Deep Learning based Classification for Head and Neck Cancer Detection with Hyperspectral Imaging in an Animal Model

• Type of Material: Article
• Authors: Ling Ma, Emory University; Guolan Lu, Georgia Institute of Technology; Dongsheng Wang, Emory University; Xu Wang, Emory University; Georgia Chen, Emory University; Susan Muller, Emory University; Amy Chen, Emory University; Baowei Fei, Emory University
• Language: English
• Date: 2017-01-01
• Publisher: Society of Photo-optical Instrumentation Engineers (SPIE)
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2017 SPIE.
• Final Published Version (URL): http://dx.doi.org/10.1117/12.2255562
• Title of Journal or Parent Work: Proceedings of SPIE
• ISSN: 0277-786X
• Volume: 10137
• Grant/Funding Information: This research is supported in part by NIH grants (CA176684, R01CA156775 and CA204254) and by Developmental Funds from the Winship Cancer Institute of Emory University under award number P30CA138292.
• Keywords: Computer Science, Artificial Intelligence; Life Sciences & Biomedicine; convolutional neural networks (CNN); Optics; SEGMENTATION; head and neck cancer; Hyperspectral imaging; Technology; Computer Science; noninvasive cancer detection; Physical Sciences; Radiology, Nuclear Medicine & Medical Imaging; Science & Technology; machine learning; spectral-spatial classification
• Research Categories: Health Sciences, Radiology

Abstract

Hyperspectral imaging (HSI) is an emerging imaging modality that can provide a noninvasive tool for cancer detection and image-guided surgery. HSI acquires high-resolution images at hundreds of spectral bands, providing big data to differentiating different types of tissue. We proposed a deep learning based method for the detection of head and neck cancer with hyperspectral images. Since the deep learning algorithm can learn the feature hierarchically, the learned features are more discriminative and concise than the handcrafted features. In this study, we adopt convolutional neural networks (CNN) to learn the deep feature of pixels for classifying each pixel into tumor or normal tissue. We evaluated our proposed classification method on the dataset containing hyperspectral images from 12 tumor-bearing mice. Experimental results show that our method achieved an average accuracy of 91.36%. The preliminary study demonstrated that our deep learning method can be applied to hyperspectral images for detecting head and neck tumors in animal models.