|
KMID : 1100520230290020145
|
|
Healthcare Informatics Research
2023 Volume.29 No. 2 p.145 ~ p.151
|
|
|
Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images
|
|
Anindita Septiarini
Hamdani Hamdani
Emy Setyaningsih
Eko Junirianto
Fitri Utaminingrum
|
|
|
Abstract
|
|
|
Objectives: The optic disc is part of the retinal fundus image structure, which influences the extraction of glaucoma features.
This study proposes a method that automatically segments the optic disc area in retinal fundus images using deep learningbased on a convolutional neural network (CNN).
Methods: This study used private and public datasets containing retinalfundus images. The private dataset consisted of 350 images, while the public dataset was the Retinal Fundus Glaucoma Challenge(REFUGE). The proposed method was based on a CNN with a single-shot multibox detector (MobileNetV2) to formimages of the region-of-interest (ROI) using the original image resized into 640 × 640 input data. A pre-processing sequencewas then implemented, including augmentation, resizing, and normalization. Furthermore, a U-Net model was applied foroptic disc segmentation with 128 × 128 input data.
Results: The proposed method was appropriately applied to the datasetsused, as shown by the values of the F1-score, dice score, and intersection over union of 0.9880, 0.9852, and 0.9763 for the privatedataset, respectively, and 0.9854, 0.9838 and 0.9712 for the REFUGE dataset.
Conclusions: The optic disc area producedby the proposed method was similar to that identified by an ophthalmologist. Therefore, this method can be considered forimplementing automatic segmentation of the optic disc area.
|
|
|
KEYWORD
|
|
|
Image Processing, Computer Vision, Fundus, Glaucoma, Optic Neuropathy
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|