Multi-modal Cell Segmentation based on U-Net++ and Attention Gate

Xinye Yang, Hao Chen
Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images, PMLR 212:1-10, 2023.

Abstract

Cell segmentation is one of the most fundamental tasks in the areas of medical image analysis, which assists in cell recognition and number counting. The seg- mentation results obtained will be poor due to the diverse cell morphology and the frequent presence of impurities in the cell pictures. In order to solve the cell segmentation which are from a competition held by Neural Information Processing Systems(NIPS), we present a network that combines attention gates with U-Net++ to segment varied sizes of cells. Using the feature filtering of the attention gate can adjust the convolution block’s output, so as to improve the segmentation effect. The F1 score of our method reached 0.5874, Rank Running Time get 2.5431 seconds.

Cite this Paper

BibTeX
@InProceedings{pmlr-v212-yang23a, title = {Multi-modal Cell Segmentation based on U-Net++ and Attention Gate}, author = {Yang, Xinye and Chen, Hao}, booktitle = {Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images}, pages = {1--10}, year = {2023}, editor = {Ma, Jun and Xie, Ronald and Gupta, Anubha and Guilherme de Almeida, José and Bader, Gary D. and Wang, Bo}, volume = {212}, series = {Proceedings of Machine Learning Research}, month = {28 Nov--09 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v212/yang23a/yang23a.pdf}, url = {https://proceedings.mlr.press/v212/yang23a.html}, abstract = {Cell segmentation is one of the most fundamental tasks in the areas of medical image analysis, which assists in cell recognition and number counting. The seg- mentation results obtained will be poor due to the diverse cell morphology and the frequent presence of impurities in the cell pictures. In order to solve the cell segmentation which are from a competition held by Neural Information Processing Systems(NIPS), we present a network that combines attention gates with U-Net++ to segment varied sizes of cells. Using the feature filtering of the attention gate can adjust the convolution block’s output, so as to improve the segmentation effect. The F1 score of our method reached 0.5874, Rank Running Time get 2.5431 seconds.} }
Endnote
%0 Conference Paper %T Multi-modal Cell Segmentation based on U-Net++ and Attention Gate %A Xinye Yang %A Hao Chen %B Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images %C Proceedings of Machine Learning Research %D 2023 %E Jun Ma %E Ronald Xie %E Anubha Gupta %E José Guilherme de Almeida %E Gary D. Bader %E Bo Wang %F pmlr-v212-yang23a %I PMLR %P 1--10 %U https://proceedings.mlr.press/v212/yang23a.html %V 212 %X Cell segmentation is one of the most fundamental tasks in the areas of medical image analysis, which assists in cell recognition and number counting. The seg- mentation results obtained will be poor due to the diverse cell morphology and the frequent presence of impurities in the cell pictures. In order to solve the cell segmentation which are from a competition held by Neural Information Processing Systems(NIPS), we present a network that combines attention gates with U-Net++ to segment varied sizes of cells. Using the feature filtering of the attention gate can adjust the convolution block’s output, so as to improve the segmentation effect. The F1 score of our method reached 0.5874, Rank Running Time get 2.5431 seconds.
APA
Yang, X. & Chen, H.. (2023). Multi-modal Cell Segmentation based on U-Net++ and Attention Gate. Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images, in Proceedings of Machine Learning Research 212:1-10 Available from https://proceedings.mlr.press/v212/yang23a.html.

Related Material