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

• Authors: Hyunkoo Chung, Georgia Institute of Technology; Guolan Lu, Georgia Institute of Technology; Zhiqiang Tian, Emory University; Dongsheng Wang, Emory University; Georgia Chen, Emory University; Baowei Fei, Emory University
• Proceedings Title: Proceedings of SPIE
• Conference Name: SPIE Biomedical Applications in Molecular, Structural and Functional Imaging Conference
• Publisher: Society of Photo-optical Instrumentation Engineers
• Conference Place: San Diego, CA
• Volume/Issue: Volume 9788
• Publication Date: 2016-01-01
• Type of Work: Conference | Post-print: After Peer Review
• Publisher DOI: http://doi.org/10.1117/12.2216559
• Subjects: Engineering, Biomedical; Health Sciences, Oncology; Health Sciences, Radiology
• Keywords: Science & Technology; Physical Sciences; Life Sciences & Biomedicine; Optics; Radiology, Nuclear Medicine & Medical Imaging; Hyperspectral Imaging; Head and neck cancer; Principal Component Analysis (PCA); Support vector machine (SVM); Superpixels; Feature Extraction; Image classification

Abstract

Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two dimensional 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 obtains 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.