Citation

Kabir, Shahriar Mahmud and Bhuiyan, Mohammed Imamul Hassan and Nazmus Shakib, Mohammed and Lim, Heng Siong (2026) RiIG-Based Contourlet Parametric Imaging and Reliability-Guided Learning for Breast Ultrasound Lesion Classification. IEEE Access, 14. pp. 155362-155390. ISSN 2169-3536

Text 2.pdf - Published Version Restricted to Repository staff only Download (5MB)

Abstract

Breast ultrasound (BUS) lesion classification remains challenging because of speckle noise, low contrast, tissue heterogeneity, and acquisition variability. This study presents a framework combining Rician Inverse Gaussian (RiIG)-based contourlet parametric imaging with reliability-guided learning. The method applies contourlet decomposition and RiIG statistical modeling to transform B-mode images into parametric representations of multiscale directional structure and heterogeneous lesion echotexture. A reliability-weighted DenseNet–Vision Transformer fusion network and teacher–student procedure are optimized using a structured composite objective, hereafter termed LoFT, which coordinates hardsample learning, imbalance-sensitive supervision, confidence control, and perturbation consistency using established loss terms rather than introducing a new loss family. The fusion mechanism adaptively integrates local echotextural and lesion-boundary evidence from DenseNet with global contextual information from the Transformer. Evaluation included leakage-aware five-fold experiments on the publicly available Breast Ultrasound Images (BUSI) dataset, UDIAT Diagnostic Centre dataset (UDIAT), Mendeley dataset, and their combined corpus; strict BUSI-to-UDIAT transfer using the BUSI-only model and threshold selection; and supplementary source-combined unseen-target testing. Proxy-group-disjoint and duplicate-audited partitions were used, although verified patient identifiers were unavailable. Five-fold accuracies were 95.58%, 86.44%, 99.60%, and 92.21%, respectively. Strict external transfer achieved 76.07% accuracy and 77.56% area under the receiver operating characteristic curve (AUC); however, 37.04% malignant sensitivity and 50.63% malignant-class F1-score indicated substantial domain-shift limitations. Supplementary evaluations further revealed inconsistent transfer across unseen target datasets. Gradient-weighted Class Activation Mapping (Grad-CAM), Integrated Gradients, Partial Dependence Plots and quantitative BUSI mask analysis showed partial correspondence between model attribution and annotated lesion regions. The results demonstrate strong within-dataset technical performance while exposing unresolved external-generalization limitations. The framework therefore supports further retrospective decision-support research while underscoring the need for improved cross-dataset robustness and prospective clinical validation.

Item Type:	Article
Uncontrolled Keywords:	Breast ultrasound lesion classification
Subjects:	R Medicine > R Medicine (General) > R856-857 Biomedical engineering. Electronics. Instrumentation T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	28 Oct 2026 03:59
Last Modified:	28 Oct 2026 03:59
URII:	http://shdl.mmu.edu.my/id/eprint/16932

Downloads

Edit (login required)