Importance Prompt and accurate diagnosis of arteritic anterior ischemic optic neuropathy (AAION) from giant cell arteritis and other systemic vasculitis can contribute to preventing irreversible vision loss from these conditions. Its clinical distinction from nonarteritic anterior ischemic optic neuropathy (NAION) can be challenging, especially when systemic symptoms are lacking or laboratory markers of the disease are not reliable. Objective To develop, train, and test a deep learning system (DLS) to discriminate AAION from NAION on color fundus images during the acute phase. Design, Setting, and Participants This was an international study including color fundus images of 961 eyes of 802 patients with confirmed AAION and NAION. Training was performed using images from 21 expert neuro-ophthalmology centers in 16 countries, while external testing was performed in a cohort from 5 expert neuro-ophthalmology centers in the US and Europe. Data for training and external testing were collected from August 2018 to January 2023. A mix of deidentified images of 2 fields of view (optic disc centered and macula centered) were used. For training and internal validation, images were from 16 fundus camera models with fields of 30° to 55°. For external testing, images were from 5 fundus cameras with fields of 30° to 50°. Data were analyzed from January 2023 to January 2024. Main Outcomes and Measures The performance of the DLS was measured using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Results In the training and validation sets, 374 (54.9%) of patients were female, 301 (44.2%) were male, and 6 (0.9%) were of unknown sex; the median (range) age was 66 (23-96) years. When tested on the external dataset including 121 patients (35 [28.9%] female, 44 [36.4%] male, and 42 [34.7%] of unknown sex; median [range] age, 69 [37-89] years), the DLS achieved an AUC of 0.97 (95% CI, 0.95-0.99), a sensitivity of 91.1% (95% CI, 85.2-96.9), a specificity of 93.4% (95% CI, 91.1-98.2), and an accuracy of 92.6% (95% CI, 90.5-96.6). The accuracy of the 2 experts for classification of the same dataset was 74.3% (95% CI, 66.7-81.9) and 81.6% (95% CI, 74.8-88.4), respectively. Conclusions and Relevance A DLS showing disease-specific averaged class-activation maps had greater than 90% accuracy at discriminating between acute AAION from NAION on color fundus images, at the eye level, without any clinical or biomarker information. A DLS that identifies AAION could improve clinical decision-making, potentially reducing the risk of misdiagnosis and improving patient outcomes.

中文翻译：

---

深度学习在彩色图像上区分动脉炎性和非动脉炎性缺血性视神经病变。


重要性 及时准确地诊断巨细胞动脉炎和其他系统性血管炎引起的动脉炎性前缺血性视神经病变 （AAION） 有助于防止这些疾病引起的不可逆性视力丧失。它与非动脉炎性前部缺血性视神经病变 （NAION） 的临床鉴别可能具有挑战性，尤其是当缺乏全身症状或疾病的实验室标志物不可靠时。目的 开发、训练和测试深度学习系统 （DLS），以区分急性期彩色眼底图像上的 AAION 和 NAION。设计、设置和参与者 这是一项国际研究，包括 961 名确诊 AAION 和 NAION 患者的 802 只眼睛的彩色眼底图像。使用来自 16 个国家/地区的 21 个神经眼科专家中心的图像进行培训，同时对来自美国和欧洲 5 个神经眼科专家中心的队列进行外部测试。从 2018 年 8 月到 2023 年 1 月收集了训练和外部测试数据。混合使用了 2 个视野 （视盘居中和黄斑居中） 的去识别化图像。为了进行训练和内部验证，图像来自 16 个视野为 30° 至 55° 的眼底相机模型。对于外部测试，图像来自 5 个视野为 30° 至 50° 的眼底相机。数据分析时间为 2023 年 1 月至 2024 年 1 月。主要结局和措施 DLS 的性能是使用受试者工作特征曲线下面积 （AUC） 、敏感性、特异性和准确性来衡量的。结果 在训练集和验证集中，女性 374 例 （54.9%） 患者，男性 301 例 （44.2%） 患者，性别未知 6 例 （0.9%） 患者;中位 （范围） 年龄为 66 （23-96） 岁。 在包括 121 名患者（35 名 [28.9%] 女性，44 名 [36.4%] 男性和 42 名 [34.7%] 性别未知患者;中位 [范围] 年龄为 69 [37-89] 岁）的外部数据集上进行测试时，DLS 的 AUC 为 0.97（95% CI，0.95-0.99），敏感性为 91.1%（95% CI，85.2-96.9），特异性为 93.4%（95% CI，91.1-98.2），准确性为 92.6%（95% CI， 90.5-96.6）. 2 位专家对同一数据集的分类准确率分别为 74.3% （95% CI， 66.7-81.9） 和 81.6% （95% CI， 74.8-88.4）。结论和相关性 显示疾病特异性平均类别激活图的 DLS 在彩色眼底图像上区分急性 AAION 和 NAION 的准确率超过 90%，在没有任何临床或生物标志物信息的情况下。识别 AAION 的 DLS 可以改善临床决策，有可能降低误诊风险并改善患者预后。