for rare diseases. Furthermore, a deep learning system trained on a data set with only one or a few diseases cannot detect other diseases, limiting the system's practical use in disease identification. We have introduced an unsupervised approach for detecting anomalies in retinal images to overcome this issue. We have proposed a simple, memory effic…

基于双分辨率注意力的深度学习在糖尿病视网膜病变分级中的鲁棒性研究

Dual-Resolution Attention-Gated Deep Learning with Ordinal Regression for Diabetic Retinopathy Grading: A Quantified Assessment of Cross-Domain Generalization

本文提出双分辨率注意力深度学习框架，结合顺序回归提升跨数据集泛化能力，通过互补特征融合和有序回归实现鲁棒的DR分级。

通过视网膜眼底图像评估心血管疾病与风险因素的人工智能：近十年综述

Artificial Intelligence in Assessing Cardiovascular Diseases and Risk Factors via Retinal Fundus Images: A Review of the Last Decade

本综述梳理近十年AI结合视网膜眼底图像评估心血管疾病的研究进展，通过多数据库检索纳入87篇相关文献，总结技术现状与难点，指出其在心血管病早诊早筛中的潜力及落地挑战。

当领域特定基础模型是否值得其成本？跨视网膜成像任务的系统评估

When Do Domain-Specific Foundation Models Justify Their Cost? A Systematic Evaluation Across Retinal Imaging Tasks

本文通过系统评估发现，紧凑型通用模型在大多数视网膜分类任务中表现优异，而专门领域模型仅在特定高难度任务中值得其成本。

GLEAM：一种多模态成像数据集和HAMM用于青光眼分类

GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification

本文提出GLEAM数据集，包含三种多模态图像，用于青光眼分类，并提出HAMM方法整合跨模态信息以提高诊断准确性。

跨模态视网膜图像在大视野差异下的配准

Cross-modal Fundus Image Registration under Large FoV Disparity

本文提出CARe方法，用于解决大视野差异下的跨模态视网膜图像配准问题，通过裁剪和双拟合对齐改进配准效果。

UrFound：通过知识引导的掩码建模构建通用视网膜基础模型

UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling

针对现有视网膜基础模型单模态限制、领域知识利用不足的问题，提出配备模态无关编码器、采用知识引导掩码建模的UrFound模型，仅用18万张图像训练即在8个数据集上超越用160万张图训练的SOTA模型，泛化性与数据效率更优。

Designing the Architecture of a Convolutional Neural Network Automatically for Diabetic Retinopathy Diagnosis

The prevalence of diabetic retinopathy (DR) has reached 34.6% worldwide and is a major cause of blindness among middle-aged diabetic patients. Regular DR screening using fundus photography helps detect its complications and prevent its progression to advanced levels. As manual screening is time-consuming and subjective, machine learning (ML) and deep learning (DL) have been employed to aid graders. However, the existing CNN-based methods use either pre-trained CNN models or a brute force approach to design new CNN models, which are not customized to the complexity of fundus images. To overcome…

人工智能在危及生命疾病早期检测中的作用：视网膜影像视角

The Role of AI in Early Detection of Life-Threatening Diseases: A Retinal Imaging Perspective

本文综述视网膜影像结合AI技术在糖尿病、心血管等致命疾病早期检测中的进展，并提出标准化与临床整合路线图。

Blindness (Diabetic Retinopathy) Severity Scale Detection

Diabetic retinopathy (DR) is a severe complication of diabetes that can cause permanent blindness. Timely diagnosis and treatment of DR are critical to avoid total loss of vision. Manual diagnosis is time consuming and error-prone. In this paper, we propose a novel deep learning based method for automatic screening of retinal fundus images to detect and classify DR based on the severity. The method uses a dual-path configuration of deep neural networks to achieve the objective. In the first step, a modified UNet++ based retinal vessel segmentation is used to create a fundus image that emphasis…

TaGAT：用于多模态视网膜图像融合的拓扑感知图注意力网络

TaGAT: Topology-Aware Graph Attention Network For Multi-modal Retinal Image Fusion

提出TaGAT网络，通过拓扑感知编码器结合图注意力机制，融合多模态视网膜图像，保留血管拓扑细节，优于现有方法。

四象限分割视觉语言模型结合少样本适应与基于OCT学习的可解释方法用于糖尿病视网膜病变

Quadrant Segmentation VLM with Few-Shot Adaptation and OCT Learning-based Explainability Methods for Diabetic Retinopathy

本文提出一种基于四象限分割和少样本学习的多模态视觉语言模型，利用OCT和视网膜图像生成可解释性热图，提升糖尿病视网膜病变的诊断效果。

VesselMorph：通过形状感知表示实现领域泛化的视网膜血管分割

VesselMorph: Domain-Generalized Retinal Vessel Segmentation via Shape-Aware Representation

针对视网膜血管分割中的领域偏移问题，提出 VesselMorph 方法，利用基于 Hessian 的双极张量场提取血管形状不变特征，并通过潜在空间融合提升跨数据集泛化性能。

使用多模态视网膜图像的影像组学特征预测1型糖尿病心血管风险的机器学习

Machine Learning Prediction of Cardiovascular Risk in Type 1 Diabetes Mellitus Using Radiomics Features from Multimodal Retinal Images

本研究利用眼底照相、OCT和OCTA等多模态视网膜图像的影像组学特征结合临床数据训练机器学习模型，有效区分了1型糖尿病患者的心血管风险等级，证明了眼组学在心血管风险评估中的潜力。

Fundus-R1: 基于公共数据训练具备知识感知推理能力的视网膜图像阅读MLLM

Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data

本文提出Fundus-R1，通过公共数据集训练具备知识感知推理能力的视网膜图像阅读MLLM，采用RAG方法生成知识感知推理轨迹，并通过过程奖励增强RLVR，实验证明其在三个基准测试中优于多个基线模型。

用于医学图像的分解卷积奇异值平坦化

Flattening Singular Values of Factorized Convolution for Medical Images

针对分解卷积表达能力受限的问题，本文提出 SFConv，通过低秩分解及最小化权重矩阵与均匀分布的 KL 散度来均衡奇异值，在眼底和 OCTA 数据上以更低复杂度取得接近普通卷积的表达能力。

Exploiting the Transferability of Deep Learning Systems Across Multi-modal Retinal Scans for Extracting Retinopathy Lesions

Retinal lesions play a vital role in the accurate classification of retinal abnormalities. Many researchers have proposed deep lesion-aware screening systems that analyze and grade the progression of retinopathy. However, to the best of our knowledge, no literature exploits the tendency of these systems to generalize across multiple scanner specifications and multi-modal imagery. Towards this end, this paper presents a detailed evaluation of semantic segmentation, scene parsing and hybrid deep learning systems for extracting the retinal lesions such as intra-retinal fluid, sub-retinal fluid, h…

ETSCL：基于证据理论的多模态青光眼分级监督对比学习框架

ETSCL: An Evidence Theory-Based Supervised Contrastive Learning Framework for Multi-modal Glaucoma Grading

提出ETSCL框架，结合监督对比学习和证据理论融合，处理多模态青光眼分级中的特征提取和不确定性估计问题，实现最先进性能。

眼科中的生成式人工智能：基于卷积神经网络的多模态视网膜图像用于阿尔茨海默病诊断

Generative artificial intelligence in ophthalmology: multimodal retinal images for the diagnosis of Alzheimer's disease with convolutional neural networks

本研究利用生成式AI（DDPM）合成多模态视网膜图像，预训练CNN以预测阿尔茨海默病相关AmyloidPET状态，结合元数据将AUPR提升至0.634。

使用生物学信息异构图表征的可解释视网膜疾病预测

Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations

提出一种基于生物学信息异构图表征的方法，将OCTA图像中的视网膜结构建模为图，用于糖尿病视网膜病变分期，在保持高准确率（AUC-ROC 84%）的同时提供详细可解释的异常血管定位。

KLDD：视网膜图像分割中基于卡尔曼滤波的线性可变形扩散模型

KLDD: Kalman Filter based Linear Deformable Diffusion Model in Retinal Image Segmentation

针对 U-Net 易丢失视网膜细小血管的问题，本文提出 KLDD 模型，融合线性可变形卷积、卡尔曼滤波、注意力聚合与扩散模型，并在多个视网膜数据集上取得优于现有方法的分割性能。

VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers

In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In contrast, color fundus imaging is a non-invasive technique used for photographing the retina but does not have sufficient fidelity for capturing its vascular structure. The only non-invasive method for capturing retinal vasculature is optical coherence tomography-angiography (OCTA). However, OCTA equipment is quite expensive, and stable imaging is limited to s…

Localizing Anatomical Landmarks in Ocular Images using Zoom-In Attentive Networks

Localizing anatomical landmarks are important tasks in medical image analysis. However, the landmarks to be localized often lack prominent visual features. Their locations are elusive and easily confused with the background, and thus precise localization highly depends on the context formed by their surrounding areas. In addition, the required precision is usually higher than segmentation and object detection tasks. Therefore, localization has its unique challenges different from segmentation or detection. In this paper, we propose a zoom-in attentive network (ZIAN) for anatomical landmark loc…

语义空间中‘少即是多’：通过Clifford-M实现内在解耦以用于视网膜图像分类

Less is More in Semantic Space: Intrinsic Decoupling via Clifford-M for Fundus Image Classification

本文提出Clifford-M模型，通过稀疏几何交互替代传统频率分解模块，实现高效的视网膜图像分类，在ODIR-5K数据集上取得优于其他模型的性能。

MedImageInsight：面向通用医学影像领域的开源嵌入模型

MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging

本研究提出开源多领域医学影像嵌入模型MedImageInsight，在多类影像任务上达到SOTA或人类专家水平，具备临床决策支持能力，公平性优于同类公开模型，助力医学影像AI研发。

Learning Two-Stream CNN for Multi-Modal Age-related Macular Degeneration Categorization

This paper tackles automated categorization of Age-related Macular Degeneration (AMD), a common macular disease among people over 50. Previous research efforts mainly focus on AMD categorization with a single-modal input, let it be a color fundus photograph (CFP) or an OCT B-scan image. By contrast, we consider AMD categorization given a multi-modal input, a direction that is clinically meaningful yet mostly unexplored. Contrary to the prior art that takes a traditional approach of feature extraction plus classifier training that cannot be jointly optimized, we opt for end-to-end multi-modal C…

PathVLM-R1：一种基于强化学习的病理学视觉语言任务推理模型

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks

针对病理图像诊断中VLMs推理能力弱和缺乏监督过程的问题，提出基于Qwen2.5-VL-7B-Instruct的PathVLM-R1模型，通过监督微调及双奖励驱动强化学习优化，在病理问答任务准确率提升14%且迁移性能平均提升17.3%。

边缘重要吗？探究医学图像分割中的边缘增强预训练

Do Edges Matter? Investigating Edge-Enhanced Pre-Training for Medical Image Segmentation

本研究探究边缘增强预训练对医学图像分割的影响，发现其效果因模态而异，并提出基于图像标准差和熵的元学习策略来选择最优预训练模型，整体性能提升16.42%至19.30%。

Proxy-bridged Image Reconstruction Network for Anomaly Detection in Medical Images

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity mapping and reduces the sensitivity to anomalies. To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images. Specifically, we use an intermediate proxy to bridge the input image and the reconstructed image. We study different proxy types, and we find that the sup…

基于最优传输的图匹配用于3D视网膜OCT图像配准

Optimal Transport-based Graph Matching for 3D retinal OCT image registration

本文提出基于最优传输图匹配（OT-GM）的3D小鼠视网膜OCT图像配准框架，结合自适应加权血管图描述符和3D立方体描述符进行x-y平面对齐，并利用ILM和HR分割引导z方向配准，在合理时间内优于现有方法。