Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging

Hyunkoo Chung, Guolan Lu, Zhiqiang Tian, Dongsheng Wang, Zhuo Georgia Chen, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two di- mensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and ob-tains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016
Subtitle of host publicationBiomedical Applications in Molecular, Structural, and Functional Imaging
EditorsBarjor Gimi, Andrzej Krol
PublisherSPIE
ISBN (Electronic)9781510600232
DOIs
StatePublished - Jan 1 2016
Externally publishedYes
EventMedical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging - San Diego, United States
Duration: Mar 1 2016Mar 3 2016

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9788
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging
CountryUnited States
CitySan Diego
Period3/1/163/3/16

Fingerprint

Head and Neck Neoplasms
cancer
principal components analysis
mice
emerging
Neoplasms
tumors
Medical applications
Diagnostic Imaging
Principal Component Analysis
Principal component analysis
Support vector machines
Tumors
sensitivity
wavelengths
Tissue
Technology
Imaging techniques
Wavelength
Research

Keywords

  • Feature extraction
  • Head and neck cancer
  • Hyperspectral imaging
  • Image classification
  • Principal component analysis (PCA)
  • Superpixels
  • Support vector machine (SVM)

ASJC Scopus subject areas

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

Cite this

Chung, H., Lu, G., Tian, Z., Wang, D., Chen, Z. G., & Fei, B. (2016). Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging. In B. Gimi, & A. Krol (Eds.), Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging [978813] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9788). SPIE. https://doi.org/10.1117/12.2216559

Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging. / Chung, Hyunkoo; Lu, Guolan; Tian, Zhiqiang; Wang, Dongsheng; Chen, Zhuo Georgia; Fei, Baowei.

Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging. ed. / Barjor Gimi; Andrzej Krol. SPIE, 2016. 978813 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9788).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chung, H, Lu, G, Tian, Z, Wang, D, Chen, ZG & Fei, B 2016, Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging. in B Gimi & A Krol (eds), Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging., 978813, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9788, SPIE, Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging, San Diego, United States, 3/1/16. https://doi.org/10.1117/12.2216559
Chung H, Lu G, Tian Z, Wang D, Chen ZG, Fei B. Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging. In Gimi B, Krol A, editors, Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging. SPIE. 2016. 978813. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2216559
Chung, Hyunkoo ; Lu, Guolan ; Tian, Zhiqiang ; Wang, Dongsheng ; Chen, Zhuo Georgia ; Fei, Baowei. / Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging. Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging. editor / Barjor Gimi ; Andrzej Krol. SPIE, 2016. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{93d84b2229a04c64a317f9d9469398d4,
title = "Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging",
abstract = "Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two di- mensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and ob-tains an average sensitivity of 93{\%} and an average specificity of 85{\%} for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.",
keywords = "Feature extraction, Head and neck cancer, Hyperspectral imaging, Image classification, Principal component analysis (PCA), Superpixels, Support vector machine (SVM)",
author = "Hyunkoo Chung and Guolan Lu and Zhiqiang Tian and Dongsheng Wang and Chen, {Zhuo Georgia} and Baowei Fei",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/12.2216559",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Barjor Gimi and Andrzej Krol",
booktitle = "Medical Imaging 2016",

}

TY - GEN

T1 - Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging

AU - Chung, Hyunkoo

AU - Lu, Guolan

AU - Tian, Zhiqiang

AU - Wang, Dongsheng

AU - Chen, Zhuo Georgia

AU - Fei, Baowei

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two di- mensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and ob-tains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.

AB - Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two di- mensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and ob-tains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.

KW - Feature extraction

KW - Head and neck cancer

KW - Hyperspectral imaging

KW - Image classification

KW - Principal component analysis (PCA)

KW - Superpixels

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=84978803763&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978803763&partnerID=8YFLogxK

U2 - 10.1117/12.2216559

DO - 10.1117/12.2216559

M3 - Conference contribution

C2 - 27656035

AN - SCOPUS:84978803763

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

BT - Medical Imaging 2016

A2 - Gimi, Barjor

A2 - Krol, Andrzej

PB - SPIE

ER -