Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification

arXiv:2311.10319v3 Announce Type: replace
Abstract: Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages the advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, …

abstract annotated data annotation arxiv classification clinical cs.ai cs.cv data image limitations machine medical process segmentation self-supervised learning supervised learning supervision treatment type