文献速递神经眼科

深度学习在彩色图像上区分动脉炎性与非动脉炎性缺血性视神经病变

Deep Learning to Discriminate Arteritic From Nonarteritic Ischemic Optic Neuropathy on Color Images.
PubMed 文献 · JAMA Ophthalmol · 2024-01-01

这项国际研究利用16国21个神经眼科中心的彩色眼底图像训练深度学习系统,并在5个中心的外部数据集中测试其区分急性动脉炎性前部缺血性视神经病变(AAION)与非动脉炎性前部缺血性视神经病变(NAION)的能力,外部测试AUC为0.97,准确率92.6%,高于两位专家的74.3%和81.6%。

要点

  • 深度学习系统在外部测试集区分AAION与NAION的AUC为0.97,敏感度91.1%,特异度93.4%,准确率92.6%。
  • 同一外部测试集上两位专家的分类准确率分别为74.3%和81.6%。
  • 该系统仅基于彩色眼底图像,无需临床或生物标志物信息。

核心结论

  • 深度学习系统在眼别水平上区分急性AAION与NAION的准确率超过90%,且无需任何临床或生物标志物信息。
  • 作者认为识别AAION的深度学习系统可改善临床决策,可能降低误诊风险并改善患者结局。

研究设计与样本

  • 国际研究,纳入961只眼(802例确诊AAION和NAION患者)的彩色眼底图像。
  • 训练使用16个国家21个神经眼科专家的图像,外部测试使用美国和欧洲5个神经眼科中心的队列。
  • 训练和外部测试数据收集时间为2018年8月至2023年1月,数据分析时间为2023年1月至2024年1月。
  • 训练和内部验证图像来自16种眼底相机型号(视野30°至55°),外部测试图像来自5种眼底相机(视野30°至50°)。

主要发现

  • 训练和验证集:374例(54.9%)女性,301例(44.2%)男性,6例(0.9%)性别未知;中位(范围)年龄66(23-96)岁。
  • 外部测试集包括121例患者(35例[28.9%]女性,44例[36.4%]男性,42例[34.7%]性别未知;中位[范围]年龄69[37-89]岁)。
  • 外部测试集上深度学习系统的AUC为0.97(95%CI,0.95-0.99),敏感度91.1%(95%CI,85.2-96.9),特异度93.4%(95%CI,91.1-98.2),准确率92.6%(95%CI,90.5-96.6)。
  • 同一数据集上两位专家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)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

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.

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Gungor A, Najjar RP, Hamann S, et al. Deep Learning to Discriminate Arteritic From Nonarteritic Ischemic Optic Neuropathy on Color Images. JAMA Ophthalmol. 2024. PMID: 39418057. doi:10.1001/jamaophthalmol.2024.4269

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。