Text mining in radiology reports by statistical machine translation approach

Medical text mining has gained increasing popularity in recent years. Now a days, large amount of medical text data are daily generated in health institutions, but never refer again as it is very time consuming task. In Radiology domain, most of the reports are in free text format and usually unprocessed, hence it is difficult to access the valuable information for medical professional unless proper text mining is not applied. There are some systems existing for radiology report information retrieval like MedLEE, NeuRadIR, CBIR but very few of them make use of text associated with image. This paper proposes a text mining system to deals with this problem by using statistical machine translation approach. The System stores the text and image features to find the match report. The SVM classifier is use in SMT approach to check whether entered report present in database or not. The system will return the similar report match with the entered report from the database.