Classifier Feature Fusion Using Deep Learning Model for Non-Invasive Detection of Oral Cancer from Hyperspectral Image

Abstract

In this paper we present a state-of-the-art infrastructure approach to detect and classify oral cancer from the hyperspectral imaging of investigating maxillofacial region. Oral and neck cancer is one of the rampant forms of cancer and this cancer is mostly experienced by socio-economic backward population. The hyperspectral image analysis is emerging as a non-invasive method for classification of cancer. Due to dearth of modern digital tool for computer-aided classification and pre-detection of cancer cells, we have proposed a Deep Boltzmann Machine (DBM) and SVM classification fusion for learning and classifying the pre- and post-cancerous tissue and normal tissue from the hyperspectral imaging. The mixed pixel from background is projected for cancerous region detection. The result of a patient hypercube is presented for the validation of deep learning technique pixel-wise probability map of cancerous and normal healthy tissues on hyperspectral imaging. Moreover, we have obtained a classifier accuracy of 94.75% by classifier fusion by majority voting as compared to conventional classification using the deep learning method imaging technique in hyperspectral image. Hence, the proposed digital pre-screening framework using deep learning classifier fusion on hyperspectral thermal imaging provides a high potential cancer identification tool for socio-economic backward patients in modern healthcare system.

KEYWORDS:

• Classifier fusion
• Dataset formation
• Deep learning model
• Hyperspectral imaging
• Image classification
• Non-Invasive cancer detection

ACKNOWLEDGEMENT

The authors would like to acknowledge Indian Institute of Technology, Delhi and Mepco Schlenk Engineering College (Autonomous), Sivakasi, for providing us the necessary facilities to carry out their research work.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Pandia Rajan Jeyaraj

Pandia Rajan Jeyaraj received his BE degree in 2009 and MTech degree in 2011 with first class distinction. He is currently pursuing PhD research work in electrical engineering at Anna University, Chennai by serving as an assistant professor (Senior Grade) at Mepco Schlenk Engineering College, Sivakasi. He has authored over 6 research papers in the reputed international journals. He has received research fellowship by Science Academies at Indian Institute of Technology, Delhi. His research area includes image processing, wireless sensor network, deep learning algorithm applications, internet of things. He is a life member of Indian Society for Technical Education (ISTE).

Bijaya Ketan Panigrahi

Bijaya Ketan Panigrahi (SM’06) received the PhD degree from Sambalpur University, Burla, India, in 2004. In 2005, he joined the Department of Electrical Engineering, Indian Institute of Technology (IIT) Delhi, New Delhi, India, where he currently serves as a professor. Prior to joining IIT Delhi, he was a lecturer with the University College of Engineering Burla, Burla, India, for about 13 years. His research interests include the intelligent control of flexible alternating-current transmission system (FACTS) devices, power system protection, digital signal processing, power quality assessment, and the application of soft computing, evolutionary computing, and machine intelligence techniques to power systems. Email: [email protected]

Edward Rajan Samuel Nadar

Edward Rajan Samuel Nadar is working as a senior professor in the Department of Electrical and Electronics Engineering of Mepco Schlenk Engineering College (Autonomous), Sivakasi, India. He is recognized as an approved research supervisor for guiding PhD by Anna University, Chennai. Presently, under his supervision, six scholars are pursuing their PhD and seven scholars have been awarded their PhD under Anna University, Chennai. He has published 41 research papers in reputed international journals. His main research interests include modelling and simulation of instrumentation systems, medical image processing and bio-medical instrumentation. He is a life member in Indian Society for Technical Education, member in The Institution of Engineers (India), IAENG International Association of Engineers Hong Kong and also a fellow member of The Institute of Research Engineers and Doctors (IRED), New York, USA. Email: [email protected]