相关实验视频

Updated: Sep 10, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

在视网膜图像分析中培训视觉语言模型的专业课程

Robbie Holland¹, Thomas R P Taylor², Christopher Holmes³

¹Biomedical Image Analysis, Department of Computing, Imperial College London, London, United Kingdom. robbie.holland@stanford.edu.

NPJ digital medicine

|August 19, 2025

概括

一个新的培训课程显著改进了一个专门的视觉语言模型 (VLM) 对于与年龄相关的黄斑变性 (AMD) 任务. 增强的VLM现在可以与初级眼科医生竞争,超过像ChatGPT-4o这样的一般模型.

科学领域:

眼科医生眼科眼科
人工智能的人工智能
医学成像分析医学成像分析

背景情况:

临床医生在审查医学图像和转录发现时面临着相当大的时间负担.
整合视觉和文本数据的基础模型显示了减少工作负载的潜力,但临床价值尚不确定.
目前的一般和医疗视觉语言模型 (VLMs) 在与年龄相关的黄斑变性 (AMD) 任务中表现低于眼科医生.

研究的目的:

开发和评估专门的培训课程,以优化眼科临床决策的VLM.
评估课程增强的VLM与一般基础模型和AMD相关任务的人类专家的性能.

主要方法:

专业领域专家设计了一个专门的培训课程,以优化临床决策的VLM.
专门模型 (RetinaVLM-Specialist) 的性能与基础医疗VLM和ChatGPT-4o在AMD疾病阶段和转诊任务中进行了比较.
一项涉及高级眼科医生的读者研究评估了RetinaVLM-Specialist与ChatGPT-4o生成的报告的准确性.

主要成果:

视网膜VLM-Specialist在AMD疾病阶段化 (F1:0.63对0.33) 和转诊 (0.67对0.50) 中显著优于基础医疗VLM和ChatGPT-4o.
专门的VLM取得了与初级眼科医生相提并论的表现.
高级眼科医生发现RetinaVLM-Specialist报告比ChatGPT-4o报告 (64.3%对14.3%) 准确得多.

结论:

基于课程的培训方法可以有效地适应基础模型用于专门的医疗应用.
优化的VLM显示出有潜力协助临床医生完成现实世界的医疗任务,提高准确性和效率.
这项研究为增强眼科和其他医学领域的人工智能模型提供了蓝图.

更多相关视频

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

相关概念视频

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

Visual System

Visual System

Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...