Automated measurement of the disc-fovea angle based on DeepLabv3+

Abstract

PurposeTo assess the value of automatic disc-fovea angle (DFA) measurement using the DeepLabv3+ segmentation model.MethodsA total of 682 normal fundus image datasets were collected from the Eye Hospital of Nanjing Medical University. The following parts of the images were labeled and subsequently reviewed by ophthalmologists: optic disc center, macular center, optic disc area, and virtual macular area. A total of 477 normal fundus images were used to train DeepLabv3+, U-Net, and PSPNet model, which were used to obtain the optic disc area and virtual macular area. Then, the coordinates of the optic disc center and macular center were obstained by using the minimum outer circle technique. Finally the DFA was calculated.ResultsIn this study, 205 normal fundus images were used to test the model. The experimental results showed that the errors in automatic DFA measurement using DeepLabv3+, U-Net, and PSPNet segmentation models were 0.76°, 1.4°, and 2.12°, respectively. The mean intersection over union (MIoU), mean pixel accuracy (MPA), average error in the center of the optic disc, and average error in the center of the virtual macula obstained by using DeepLabv3+ model was 94.77%, 97.32%, 10.94 pixels, and 13.44 pixels, respectively. The automatic DFA measurement using DeepLabv3+ got the less error than the errors that using the other segmentation models. Therefore, the DeepLabv3+ segmentation model was finally chosen to measure DFA automatically.ConclusionsThe DeepLabv3+ segmentation model -based automatic segmentation techniques can produce accurate and rapid DFA measurements.

Effectiveness of modified inferior oblique muscle belly transposition for V-pattern exotropia combined with mild to moderate inferior oblique muscle overaction

“…The common approach to measuring the FDA is that operators locate three points in the angle or connect the two characteristic points with the disc horizontal line by the "Angle" tools [31] . In fact, the manual measurement error of FDA is hard to avoid [32] with a reported error of 2.0°±1.8° on average [33] . So we took advantage of the built-in horizontal line function on the "Straight" program in Image J to simplify the process and reduce the measuring-error by less manually markers.…”

A novel vessel segmentation algorithm for pathological en-face images based on matched filter

“…Deeplabv3+ is a semantic segmentation network, based on deeplabv3 (Chen et al 2017), it adds a simple and effective Decoder to refine the segmentation results, especially the segmentation results along the boundary of the target object, and it is implemented by using a spatial pyramid pool module or a combination of encoding and decoding structures. Zheng et al (2022) use the DeepLabv3 + segmentation model assess the value of automatic disc-fovea angle (DFA) measurement. In Xu et al (2022), a method using SegNet is proposed to improve the accuracy of retinal blood vessel segmentation.…”

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

“…In recent years, the application of artificial intelligence in the medical field has become one of the research hotspots [8] . Many scholars have conducted in-depth research [9][10][11][12][13][14][15][16] . And deep learning technology has gradually been applied to the prevention and early detection of HMM.…”