Automated classification of elliptical cancer cells with stain-free holographic imaging and self-supervised learning

Abdur Rehman, Hyunbin An, Seonghwan Park, Inkyu Moon

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Image-based stain-free elliptical cancer cell classification is challenging, due to the inter-class morphological similarity. In this paper, we address the classification of different types of cancer cell lines (lung, breast, bladder, and skin) by utilizing self-supervised learning, and compare it with supervised learning based on convolutional neural network. Digital holography in a microscopic configuration was used to obtain stain-free quantitative phase images representing the intracellular content and morphology of cells. The performance of self-supervised learning in natural images shows promising results, and consistently closes the gap between self-supervised and supervised learning. The ability of self-supervised learning to effectively utilize unlabeled data for training is instrumental in the biomedical domain, where labeled data is scarce. Our goal is to study different self-supervised frameworks of biomedical holographic data, and determine how they can be utilized to advance liquid biopsy for the detection of cancer cells. After extensive experimentation, we conclude that self-supervised learning improves the classification performance on cancer cell datasets, and outperforms supervised learning when training data is limited, which is mostly the case in biomedical imaging.

Original languageEnglish
Article number110646
JournalOptics and Laser Technology
Volume174
DOIs
StatePublished - Jul 2024

Bibliographical note

Publisher Copyright:
© 2024 Elsevier Ltd

Keywords

  • Classification of cancer cells
  • Deep learning
  • Holographic cell imaging
  • Self-supervised learning
  • Stain-free analysis of cancer cells

Fingerprint

Dive into the research topics of 'Automated classification of elliptical cancer cells with stain-free holographic imaging and self-supervised learning'. Together they form a unique fingerprint.

Cite this