Simultaneous Registration of Location and Orientation in Intravascular Ultrasound Pullbacks Pairs Via 3D Graph-Based Optimization PROJECT TITLE :Simultaneous Registration of Location and Orientation in Intravascular Ultrasound Pullbacks Pairs Via 3D Graph-Based OptimizationABSTRACT:A novel method is reported for simultaneous registration of location (axial direction) and orientation (circumferential direction) of two intravascular ultrasound (IVUS) pullbacks of the identical vessel taken at totally different times. Monitoring plaque progression or regression (e.g., throughout lipid treatment) is of high clinical relevance. Our technique uses a 3D graph optimization approach, in that the price function jointly reflects similarity of plaque morphology and plaque/perivascular image look. Graph arcs incorporate prior information concerning temporal correspondence of the two IVUS sequences and restricted angular twisting between consecutive IVUS images. Additionally, our approach automatically identifies beginning and ending frame pairs in the 2 IVUS pullbacks. Validation of our technique was performed in 29 pairs of IVUS baseline/follow-up pullback sequences consisting of eight 62two IVUS image frames in total. Compared to manual registration by three experts, the average location and orientation registration errors ranged from zero.72 mm to zero.seventy nine mm and from seven.three$^circ$ to 9.3$^circ$ , respectively, all shut to the inter-observer variability with no distinction being statistically significant $(p = rm NS)$ . Rotation angles determined by our automated approach and professional observers showed high correlation ( $r^2$ of 0.97 to 0.98) and agreed closely (mutual bias between the automated methodology and knowledgeable observers ranged from $-one.fifty seven^circ$ to zero.15$^circ$ ). Compared with state-of-the-art approaches, the new methodology offers lower errors in each location and orientation regis- ration. Our method offers highly automated and accurate IVUS pullback registration and will be utilized in IVUS-primarily based studies of coronary disease progression, enabling more focal studies of coronary plaque development and transition of vulnerability. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Statistical Biomechanical Surface Registration: Application to MR-TRUS Fusion for Prostate Interventions Comparison of Mixed-Integer Linear Models for Fuel-Optimal Air Conflict Resolution With Recovery