Automatic Classification of Nodules from 2D Ultrasound Images Using Deep Learning Networks
We propose a deep learning architecture that effectively classifies thyroid nodules as requiring FNA or not from ultrasound images. Despite challenges related to image variability, class imbalance, and interpretability, our method demonstrated a high classification accuracy with minimal false negatives, showing its potential to reduce unnecessary FNAs in clinical settings.
Authors
- E. Crevisy
- Alain Lalande (ORCID: https://orcid.org/0000-0002-7970-366X)
- S. Angiolini
- P. Buffier
- Pauline Legris
- C. Vuillemin
- Sarah Leclerc (ORCID: https://orcid.org/0000-0002-4271-0292)
- Tewele W. Tareke
- Marie-Paule Monnier Meteau
- Amandine Nguyen
Institutions
- Centre National de la Recherche Scientifique (FR)
- Université de Bourgogne (FR)
- Institut Régional d'Administration de Bastia (FR)
- Maison des Sciences sociales et des Humanités de Dijon (FR)
Publication Details
- Journal
- Journal of Imaging
- Published
- 2024-08-22
- DOI
- https://doi.org/10.3390/jimaging10080203
- Citations
- 1
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.36