TY - GEN
T1 - Lung cancer detection using Local Energy-based Shape Histogram (LESH) feature extraction and cognitive machine learning techniques
AU - Wajid, Summrina Kanwal
AU - Hussain, Amir
AU - Huang, Kaizhu
AU - Boulila, Wadii
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/2/21
Y1 - 2017/2/21
N2 - The novel application of Local Energy-based Shape Histogram (LESH) feature extraction technique was recently proposed for breast cancer diagnosis using mammogram images [22]. This paper extends our original work to apply the LESH technique to detect lung cancer. The JSRT Digital Image Database of chest radiographs is selected for research experimentation. Prior to LESH feature extraction, we enhanced the radiograph images using a contrast limited adaptive histogram equalization (CLAHE) approach. Selected state-of-the-art cognitive machine learning classifiers, namely extreme learning machine (ELM), support vector machine (SVM) and echo state network (ESN) are then applied using the LESH extracted features for efficient diagnosis of correct medical state (existence of benign or malignant cancer) in the x-ray images. Comparative simulation results, evaluated using the classification accuracy performance measure, are further bench-marked against state-of-the-art wavelet based features, and authenticate the distinct capability of our proposed framework for enhancing the diagnosis outcome.
AB - The novel application of Local Energy-based Shape Histogram (LESH) feature extraction technique was recently proposed for breast cancer diagnosis using mammogram images [22]. This paper extends our original work to apply the LESH technique to detect lung cancer. The JSRT Digital Image Database of chest radiographs is selected for research experimentation. Prior to LESH feature extraction, we enhanced the radiograph images using a contrast limited adaptive histogram equalization (CLAHE) approach. Selected state-of-the-art cognitive machine learning classifiers, namely extreme learning machine (ELM), support vector machine (SVM) and echo state network (ESN) are then applied using the LESH extracted features for efficient diagnosis of correct medical state (existence of benign or malignant cancer) in the x-ray images. Comparative simulation results, evaluated using the classification accuracy performance measure, are further bench-marked against state-of-the-art wavelet based features, and authenticate the distinct capability of our proposed framework for enhancing the diagnosis outcome.
KW - Clinical Decision Support Systems (CDSSs)
KW - Echo State Network (ESN)
KW - Echo State Network (ESN)
KW - Extreme Learning Machine (ELM)
KW - Local Energy based Shape Histogram (LESH)
KW - Support Vector Machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=85016209357&partnerID=8YFLogxK
U2 - 10.1109/ICCI-CC.2016.7862060
DO - 10.1109/ICCI-CC.2016.7862060
M3 - Conference Proceeding
AN - SCOPUS:85016209357
T3 - Proceedings of 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
SP - 359
EP - 366
BT - Proceedings of 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
A2 - Plataniotis, Kostas
A2 - Widrow, Bernard
A2 - Howard, Newton
A2 - Zadeh, Lotfi A.
A2 - Wang, Yingxu
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2016
Y2 - 22 August 2016 through 23 August 2016
ER -