Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier

详细信息    查看全文

• 作者：Ryo Asaoka ; MD ; PhD¹ ; ^{rasaoka-tky@umin.ac.jp" class="auth_mail" title="E-mail the corresponding author} ; Hiroshi Murata ; MD¹ ; Aiko Iwase ; MD ; PhD² ; Makoto Araie ; MD ; PhD¹ ; ³
• 关键词：AUC ; area under the receiver operating characteristic curve ; CI ; confidence interval ; D ; diopter ; DL ; deep learning ; FNN ; feed-forward neural network ; HFA ; Humphrey Field Analyzer ; MD ; mean deviation ; ML ; machine learning ; NN ; neural network ; OAG ; open-angle glaucoma ; OCT ; optical coherence tomography ; PPGVF ; preperimetric glaucoma visual field ; PSD ; pattern standard deviation ; RF ; random forests ; SVM ; support vector machine ; TD ; total deviation ; VF ; visual field
• 刊名：Ophthalmology
• 出版年：2016
• 出版时间：September 2016
• 年：2016
• 卷：123
• 期：9
• 页码：1974-1980
• 全文大小：1250 K

文摘

To differentiate the visual fields (VFs) of preperimetric open-angle glaucoma (OAG) patients from the VFs of healthy eyes using a deep learning (DL) method.

Design

Cohort study.

Participants

One hundred seventy-one preperimetric glaucoma VFs (PPGVFs) from 53 eyes in 51 OAG patients and 108 healthy eyes of 87 healthy participants.

Methods

Preperimetric glaucoma VFs were defined as all VFs before a first diagnosis of manifest glaucoma (Anderson-Patella's criteria). In total, 171 PPGVFs from 53 eyes in 51 OAG patients and 108 VFs from 108 healthy eyes in 87 healthy participants were analyzed (all VFs were tested using the Humphrey Field Analyzer 30-2 program; Carl Zeiss Meditec, Dublin, CA). The 52 total deviation, mean deviation, and pattern standard deviation values were used as predictors in the DL classifier: a deep feed-forward neural network (FNN), along with other machine learning (ML) methods, including random forests (RF), gradient boosting, support vector machine, and neural network (NN). The area under the receiver operating characteristic curve (AUC) was used to evaluate the accuracy of discrimination for each method.

Main Outcome Measures

The AUCs obtained with each classifier method.

Results

A significantly larger AUC of 92.6% (95% confidence interval [CI], 89.8%–95.4%) was obtained using the deep FNN classifier compared with all other ML methods: 79.0% (95% CI, 73.5%–84.5%) with RF, 77.6% (95% CI, 71.7%–83.5%) with gradient boosting, 71.2% (95% CI, 65.0%–77.5%), and 66.7% (95% CI, 60.1%–73.3%) with NN.

Conclusions

Preperimetric glaucoma VFs can be distinguished from healthy VFs with very high accuracy using a deep FNN classifier.