Unknown

Dataset Information

Self-supervised identification and elimination of harmful datasets in distributed machine learning for medical image analysis.


ABSTRACT: Distributed learning enables collaborative machine learning model training without requiring cross-institutional data sharing, thereby addressing privacy concerns. However, local quality control variability can negatively impact model performance while systematic human visual inspection is time-consuming and may violate the goal of keeping data inaccessible outside acquisition centers. This work proposes a novel self-supervised method to identify and eliminate harmful data during distributed learning model training fully-automatically. Harmful data is defined as samples that, when included in training, increase misdiagnosis rates. The method was tested using neuroimaging data from 83 centers for Parkinson's disease classification with simulated inclusion of a few harmful data samples. The

SUBMITTER: Souza R 

PROVIDER: S-EPMC11830037 | biostudies-literature | 2025 Feb

REPOSITORIES: biostudies-literature