Exemplar Darknet19 feature generation technique for automated kidney stone detection with coronal CT images

Mehmet Baygin; Orhan Yaman; Prabal Datta Barua; Sengul Dogan; Turker Tuncer; U Rajendra Acharya

doi:10.1016/j.artmed.2022.102274

Exemplar Darknet19 feature generation technique for automated kidney stone detection with coronal CT images

Artif Intell Med. 2022 May:127:102274. doi: 10.1016/j.artmed.2022.102274. Epub 2022 Mar 5.

Authors

Mehmet Baygin¹, Orhan Yaman², Prabal Datta Barua³, Sengul Dogan⁴, Turker Tuncer⁵, U Rajendra Acharya⁶

Affiliations

¹ Department of Computer Engineering, College of Engineering, Ardahan University, Elazig, Turkey. Electronic address: mehmetbaygin@ardahan.edu.tr.
² Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey. Electronic address: orhanyaman@firat.edu.tr.
³ School of Management & Enterprise, University of Southern Queensland, Australia; Faculty of Engineering and Information Technology, University of Technology Sydney, Australia; Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia. Electronic address: Prabal.Barua@usq.edu.au.
⁴ Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey. Electronic address: sdogan@firat.edu.tr.
⁵ Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey. Electronic address: turkertuncer@firat.edu.tr.
⁶ Ngee Ann Polytechnic, Department of Electronics and Computer Engineering, 599489, Singapore; Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore; Department of Biomedical Informatics and Medical Engineering, Asia, University, Taichung, Taiwan. Electronic address: aru@np.edu.sg.

PMID: 35430036
DOI: 10.1016/j.artmed.2022.102274

Abstract

Kidney stone is a commonly seen ailment and is usually detected by urologists using computed tomography (CT) images. It is difficult and time-consuming to detect small stones in CT images. Hence, an automated system can help clinicians to detect kidney stones accurately. In this work, a novel transfer learning-based image classification method (ExDark19) has been proposed to detect kidney stones using CT images. The iterative neighborhood component analysis (INCA) is employed to select the most informative feature vectors and these selected features vectors are fed to the k nearest neighbor (kNN) classifier to detect kidney stones with a ten-fold cross-validation (CV) strategy. The proposed ExDark19 model yielded an accuracy of 99.22% with 10-fold CV and 99.71% using the hold-out validation method. Our results demonstrate that the proposed ExDark19 detect kidney stones over 99% accuracies for two validation techniques. This developed automated system can assist the urologists to validate their manual screening of kidney stones and hence reduce the possible human error.

Keywords: Biomedical image classification; ExDark19; INCA; Kidney stone detection; Pre-trained model; Transfer learning.

MeSH terms

Female
Humans
Kidney Calculi* / diagnostic imaging
Male
Tomography, X-Ray Computed / methods