高光谱成像用于年龄相关性黄斑变性玻璃膜疣的分类与分析
本研究为观察性横断面前瞻性研究,纳入100名非渗出性年龄相关性黄斑变性(AMD)患者的152只眼,采集高光谱视网膜图像及对应OCT图像,由视网膜专家基于OCT手动标注148只眼的玻璃膜疣,并使用光谱角映射(SAM)和随机森林分类器进行自动识别。结果显示,玻璃膜疣在特定波段具有独特空间-光谱特征,随机森林分类器整体性能更高,灵敏度88%、特异度99%、AUC 0.96。
要点
- 网状假性玻璃膜疣在470-500 nm最明显,软性玻璃膜疣在525-575 nm。
- 随机森林分类器识别玻璃膜疣:灵敏度88%、特异度99%、AUC 0.96。
- SAM分类器识别玻璃膜疣:灵敏度97%、特异度70%。
核心结论
- 高光谱成像可识别软性、硬性和网状假性玻璃膜疣的独特空间-光谱特征。
- SAM和随机森林分类器对自动检测玻璃膜疣均显示出良好前景。
- 高光谱视网膜成像有望作为非渗出性AMD中自动玻璃膜疣定位和患者风险分层的无创工具。
研究设计与样本
- 观察性、横断面、前瞻性研究,纳入100名非渗出性AMD患者的152只眼。
- 采集高光谱视网膜图像和对应OCT图像,由视网膜专家基于OCT手动标注148只眼(97名参与者)的玻璃膜疣。
- 使用光谱角映射(SAM)和随机森林分类器进行自动玻璃膜疣识别。
主要发现
- 网状假性玻璃膜疣(RPD)在470-500 nm最明显,软性玻璃膜疣在525-575 nm,硬性玻璃膜疣在620-675 nm,色素异常在650-725 nm。
- SAM分类器识别玻璃膜疣的灵敏度为97%,特异度为70%。
- 随机森林分类器整体性能更高,灵敏度88%、特异度99%、受试者工作特征曲线下面积(AUC)为0.96。
- 像素级SAM映射可勾画玻璃膜疣和健康视网膜,且范围超出标注区域。
关键数值与推荐
- 网状假性玻璃膜疣特征波段:470-500 nm。
- 软性玻璃膜疣特征波段:525-575 nm。
- 硬性玻璃膜疣特征波段:620-675 nm。
- 色素异常特征波段:650-725 nm。
- 随机森林分类器:灵敏度88%、特异度99%、AUC 0.96。
临床怎么用
- 高光谱视网膜成像可作为非侵入性工具,用于非渗出性AMD的玻璃膜疣自动定位。
- 自动玻璃膜疣检测可能辅助患者风险分层。
- SAM和随机森林分类器均可用于玻璃膜疣识别,随机森林整体性能更优。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: To characterize the spatial-spectral signatures of drusenoid deposits [soft, hard, and reticular pseudodrusen (RPD)] in eyes with non-exudative age-related macular degeneration (AMD). METHODS: In this observational, cross-sectional, prospective study, hyperspectral retinal images and corresponding Optical Coherence Tomography (OCT) images were collected from 152 eyes of 100 participants with non-exudative AMD. Drusenoid deposits were manually annotated in 148 eyes (97 participants) by retinal specialists using OCT as the reference standard. Automated drusen identification was then performed using spectral angle mapper (SAM) and random forest classifiers. RESULTS: Hyperspectral imaging revealed that RPD was most distinct at 470-500 nm, soft drusen at 525-575 nm, hard drusen at 620-675 nm, and pigmentary abnormalities at 650-725 nm. Using the SAM classifier, drusenoid deposits were identified with 97% sensitivity and 70% specificity. The random forest classifier achieved higher overall performance, with 88% sensitivity, 99% specificity, and an area under the receiver operating characteristic curve of 0.96. Pixel-wise SAM mapping delineated drusenoid deposits and healthy retina, extending beyond annotated regions. CONCLUSIONS: Distinct spatial-spectral signatures for soft drusen, hard drusen, and RPD were identified using hyperspectral imaging. Both SAM and random forest classifiers demonstrated promising results for automated drusenoid deposit detection. These findings support the role of hyperspectral retinal imaging as a noninvasive tool for automated drusen mapping and patient risk stratification in nonexudative AMD.
引用
- Chen C, Razavi R, Romano F, et al. Hyperspectral Imaging for the Classification and Analysis of Drusen in Age-Related Macular Degeneration. Invest Ophthalmol Vis Sci. 2026. PMID: 41784336. doi:10.1167/iovs.67.3.10
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。