A Weakly Supervised U-Net Model for Precise Whole Brain Immunolabeled Cell Detection

Li-Wen Wang; Ya-Lun Wu; Chih-Lin Lee; C.-C. Cheng; Kuan-Yi Lu; Jyun-Huei Tsai; Ya‐Hui Lin; Ching‐Han Hsu; Tsung-Han Kuo; Li‐An Chu

doi:10.1101/2023.03.16.531434

NeurosciencebioRxivMar 16, 2023

Preprint

A Weakly Supervised U-Net Model for Precise Whole Brain Immunolabeled Cell Detection

Li-Wen Wang, Ya-Lun Wu iD, Chih-Lin Lee iD, C.-C. Cheng, Kuan-Yi Lu, Jyun-Huei Tsai, Ya‐Hui Lin iD, Ching‐Han Hsu iD, Tsung-Han Kuo iD, Li‐An Chu iD

PDF DOI

Post to X

Threads on X Post to Bluesky Threads on Bluesky

Abstract

Cell segmentations low precision due to the intensity differences hinders widespread use of whole brain microscopy imaging. Previous studies used ResNet or CNN to account for this problem, but are unapplicable to immunolabeled signals across samples. Here we present a semiauto ground truth generation and weakly-supervised U-Net-based Deep-learning precise segmentation pipeline for whole brain immunopositive c-FOS signals, which reveals the distinct neural activity maps with different social motivations.