Adaptive Bandelet Transform and Transfer Learning for Geometry-Aware Thyroid Cancer Ultrasound Classification

Habchi, Y ORCID: 0000-0002-8764-9675, Kheddar, H ORCID: 0000-0002-9532-2453, Ghanem, MC ORCID: 0000-0002-7067-7848 and Hwaidi, J (2026) Adaptive Bandelet Transform and Transfer Learning for Geometry-Aware Thyroid Cancer Ultrasound Classification Diagnostics, 16 (4). 554-. ISSN 2075-4418, 2075-4418

Access the full-text of this item by clicking on the Open Access link.

Abstract

Background and Objectives: Classification of thyroid nodules (TN) in ultrasound remains challenging due to limited labelled data and the limited capacity of conventional feature representations to capture complex, multi-directional textures. This work aims to improve data-efficient TN classification by integrating a geometry-adaptive Bandelet Transform (BT) with transfer learning (TL) to enhance feature representation and generalisation. Methods: The proposed pipeline first applies BT to strengthen directional and structural encoding in ultrasound images via quadtree-driven geometric adaptation. It then mitigates class imbalance using SMOTE and increases data diversity through targeted data augmentation. The resulting representations are classified using multiple ImageNet-pretrained architectures, where VGG19 yields the most consistent performance. Results: Experiments on the publicly available DDTI dataset show that BT-based preprocessing consistently improves performance over classical wavelet representations across multiple quadtree thresholds, with the best results obtained at (Formula presented.). Under this setting, the proposed BT+TL (VGG19) model achieves 98.91% accuracy, 98.11% sensitivity, 97.31% specificity, and a 98.89% F1-score, outperforming comparable approaches reported in the literature. Conclusions: Coupling geometry-adaptive transforms with modern TL backbones provides a robust and data-efficient strategy for ultrasound TN classification, particularly under limited annotation and challenging texture variability. The complete project is publicly available.

Item Type:	Article
Uncontrolled Keywords:	bandelet transform, transfer learning, thyroid cancer, deep learning, medical imaging, diagnostic
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Computer Science & Informatics Faculty of Science & Engineering > School of Computer Science & Informatics > School of Computer Science & Informatics
Depositing User:	Symplectic Admin
Date Deposited:	17 Feb 2026 10:40
Last Modified:	14 Mar 2026 14:43
DOI:	10.3390/diagnostics16040554
Open Access URL:	https://doi.org/10.3390/diagnostics16040554
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3197070
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.