DEEP LEARNING FOR AUTOMATIC CELL DETECTION IN WIDE-FIELD MICROSCOPY ZEBRAFISH IMAGES

The zebrafish has become a popular experimental model organism for biomedical research. In this paper, a unique framework is proposed for automatically detecting Tyrosine Hydroxylase-containing (TH-labeled) cells in larval zebrafish brain z-stack images recorded through the wide-field microscope. In this framework, a supervised max-pooling Convolutional Neural Network (CNN) is trained to detect cell pixels in regions that are preselected by a Support Vector Machine (SVM) classifier. The results show that the proposed deep-learned method outperforms hand-crafted techniques and demonstrate its potential for automatic cell detection in wide-field microscopy z-stack zebrafish images.