Artificial Intelligence in Diagnostic Imaging: Enhancing Accuracy and Efficiency

Authors

Aung Kyaw, Thandar Hlaing Department of Electrical Engineering, University of Yangon, Myanmar, Department of Mechanical Engineering, Mandalay Technological University, Myanmar Author

Artificial Intelligence, Diagnostic Imaging, Deep Learning, Convolutional Neural Networks (CNN), Radiology, Computer-Aided Detection (CAD).

The integration of Artificial Intelligence (AI), particularly deep learning algorithms, into diagnostic imaging

represents a paradigm shift in radiological practice. This paper examines the potential of AI-powered tools to augment

the capabilities of radiologists by improving diagnostic accuracy, reducing interpretation times, and identifying subtle

patterns beyond human perception. Convolutional Neural Networks (CNNs) are at the forefront of this revolution,

demonstrating exceptional performance in detecting anomalies in mammography, computed tomography (CT), and

magnetic resonance imaging (MRI). This research outlines a methodology for developing and validating a CNN

model for the detection of pulmonary nodules in chest CT scans. The results indicate a significant increase in

detection sensitivity and a decrease in false-negative rates compared to traditional reading methods. The discussion

addresses challenges related to dataset curation, model generalizability, and the critical role of human-AI

collaboration, concluding that AI is poised to become an indispensable second reader in the radiology workflow