EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis

Early detection of eye diseases like glaucoma, macular degeneration, and diabetic retinopathy is crucial for preventing vision loss. While artificial intelligence (AI) foundation models hold significant promise for addressing these challenges, existing ophthalmic foundation models primarily focus on a single modality, whereas diagnosing eye diseases requires multiple modalities. A critical yet often overlooked aspect is harnessing the multi-view information across various modalities for the same patient. Additionally, due to the long-tail nature of ophthalmic diseases, standard fully supervised or unsupervised learning approaches often struggle. Therefore, it is essential to integrate clinical text to capture a broader spectrum of diseases. We propose EyeCLIP, a visual-language foundation model developed using over 2.77 million multi-modal ophthalmology images with partial text data. To fully leverage the large multi-modal unlabeled and labeled data, we introduced a pretraining strategy that combines self-supervised reconstructions, multi-modal image contrastive learning, and image-text contrastive learning to learn a shared representation of multiple modalities. Through evaluation using 14 benchmark datasets, EyeCLIP can be transferred to a wide range of downstream tasks involving ocular and systemic diseases, achieving state-of-the-art performance in disease classification, visual question answering, and cross-modal retrieval. EyeCLIP represents a significant advancement over previous methods, especially showcasing few-shot, even zero-shot capabilities in real-world long-tail scenarios.

Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance

Fundus Fluorescein Angiography (FFA) is a critical tool for assessing retinal vascular dynamics and aiding in the diagnosis of eye diseases. However, its invasive nature and less accessibility compared to Color Fundus (CF) images pose significant challenges. Current CF to FFA translation methods are limited to static generation. In this work, we pioneer dynamic FFA video generation from static CF images. We introduce an autoregressive GAN for smooth, memory-saving frame-by-frame FFA synthesis. To enhance the focus on dynamic lesion changes in FFA regions, we design a knowledge mask based on clinical experience. Leveraging this mask, our approach integrates innovative knowledge mask-guided techniques, including knowledge-boosted attention, knowledge-aware discriminators, and mask-enhanced patchNCE loss, aimed at refining generation in critical areas and addressing the pixel misalignment challenge. Our method achieves the best FVD of 1503.21 and PSNR of 11.81 compared to other common video generation approaches. Human assessment by an ophthalmologist confirms its high generation quality. Notably, our knowledge mask surpasses supervised lesion segmentation masks, offering a promising non-invasive alternative to traditional FFA for research and clinical applications. The code is available at https://github.com/Michi-3000/Fundus2Video.

UWF-RI2FA: Generating Multi-frame Ultrawide-field Fluorescein Angiography from Ultrawide-field Retinal Imaging Improves Diabetic Retinopathy Stratification

Ultrawide-field fluorescein angiography (UWF-FA) facilitates diabetic retinopathy (DR) detection by providing a clear visualization of peripheral retinal lesions. However, the intravenous dye injection with potential risks hamper its application. We aim to acquire dye-free UWF-FA images from noninvasive UWF retinal imaging (UWF-RI) using generative artificial intelligence (GenAI) and evaluate its effectiveness in DR screening. A total of 18,321 UWF-FA images of different phases were registered with corresponding UWF-RI images and fed into a generative adversarial networks (GAN)-based model for training. The quality of generated UWF-FA images was evaluated through quantitative metrics and human evaluation. The DeepDRiD dataset was used to externally assess the contribution of generated UWF-FA images to DR classification, using area under the receiver operating characteristic curve (AUROC) as outcome metrics. The generated early, mid, and late phase UWF-FA images achieved high authenticity, with multi-scale similarity scores ranging from 0.70 to 0.91 and qualitative visual scores ranging from 1.64 to 1.98 (1=real UWF-FA quality). In fifty randomly selected images, 56% to 76% of the generated images were difficult to distinguish from real images in the Turing test. Moreover, adding these generated UWF-FA images for DR classification significantly increased the AUROC from 0.869 to 0.904 compared to the baseline model using UWF-RI images (P < .001). The model successfully generates realistic multi-frame UWF-FA images for enhancing DR stratification without intravenous dye injection.

Generating Multi-frame Ultrawide-field Fluorescein Angiography from Ultrawide-field Color Imaging Improves Diabetic Retinopathy Stratification

Ultrawide-field fluorescein angiography (UWF-FA) facilitates diabetic retinopathy (DR) detection by providing a clear visualization of peripheral retinal lesions. However, the intravenous dye injection with potential risks hamper its application. We aim to acquire dye-free UWF-FA images from noninvasive UWF color fundus (UWF-CF) images using generative artificial intelligence (GenAI) and evaluate its effectiveness in DR screening. A total of 18,321 UWF-FA images of different phases were registered with corresponding UWF-CF images and fed into a generative adversarial networks (GAN)-based model for training. The quality of generated UWF-FA images was evaluated through quantitative metrics and human evaluation. The DeepDRiD dataset was used to externally assess the contribution of generated UWF-FA images to DR classification, using area under the receiver operating characteristic curve (AUROC) as outcome metrics. The generated early, mid, and late phase UWF-FA images achieved high authenticity, with multi-scale similarity scores ranging from 0.70 to 0.91 and qualitative visual scores ranging from 1.64 to 1.98 (1=real UWF-FA quality). In fifty randomly selected images, 56% to 76% of the generated images were difficult to distinguish from real images in the Turing test. Moreover, adding these generated UWF-FA images for DR classification significantly increased the AUROC from 0.869 to 0.904 compared to the baseline model using UWF-CF images (P < .001). The model successfully generates realistic multi-frame UWF-FA images without intravenous dye injection. The generated UWF-FA enhanced DR stratification.

Choroidal Vessel Segmentation on Indocyanine Green Angiography Images via Human-in-the-Loop Labeling

Human-in-the-loop (HITL) strategy has been recently introduced into the field of medical image processing. Indocyanine green angiography (ICGA) stands as a well-established examination for visualizing choroidal vasculature and detecting chorioretinal diseases. However, the intricate nature of choroidal vascular networks makes large-scale manual segmentation of ICGA images challenging. Thus, the study aims to develop a high-precision choroidal vessel segmentation model with limited labor using HITL framework. We utilized a multi-source ICGA dataset, including 55 degree view and ultra-widefield ICGA (UWF-ICGA) images for model development. The choroidal vessel network was pre-segmented by a pre-trained vessel segmentation model, and then manually modified by two ophthalmologists. Choroidal vascular diameter, density, complexity, tortuosity, and branching angle were automatically quantified based on the segmentation. We finally conducted four cycles of HITL. One hundred and fifty 55 degree view ICGA images were used for the first three cycles (50 images per cycle), and twenty UWF-ICGA images for the last cycle. The average time needed to manually correct a pre-segmented ICGA image per cycle reduced from 20 minutes to 1 minute. High segmentation accuracy has been achieved on both 55 degree view ICGA and UWF-ICGA images. Additionally, the multi-dimensional choroidal vascular parameters were significantly associated with various chorioretinal diseases. Our study not only demonstrated the feasibility of the HITL strategy in improving segmentation performance with reduced manual labeling, but also innovatively introduced several risk predictors for choroidal abnormalities.

EyeFound: A Multimodal Generalist Foundation Model for Ophthalmic Imaging

Artificial intelligence (AI) is vital in ophthalmology, tackling tasks like diagnosis, classification, and visual question answering (VQA). However, existing AI models in this domain often require extensive annotation and are task-specific, limiting their clinical utility. While recent developments have brought about foundation models for ophthalmology, they are limited by the need to train separate weights for each imaging modality, preventing a comprehensive representation of multi-modal features. This highlights the need for versatile foundation models capable of handling various tasks and modalities in ophthalmology. To address this gap, we present EyeFound, a multimodal foundation model for ophthalmic images. Unlike existing models, EyeFound learns generalizable representations from unlabeled multimodal retinal images, enabling efficient model adaptation across multiple applications. Trained on 2.78 million images from 227 hospitals across 11 ophthalmic modalities, EyeFound facilitates generalist representations and diverse multimodal downstream tasks, even for detecting challenging rare diseases. It outperforms previous work RETFound in diagnosing eye diseases, predicting systemic disease incidents, and zero-shot multimodal VQA. EyeFound provides a generalizable solution to improve model performance and lessen the annotation burden on experts, facilitating widespread clinical AI applications for retinal imaging.

Evaluating large language models in medical applications: a survey

Large language models (LLMs) have emerged as powerful tools with transformative potential across numerous domains, including healthcare and medicine. In the medical domain, LLMs hold promise for tasks ranging from clinical decision support to patient education. However, evaluating the performance of LLMs in medical contexts presents unique challenges due to the complex and critical nature of medical information. This paper provides a comprehensive overview of the landscape of medical LLM evaluation, synthesizing insights from existing studies and highlighting evaluation data sources, task scenarios, and evaluation methods. Additionally, it identifies key challenges and opportunities in medical LLM evaluation, emphasizing the need for continued research and innovation to ensure the responsible integration of LLMs into clinical practice.

EyeGPT: Ophthalmic Assistant with Large Language Models

Artificial intelligence (AI) has gained significant attention in healthcare consultation due to its potential to improve clinical workflow and enhance medical communication. However, owing to the complex nature of medical information, large language models (LLM) trained with general world knowledge might not possess the capability to tackle medical-related tasks at an expert level. Here, we introduce EyeGPT, a specialized LLM designed specifically for ophthalmology, using three optimization strategies including role-playing, finetuning, and retrieval-augmented generation. In particular, we proposed a comprehensive evaluation framework that encompasses a diverse dataset, covering various subspecialties of ophthalmology, different users, and diverse inquiry intents. Moreover, we considered multiple evaluation metrics, including accuracy, understandability, trustworthiness, empathy, and the proportion of hallucinations. By assessing the performance of different EyeGPT variants, we identify the most effective one, which exhibits comparable levels of understandability, trustworthiness, and empathy to human ophthalmologists (all Ps>0.05). Overall, ur study provides valuable insights for future research, facilitating comprehensive comparisons and evaluations of different strategies for developing specialized LLMs in ophthalmology. The potential benefits include enhancing the patient experience in eye care and optimizing ophthalmologists' services.

Camera Adaptation for Fundus-Image-Based CVD Risk Estimation

Recent studies have validated the association between cardiovascular disease (CVD) risk and retinal fundus images. Combining deep learning (DL) and portable fundus cameras will enable CVD risk estimation in various scenarios and improve healthcare democratization. However, there are still significant issues to be solved. One of the top priority issues is the different camera differences between the databases for research material and the samples in the production environment. Most high-quality retinography databases ready for research are collected from high-end fundus cameras, and there is a significant domain discrepancy between different cameras. To fully explore the domain discrepancy issue, we first collect a Fundus Camera Paired (FCP) dataset containing pair-wise fundus images captured by the high-end Topcon retinal camera and the low-end Mediwork portable fundus camera of the same patients. Then, we propose a cross-laterality feature alignment pre-training scheme and a self-attention camera adaptor module to improve the model robustness. The cross-laterality feature alignment training encourages the model to learn common knowledge from the same patient's left and right fundus images and improve model generalization. Meanwhile, the device adaptation module learns feature transformation from the target domain to the source domain. We conduct comprehensive experiments on both the UK Biobank database and our FCP data. The experimental results show that the CVD risk regression accuracy and the result consistency over two cameras are improved with our proposed method. The code is available here: \url{https://github.com/linzhlalala/CVD-risk-based-on-retinal-fundus-images}

Label uncertainty-guided multi-stream model for disease screening

The annotation of disease severity for medical image datasets often relies on collaborative decisions from multiple human graders. The intra-observer variability derived from individual differences always persists in this process, yet the influence is often underestimated. In this paper, we cast the intra-observer variability as an uncertainty problem and incorporate the label uncertainty information as guidance into the disease screening model to improve the final decision. The main idea is dividing the images into simple and hard cases by uncertainty information, and then developing a multi-stream network to deal with different cases separately. Particularly, for hard cases, we strengthen the network's capacity in capturing the correct disease features and resisting the interference of uncertainty. Experiments on a fundus image-based glaucoma screening case study show that the proposed model outperforms several baselines, especially in screening hard cases.