Patient information extraction in digitized X-ray imagery

摘要

Digital imagery is gradually replacing the traditional radiograph with the development of digital radiography and film scanner. This paper presents a new method to extract the patient information number (PIN) field automatically from the film-scanned image using image analysis technique. In order to evaluate the PIN field extraction algorithm, two formats of label acquired from two different hospitals are tested. Given the available films with no constraints on the way the labels are written and positioned, the correct field extraction rates are 73 and 84%, respectively. The film is rejected and will not be filed automatically if the PIN field was not extracted successfully. For the properly extracted PIN field, numerals representing patient's ID inside can then be recognized by a multilayer cluster neural network with a 99% recognition rate. This extracted PIN information is linked with Radiology Information System or Hospital Information System and the image scanned from the film can be filed into database automatically. The efficiency this method offers can greatly simplify the image filing process and improve the user-friendliness of the overall image digitization system. We believe the success of this technique will benefit the development of the Picture Archiving and Communication System and teleradiology.