http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Detection of OCT image Parameters Based on Deep Learning algorithm
Md Habibur Rahman(하비부르 라만),Hang Chan Jo(조항찬),Dong Jin Lee(이동진),Dae Yu Kim(김대유) 대한전자공학회 2021 대한전자공학회 학술대회 Vol.2021 No.6
In this article, we present a computerized detection of optical coherence tomography (OCT) image parameters using a deep learning method. To detect the parameters, Bruch’s membrane opening (BMO) and laminar cribrosa (LC) in OCT image, proposed system work with a convolutional neural network (CNN) algorithm. Herein, we designed detection method using YOLOv3 algorithm where darknet53 CNN used as a backbone network. We used OCT medical images for testing the detection performance. The excremental result for detection performance show that, 99.92% and 99.18% average detection precision of parameters BMO and LC, respectively on the testing image.