An Explainable Deep Learning Framework for Kidney Cancer Classification Using VGG16 and Layer-Wise Relevance Propagation on CT Images

Asma Batool¹, Fahad Ahmed¹, Naila Sammar Naz¹, Ayman Altameem², Ateeq Ur Rehman^3,4, Khan Muhammad Adnan^5,*, Ahmad Almogren^6,*
1 School of Computer Science, National College of Business Administration and Economics, Lahore, 5400, Pakistan
2 Department of Computer Science and Engineering, College of Applied Studies, King Saud University, Riyadh, 11543, Saudi Arabia
3 Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, Tamilnadu
4 Applied Science Research Center, Applied Science Private University, Amman, 11931, Jordan
5 Department of Software, Faculty of Artificial Intelligence and Software, Gachon University, Seongnam-si, 13557, Republic of Korea
6 Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, 11633, Saudi Arabia
* Corresponding Author: Khan Muhammad Adnan. Email: email ; Ahmad Almogren. Email: email

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2025.073149

Received 11 September 2025; Accepted 14 November 2025; Published online 08 December 2025

Download PDF

Abstract

Early and accurate cancer diagnosis through medical imaging is crucial for guiding treatment and enhancing patient survival. However, many state-of-the-art deep learning (DL) methods remain opaque and lack clinical interpretability. This paper presents an explainable artificial intelligence (XAI) framework that combines a fine-tuned Visual Geometry Group 16-layer network (VGG16) convolutional neural network with layer-wise relevance propagation (LRP) to deliver high-performance classification and transparent decision support. This approach is evaluated on the publicly available Kaggle kidney cancer imaging dataset, which comprises labeled cancerous and non-cancerous kidney scans. The proposed model achieved 98.75% overall accuracy, with precision, recall, and F1-score each exceeding 98% on an independent test set. Crucially, LRP-derived heatmaps consistently localize anatomically and pathologically significant regions such as tumor margins in agreement with established clinical criteria. The proposed framework enhances clinician trust by delivering pixel-level justifications alongside state-of-the-art predictive performance. It facilitates informed decision-making, thereby addressing a key barrier to the clinical adoption of DL in oncology.