Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, 40, Avenue de Verdun, 94100, Créteil, France.
Catholic University of "Sacro Cuore", Rome, Italy.
Sci Rep. 2023 Nov 21;13(1):20354. doi: 10.1038/s41598-023-47854-7.
To create a deep learning (DL) classifier pre-trained on fundus autofluorescence (FAF) images that can assist the clinician in distinguishing age-related geographic atrophy from extensive macular atrophy and pseudodrusen-like appearance (EMAP). Patients with complete outer retinal and retinal pigment epithelium atrophy secondary to either EMAP (EMAP Group) or to dry age related macular degeneration (AMD group) were retrospectively selected. Fovea-centered posterior pole (30° × 30°) and 55° × 55° degree-field-of-view FAF images of sufficiently high quality were collected and used to train two different deep learning (DL) classifiers based on ResNet-101 design. Testing was performed on a set of images coming from a different center. A total of 300 patients were recruited, 135 belonging to EMAP group and 165 belonging to AMD group. The 30° × 30° FAF based DL classifier showed a sensitivity of 84.6% and a specificity of 85.3% for the diagnosis of EMAP. The 55° × 55° FAF based DL classifier showed a sensitivity of 90% and a specificity of 84.6%, a performance that was significantly higher than that of the 30° × 30° classifer (p = 0.037). Artificial intelligence can accurately distinguish between atrophy caused by AMD or by EMAP on FAF images. Its performance are improved using wide field acquisitions.
为了创建一个基于眼底自发荧光（FAF）图像的深度学习（DL）分类器，以帮助临床医生区分与年龄相关的地图状萎缩与广泛的黄斑萎缩和假性渗出样外观（EMAP）。回顾性选择了由于 EMAP（EMAP 组）或干性年龄相关性黄斑变性（AMD 组）而导致完全外视网膜和视网膜色素上皮萎缩的患者。收集了足够高质量的以黄斑为中心的后极（30°×30°）和 55°×55°视场 FAF 图像，并用于基于 ResNet-101 设计的两个不同的深度学习（DL）分类器进行训练。在来自不同中心的一组图像上进行测试。共招募了 300 名患者，其中 135 名属于 EMAP 组，165 名属于 AMD 组。基于 30°×30° FAF 的 DL 分类器对 EMAP 的诊断灵敏度为 84.6％，特异性为 85.3％。基于 55°×55° FAF 的 DL 分类器的灵敏度为 90％，特异性为 84.6％，性能明显高于 30°×30°分类器（p=0.037）。人工智能可以准确区分 FAF 图像上由 AMD 或 EMAP 引起的萎缩。使用广角采集可以提高其性能。
