Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra

Masahiro Ishikawa; Chisato Okamoto; Kazuma Shinoda; Hideki Komagata; Chika Iwamoto; Kenoki Ohuchida; Makoto Hashizume; Akinobu Shimizu; Naoki Kobayashi

doi:10.1364/BOE.10.004568

Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra

Biomed Opt Express. 2019 Aug 9;10(9):4568-4588. doi: 10.1364/BOE.10.004568. eCollection 2019 Sep 1.

Authors

Masahiro Ishikawa¹, Chisato Okamoto¹, Kazuma Shinoda^{1

2}, Hideki Komagata¹, Chika Iwamoto³, Kenoki Ohuchida³, Makoto Hashizume³, Akinobu Shimizu⁴, Naoki Kobayashi¹

Affiliations

¹ Saitama Medical University, Faculty of Health & Medical Care, Yamane-1397-1, Hidaka-shi, 350-1241, Japan.
² Graduate School of Engineering, Utsunomiya University, 7-1-2 Yoto, Utsunomiya, Tochigi 321-8585, Japan.
³ Department of Advanced Medical Initiatives, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
⁴ Tokyo University of Agriculture and Technology, Nakacho 2-24-16, Koganei, Tokyo 184-8588, Japan.

Abstract

Hyperspectral imaging (HSI) provides more detailed information than red-green-blue (RGB) imaging, and therefore has potential applications in computer-aided pathological diagnosis. This study aimed to develop a pattern recognition method based on HSI, called hyperspectral analysis of pathological slides based on stain spectrum (HAPSS), to detect cancers in hematoxylin and eosin-stained pathological slides of pancreatic tumors. The samples, comprising hyperspectral cubes of 420-750 nm, were harvested for HSI and tissue microarray (TMA) analysis. As a result of conducting HAPSS experiments with a support vector machine (SVM) classifier, we obtained maximal accuracy of 94%, a 14% improvement over the widely used RGB images. Thus, HAPSS is a suitable method to automatically detect tumors in pathological slides of the pancreas.