Texture analysis of gradient images for benign-malignant mass classification Conference Paper
| Authors: | Rabidas, R.; Midya, A.; Chakraborty, J.; Arif, W. |
| Title: | Texture analysis of gradient images for benign-malignant mass classification |
| Conference Title: | 2017 4th International Conference on Signal Processing and Integrated Networks (SPIN 2017) |
| Abstract: | In this correspondence, texture analysis of gradient images has been analyzed for the categorization of mammographic masses as benign or malignant. In addition to the local texture feature, Local Binary Pattern, approximation coefficients have been extracted from the gradient images using wavelet transform to evaluate their efficiency in a Computer-Aided Diagnosis (CADx) system. The experiments have been conducted with the DDSM database containing 200 mammograms where 10 fold cross validation technique has been incorporated with Fisher Linear Discriminant Analysis (FLDA) over the optimal set of features acquired via stepwise logistic regression method. An A, value of 0.91 has been achieved as the best case which indicates an improvement over the results obtained with the normal mass region. |
| Keywords: | breast cancer; mammography; local; recognition; mammograms; local binary patterns; mass classification; gradient image; binary pattern; discrete wavelet transform |
| Journal Title | 2017 4th International Conference on Signal Processing and Integrated Networks |
| Conference Dates: | 2017 Feb 2-3 |
| Conference Location: | Noida, India |
| ISBN: | 978-1-5090-2798-9 |
| Publisher: | IEEE |
| Date Published: | 2017-01-01 |
| Start Page: | 201 |
| End Page: | 205 |
| Language: | English |
| ACCESSION: | WOS:000426076800041 |
| PROVIDER: | wos |
| DOI: | 10.1109/SPIN.2017.8049944 |
| Notes: | SPIN -- Proceedings Paper -- 4th International Conference on Signal Processing and Integrated Networks (SPIN) -- FEB 02-03, 2017 -- Amity Univ, Noida, INDIA -- Amity Sch Engn & Technol, IEEE, IEEE UP Sect -- 345 E 47TH ST, NEW YORK, NY 10017 USA -- Source: Wos |
