OCTID: a one-class learning-based Python package for tumor image detection

Yanan Wang, Litao Yang, Geoffrey I. Webb, Zongyuan Ge, Jiangning Song

Abstract: Tumor tile selection is a necessary prerequisite in patch-based cancer whole slide image analysis, which is labor-intensive and requires expertise. Whole slides are annotated as tumor or tumor free, but tiles within a tumor slide are not. As all tiles within a tumor free slide are tumor free, these can be used to capture tumor-free patterns using the one-class learning strategy.