A knowledge-integrated deep learning framework for cellular image analysis in parasite microbiology

Ruijun Feng; Sen Li; Yang Zhang

doi:10.1016/j.xpro.2023.102452

A knowledge-integrated deep learning framework for cellular image analysis in parasite microbiology

STAR Protoc. 2023 Sep 15;4(3):102452. doi: 10.1016/j.xpro.2023.102452. Epub 2023 Aug 1.

Authors

Ruijun Feng¹, Sen Li¹, Yang Zhang²

Affiliations

¹ School of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China.
² School of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China. Electronic address: zhangyang07@hit.edu.cn.

Abstract

Cellular image analysis is an important method for microbiologists to identify and study microbes. Here, we present a knowledge-integrated deep learning framework for cellular image analysis, using three tasks as examples: classification, detection, and reconstruction. Alongside thorough descriptions of different models and datasets, we describe steps for computing environment setup, knowledge representation, data pre-processing, and training and tuning. We then detail evaluation and visualization. For complete details on the use and execution of this protocol, please refer to Li et al. (2021),¹ Jiang et al. (2020),² and Zhang et al. (2022).³.

Keywords: Bioinformatics; Computer sciences; Microscopy.

MeSH terms

Animals
Deep Learning*
Image Processing, Computer-Assisted
Parasites*