TWO NOVEL ACM (ACTIVE CONTOUR MODEL) METHODS FOR INTRAVASCULAR ULTRASOUND IMAGE SEGMENTATION

• Published in: AIP conference proceedings Vol. 1211; no. 1
• Main Authors: Chen, Chi Hau, Potdat, Labhesh, Chittineni, Rakesh
• Format: Journal Article
• Language: English
• Published: United States 01.01.2010
• Subjects: ACCURACY; ALGORITHMS; CORRECTIONS; DIAGNOSTIC USES; DISEASES; IMAGE PROCESSING; MATHEMATICAL LOGIC; NEURAL NETWORKS; OPERATION; PROCESSING; RADIOLOGY AND NUCLEAR MEDICINE; SOUND WAVES; ULTRASONIC WAVES; USES; VASCULAR DISEASES
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/1.3362467

One of the attractive image segmentation methods is the Active Contour Model (ACM) which has been widely used in medical imaging as it always produces sub-regions with continuous boundaries. Intravascular ultrasound (IVUS) is a catheter based medical imaging technique which is used for quantitative assessment of atherosclerotic disease. Two methods of ACM realizations are presented in this paper. The gradient descent flow based on minimizing energy functional can be used for segmentation of IVUS images. However this local operation alone may not be adequate to work with the complex IVUS images. The first method presented consists of basically combining the local geodesic active contours and global region-based active contours. The advantage of combining the local and global operations is to allow curves deforming under the energy to find only significant local minima and delineate object borders despite noise, poor edge information and heterogeneous intensity profiles. Results for this algorithm are compared to standard techniques to demonstrate the method's robustness and accuracy. In the second method, the energy function is appropriately modified and minimized using a Hopfield neural network. Proper modifications in the definition of the bias of the neurons have been introduced to incorporate image characteristics. The method overcomes distortions in the expected image pattern, such as due to the presence of calcium, and employs a specialized structure of the neural network and boundary correction schemes which are based on a priori knowledge about the vessel geometry. The presented method is very fast and has been evaluated using sequences of IVUS frames.