Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach

Myeongseop Kim; Hee Ryung Lee; Razvigor Ossikovski; Aude Jobart-Malfait; Dominique Lamarque; Tatiana Novikova

doi:10.1117/12.3021846

Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach

Myeongseop Kim
, Hee Ryung Lee
, Razvigor Ossikovski
, Aude Jobart-Malfait
, Dominique Lamarque
, Tatiana Novikova

Institut polytechnique de Paris
Institute of Biological and Medical Imaging
Technical University of Munich
Université Versailles-Saint Quentin
Florida International University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We investigated gastric tissue biopsies using a liquid crystal-based Mueller microscope and a machine-learning approach to examine the degree of inflammation. Machine learning and statistical analysis were performed with the multidimensional dataset including the polarimetric properties (linear retardance and dichroism, and circular depolarization) and total transmitted intensity images of the unstained thin sections of gastric tissue to identify and quantify the microstructural differences between healthy control, chronic gastritis, and gastric cancer.

Original language	English
Title of host publication	Liquid Crystals Optics and Photonic Devices
Editors	Ibrahim Abdulhalim, Camilla Parmeggiani
Publisher	SPIE
ISBN (Electronic)	9781510673502
DOIs	https://doi.org/10.1117/12.3021846
Publication status	Published - 1 Jan 2024
Event	Liquid Crystals Optics and Photonic Devices 2024 - Strasbourg, France Duration: 8 Apr 2024 → 11 Apr 2024

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13016
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Liquid Crystals Optics and Photonic Devices 2024
Country/Territory	France
City	Strasbourg
Period	8/04/24 → 11/04/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Gastric cancer
Mueller microscopy
Optical anisotropy
Statistical image analysis

Access to Document

10.1117/12.3021846

Cite this

Kim, M., Lee, H. R., Ossikovski, R., Jobart-Malfait, A., Lamarque, D., & Novikova, T. (2024). Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach. In I. Abdulhalim, & C. Parmeggiani (Eds.), Liquid Crystals Optics and Photonic Devices Article 1301607 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13016). SPIE. https://doi.org/10.1117/12.3021846

@inproceedings{199a860ed38f4ff3806df2455109b276,

title = "Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach",

abstract = "We investigated gastric tissue biopsies using a liquid crystal-based Mueller microscope and a machine-learning approach to examine the degree of inflammation. Machine learning and statistical analysis were performed with the multidimensional dataset including the polarimetric properties (linear retardance and dichroism, and circular depolarization) and total transmitted intensity images of the unstained thin sections of gastric tissue to identify and quantify the microstructural differences between healthy control, chronic gastritis, and gastric cancer.",

keywords = "Gastric cancer, Mueller microscopy, Optical anisotropy, Statistical image analysis",

author = "Myeongseop Kim and Lee, \{Hee Ryung\} and Razvigor Ossikovski and Aude Jobart-Malfait and Dominique Lamarque and Tatiana Novikova",

note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; Liquid Crystals Optics and Photonic Devices 2024 ; Conference date: 08-04-2024 Through 11-04-2024",

year = "2024",

month = jan,

day = "1",

doi = "10.1117/12.3021846",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Ibrahim Abdulhalim and Camilla Parmeggiani",

booktitle = "Liquid Crystals Optics and Photonic Devices",

}

Kim, M, Lee, HR, Ossikovski, R, Jobart-Malfait, A, Lamarque, D & Novikova, T 2024, Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach. in I Abdulhalim & C Parmeggiani (eds), Liquid Crystals Optics and Photonic Devices., 1301607, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13016, SPIE, Liquid Crystals Optics and Photonic Devices 2024, Strasbourg, France, 8/04/24. https://doi.org/10.1117/12.3021846

Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach. / Kim, Myeongseop; Lee, Hee Ryung; Ossikovski, Razvigor et al.
Liquid Crystals Optics and Photonic Devices. ed. / Ibrahim Abdulhalim; Camilla Parmeggiani. SPIE, 2024. 1301607 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach

AU - Kim, Myeongseop

AU - Lee, Hee Ryung

AU - Ossikovski, Razvigor

AU - Jobart-Malfait, Aude

AU - Lamarque, Dominique

AU - Novikova, Tatiana

PY - 2024/1/1

Y1 - 2024/1/1

N2 - We investigated gastric tissue biopsies using a liquid crystal-based Mueller microscope and a machine-learning approach to examine the degree of inflammation. Machine learning and statistical analysis were performed with the multidimensional dataset including the polarimetric properties (linear retardance and dichroism, and circular depolarization) and total transmitted intensity images of the unstained thin sections of gastric tissue to identify and quantify the microstructural differences between healthy control, chronic gastritis, and gastric cancer.

AB - We investigated gastric tissue biopsies using a liquid crystal-based Mueller microscope and a machine-learning approach to examine the degree of inflammation. Machine learning and statistical analysis were performed with the multidimensional dataset including the polarimetric properties (linear retardance and dichroism, and circular depolarization) and total transmitted intensity images of the unstained thin sections of gastric tissue to identify and quantify the microstructural differences between healthy control, chronic gastritis, and gastric cancer.

KW - Gastric cancer

KW - Mueller microscopy

KW - Optical anisotropy

KW - Statistical image analysis

U2 - 10.1117/12.3021846

DO - 10.1117/12.3021846

M3 - Conference contribution

AN - SCOPUS:85200116483

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Liquid Crystals Optics and Photonic Devices

A2 - Abdulhalim, Ibrahim

A2 - Parmeggiani, Camilla

PB - SPIE

T2 - Liquid Crystals Optics and Photonic Devices 2024

Y2 - 8 April 2024 through 11 April 2024

ER -

Kim M, Lee HR, Ossikovski R, Jobart-Malfait A, Lamarque D, Novikova T. Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach. In Abdulhalim I, Parmeggiani C, editors, Liquid Crystals Optics and Photonic Devices. SPIE. 2024. 1301607. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.3021846

Digital histology of gastric tissue biopsies with liquid crystal-based Mueller microscope and machine learning approach

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this