It is widely known that the state of a patient's coronary heart disease can be better assessed using intravascular ultrasound (IVUS) than with more conventional angiography. Recent work has shown that segmentation and 3D reconstruction of IVUS pull-back sequence images can be used for computational fluid dynamic simulation of blood flow through the coronary arteries. This map of shear stress in the blood vessel walls can be used to predict susceptibility of a region of the arteries to future arteriosclerosis and disease. Manual segmentation of images is time consuming as well as cost prohibitive for routine diagnostic use. Current segmentation algorithms do not achieve a high enough accuracy because of the presence of speckle due to blood flow, relatively low resolution of images and presence of various artifacts including guide-wires, stents, vessel branches, and some other growth or inflammations. On the other hand, the image may be induced with additional blur due to movement distortions, as well as resolution-related mixing of closely resembling pixels thus forming a type of out-of-focus blur.. Robust automated segmentation achieving high accuracy of 95% or above has been elusive despite of work by a large community of researchers in the machine vision field. We propose a comprehensive approach where a multitude of algorithms are applied simultaneously to the segmentation problem. In an initial step, pattern recognition methods are used to detect and localize artifacts. We have achieved a high accuracy of 95% or better in detecting frames with stents and location of guide-wire in a large data-set consisting of 15 pull-back sequences with about 1000 image frames each. Our algorithms for lumen segmentation using spatio-temporal texture detection and active contour models have achieved accuracies approaching 70% in the same data-set which is on the high-side of reported accuracies in the literature. Further work is required to combine these methods to increase segmentation accuracy. One approach we are investigating is to combine algorithms using a meta-algorithmic approach. Each segmentation algorithm computes along with the segmentation a measure of confidence in the segmentation which can be biased on prior information about the presence of artifacts. A meta-algorithm then runs a library of algorithms on a sub-sequence of images to be segmented and chooses the segmentation based on computed confidence measures. Machine learning and testing is performed on a large data base. This research is in collaboration with Brigham and Women Hospital in Boston that provides well over 45,000 frames of data for the study.


Article metrics loading...

Loading full text...

Full text loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error