RejectionClass
Algorithm for classification of kidney transplant pathology
Description:
RejectionClass is a web-based software designed to classify kidney transplant rejection, integrating information on donor-specific anti-HLA antibodies and acute histological Banff lesion scores of kidney transplant biopsies. RejectionClass uses a semi-supervised clustering approach and provides an easily interpretable two-dimensional visual and quantitative presentation of the multidimensional histologic data. This tool is for research use only.
More Information:
Originates from the AI-Driven Data Science research challenge (FAIR 2019–2023).
Responsible Research Lead: Maarten Naesens
Authors: Thibaut Vaulet, Maarten Naesens, Bart De Moor
Programming Language: Python
Categories: Time series, active learning, anomaly detection, un/semi-supervised learning
Publications:
Vaulet, Thibaut, et al. “Data-Driven Chronic Allograft Phenotypes: A Novel and Validated Complement for Histologic Assessment of Kidney Transplant Biopsies.” Journal of the American Society of Nephrology, September 7, 2022. https://doi.org/10.1681/ASN.2022030290.
Vaulet, Thibaut, et al. “Data-Driven Derivation and Validation of Novel Phenotypes for Acute Kidney Transplant Rejection Using Semi-Supervised Clustering.” Journal of the American Society of Nephrology, March 9, 2021. https://doi.org/10.1681/ASN.2020101418.