A novel deep learning framework for generation and evaluation of thyroid ultrasound elastography: a multicenter study

Background: Ultrasound examination has long been the primary method for detecting thyroid nodules. Elastography, introduced as a supplementary ultrasound modality, has shown promise in enhancing the accuracy of non-invasive assessments for thyroid nodule malignancy. However, its reliance on specialized equipment and subjective interpretation by specialists poses challenges and introduces variability.