文献速递青光眼

使用深度学习在高眼压治疗研究中检测青光眼

Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning.
PubMed 文献 · JAMA Ophthalmol · 2022-01-01

本研究基于高眼压治疗研究(OHTS)中1636名参与者、3272只眼的66715张眼底照片,训练并测试ResNet-50深度学习模型检测原发性开角型青光眼(POAG),模型对OHTS终点委员会判定的视盘或视野改变达到AUROC 0.88,提示深度学习有潜力标准化和自动化临床试验及管理中的POAG判定。

要点

  • 深度学习模型对OHTS终点委员会判定的视盘或视野改变AUROC为0.88(95%CI 0.82-0.92)。
  • 基于视盘改变和视野改变的AUROC分别为0.91(95%CI 0.88-0.94)和0.86(95%CI 0.76-0.93)。
  • 在90%特异度下,后来发生POAG的眼早期照片假阳性率27.5%(56/204),未发生POAG的眼为11.4%(50/440)。

核心结论

  • 模型在OHTS照片上展现高诊断准确度,提示深度学习有潜力标准化和自动化临床试验及管理中的POAG判定。
  • 后来发生POAG的眼早期照片假阳性率更高,提示深度学习模型在某些眼上比OHTS终点委员会更早检测到POAG,反映OHTS设计强调POAG判定的高特异度、要求较基线有临床显著改变。

研究设计与样本

  • 本诊断研究纳入来自22个中心的1636名OHTS参与者,平均(范围)随访10.7(0-14.3)年。
  • 共使用3272只眼的66715张照片训练和测试ResNet-50模型,以检测OHTS终点委员会基于视盘(287只眼,3502张照片)和/或视野(198只眼,2300个视野)改变的POAG判定。
  • 训练集1147名参与者(661名[57.6%]女性;平均年龄57.2岁;95%CI 56.6-57.8),验证集167名(97名[58.1%]女性;平均年龄57.1岁;95%CI 55.6-58.7),测试集322名(173名[53.7%]女性;平均年龄57.2岁;95%CI 56.1-58.2)。
  • 使用3个独立测试集评估模型的泛化能力。

主要发现

  • 深度学习模型对OHTS终点委员会判定的视盘或视野改变AUROC为0.88(95%CI 0.82-0.92)。
  • 基于视盘改变的OHTS终点AUROC为0.91(95%CI 0.88-0.94),基于视野改变的AUROC为0.86(95%CI 0.76-0.93)。
  • 在90%特异度下,后来经视盘或视野发生POAG的眼照片假阳性率为27.5%(56/204),未发生POAG的眼为11.4%(50/440)。
  • 基于视盘终点开发的深度学习模型应用于3个独立数据集时诊断准确度较低,AUROC范围为0.74(95%CI 0.70-0.77)至0.79(95%CI 0.78-0.81)。

局限性

  • 基于视盘终点开发的深度学习模型应用于3个独立数据集时诊断准确度较低,AUROC范围为0.74(95%CI 0.70-0.77)至0.79(95%CI 0.78-0.81)。

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: Automated deep learning (DL) analyses of fundus photographs potentially can reduce the cost and improve the efficiency of reading center assessment of end points in clinical trials. OBJECTIVE: To investigate the diagnostic accuracy of DL algorithms trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG). DESIGN, SETTING, AND PARTICIPANTS: In this diagnostic study, 1636 OHTS participants from 22 sites with a mean (range) follow-up of 10.7 (0-14.3) years. A total of 66 715 photographs from 3272 eyes were used to train and test a ResNet-50 model to detect the OHTS Endpoint Committee POAG determination based on optic disc (287 eyes, 3502 photographs) and/or visual field (198 eyes, 2300 visual fields) changes. Three independent test sets were used to evaluate the generalizability of the model. MAIN OUTCOMES AND MEASURES: Areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities were calculated to compare model performance. Evaluation of false-positive rates was used to determine whether the DL model detected POAG before the OHTS Endpoint Committee POAG determination. RESULTS: A total of 1147 participants were included in the training set (661 [57.6%] female; mean age, 57.2 years; 95% CI, 56.6-57.8), 167 in the validation set (97 [58.1%] female; mean age, 57.1 years; 95% CI, 55.6-58.7), and 322 in the test set (173 [53.7%] female; mean age, 57.2 years; 95% CI, 56.1-58.2). The DL model achieved an AUROC of 0.88 (95% CI, 0.82-0.92) for the OHTS Endpoint Committee determination of optic disc or VF changes. For the OHTS end points based on optic disc changes or visual field changes, AUROCs were 0.91 (95% CI, 0.88-0.94) and 0.86 (95% CI, 0.76-0.93), respectively. False-positive rates (at 90% specificity) were higher in photographs of eyes that later developed POAG by disc or visual field (27.5% [56 of 204]) compared with eyes that did not develop POAG (11.4% [50 of 440]) during follow-up. The diagnostic accuracy of the DL model developed on the optic disc end point applied to 3 independent data sets was lower, with AUROCs ranging from 0.74 (95% CI, 0.70-0.77) to 0.79 (95% CI, 0.78-0.81). CONCLUSIONS AND RELEVANCE: The model's high diagnostic accuracy using OHTS photographs suggests that DL has the potential to standardize and automate POAG determination for clinical trials and management. In addition, the higher false-positive rate in early photographs of eyes that later developed POAG suggests that DL models detected POAG in some eyes earlier than the OHTS Endpoint Committee, reflecting the OHTS design that emphasized a high specificity for POAG determination by requiring a clinically significant change from baseline.

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Fan R, Bowd C, Christopher M, et al. Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning. JAMA Ophthalmol. 2022. PMID: 35297959. doi:10.1001/jamaophthalmol.2022.0244

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。