Prior-SSL: A Thickness Distribution Prior and Uncertainty Guided Semi-supervised Learning Method for Choroidal Segmentation in OCT Images

Zhang, Huihong1,2; Zhang, Xiaoqing2; Zhang, Yinlin2,7; Higashita, Risa2,3; Liu, Jiang2,4,5,6

10.1007/978-3-031-44210-0_46

2023

32nd International Conference on Artificial Neural Networks (ICANN)

0302-9743

1611-3349

978-3-031-44209-4

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II

14255

SEP 26-29, 2023

null,Heraklion,GREECE

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Choroid structure is crucial for the diagnosis of ocular diseases, and deep supervised learning (SL) techniques have been widely applied to segment the choroidal structure based on OCT images. However, SL requires massive annotated data, which is difficult to obtain. Researchers have explored semi-supervised learning (SSL) methods based on consistency regularization and achieved strong performance. However, these methods suffer from heavy computational burdens and introduce noise that hinders the training process. To address these issues, we propose a thickness distribution prior and uncertainty aware pseudo-label selection SSL framework (Prior-SSL) for OCT choroidal segmentation. Specifically, we compute the instance-level uncertainty of the pseudo-label candidate, which significantly reduces the computational burden of uncertainty estimation. In addition, we consider the physiological characteristics of the choroid, explore the choroidal thickness distribution as prior knowledge in the pseudo-label selection procedure, and thereby obtain more reliable and accurate pseudo-labels. Finally, these two branches are combined via a Modified AND-Gate (MAG) to assign confidence levels to pseudo-label candidates. We achieve state-of-the-art performance for the choroidal segmentation task on the GOALS and NIDEK OCT datasets. Ablation studies verify the effectiveness of the Prior-SSL in selecting high-quality pseudo-labels.

OCT image choroidal segmentation semi-supervised learning (SSL) pseudo-label prior knowledge

通讯

英语

EI ; CPCI-S

General Program of National Natural Science Foundation of China[82272086] ; Shenzhen Natural Science Fund["JCYJ20200109140820699","20200925174052004"]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:001156957400046

Web of Science

1.Harbin Institute of Technology, Harbin, China
2.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen; 518055, China
3.TOMEY Corporation, Nagoya; 4510051, Japan
4.Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen; 518055, China
5.Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen; 518055, China
6.Singapore Eye Research Institute, Singapore; 169856, Singapore
7.School of Computer Science, University of Nottingham Ningbo China, Ningbo; 315100, China

Zhang, Huihong,Zhang, Xiaoqing,Zhang, Yinlin,et al. Prior-SSL: A Thickness Distribution Prior and Uncertainty Guided Semi-supervised Learning Method for Choroidal Segmentation in OCT Images[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2023.