可解释的机器学习框架用于使用视觉特征识别白内障
Xiao Wu1, Lingxi Hu1,2, Zunjie Xiao1
1Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, China.
Visual computing for industry, biomedicine, and art
|January 17, 2025
概括
本研究介绍了一种可解释的机器学习框架,用于使用前段光学连贯断层扫描 (AS-OCT) 图像进行白内障严重程度的自动分级. 该方法为临床使用提供了准确,可解释的结果.
科学领域:
- 眼科医生 眼科 眼科
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 白内障是全球失明和视力障碍的主要原因.
- 深度神经网络 (DNN) 在AS-OCT图像上的白内障识别方面表现有前途,但缺乏临床解释性.
- 来自AS-OCT图像的视觉特征提供了可解释性,但仍未得到充分探索.
研究的目的:
- 开发一种可解释的机器学习框架,用于使用AS-OCT图像自动识别白内障严重程度.
- 为了提高临床诊断实践,利用可解释的视觉特征.
主要方法:
- 使用基于强度的统计方法从AS-OCT图像和历史图中提取视觉特征.
- 通过夏普利添加式扩展和皮尔森相关系数进行特征重要性分析和选择.
- 综合多类回归用于白内障严重程度的识别.
主要成果:
- 与AS-OCT-NC数据集上的DNN相比,拟议的框架实现了竞争性性能.
- 该框架表现出强大的可解释性,与临床诊断需求保持一致.
- 选择的视觉特征有效地为准确的白内障严重程度分类做出了贡献.
结论:
- 开发的可解释的机器学习框架为自动化白内障分级提供了可行的和可解释的方法.
- 这种方法提高了AS-OCT成像在眼科的临床适用性.
- 将视觉特征与可解释的AI相结合,为诊断白内障严重程度提供了强大的解决方案.
相关概念视频
Vision
52.9K
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.
52.9K
Photoreceptors and Visual Pathways
5.6K
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,...
5.6K


