Retinal OCT Image Classification Based on Domain Adaptation Convolutional Neural Networks

Li, Zhide1; Cheng, Ken1; Qin, Peiwu1; Dong, Yuhan1; Yang, Chengming2; Jiang, Xuefeng3

10.1109/CISP-BMEI53629.2021.9624429

2021

14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

978-1-6654-0005-3

2021 14TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2021)

1-5

OCT 23-25, 2021

null,Shanghai,PEOPLES R CHINA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Computer-aided diagnosis of retinopathy is a hot research topic in the field of medical image classification, where optical coherence tomography (OCT) is an important basis for the diagnosis of ophthalmic diseases. In this paper, two publicly available retinal OCT image datasets are integrated and screened. Then, an end-to-end deep learning algorithmic framework based on domain adaptation Inception V3 was proposed to automatically and reliably classify six categories of retinal OCT images using the prior knowledge of a similar domain. Numerical results suggest that the proposed algorithm works well in terms of accuracy, precision, sensitivity and specificity, approaching or even partially surpassing the performance of clinical experts. It is valuable in promoting computer-aided diagnosis towards practical clinical applications and improving the efficiency of clinical diagnosis of retinal diseases.

retinopathy optical coherence tomography (OCT) neural network transfer learning

通讯

英语

CPCI-S ; EI

National Key R&D Program of China[2018YFC0116800] ; Key R&D Program of Department of Education of Guangdong Province[2021ZDZX1102]

Engineering ; Medical Informatics ; Imaging Science & Photographic Technology

Engineering, Biomedical ; Medical Informatics ; Imaging Science & Photographic Technology

WOS:000789442100136

Web of Science

1.Tsinghua Univ, Shenzhen Int Grad Sch, Shenzhen 518055, Peoples R China
2.Southern Univ Sci & Technol Hosp, Dept Ophthalmol, Shenzhen 518055, Peoples R China
3.Shenzhen Polytech, Artificial Intelligent Coll, Shenzhen 518055, Peoples R China

Li, Zhide,Cheng, Ken,Qin, Peiwu,et al. Retinal OCT Image Classification Based on Domain Adaptation Convolutional Neural Networks[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:1-5.