A hybrid rules-plus-AI pipeline for DICOM de-identification achieved 99.91% accuracy on the MIDI-B test set, with missed PHI detection as the largest failure category.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Hybrid AI-based and Rule-based Approach to DICOM De-identification: A Solution for the MIDI-B Challenge
A hybrid rules-plus-AI pipeline for DICOM de-identification achieved 99.91% accuracy on the MIDI-B test set, with missed PHI detection as the largest failure category.