Boundary-enhanced semi-supervised retinal layer segmentation in optical coherence tomography images using fewer labels

Lu，Ye1; Shen，Yutian1; Xing，Xiaohan2; Ye，Chengwei1; Meng，Max Q.H.1,3,4

2023-04-01

10.1016/j.compmedimag.2023.102199

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS   影响因子和分区

0895-6111

1879-0771

Automatic segmentation of multiple layers in retinal optical coherence tomography (OCT) images is crucial for eye disease diagnosis and treatment. Despite the success of deep learning algorithms, it still remains a challenge due to the blurry layer boundaries and lack of adequate pixel-wise annotations. To tackle these issues, we propose a Boundary-Enhanced Semi-supervised Network (BE-SemiNet) that exploits an auxiliary distance map regression task to improve retinal layer segmentation with scarce labeled data and abundant unlabeled data. Specifically, a novel Unilaterally Truncated Distance Map (UTDM) is firstly introduced to alleviate the class imbalance problem and enhance the layer boundary learning in the regression task. Then for the pixel-wise segmentation and UTDM regression branches, we impose task-level and data-level consistency regularization on unlabeled data to enrich the diversity of unsupervised information and improve the regularization effects. Pseudo supervision is incorporated in consistency regularization to bridge the task prediction spaces for consistency and expand training labeled data. Experiments on two public retinal OCT datasets show that our method can greatly improve the supervised baseline performance with only 5 annotations and outperform the state-of-the-art methods. Since it is difficult and labor-expensive to obtain adequate pixel-wise annotations in practice, our method has a promising application future in clinical retinal OCT image analysis.

Distance transform map Optical coherence tomography Retinal layer segmentation Semi-supervised learning

SCI ; EI

英语

其他

National Key R&D program of China[2019YFB1312400] ; Hong Kong RGC CRF[C4063-18G]

Engineering ; Radiology, Nuclear Medicine & Medical Imaging

Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000943940200001

PERGAMON-ELSEVIER SCIENCE LTD

20230813615643

Deep learning ; Diagnosis ; Image enhancement ; Image segmentation ; Learning algorithms ; Ophthalmology ; Pixels ; Regression analysis

Ergonomics and Human Factors Engineering:461.4 ; Medicine and Pharmacology:461.6 ; Machine Learning:723.4.2 ; Optical Devices and Systems:741.3 ; Mathematical Statistics:922.2

CLINICAL MEDICINE

2-s2.0-85148332754

Scopus

1.Department of Electronic Engineering,The Chinese University of Hong Kong,Hong Kong
2.Department of Electrical Engineering,The City University of Hong Kong,Hong Kong
3.Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,China
4.Shenzhen Research Institute of The Chinese University of Hong Kong,Shenzhen,China

Lu，Ye,Shen，Yutian,Xing，Xiaohan,et al. Boundary-enhanced semi-supervised retinal layer segmentation in optical coherence tomography images using fewer labels[J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS,2023,105.

Lu，Ye,Shen，Yutian,Xing，Xiaohan,Ye，Chengwei,&Meng，Max Q.H..(2023).Boundary-enhanced semi-supervised retinal layer segmentation in optical coherence tomography images using fewer labels.COMPUTERIZED MEDICAL IMAGING AND GRAPHICS,105.

Lu，Ye,et al."Boundary-enhanced semi-supervised retinal layer segmentation in optical coherence tomography images using fewer labels".COMPUTERIZED MEDICAL IMAGING AND GRAPHICS 105(2023).