SECURITY FILTERING OF MEDICAL IMAGES USING OCR

Before digital medical images in computer-based patient record systems can be distributed online, it is necessary for confidentiality reasons to eliminate patient identification information that appears in the images. We present an automatic security filtering algorithm for on-line medical image distribution using Daubechies' wavelets [Dau92] and Optical Character Recognition (OCR). The system is practical for realworld applications, processing and coding each 12-bit image of size 512 x 512 within 2 seconds on a Pentium Pro. Besides its exceptional speed, the security filter has demonstrated high accuracy in detecting sensitive textual information within current or digitized previous medical images. The algorithm is of linear run time.

[1]  James Ze Wang,et al.  SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Rama Chellappa,et al.  Page segmentation using decision integration and wavelet packets , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[3]  G. Wiederhold,et al.  A security mediator for health care information. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[4]  David S. Doermann.  Document Understanding Research At Maryland , 1994 .

[5]  Simson L. Garfinkel,et al.  PGP: Pretty Good Privacy , 1994 .

[6]  Yuan Yan Tang,et al.  Quadratic spline wavelet approach to automatic extraction of baselines from document images , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[7]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[8]  James Ze Wang,et al.  Unsupervised Multiresolution Segmentation for Images with Low Depth of Field , 2001, IEEE Trans. Pattern Anal. Mach. Intell..