An automated patient recognition method based on an image-matching technique using previous chest radiographs in the picture archiving and communication system environment

An automated patient recognition method for correcting ''wrong'' chest radi ographs being stored in a picture archiving and communication system (PACS) environment has been developed. The method is based on an image-matching t echnique that uses previous chest radiographs. For identification of a "wro ng" patient, the correlation value was determined for a previous image of a patient and a new, current image of the presumed corresponding patient. Th e current image was shifted horizontally and vertically and rotated, so tha t we could determine the best match between the two images. The results ind icated that the correlation values between the current and previous images for the same, "correct" patients were generally greater than those for diff erent, "wrong" patients. Although the two histograms for the same patient a nd for different patients overlapped at correlation values greater than 0.8 0, most parts of the histograms were separated. The correlation value was c ompared with a threshold value that was determined based on an analysis of the histograms of correlation values obtained for the same patient and for different patients. If the current image is considered potentially to belon g to a "wrong" patient, then a warning sign with the probability for a ''wr ong'' patient is provided to alert radiology personnel. Our results indicat e that at least half of the ''wrong'' images in our database can be identif ied correctly with the method described in this study. The overall performa nce in terms of a receiver operating characteristic curve showed a high per formance of the system. The results also indicate that some readings of "wr ong" images for a given patient in the PACS environment can be prevented by use of the method we developed. Therefore an automated warning system for patient recognition would be useful in correcting "wrong" images being stor ed in the PACS environment. (C) 2001 American Association of Physicists in Medicine.