Abstract 5186: Label-free imaging identification of white blood cells using quantitative phase microscopy for negative selection of circulating tumor cells

Abstract

Abstract Background: Circulating tumor cells (CTCs) are cancer cells which are shed from primary tumors and circulating in the bloodstream, and thought to play a key role in metastasis. Existing CTC capture methods are largely based on surface markers such as cytokeratins. However, invasive tumor cells tend to lose their epithelial markers and change into mesenchymal phenotype by the epithelial mesenchymal transition (EMT). It seems that conventional CTC capture methods miss the mesenchymal CTCs which are supposed to have highly malignant potentials. Because the features of CTCs are not fully understood, it is difficult to retrieve all CTCs by positive selection using CTC-surface markers. Considering the fact that vast majority of nucleated cells circulating in the blood stream are WBCs, eliminating WBCs from circulation is an efficient way to purify CTCs. In this study, we attempted to develop a novel method for the identification of WBCs in the blood using Quantitative Phase Imaging Microscopy (QPM). Methods: We analyzed WBCs and cancer cell lines using QPM that can image optical path-length of living cells with a high resolution of 1nm without staining in non-cytotoxic way. Obtained images, quantitative phase images (QPIs), were analyzed by a computer vision application which automatically identifies an object in digital images based on features extracted from the dataset we had developed by machine learning. Results: We imaged 325 WBCs obtained from healthy donors and 325 cell-line cells (including 5 different cell lines) with QPM. Then, we extracted certain features from the QPIs and used them as training images for machine learning. We employed 5-fold cross validation to create an algorithm to detect WBCs circulating in the blood. The algorithm successfully recognized WBCs among QPIs mixed in with WBCs and cancer cell lines. The ROC AUC value was 0.98, indicating that the algorithm was not random selection. Conclusions: We successfully differentiated WBCs from cancer cell lines based on the features of QPIs. The object recognition method applying to QPIs of the cell is expected as a useful, non-cytotoxic, marker free isolation of CTCs. Citation Format: Yusuke Ozaki, Hidenao Iwai, Hirotoshi Kikuchi, Tomohiro Matsumoto, Shinichiro Miyazaki, Toshiki Kawabata, Yoshihiro Hiramatsu, Manabu Ohta, Kinji Kamiya, Megumi Baba, Kentaro Goto, Toyohiko Yamauchi, Yukio Ueda, Shigetoshi Okazaki, Hiroyuki Konno. Label-free imaging identification of white blood cells using quantitative phase microscopy for negative selection of circulating tumor cells. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 5186. doi:10.1158/1538-7445.AM2015-5186