Automatic localization of blood vessels is important to many clinical procedures. In this contribution we have improved our automatic technique, presented last year at MICCAI 2014, by increasing the accuracy of the algorithm and extending the range of applications to include ultrasound imaging. Our new contribution incorporates a mathematical model of radial distension (expansion and contraction of vessel-like structures) to highlight structures that pulsate like a blood vessel, while ignoring tissues that merely translate at pulsatile frequencies.
If you do not have access to the download page, request access by filling the form below.
A. Amir-Khalili, G. Hamarneh, R. Abugharbieh. “Automatic Vessel Segmentation from Pulsatile Radial Motion”. Medical Image Computing and Computer Assisted Intervention (MICCAI), Munich-Germany, Oct 2015, pp. 403-410 [PDF]
A. Amir-Khalili, J.-M. Peyrat, J. Abinahed, O. AlAlao, A. Al-Ansari, G. Hamarneh, R. Abugharbieh. “Automatic Segmentation of Occluded Vasculature via Pulsatile Motion Analysis in Endoscopic Robot-Assisted Partial Nephrectomy Video”. Medical Image Analysis (MedIA), Elsevier, volume 25, Oct 2015, pp. 103-110 [PDF]
A. Amir-Khalili, J.-M. Peyrat, J. Abinahed, O. AlAlao, A. Al-Ansari, G. Hamarneh, R. Abugharbieh. “Auto Localization and Segmentation of Occluded Vessels in Robot-Assisted Partial Nephrectomy”. Medical Image Computing and Computer Assisted Intervention (MICCAI), Boston-USA, Sept 2014, pp. 407-414 [PDF]