ThyroidEffi 1.0: A Cost-Effective System for High-Performance Multi-Class Thyroid Carcinoma Classification

2025-04-19

AI Summary

This study addresses the clinical need for triaging thyroid fine-needle aspiration biopsy (FNAB) images from Vietnamese patients into three diagnostic categories (Bethesda System categories B2, B5, and B6) using an efficient and interpretable deep learning system. Methodologically, it introduces three key innovations: (1) YOLOv10-based detection of cellular clusters; (2) curriculum learning-guided multi-scale training; and (3) a lightweight Transformer-based multi-region fusion module, built upon an adaptive EfficientNet-B0 backbone (4M parameters) with Grad-CAM for model interpretability. Evaluated on internal test data, the system achieves a macro-F1 score of 89.77% and a maximum AUC of 0.98. External validation yields per-class AUCs of 0.9495 (B2), 0.7436 (B5), and 0.8396 (B6), demonstrating strong generalizability across centers. Inference on 1,000 samples takes only 30 seconds on a 12-core CPU, balancing high diagnostic accuracy, computational efficiency, cross-site robustness, and clinical interpretability.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Background: Automated classification of thyroid fine needle aspiration biopsy (FNAB) images faces challenges in limited data, inter-observer variability, and computational cost. Efficient, interpretable models are crucial for clinical support. Objective: To develop and externally validate a deep learning system for the multi-class classification of thyroid FNAB images into three key categories that directly guide post-biopsy treatment decisions in Vietnam: benign (B2), suspicious for malignancy (B5), and malignant (B6), while achieving high diagnostic accuracy with low computational overhead. Methods: Our framework features: (1) YOLOv10-based cell cluster detection for informative sub-region extraction and noise reduction; (2) a curriculum learning-inspired protocol sequencing localized crops to full images for multi-scale feature capture; (3) adaptive lightweight EfficientNetB0 (4 millions parameters) selection balancing performance and efficiency; and (4) a Transformer-inspired module for multi-scale, multi-region analysis. External validation used 1,015 independent FNAB images. Results: ThyroidEffi Basic achieved a macro F1 of 89.19% and AUCs of 0.98 (B2), 0.95 (B5), and 0.96 (B6) on the internal test set. External validation yielded AUCs of 0.9495 (B2), 0.7436 (B5), and 0.8396 (B6). ThyroidEffi Premium improved macro F1 to 89.77%. Grad-CAM highlighted key diagnostic regions, confirming interpretability. The system processed 1000 cases in 30 seconds, demonstrating feasibility on widely accessible hardware like a 12-core CPU. Conclusions: This work demonstrates that high-accuracy, interpretable thyroid FNAB image classification is achievable with minimal computational demands.

Problem

• Automated classification of thyroid FNAB images with limited data
• Reducing inter-observer variability in thyroid carcinoma diagnosis
• Achieving high diagnostic accuracy with low computational cost

Innovation

• YOLOv10-based cell cluster detection
• Curriculum learning for multi-scale features
• Lightweight EfficientNetB0 with Transformer module