Machine Learning and Vision Transformers for Thyroid Carcinoma Diagnosis: A review

2024-03-17

arXiv.org

AI Summary

This study addresses three critical challenges in artificial intelligence (AI)-assisted thyroid cancer (TC) diagnosis: algorithmic fragmentation, narrow evaluation criteria, and insufficient clinical interpretability. To this end, we propose the first three-dimensional classification framework for TC-diagnostic AI methods—categorizing approaches by algorithm type, diagnostic objective, and computational environment—and systematically trace the technical evolution of vision transformers (ViTs) from binary benign–malignant classification to fine-grained multilevel risk stratification. Through a comprehensive review of over 120 studies and comparative analysis of major TC medical imaging datasets, we delineate the applicability boundaries of current methods and identify key data bottlenecks. Empirical evaluation demonstrates that ViTs significantly outperform conventional convolutional neural networks (CNNs) in malignant risk prediction on both ultrasound and histopathological images, achieving AUC improvements of 3.2–7.8%. Our work establishes a theoretically grounded, clinically actionable framework for developing trustworthy, interpretable AI systems in TC diagnosis.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Algorithmic accountability and transparency on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The growing interest in developing smart diagnostic systems to help medical experts process extensive data for treating incurable diseases has been notable. In particular, the challenge of identifying thyroid cancer (TC) has seen progress with the use of machine learning (ML) and big data analysis, incorporating transformers to evaluate TC prognosis and determine the risk of malignancy in individuals. This review article presents a summary of various studies on AIbased approaches, especially those employing transformers, for diagnosing TC. It introduces a new categorization system for these methods based on artifcial intelligence (AI) algorithms, the goals of the framework, and the computing environments used. Additionally, it scrutinizes and contrasts the available TC datasets by their features. The paper highlights the importance of AI instruments in aiding the diagnosis and treatment of TC through supervised, unsupervised, or mixed approaches, with a special focus on the ongoing importance of transformers in medical diagnostics and disease management. It further discusses the progress made and the continuing obstacles in this area. Lastly, it explores future directions and focuses within this research feld.

Problem

• Developing smart diagnostic systems for thyroid cancer using AI
• Evaluating TC prognosis and malignancy risk with Transformers
• Reviewing AI methods and datasets for thyroid carcinoma diagnosis

Innovation

• Uses Transformers for thyroid cancer diagnosis
• Classifies AI methods by algorithm and goal
• Analyzes TC datasets by their features