An On-Premise, Open-Weights Vision-Language Pipeline for Burned-In PHI Removal: Detection, Decision, and Image Degradation on MIDI-B
Burned-in protected health information (PHI) in DICOM pixel data blocks multi-site imaging research, and better recognition is assumed to be the route to removal. We asked whether detection or the PHI decision limits removal. A layered pixel pipeline built on Florence-2 OCR was evaluated on MIDI-B with the CBIIT validation script. Against the answer key's OCR-independent coordinates, two controlled arms swapped the engine with the decision fixed, then varied the decision over detections. A nine-condition degradation sweep ran to redaction, with Wilson intervals and exact McNemar tests. On clean images, a 0.23 B vision-language model and a CNN OCR at library defaults detected 34/35 and 35/35 regions, flagged the same 10/35 with the decision fixed, and removed the same 33/35. Over fixed detections, Microsoft Presidio flagged 12/35 and a generic rule set 10/35, as 25 of 35 regions are unpatterned markers; redacting every detection reached 35/35, so both shipped misses were decision misses. Under degradation, both engines detected the text in every condition; removal differed most at blur radius 4, 32 versus 26 (p = 0.07), where the CNN OCR misread short markers (exact match 17/25 versus 10/25). An earlier-reported collapse to 18/35 came from a confidence floor in our harness. The strict profile scored 33/35 at 86.7% series accuracy, and the retain profile 32/35 at 97.6%. Removal on clean text is limited by the PHI decision, not the detector. Under synthetic degradation, the engines differ in transcribing short strings, not in detecting them, by a margin this sample cannot resolve. Results are benchmark- and engine-specific.
Authors
- D. Patil (ORCID: https://orcid.org/0009-0003-6878-1712)
Institutions
- University at Buffalo, State University of New York (US)
Publication Details
- Journal
- Journal of Imaging Informatics in Medicine
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1007/s10278-026-02452-7
- Primary Topic
- Handwritten Text Recognition Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00