Multi-stream Cell Segmentation with Low-level Cues for Multi-modality Images
This work addresses the challenge of segmenting cells in complex multi-modal images, which is important for biomedical research, but it appears incremental as it builds on existing segmentation methods with tailored adaptations.
The paper tackles cell segmentation in multi-modal microscopy images by developing an automatic classification pipeline based on low-level cues and training separate segmentation models for different categories and cell shapes, achieving an F1-score of 0.8795 on the NeurIPS 2022 challenge dataset.
Cell segmentation for multi-modal microscopy images remains a challenge due to the complex textures, patterns, and cell shapes in these images. To tackle the problem, we first develop an automatic cell classification pipeline to label the microscopy images based on their low-level image characteristics, and then train a classification model based on the category labels. Afterward, we train a separate segmentation model for each category using the images in the corresponding category. Besides, we further deploy two types of segmentation models to segment cells with roundish and irregular shapes respectively. Moreover, an efficient and powerful backbone model is utilized to enhance the efficiency of our segmentation model. Evaluated on the Tuning Set of NeurIPS 2022 Cell Segmentation Challenge, our method achieves an F1-score of 0.8795 and the running time for all cases is within the time tolerance.