Optical biopsy technique for detection of aganglionosis in Hirschsprung disease by Raman spectroscopy combined with deep learning

Yuki Matsumoto, Katsuhiro Ogawa, Kai Tamura, Rena Yagi, Shun Onishi, Satoshi Ieiri, Tsuyoshi Etoh, Masafumi Inomata, Takashi Katagiri, Yusuke Oshima

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this study, we aimed to develop a new optical biopsy technique for aganglionosis of Hirschsprung disease (HSCR) and we then evaluated a custom designed Raman optical biopsy system combined with deep learning based on convolutional neural networks (CNNs). Surgical specimens of formalin-fixed tissue of HSCR patients were subjected to this study. In the result, we achieved more than 90% classification accuracy between the normal and the lesion segments in mucosa. This study shows that CNN is useful for discriminating Raman spectra of the human gastrointestinal wall.

Original languageEnglish
Title of host publicationAdvanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXI
EditorsCaroline Boudoux, James W. Tunnell
PublisherSPIE
ISBN (Electronic)9781510658417
DOIs
StatePublished - 2023
EventAdvanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXI 2023 - San Francisco, United States
Duration: 2023/01/282023/01/29

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12368
ISSN (Print)1605-7422

Conference

ConferenceAdvanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXI 2023
Country/TerritoryUnited States
CitySan Francisco
Period2023/01/282023/01/29

Keywords

  • Enteric nervous system
  • Hirschsprung's disease
  • Machine learning
  • Raman spectroscopy

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Optical biopsy technique for detection of aganglionosis in Hirschsprung disease by Raman spectroscopy combined with deep learning'. Together they form a unique fingerprint.

Cite this