Your browser doesn't support javascript.
loading
A Method for Efficient De-identification of DICOM Metadata and Burned-in Pixel Text.
Macdonald, Jacob A; Morgan, Katelyn R; Konkel, Brandon; Abdullah, Kulsoom; Martin, Mark; Ennis, Cory; Lo, Joseph Y; Stroo, Marissa; Snyder, Denise C; Bashir, Mustafa R.
Affiliation
  • Macdonald JA; Department of Radiology, Duke University, Durham, NC, USA. jacob.macdonald@duke.edu.
  • Morgan KR; Department of Radiology, Duke University, Durham, NC, USA.
  • Konkel B; Department of Radiology, Duke University, Durham, NC, USA.
  • Abdullah K; Department of Radiology, Duke University, Durham, NC, USA.
  • Martin M; Department of Radiology, Duke University, Durham, NC, USA.
  • Ennis C; School of Medicine, Duke University, Durham, NC, USA.
  • Lo JY; Department of Radiology, Duke University, Durham, NC, USA.
  • Stroo M; Duke Office of Clinical Research, Duke University, Durham, NC, USA.
  • Snyder DC; Clinical and Translational Science Institute, Duke University, Durham, NC, USA.
  • Bashir MR; Duke Office of Clinical Research, Duke University, Durham, NC, USA.
J Imaging Inform Med ; 2024 Apr 08.
Article in En | MEDLINE | ID: mdl-38587767
ABSTRACT
De-identification of DICOM images is an essential component of medical image research. While many established methods exist for the safe removal of protected health information (PHI) in DICOM metadata, approaches for the removal of PHI "burned-in" to image pixel data are typically manual, and automated high-throughput approaches are not well validated. Emerging optical character recognition (OCR) models can potentially detect and remove PHI-bearing text from medical images but are very time-consuming to run on the high volume of images found in typical research studies. We present a data processing method that performs metadata de-identification for all images combined with a targeted approach to only apply OCR to images with a high likelihood of burned-in text. The method was validated on a dataset of 415,182 images across ten modalities representative of the de-identification requests submitted at our institution over a 20-year span. Of the 12,578 images in this dataset with burned-in text of any kind, only 10 passed undetected with the method. OCR was only required for 6050 images (1.5% of the dataset).
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: J Imaging Inform Med Year: 2024 Document type: Article Affiliation country: United States

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: J Imaging Inform Med Year: 2024 Document type: Article Affiliation country: United States