Atherosclerosis, characterized by the deposition of fats, cholesterol, and other substances along arterial walls, poses a significant risk to cardiovascular health, leading to arterial narrowing and potentially fatal events such as heart attacks and strokes. Intravascular ultrasound (IVUS) imaging plays a crucial role in cardiovascular medicine, offering high-resolution views of arterial cross-sections. Accurate segmentation of IVUS images is essential for quantifying pathological features such as atherosclerotic plaque, which is necessary for assessing disease burden, planning therapeutic procedures, and evaluating responses to medications. This paper introduces a novel approach leveraging machine learning and deep learning techniques to segment atherosclerotic plaques in IVUS images. The proposed methodology incorporates active learning techniques into the segmentation pipeline to strategically select the most informative data points for training, thereby enhancing model performance and mitigating data dependency. Experimental results demonstrate promising outcomes, achieving comparable segmentation performance measured by mean Intersection over Union (IoU) using a significantly smaller portion of the dataset. This highlights the efficacy of our methodology in optimizing segmentation performance while reducing reliance on extensive data. We will release the dataset on https://iab-rubric.org/resources .