Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach

Marcelo Saito Nogueira; Siddra Maryam; Michael Amissah; Huihui Lu; Noel Lynch; Shane Killeen; Micheal O'Riordain; Stefan Andersson-Engels

doi:10.1117/12.2610497

Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach

Marcelo Saito Nogueira
, Siddra Maryam
, Michael Amissah
, Huihui Lu
, Noel Lynch
, Shane Killeen
, Micheal O'Riordain
, Stefan Andersson-Engels

University College Cork

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

Abstract

Colorectal cancer (CRC) is the second most deadly and third most common type of cancer worldwide. In this study, we assessed the improvement of the diagnostic potential of diffuse reflectance spectroscopy (DRS) for CRC detection upon extending the tissue probed depth (up to 2mm) and wavelength ranges (350-1919 nm) investigated in previous studies. We analyzed almost 3000 DR spectra (7.5 times more than previous studies) collected with 630-?m and 2500-?m source-detector distance probes by using support vector machines with potential to automate tissue classification. We achieved 96.1% sensitivity and 95.7% specificity and 0.987±0.005 AUC on tissue classification.

Original language	English
Title of host publication	Optical Biopsy XX
Subtitle of host publication	Toward Real-Time Spectroscopic Imaging and Diagnosis
Editors	Robert R. Alfano, Stavros G. Demos, Angela B. Seddon
Publisher	SPIE
ISBN (Electronic)	9781510647794
DOIs	https://doi.org/10.1117/12.2610497
Publication status	Published - 2022
Event	Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis 2022 - Virtual, Online Duration: 20 Feb 2022 → 24 Feb 2022

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	11954
ISSN (Print)	1605-7422

Conference

Conference	Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis 2022
City	Virtual, Online
Period	20/02/22 → 24/02/22

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Artificial intelligence
Biomedical optics
Biophotonics
Colon cancer
Colonoscopy
Colorectal cancer
Diffuse reflectance spectroscopy
Elastic scattering spectroscopy
Hyperspectral imaging
Machine learning
Near-infrared spectroscopy
Optical diagnostics
Optical spectroscopy
Surgical guidance

Access to Document

10.1117/12.2610497

Cite this

Saito Nogueira, M., Maryam, S., Amissah, M., Lu, H., Lynch, N., Killeen, S., O'Riordain, M., & Andersson-Engels, S. (2022). Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach. In R. R. Alfano, S. G. Demos, & A. B. Seddon (Eds.), Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis Article 1195404 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11954). SPIE. https://doi.org/10.1117/12.2610497

Saito Nogueira, Marcelo ; Maryam, Siddra ; Amissah, Michael et al. / Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy : A support vector machine approach. Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis. editor / Robert R. Alfano ; Stavros G. Demos ; Angela B. Seddon. SPIE, 2022. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{90ed4b5421ff4867a5cfcec8c22319d6,

title = "Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach",

abstract = "Colorectal cancer (CRC) is the second most deadly and third most common type of cancer worldwide. In this study, we assessed the improvement of the diagnostic potential of diffuse reflectance spectroscopy (DRS) for CRC detection upon extending the tissue probed depth (up to 2mm) and wavelength ranges (350-1919 nm) investigated in previous studies. We analyzed almost 3000 DR spectra (7.5 times more than previous studies) collected with 630-?m and 2500-?m source-detector distance probes by using support vector machines with potential to automate tissue classification. We achieved 96.1\% sensitivity and 95.7\% specificity and 0.987±0.005 AUC on tissue classification.",

keywords = "Artificial intelligence, Biomedical optics, Biophotonics, Colon cancer, Colonoscopy, Colorectal cancer, Diffuse reflectance spectroscopy, Elastic scattering spectroscopy, Hyperspectral imaging, Machine learning, Near-infrared spectroscopy, Optical diagnostics, Optical spectroscopy, Surgical guidance",

author = "\{Saito Nogueira\}, Marcelo and Siddra Maryam and Michael Amissah and Huihui Lu and Noel Lynch and Shane Killeen and Micheal O'Riordain and Stefan Andersson-Engels",

note = "Publisher Copyright: {\textcopyright} SPIE. Downloading of the abstract is permitted for personal use only.; Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis 2022 ; Conference date: 20-02-2022 Through 24-02-2022",

year = "2022",

doi = "10.1117/12.2610497",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Alfano, \{Robert R.\} and Demos, \{Stavros G.\} and Seddon, \{Angela B.\}",

booktitle = "Optical Biopsy XX",

address = "United States",

}

Saito Nogueira, M, Maryam, S, Amissah, M, Lu, H, Lynch, N, Killeen, S, O'Riordain, M & Andersson-Engels, S 2022, Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach. in RR Alfano, SG Demos & AB Seddon (eds), Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis., 1195404, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11954, SPIE, Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis 2022, Virtual, Online, 20/02/22. https://doi.org/10.1117/12.2610497

Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach. / Saito Nogueira, Marcelo; Maryam, Siddra; Amissah, Michael et al.
Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis. ed. / Robert R. Alfano; Stavros G. Demos; Angela B. Seddon. SPIE, 2022. 1195404 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11954).

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

TY - GEN

T1 - Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy

T2 - Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis 2022

AU - Saito Nogueira, Marcelo

AU - Maryam, Siddra

AU - Amissah, Michael

AU - Lu, Huihui

AU - Lynch, Noel

AU - Killeen, Shane

AU - O'Riordain, Micheal

AU - Andersson-Engels, Stefan

N1 - Publisher Copyright: © SPIE. Downloading of the abstract is permitted for personal use only.

PY - 2022

Y1 - 2022

N2 - Colorectal cancer (CRC) is the second most deadly and third most common type of cancer worldwide. In this study, we assessed the improvement of the diagnostic potential of diffuse reflectance spectroscopy (DRS) for CRC detection upon extending the tissue probed depth (up to 2mm) and wavelength ranges (350-1919 nm) investigated in previous studies. We analyzed almost 3000 DR spectra (7.5 times more than previous studies) collected with 630-?m and 2500-?m source-detector distance probes by using support vector machines with potential to automate tissue classification. We achieved 96.1% sensitivity and 95.7% specificity and 0.987±0.005 AUC on tissue classification.

AB - Colorectal cancer (CRC) is the second most deadly and third most common type of cancer worldwide. In this study, we assessed the improvement of the diagnostic potential of diffuse reflectance spectroscopy (DRS) for CRC detection upon extending the tissue probed depth (up to 2mm) and wavelength ranges (350-1919 nm) investigated in previous studies. We analyzed almost 3000 DR spectra (7.5 times more than previous studies) collected with 630-?m and 2500-?m source-detector distance probes by using support vector machines with potential to automate tissue classification. We achieved 96.1% sensitivity and 95.7% specificity and 0.987±0.005 AUC on tissue classification.

KW - Artificial intelligence

KW - Biomedical optics

KW - Biophotonics

KW - Colon cancer

KW - Colonoscopy

KW - Colorectal cancer

KW - Diffuse reflectance spectroscopy

KW - Elastic scattering spectroscopy

KW - Hyperspectral imaging

KW - Machine learning

KW - Near-infrared spectroscopy

KW - Optical diagnostics

KW - Optical spectroscopy

KW - Surgical guidance

UR - https://www.scopus.com/pages/publications/85128908875

U2 - 10.1117/12.2610497

DO - 10.1117/12.2610497

M3 - Conference proceeding

AN - SCOPUS:85128908875

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Optical Biopsy XX

A2 - Alfano, Robert R.

A2 - Demos, Stavros G.

A2 - Seddon, Angela B.

PB - SPIE

Y2 - 20 February 2022 through 24 February 2022

ER -

Saito Nogueira M, Maryam S, Amissah M, Lu H, Lynch N, Killeen S et al. Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach. In Alfano RR, Demos SG, Seddon AB, editors, Optical Biopsy XX: Toward Real-Time Spectroscopic Imaging and Diagnosis. SPIE. 2022. 1195404. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2610497

Improving colorectal cancer detection by extending the near-infrared wavelength range and tissue probed depth of diffuse reflectance spectroscopy: A support vector machine approach

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this