Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder, an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.
@article{arxiv.2307.08673,
title = {CohortFinder: an open-source tool for data-driven partitioning of biomedical image cohorts to yield robust machine learning models},
author = {Fan Fan and Georgia Martinez and Thomas Desilvio and John Shin and Yijiang Chen and Bangchen Wang and Takaya Ozeki and Maxime W. Lafarge and Viktor H. Koelzer and Laura Barisoni and Anant Madabhushi and Satish E. Viswanath and Andrew Janowczyk},
journal= {arXiv preprint arXiv:2307.08673},
year = {2023}
}
Comments
26 pages, 9 figures, 4 tables. Abstract was accepted by European Society of Digital and Integrative Pathology (ESDIP), Germany, 2022