Abstract

The significance of medical imaging in disease diagnosis and treatment is undeniable, with Computed Tomography (CT) imaging leading the forefront. ML reveals organ abnormalities, lung conditions, and skull changes clinically. This investigation focuses on the application of machine learning techniques within medical imaging, specifically targeting the assessment of CT image quality in vital anatomical regions such as the abdomen, chest, and skull. The primary goal is to forge a robust and precise technique that can thoroughly evaluate CT image quality, offering an early identification mechanism for potential diagnostic discrepancies and elevating the standards of patient care. This study harnesses state-of-the-art machine learning approaches to comprehensively explore the efficacy and dependability of CT imaging modalities. Utilizing Machine Learning to discern effects of CT scan parameters on DLP and CTDI_vol, uncovering hidden patterns in images. There are promising prospects for refining diagnostic precision, streamlining patient care protocols, and ultimately augmenting clinical outcomes. This investigation into ML-driven CT image quality analysis yielded promising outcomes. ML reveals how CT scan parameters influence DLP and CTDIvol, guiding adjustments for optimal image quality and patient safety. This research not only substantiates the remarkable capabilities of machine learning but also underscores its pivotal role in reshaping the landscape of medical imaging. The result underscores the need for refined ML-based CT image quality analysis techniques, aiming to bridge existing gaps and deliver more precise diagnoses while advancing healthcare delivery. The implications of the findings (The highest mean scan length are 64.36cm, 62cm, and 169.01cm for abdomen, chest, and skull respectively while the highest mean pitch are 1.60,1.63 and 0.65 for abdomen, chest and skull respectively)  transcend conventional radiology domains, signaling the advent of a novel era where artificial intelligence collaborates synergistically with human expertise to attain unprecedented excellence in healthcare delivery.