A region-level contrastive learning-based deep model for glomerular ultrastructure segmentation on electron microscope images.
10.12122/j.issn.1673-4254.2023.05.18
- Author:
Guoyu LIN
1
;
Zhentai ZHANG
1
;
Yanmeng LU
2
;
Jian GENG
3
;
Zhitao ZHOU
2
;
Lijun LU
1
;
Lei CAO
1
Author Information
1. School of Biomedical Engineering//Guangdong Provincial Key Laboratory of Medical Image Processing//Guangdong Provincial Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou 510515, China.
2. Central Laboratory, Southern Medical University, Guangzhou 510515, China.
3. School of Basic Medical Sciences, Southern Medical University, Guangzhou 510515, China.
- Publication Type:Journal Article
- Keywords:
electron microscopy;
glomerular ultrastructure segmentation;
labeled data scarcity;
self-supervised contrastive learning
- MeSH:
Humans;
Electrons;
Endothelial Cells;
Learning;
Podocytes;
Kidney Diseases
- From:
Journal of Southern Medical University
2023;43(5):815-824
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVE:We propose a novel region- level self-supervised contrastive learning method USRegCon (ultrastructural region contrast) based on the semantic similarity of ultrastructures to improve the performance of the model for glomerular ultrastructure segmentation on electron microscope images.
METHODS:USRegCon used a large amount of unlabeled data for pre- training of the model in 3 steps: (1) The model encoded and decoded the ultrastructural information in the image and adaptively divided the image into multiple regions based on the semantic similarity of the ultrastructures; (2) Based on the divided regions, the first-order grayscale region representations and deep semantic region representations of each region were extracted by region pooling operation; (3) For the first-order grayscale region representations, a grayscale loss function was proposed to minimize the grayscale difference within regions and maximize the difference between regions. For deep semantic region representations, a semantic loss function was introduced to maximize the similarity of positive region pairs and the difference of negative region pairs in the representation space. These two loss functions were jointly used for pre-training of the model.
RESULTS:In the segmentation task for 3 ultrastructures of the glomerular filtration barrier based on the private dataset GlomEM, USRegCon achieved promising segmentation results for basement membrane, endothelial cells, and podocytes, with Dice coefficients of (85.69 ± 0.13)%, (74.59 ± 0.13)%, and (78.57 ± 0.16)%, respectively, demonstrating a good performance of the model superior to many existing image-level, pixel-level, and region-level self-supervised contrastive learning methods and close to the fully- supervised pre-training method based on the large- scale labeled dataset ImageNet.
CONCLUSION:USRegCon facilitates the model to learn beneficial region representations from large amounts of unlabeled data to overcome the scarcity of labeled data and improves the deep model performance for glomerular ultrastructure recognition and boundary segmentation.
