Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations

arXiv:2403.14250v1 Announce Type: cross
Abstract: The widespread availability of publicly accessible medical images has significantly propelled advancements in various research and clinical fields. Nonetheless, concerns regarding unauthorized training of AI systems for commercial purposes and the duties of patient privacy protection have led numerous institutions to hesitate to share their images. This is particularly true for medical image segmentation (MIS) datasets, where the processes of collection and fine-grained annotation are time-intensive and laborious. Recently, Unlearnable Examples (UEs) methods have shown …

arxiv availability aware commercial cs.cr cs.cv datasets eess.iv image images institutions led medical patient privacy privacy protection research segmentation systems training unauthorized