Automatical Cranial Suture Detection based on Thresholding Method

Abstract

Purpose : The head of infants under 24 months old who has Craniosynostosis grows extraordinarily that makes head shape unusual. To diagnose the Craniosynostosis, surgeon has to inspect computed tomography(CT) images of the patient in person. It’s very time consuming process. Moreover, without a surgeon, it’s diffcult to diagnose the Craniosynostosis. Therefore, we developed technique which detects Craniosynostosis automatically from the CT volume.

Materials and Methods : At first, rotation correction is performed to the 3D CT volume for detection of the Craniosynostosis. Then, cranial area is extracted using the iterative thresholding method we proposed. Lastly, we diagnose Craniosynostosis by analyzing centroid relationships of clusters of cranial bone which was divided by cranial suture.

Results : Using this automatical cranial detection technique, we can diagnose Craniosynostosis correctly. The proposed method resulted in 100% sensitivity and 90% specificity. The method perfectly diagnosed abnormal patients.

Conclusion : By plugging-in the software on CT machine, it will be able to warn the possibility of Craniosynostosis. It is expected that early treatment of Craniosynostosis would be possible with our proposed algorithm.