Deep Learning of Cancer Stem Cell Morphology

Hiroyuki Kameda; Hiroaki Ishihata; Tomoyasu Sugiyama

doi:10.1007/978-1-0716-3730-2_17

Deep Learning of Cancer Stem Cell Morphology

Methods Mol Biol. 2024:2777:231-256. doi: 10.1007/978-1-0716-3730-2_17.

Authors

Hiroyuki Kameda^{1

2}, Hiroaki Ishihata², Tomoyasu Sugiyama³

Affiliations

¹ School of Bioscience and Biotechnology, Tokyo University of Technology, Tokyo, Japan.
² School of Computer Science, Tokyo University of Technology, Tokyo, Japan.
³ School of Bioscience and Biotechnology, Tokyo University of Technology, Tokyo, Japan. tsugiyama@stf.teu.ac.jp.

PMID: 38478348
DOI: 10.1007/978-1-0716-3730-2_17

Abstract

Knowledge regarding cancer stem cell (CSC) morphology is limited, and more extensive studies are therefore required. Image recognition technologies using artificial intelligence (AI) require no previous expertise in image annotation. Herein, we describe the construction of AI models that recognize the CSC morphology in cultures and tumor tissues. The visualization of the AI deep learning process enables insight to be obtained regarding unrecognized structures in an image.

Keywords: CGAN; Cancer stem cell; Classification; Convolutional neural network; Google colaboratory; Grad-CAM; Jupyter Notebook; Morphology; Pix2pix; Segmentation.

MeSH terms

Artificial Intelligence
Deep Learning*
Humans
Neoplasms*
Neoplastic Stem Cells
Technology