Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach

Abstract

Article Ultrasonic Image’s Annotation Removal: A Self-supervised Noise2Noise Approach Yuanheng Zhang 1, Nan Jiang 2, Zhaoheng Xie 3, Junying Cao 2,*, and Yueyang Teng 1,* 1   College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China2   The Department of Ultrasound, General Hospital of Northern Theater Command, Shenyang 110169, China3   The Institute of Medical Technology, Peking University, Beijing 100191, China*  Correspondence: shenzongchaosheng@163.com (J.C.); tengyy@bmie.neu.edu.cn (Y.T.) Received: 11 March 2024; Revised: 25 May 2024; Accepted: 28 May 2024; Published: 17 July 2024   Abstract: Accurately annotated ultrasonic images are vital components of a high-quality medical report. Hospitals often have strict guidelines on the types of annotations that should appear on imaging results. However, manually inspecting these images can be a cumbersome task. While a neural network could potentially automate the process, training such a model typically requires a dataset of paired input and target images, which in turn involves significant human labor. This study introduces an automated approach for detecting annotations in images. This is achieved by treating the annotations as noise, creating a self-supervised pretext task and using a model trained under the Noise2Noise scheme to restore the image to a clean state. We tested a variety of model structures on the denoising task against different types of annotation, including body marker annotation, radial line annotation, etc. Our results demonstrate that most models trained under the Noise2Noise scheme outperformed their counterparts trained with noisy-clean data pairs. The costumed U-Net yielded the most optimal outcome on the body marker annotation dataset, with high scores on segmentation precision and reconstruction similarity. Our approach streamlines the laborious task of manually quality-controlling ultrasound scans, with minimal human labor involved, making the quality control process efficient and scalable.