Peripapillary atrophy classification using CNN deep learning for glaucoma screening

Abstract

Glaucoma is the second leading cause of blindness worldwide, and peripapillary atrophy (PPA) is a morphological symptom associated with it. Therefore, it is necessary to clinically detect PPA for glaucoma diagnosis. This study was aimed at developing a detection method for PPA using fundus images with deep learning algorithms to be used by ophthalmologists or optometrists for screening purposes. The model was developed based on localization for the region of interest (ROI) using a mask region-based convolutional neural networks R-CNN and a classification network for the presence of PPA using CNN deep learning algorithms. A total of 2,472 images, obtained from five public sources and one Saudi-based resource (King Abdullah International Medical Research Center in Riyadh, Saudi Arabia), were used to train and test the model. First the images from public sources were analyzed, followed by those from local sources, and finally, images from both sources were analyzed together. In testing the classification model, the area under the curve's (AUC) scores of 0.83, 0.89, and 0.87 were obtained for the local, public, and combined sets, respectively. The developed model will assist in diagnosing glaucoma in screening programs; however, more research is needed on segmenting the PPA boundaries for more detailed PPA detection, which can be combined with optic disc and cup boundaries to calculate the cup-to-disc ratio.

Fig 1. The process flow of the proposed PPA detection system.

Fig 2. An example of cropping a candidate ROI from a fundus images following the proposed localization approach.

In (a) a fundus image is shown, while (b) and (c) present the localized image by the deep learning algorithm and the cropped ROI, respectively.

Fig 3. A proposed algorithm to maintain the aspect ratio for all generated bounding boxes.

Fig 4. The proposed PPA classification model architecture.

Fig 5. Confusion matrix diagram.

Fig 6. The selected architectures for the performed experiments.

Fig 7. The resultant accuracy curves while using the hinge loss function for the best model.

(a) KAIMRC dataset. (b) Public dataset. (c) Combined dataset.

Fig 8. The resultant loss curves while using the hinge loss function for the best model.

(a) KAIMRC dataset. (b) Public dataset. (c) Combined dataset.

Fig 9. The confusion matrices on the test sets.

(a) KAIMRC dataset. (b) Public dataset. (c) Combined dataset.

Fig 10. The ROC curve on the three used datasets and showing the resultant AUC score.

(a) KAIMRC dataset. (b) Public dataset. (c) Combined dataset.

Fig 11. The confusion matrices for the test sets while performing the cross validation on the KAIMRC images.

(a) First Fold. (b) Second Fold. (c) Third Fold.

Fig 12. The confusion matrices for the test sets while performing the cross validation on all the obtained public images.

(a) First Fold. (b) Second Fold. (c) Third Fold.

Fig 13. The confusion matrices for the test sets while performing the cross validation on the combined images from both public sources and KAIMRC database.

(a) First Fold. (b) Second Fold. (c) Third Fold.

Fig 14. The ROC curves while performing the cross validation on the three datasets.

(a) KAIMRC images. (b) Obtained Public images. (c) Combined images.