Science China Life Sciences recently published a paper entitled “C1M2: a universal algorithm for 3D instance segmentation, annotation, and quantification of irregular cells”. The paper comes from Professor Zhihong Zhang’s group at Wuhan National Laboratory for Optoelectronics (WNLO), Huazhong University of Science and Technology.
Cell instance segmentation is a fundamental task for many biological applications, especially for packed cells in three-dimensional (3D) microscope images that can fully display cellular morphology. In this study, the research team introduces a universal, morphology-based 3D instance segmentation algorithm called Crop Once Merge Twice (C1M2), which can segment cells from a wide range of image types and does not require nucleus images. C1M2 can be extended to quantify the fluorescence intensity of fluorescent proteins and antibodies and automatically annotate their expression levels in individual cells. The research team results suggest that C1M2 can serve as a tissue cytometry for 3D histopathological assays by quantifying fluorescence intensity with spatial localization and morphological information.
In this study, based on the exact 3D instance segmentation results from the C1M2 algorithm, the research team further developed an automatic annotation algorithm to realize the functions of tissue cytometry. C1M2 precisely quantified the fluorescence intensity by plotting the characteristic curve in 3D cell rings of each cell and automatically annotating four expression levels (none, low, middle, high) in situ so that both the morphology and spatial location information at different expression levels could be accurately measured.
Ph.D. students Hao Zheng and Dr. Songlin Huang are the co-first authors. Professor Xin Yang from the School of Electronic Information and Communications and Professor Zhihong Zhang are the corresponding authors of the paper.
This work was supported by the National Key Research and Development Program of China (2017YFA0700403, 2017YFA0700402), National Natural Science Foundation of China (62061160490), Applied Fundamental Research of Wuhan (2020010601012167), the Fundamental Research Funds for the Central Universities (2019kfyXMBZ022), and the Innovation Fund of WNLO.
Figure 1 Instance segmentation flowchart.
Figure 2 Automatic annotation algorithm flowchart.
