Combining curriculum learning and weakly supervised attention for enhanced thyroid nodule assessment in ultrasound imaging.
Authors
Affiliations (7)
Affiliations (7)
- Department of Computer Science, Faculty of Science, Ramkhamhaeng University, Bangkok, Thailand.
- Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok, Thailand.
- Artificial Intelligence Center, Asian Institute of Technology, Pathumthani, Thailand.
- Logsig Co., Ltd., Pathumthani, Thailand.
- Harbor Branch Oceanographic Institute, Florida Atlantic University, Fort Pierce, FL, USA.
- Industrial Systems Engineering Department, Asian Institute of Technology, Pathumthani, Thailand.
- Information and Communication Technologies, Asian Institute of Technology, Pathumthani, Thailand.
Abstract
The accurate assessment of thyroid nodules, which are increasingly common with age and lifestyle factors, is essential for early malignancy detection. Ultrasound imaging, the primary diagnostic tool for this purpose, holds promise when paired with deep learning. However, challenges persist with small datasets, where conventional data augmentation can introduce noise and obscure essential diagnostic features. To address dataset imbalance and enhance model generalization, this study integrates curriculum learning with a weakly supervised attention network to improve diagnostic accuracy for thyroid nodule classification. This study integrates curriculum learning with attention-guided data augmentation to improve deep learning model performance in classifying thyroid nodules. Using verified datasets from Siriraj Hospital, the model was trained progressively, beginning with simpler images and gradually incorporating more complex cases. This structured learning approach is designed to enhance the model's diagnostic accuracy by refining its ability to distinguish benign from malignant nodules. Among the curriculum learning schemes tested, schematic IV achieved the best results, with a precision of 100% for benign and 70% for malignant nodules, a recall of 82% for benign and 100% for malignant, and F1-scores of 90% and 83%, respectively. This structured approach improved the model's diagnostic sensitivity and robustness. These findings suggest that automated thyroid nodule assessment, supported by curriculum learning, has the potential to complement radiologists in clinical practice, enhancing diagnostic accuracy and aiding in more reliable malignancy detection.