Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor

2025-09-19

AI Summary

To address texture ambiguity, noise interference, and variable tissue density in thyroid ultrasound images—challenges arising from anatomical complexity—this paper proposes BPD-LDCT, a novel texture descriptor that uniquely couples Local Discrete Cosine Transform (LDCT) with Improved Local Binary Patterns (ILBP). By embedding a binary-pattern-driven mechanism into the local frequency domain, BPD-LDCT simultaneously enhances fine-grained texture representation and noise robustness. Integrated with a nonlinear Support Vector Machine (SVM) and a multi-stage classification framework, the method jointly performs two tasks: benign/malignant classification and TI-RADS subtype stratification. Evaluated on the TDID and AUITD datasets, it achieves classification accuracies of 99.8% and 97.0% for malignancy detection, and 99.6% and 99.1% for TI-RADS subtyping—substantially outperforming state-of-the-art approaches.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Text Classification & Sentiment Analysis
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this study, we develop a new CAD system for accurate thyroid cancer classification with emphasis on feature extraction. Prior studies have shown that thyroid texture is important for segregating the thyroid ultrasound images into different classes. Based upon our experience with breast cancer classification, we first conjuncture that the Discrete Cosine Transform (DCT) is the best descriptor for capturing textural features. Thyroid ultrasound images are particularly challenging as the gland is surrounded by multiple complex anatomical structures leading to variations in tissue density. Hence, we second conjuncture the importance of localization and propose that the Local DCT (LDCT) descriptor captures the textural features best in this context. Another disadvantage of complex anatomy around the thyroid gland is scattering of ultrasound waves resulting in noisy and unclear textures. Hence, we third conjuncture that one image descriptor is not enough to fully capture the textural features and propose the integration of another popular texture capturing descriptor (Improved Local Binary Pattern, ILBP) with LDCT. ILBP is known to be noise resilient as well. We term our novel descriptor as Binary Pattern Driven Local Discrete Cosine Transform (BPD-LDCT). Final classification is carried out using a non-linear SVM. The proposed CAD system is evaluated on the only two publicly available thyroid cancer datasets, namely TDID and AUITD. The evaluation is conducted in two stages. In Stage I, thyroid nodules are categorized as benign or malignant. In Stage II, the malignant cases are further sub-classified into TI-RADS (4) and TI-RADS (5). For Stage I classification, our proposed model demonstrates exceptional performance of nearly 100% on TDID and 97% on AUITD. In Stage II classification, the proposed model again attains excellent classification of close to 100% on TDID and 99% on AUITD.

Problem

• Develops a CAD system for accurate thyroid cancer classification
• Proposes a novel descriptor to capture challenging ultrasound textures
• Addresses classification of benign vs malignant thyroid nodules

Innovation

• Developed Local DCT descriptor for thyroid texture features
• Integrated Improved Local Binary Pattern for noise resilience
• Used non-linear SVM for final cancer classification