EnNuSegNet: Enhancing Weakly Supervised Nucleus Segmentation through Feature Preservation and Edge Refinement
-
Published:2024-01-25
Issue:3
Volume:13
Page:504
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Chen Xiaohui12ORCID, Ruan Qisheng12, Chen Lingjun3ORCID, Sheng Guanqun12, Chen Peng12
Affiliation:
1. Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang 443002, China 2. College of Computer and Information Technology, China Three Gorges University, Yichang 443002, China 3. Yichang Power Supply Company, State Grid Hubei Electric Power Co., Ltd., Yichang 443002, China
Abstract
Nucleus segmentation plays a crucial role in tissue pathology image analysis. Despite significant progress in cell nucleus image segmentation algorithms based on fully supervised learning, the large number and small size of cell nuclei pose a considerable challenge in terms of the substantial workload required for label annotation. This difficulty in acquiring datasets has become exceptionally challenging. This paper proposes a novel weakly supervised nucleus segmentation method that only requires point annotations of the nuclei. The technique is an encoder–decoder network which enhances the weakly supervised nucleus segmentation performance (EnNuSegNet). Firstly, we introduce the Feature Preservation Module (FPM) in both encoder and decoder, which preserves more low-level features from the shallow layers of the network during the early stages of training while enhancing the network’s expressive capability. Secondly, we incorporate a Scale-Aware Module (SAM) in the bottleneck part of the network to improve the model’s perception of cell nuclei at different scales. Lastly, we propose a training strategy for nucleus edge regression (NER), which guides the model to optimize the segmented edges during training, effectively compensating for the loss of nucleus edge information and achieving higher-quality nucleus segmentation. Experimental results on two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art approaches, with improvements of 2.02%, 1.41%, and 1.59% in terms of F1 score, Dice coefficient, and Average Jaccard Index (AJI), respectively. This indicates the effectiveness of our method in improving segmentation performance.
Funder
National Key Research and Development Program of China National Natural Science Foundation of China
Reference34 articles.
1. Wong, A.N.N., He, Z., Leung, K.L., To, C.C.K., Wong, C.Y., Wong, S.C.C., Yoo, J.S., Chan, C.K.R., Chan, A.Z., and Lacambra, M.D. (2022). Current developments of artificial intelligence in digital pathology and its future clinical applications in gastrointestinal cancers. Cancers, 14. 2. Wang, Y., Wang, W., Liu, D., Hou, W., Zhou, T., and Ji, Z. (2023). GeneSegNet: A deep learning framework for cell segmentation by integrating gene expression and imaging. Genome Biol., 24. 3. Segmentation of nuclei in histopathology images by deep regression of the distance map;Naylor;IEEE Trans. Med. Imaging,2018 4. Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images;Aatresh;Comput. Med. Imaging Graph.,2021 5. Kiran, I., Raza, B., Ijaz, A., and Khan, M.A. (2022). DenseRes-Unet: Segmentation of overlapped/clustered nuclei from multi organ histopathology images. Comput. Biol. Med., 143.
|
|