Self-Training with High-Dimensional Markers for Cell Instance Segmentation
Journal
Proceedings - International Symposium on Biomedical Imaging
Journal Volume
2023-April
ISBN
9781665473583
Date Issued
2023-01-01
Author(s)
Lo, Kuang Cheng
Lin, Cheng Wei
Lee, Hsin Ying
Hsu, Hao
Chen, Shih Yu
Abstract
Cellular segmentation is a fundamental prerequisite to many biological analyses. With the development of multiplexed imaging technologies, the need for accurately segmenting individual cells has significantly increased in recent years. However, current deep learning methods cannot deal with staining markers in an arbitrary order or different numbers. Moreover, acquiring pixel-level annotation is incredibly time-consuming in high-dimensional images. To tackle these issues, we incorporate pathology knowledge into our model and present a novel self-training framework. Concretely, we apply a serial attention mechanism and pooling operation to compress the multi-channel image during the training process. Afterward, the nuclei information guides the self-training in the pseudo-label stage. Experiments demonstrate our method is superior to the existing methods in both qualitative and quantitative results.
Subjects
Cell segmentation | CODEX | deep learning | highly-multiplexed imaging | self-training
SDGs
Type
conference paper