Semi-Supervised Cell Instance Segmentation for Multi-Modality Microscope Images

Ziyue Wang, Zijie Fang, Yang Chen, Zexi Yang, Xinhao Liu, Yongbing Zhang
Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images, PMLR 212:1-11, 2023.

Abstract

Many clinical and biological tasks depend on accurate cell instance segmentation. Currently, the rapid development of deep learning realizes the automation of cell segmentation, which significantly decreases the workload of clinicians and researchers. However, most existing cell segmentation frameworks are fully supervised and modality-specific. Towards this end, this paper proposes a semi-supervised cell instance segmentation framework for multi-modality microscope images. Firstly, $K$-Means clustering is utilized to discriminate the image modality. Then, for phase contrast and differential interference contrast images, Cellpose is adopted. For brightfield images, we subdivide them into two sub-categories according to the cell diameter by $K$-Means and optimize a U-Net for the large diameter group. For fluorescence images, we propose a semi-supervised learning strategy using CDNet. The leaderboard shows that our proposed framework reaches an F1 score of 0.8428 on the tuning set, which ranks 6th among all teams.

Cite this Paper

BibTeX
@InProceedings{pmlr-v212-wang23a, title = {Semi-Supervised Cell Instance Segmentation for Multi-Modality Microscope Images}, author = {Wang, Ziyue and Fang, Zijie and Chen, Yang and Yang, Zexi and Liu, Xinhao and Zhang, Yongbing}, booktitle = {Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images}, pages = {1--11}, 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/wang23a/wang23a.pdf}, url = {https://proceedings.mlr.press/v212/wang23a.html}, abstract = {Many clinical and biological tasks depend on accurate cell instance segmentation. Currently, the rapid development of deep learning realizes the automation of cell segmentation, which significantly decreases the workload of clinicians and researchers. However, most existing cell segmentation frameworks are fully supervised and modality-specific. Towards this end, this paper proposes a semi-supervised cell instance segmentation framework for multi-modality microscope images. Firstly, $K$-Means clustering is utilized to discriminate the image modality. Then, for phase contrast and differential interference contrast images, Cellpose is adopted. For brightfield images, we subdivide them into two sub-categories according to the cell diameter by $K$-Means and optimize a U-Net for the large diameter group. For fluorescence images, we propose a semi-supervised learning strategy using CDNet. The leaderboard shows that our proposed framework reaches an F1 score of 0.8428 on the tuning set, which ranks 6th among all teams.} }
Endnote
%0 Conference Paper %T Semi-Supervised Cell Instance Segmentation for Multi-Modality Microscope Images %A Ziyue Wang %A Zijie Fang %A Yang Chen %A Zexi Yang %A Xinhao Liu %A Yongbing Zhang %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-wang23a %I PMLR %P 1--11 %U https://proceedings.mlr.press/v212/wang23a.html %V 212 %X Many clinical and biological tasks depend on accurate cell instance segmentation. Currently, the rapid development of deep learning realizes the automation of cell segmentation, which significantly decreases the workload of clinicians and researchers. However, most existing cell segmentation frameworks are fully supervised and modality-specific. Towards this end, this paper proposes a semi-supervised cell instance segmentation framework for multi-modality microscope images. Firstly, $K$-Means clustering is utilized to discriminate the image modality. Then, for phase contrast and differential interference contrast images, Cellpose is adopted. For brightfield images, we subdivide them into two sub-categories according to the cell diameter by $K$-Means and optimize a U-Net for the large diameter group. For fluorescence images, we propose a semi-supervised learning strategy using CDNet. The leaderboard shows that our proposed framework reaches an F1 score of 0.8428 on the tuning set, which ranks 6th among all teams.
APA
Wang, Z., Fang, Z., Chen, Y., Yang, Z., Liu, X. & Zhang, Y.. (2023). Semi-Supervised Cell Instance Segmentation for Multi-Modality Microscope Images. Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images, in Proceedings of Machine Learning Research 212:1-11 Available from https://proceedings.mlr.press/v212/wang23a.html.

Related Material