Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach
This addresses the cumbersome task of manual inspection for hospitals by automating annotation removal in medical imaging, though it appears incremental as it applies an existing method to a new domain.
This study tackled the problem of automatically detecting and removing annotations from ultrasonic images by treating annotations as noise and using a self-supervised Noise2Noise approach, with results showing that most models outperformed those trained with noisy-clean pairs, and a custom U-Net achieved high scores in segmentation precision and reconstruction similarity.
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 labour. 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. We released our code at https://github.com/GrandArth/UltrasonicImage-N2N-Approach.