Looking into Algorithms to Evolve a Robust Classification of Ultrasound Image of Human Liver Steatosis Using Two Independent Image Sources
- 77 Downloads
Supervised classification is found to be data specific. A single data set is usually partitioned into training and test subsets usually with several fold cross validation. An ideal classification model trained with exhaustive variation in training examples should work with other similar but unseen data from an independent source. Present authors developed an efficient algorithm to classify fatty liver versus normal liver from ultrasonogram (US) of human liver. In this article it is explored how far that algorithm is applicable for classification of US image obtained from two different sources and how the classification accuracy is affected if two data sets are pooled together. Finally we explore the possibility of training by one source and testing by another source. Idea is to find out a robust algorithm which works in a portable environment.
KeywordsUltrasound Human liver Data source Classification PSO Anisotropy features
We would like to thank Dr. Suparna Majumdar, Department of Radio diagnosis, Chittaranjan National Cancer Institute, Kolkata-700026, India. We would like to thank Dr. Tarun Kumar Roy, Senior Consultant Radiologist, Surakha Diagnostic Center, Phoolbagan, Kolkata-700054, India.
- 2.Moldovanu, S., Moraru, L., Bibicu, D.: Computerized decision support in liver steatosis investigation. Int. J. Biol. Biomed. Eng. 6(1), 69–76 (2012)Google Scholar
- 3.Acharya, U.R., Fujita, H., Sudarshan, V.K., Mookiah, M.R.K., Koh, J.E., Tan, J.H., Hagiwara, Y., Chua, C.K., Junnarkar, S.P., Vijayananthan, A., Ng, K.H.: An integrated index for identification of fatty liver disease using radon transform and discrete cosine transform features in ultrasound images. Inf. Fusion 31, 43–53 (2016)CrossRefGoogle Scholar
- 8.Acharya, U.R., Raghavendra, U., Fujita, H., Hagiwara, Y., Koh, J.E., Hong, T.J., Sudarshan, V.K., Vijayananthan, A., Yeong, C.H., Gudigar, A., Ng, K.H.: Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. Comput. Biol. Med. 79, 250–2508 (2016)CrossRefGoogle Scholar
- 10.Neogi, N., Adhikari, A., Roy, M.: Anisotropy of the texture in the ultra-sonogram of human livers. In: 2016 International Conference on Information Science (ICIS), pp. 114–119. IEEE (2016)Google Scholar
- 11.Neogi, N., Adhikari, A., Roy, M.: Use of a novel set of features based on texture anisotropy for identification of liver steatosis from ultrasound images: a simple method. Multimed. Tools Appl. 67(3), 1–23 (2018)Google Scholar
- 15.Chetverikov, D.: GLDH based analysis of texture anisotropy and symmetry, an experimental study. In: IEEE Proceedings of the 12th IAPR International Conference on Computer Vision & Image Processing. vol. 1, pp. 444–448 (1994)Google Scholar
- 17.Kennedy, J., Eberhart, R.: Particle swarm optimization. In: IEEE Conference on Neural Networks, pp. 1942–1948 (1995)Google Scholar
- 19.Mukherjee, S., Adhikari A., Roy, M.: Malignant melanoma classification using cross-platform dataset with deep learning CNN architecture. In: Recent Trends in Signal and Image Processing. AISC, vol. 922, pp. 31–41. Springer, Singapore (2019)Google Scholar
- 20.Neogi, N., Adhikari, A., Roy, M.: Classification of multisource ultrasonogram image of steatosis. Presented at International Conference on Advanced Informatics for Computing Research (ICAICR), 15–16th June 2019, Simla, India (2019)Google Scholar