Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network.
The analysis of pathological images, such as cell counting and nuclear morphological measurement, is an essential part in clinical histopathology researches. Due to the diversity of uncertain cell boundaries after staining, automated nuclei segmentation of Hematoxylin-Eosin (HE) stained pathological...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0273682 |
| _version_ | 1828104521115500544 |
|---|---|
| author | Peng Shi Jing Zhong Liyan Lin Lin Lin Huachang Li Chongshu Wu |
| author_facet | Peng Shi Jing Zhong Liyan Lin Lin Lin Huachang Li Chongshu Wu |
| author_sort | Peng Shi |
| collection | DOAJ |
| description | The analysis of pathological images, such as cell counting and nuclear morphological measurement, is an essential part in clinical histopathology researches. Due to the diversity of uncertain cell boundaries after staining, automated nuclei segmentation of Hematoxylin-Eosin (HE) stained pathological images remains challenging. Although better performances could be achieved than most of classic image processing methods do, manual labeling is still necessary in a majority of current machine learning based segmentation strategies, which restricts further improvements of efficiency and accuracy. Aiming at the requirements of stable and efficient high-throughput pathological image analysis, an automated Feature Global Delivery Connection Network (FGDC-net) is proposed for nuclei segmentation of HE stained images. Firstly, training sample patches and their corresponding asymmetric labels are automatically generated based on a Full Mixup strategy from RGB to HSV color space. Secondly, in order to add connections between adjacent layers and achieve the purpose of feature selection, FGDC module is designed by removing the jumping connections between codecs commonly used in UNet-based image segmentation networks, which learns the relationships between channels in each layer and pass information selectively. Finally, a dynamic training strategy based on mixed loss is used to increase the generalization capability of the model by flexible epochs. The proposed improvements were verified by the ablation experiments on multiple open databases and own clinical meningioma dataset. Experimental results on multiple datasets showed that FGDC-net could effectively improve the segmentation performances of HE stained pathological images without manual interventions, and provide valuable references for clinical pathological analysis. |
| first_indexed | 2024-04-11T09:48:18Z |
| format | Article |
| id | doaj.art-1daaac8ec1e64814909f88a16c4b414d |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-11T09:48:18Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-1daaac8ec1e64814909f88a16c4b414d2022-12-22T04:30:55ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01179e027368210.1371/journal.pone.0273682Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network.Peng ShiJing ZhongLiyan LinLin LinHuachang LiChongshu WuThe analysis of pathological images, such as cell counting and nuclear morphological measurement, is an essential part in clinical histopathology researches. Due to the diversity of uncertain cell boundaries after staining, automated nuclei segmentation of Hematoxylin-Eosin (HE) stained pathological images remains challenging. Although better performances could be achieved than most of classic image processing methods do, manual labeling is still necessary in a majority of current machine learning based segmentation strategies, which restricts further improvements of efficiency and accuracy. Aiming at the requirements of stable and efficient high-throughput pathological image analysis, an automated Feature Global Delivery Connection Network (FGDC-net) is proposed for nuclei segmentation of HE stained images. Firstly, training sample patches and their corresponding asymmetric labels are automatically generated based on a Full Mixup strategy from RGB to HSV color space. Secondly, in order to add connections between adjacent layers and achieve the purpose of feature selection, FGDC module is designed by removing the jumping connections between codecs commonly used in UNet-based image segmentation networks, which learns the relationships between channels in each layer and pass information selectively. Finally, a dynamic training strategy based on mixed loss is used to increase the generalization capability of the model by flexible epochs. The proposed improvements were verified by the ablation experiments on multiple open databases and own clinical meningioma dataset. Experimental results on multiple datasets showed that FGDC-net could effectively improve the segmentation performances of HE stained pathological images without manual interventions, and provide valuable references for clinical pathological analysis.https://doi.org/10.1371/journal.pone.0273682 |
| spellingShingle | Peng Shi Jing Zhong Liyan Lin Lin Lin Huachang Li Chongshu Wu Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. PLoS ONE |
| title | Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. |
| title_full | Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. |
| title_fullStr | Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. |
| title_full_unstemmed | Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. |
| title_short | Nuclei segmentation of HE stained histopathological images based on feature global delivery connection network. |
| title_sort | nuclei segmentation of he stained histopathological images based on feature global delivery connection network |
| url | https://doi.org/10.1371/journal.pone.0273682 |
| work_keys_str_mv | AT pengshi nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork AT jingzhong nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork AT liyanlin nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork AT linlin nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork AT huachangli nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork AT chongshuwu nucleisegmentationofhestainedhistopathologicalimagesbasedonfeatureglobaldeliveryconnectionnetwork |