Deep learning algorithm performance evaluation in detection and classification of liver disease using CT images

R V Manjunath; Anshul Ghanshala; Karibasappa Kwadiki

doi:10.1007/s11042-023-15627-z

Deep learning algorithm performance evaluation in detection and classification of liver disease using CT images

Multimed Tools Appl. 2023 May 15:1-18. doi: 10.1007/s11042-023-15627-z. Online ahead of print.

Authors

R V Manjunath¹, Anshul Ghanshala², Karibasappa Kwadiki³

Affiliations

¹ Department of Electronics &Communication Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore-82, India.
² The Chinese University of Hong Kong, Hong Kong, SAR China.
³ Department of CS&IT, Graphic Era Deemed to be University, Dehradun, 248002 India.

Abstract

To diagnose the liver diseases computed tomography images are used. Most of the time even experienced radiologists find it very tough to note the type, size, and severity of the tumor from computed tomography images due to various complexities involved around the liver. In recent years it is very much essential to develop a computer-assisted imaging technique to diagnose liver disease in turn which improves the diagnosis of a doctor. This paper explains a novel deep learning model for detecting a liver disease tumor and its classification. Tumor from computed tomography images has been classified between Metastasis and Cholangiocarcinoma. We demonstrate that our model predominantly performs very well concerning the accuracy, dice similarity coefficient, and specificity parameters compared to well-known existing algorithms, and adapts very well for different datasets. A dice similarity coefficient value of 98.59% indicates the supremacy of the model.

Keywords: Carcinoma; Cholangiocarcinoma; Computed tomography; Deep learning; Labelled images; Metastasis; Unet.

© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.