OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method

Zhicong Tan, Qinqin Zhang, Gongpu Lan, Jingjiang Xu, Chubin Ou, Lin An, Jia Qin and Yanping Huang ()
Additional contact information
Zhicong Tan: School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, China
Qinqin Zhang: Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, China
Gongpu Lan: Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, China
Jingjiang Xu: Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, China
Chubin Ou: Innovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, China
Lin An: Innovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, China
Jia Qin: Innovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, China
Yanping Huang: Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, China

Mathematics, 2024, vol. 12, issue 2, 1-16

Abstract: Conventional OCT retinal disease classification methods primarily rely on fully supervised learning, which requires a large number of labeled images. However, sometimes the number of labeled images in a private domain is small but there exists a large annotated open dataset in the public domain. In response to this scenario, a new transfer learning method based on sub-domain adaptation (TLSDA), which involves a first sub-domain adaptation and then fine-tuning, was proposed in this study. Firstly, a modified deep sub-domain adaptation network with pseudo-label (DSAN-PL) was proposed to align the feature spaces of a public domain (labeled) and a private domain (unlabeled). The DSAN-PL model was then fine-tuned using a small amount of labeled OCT data from the private domain. We tested our method on three open OCT datasets, using one as the public domain and the other two as the private domains. Remarkably, with only 10% labeled OCT images (~100 images per category), TLSDA achieved classification accuracies of 93.63% and 96.59% on the two private datasets, significantly outperforming conventional transfer learning approaches. With the Gradient-weighted Class Activation Map (Grad-CAM) technique, it was observed that the proposed method could more precisely localize the subtle lesion regions for OCT image classification. TLSDA could be a potential technique for applications where only a small number of images is labeled in a private domain and there exists a public database having a large number of labeled images with domain difference.

Keywords: optical coherence tomography; retinopathy classification; deep learning; transfer learning; sub-domain adaptation (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/2/347/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/2/347/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:2:p:347-:d:1323453

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().