Citation

Nabi, Md Serajun and Fauzi, Mohammad Faizal Ahmad and Abdul Karim, Hezerul and Khalid, Ahmad Shahrafidz and Tang, Tong Boon and Razak, Normy N. (2025) Explainable AI for Breast Cancer Diagnosis Using EfficientNetB3 with Attention Mechanism. In: TENCON 2025 - 2025 IEEE Region 10 Conference (TENCON), 27-30 October 2025, Kota Kinabalu, Malaysia.

Text 21.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

Accurate classification of HER2 immunohistochemistry (IHC) scores is essential for determining effective breast cancer treatment, yet it remains challenging due to subjective manual interpretation, especially for borderline scores (1+ and 2+). This study proposes an interpretable deep learning framework that combines EfficientNetB3 with a Convolutional Block Attention Module (CBAM) to strengthen feature extraction and attention to regions of interest that are diagnostically significant. To facilitate clinical trust, explainable AI (XAI) is performed using Gradient-weighted Class Activation Mapping (Grad-CAM). Evaluated on a HER2-IHC-40xWSI dataset of 10,997 image patches distributed over four HER2 classes (0,1+,2+,3+), the proposed model achieved an overall accuracy of 96% and a macro-averaged F1-score of 93%, demonstrating strong performance, particularly in borderline cases. The system demonstrates promising performance within the dataset, particularly in borderline cases, suggesting potential for broader generalization. These results highlight the potential of applying attention mechanisms with explainable AI for stable and interpretable HER2 IHC scoring in digital pathology.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	HER2 IHC, breast Cancer, efficientNetB3, attention mechanism, CBAM, Grad-CAM, explainable AI (XAI), digital pathology
Subjects:	R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	20 Apr 2026 03:40
Last Modified:	20 Apr 2026 03:40
URII:	http://shdl.mmu.edu.my/id/eprint/15773

Downloads

Edit (login required)