Graph-based cell pattern recognition for merging the multi-modal optical microscopic image of neurons

Wenwei Li, Wu Chen, Zimin Dai, Xiaokang Chai, Sile An, Zhuang Guan, Wei Zhou, Jianwei Chen, Hui Gong, Qingming Luo, Zhao Feng, Anan Li

Abstract: Highlights•Introduced a method that uses the distribution of neurons as a similarity measure, achieving cross-modal data matching between functional and structural imaging.•Employed a high-order graph model where triplets of neuronal nodes form hyperedges, measuring the similarity of hyperedges based on the angles of triangles, enhancing the method's robustness to scaling transformations.•Employ nonlinear optimization strategies to address the challenge of local-to-global matching.•Integrated matched neuronal positional information with image similarity to construct a joint probability model, further enhancing the accuracy of the matching process.