相关实验视频

Updated: Feb 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

揭开黑盒子:可解释的转移学习用于眼部疾病诊断

Zaib Un Nisa¹, Arfan Jaffar¹, Sohail Masood Bhatti¹

¹Department of Computer Science and Information Technology, The Superior University, Lahore, Pakistan.

|February 16, 2026

概括

转移学习模型在诊断糖尿病视网膜病变等眼睛疾病方面表现有前途. 然而,可解释的人工智能对于可靠的模型选择至关重要,特别是对于像玻璃眼这样的疾病.

科学领域:

眼科医生眼科眼科
人工智能的人工智能
医疗成像医学成像

背景情况:

多种类型的眼病诊断对于患者的治疗结果至关重要.
转移学习 (TL) 和深度学习为自动诊断提供了潜力.
评估模型可靠性和可解释性对于临床采用至关重要.

研究的目的:

系统地评估用于多类眼病诊断的转移学习模型.
使用可解释的人工智能 (AI) 评估这些模型的可靠性.

主要方法:

在公开数据集上评估了8个预训练的卷积神经网络 (CNN) 模型.
性能指标包括准确性,精度,回忆和F1分数.
使用了可解释性技术 (Grad-CAM,LIME,SHAP).

主要成果:

模型实现了糖尿病视网膜病变和白内障检测的高精度 (DenseNet121,XceptionNet).
青光眼的诊断结果较弱,这表明需要基于细分的方法.
可解释性揭示了模型注意力的显著差异,尽管准确性相似.

结论:

对于值得信赖的医疗人工智能来说,单纯的准确性是不够的.
可解释的AI对于选择可靠的诊断模型至关重要.
EfficientNetB3展示了性能和可解释性的良好平衡; 青光眼诊断需要先进的管道.

关键词:

眼睛疾病眼睛疾病白内障是什么?白内障是什么?白内障是什么?糖尿病视网膜病变糖尿病视网膜病变可以解释的人工智能AI 玻璃眼 glaucoma 玻璃眼玻璃眼玻璃眼玻璃眼转移学习转移学习

更多相关视频

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

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

相关概念视频

Photoreceptors and Visual Pathways

Photoreceptors and Visual Pathways

At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...