Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotation

arXiv:2404.14852v1 Announce Type: new
Abstract: Recent advances in deep learning have greatly facilitated the automated segmentation of ultrasound images, which is essential for nodule morphological analysis. Nevertheless, most existing methods depend on extensive and precise annotations by domain experts, which are labor-intensive and time-consuming. In this study, we suggest using simple aspect ratio annotations directly from ultrasound clinical diagnoses for automated nodule segmentation. Especially, an asymmetric learning framework is developed by extending the aspect ratio annotations with two types of …

abstract advances analysis annotation annotations arxiv automated clinical cs.cv deep learning domain domain experts experts images labor segmentation simple study type