In IVUS, not only the lumen of the coronary arteries can be correctly shown but also the atheroma hide within the wall. In clinical research, IVUS has thus allowed progress to be made to provide a more comprehensive perspective and understanding. The cardiovascular arteries are the most common IVUS imagery target. IVUS is used to assess the quantity for atheromatous plaque in the coronary artery at any particular level. In IVUS, regression progress is a special approach for learning. The IVUS image classification using Stochastic Gradient Descent (SGD) algorithm is described in this study. The IVUS images are given to frequency domain for feature extraction and SGD algorithm is used for detection. Experimental results show the performance of proposed system.