OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method
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...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/2/347 |
| _version_ | 1797342972512043008 |
|---|---|
| author | Zhicong Tan Qinqin Zhang Gongpu Lan Jingjiang Xu Chubin Ou Lin An Jia Qin Yanping Huang |
| author_facet | Zhicong Tan Qinqin Zhang Gongpu Lan Jingjiang Xu Chubin Ou Lin An Jia Qin Yanping Huang |
| author_sort | Zhicong Tan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T10:40:56Z |
| format | Article |
| id | doaj.art-060fadffea454f2b81584f911c8ece24 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T10:40:56Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-060fadffea454f2b81584f911c8ece242024-01-26T17:34:21ZengMDPI AGMathematics2227-73902024-01-0112234710.3390/math12020347OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning MethodZhicong Tan0Qinqin Zhang1Gongpu Lan2Jingjiang Xu3Chubin Ou4Lin An5Jia Qin6Yanping Huang7School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, ChinaGuangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, ChinaGuangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, ChinaInnovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, ChinaInnovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, ChinaInnovation and Entrepreneurship Teams Project of Guangdong Provincial Pearl River Talents Program, Guangdong Weiren Meditech Co., Ltd., Foshan 528015, ChinaGuangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology, School of Physics and Optoelectronic Engineering, Foshan University, Foshan 528225, ChinaConventional 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.https://www.mdpi.com/2227-7390/12/2/347optical coherence tomographyretinopathy classificationdeep learningtransfer learningsub-domain adaptation |
| spellingShingle | Zhicong Tan Qinqin Zhang Gongpu Lan Jingjiang Xu Chubin Ou Lin An Jia Qin Yanping Huang OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method Mathematics optical coherence tomography retinopathy classification deep learning transfer learning sub-domain adaptation |
| title | OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method |
| title_full | OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method |
| title_fullStr | OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method |
| title_full_unstemmed | OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method |
| title_short | OCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method |
| title_sort | oct retinopathy classification via a semi supervised pseudo label sub domain adaptation and fine tuning method |
| topic | optical coherence tomography retinopathy classification deep learning transfer learning sub-domain adaptation |
| url | https://www.mdpi.com/2227-7390/12/2/347 |
| work_keys_str_mv | AT zhicongtan octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT qinqinzhang octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT gongpulan octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT jingjiangxu octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT chubinou octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT linan octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT jiaqin octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod AT yanpinghuang octretinopathyclassificationviaasemisupervisedpseudolabelsubdomainadaptationandfinetuningmethod |