Thesis Abstract

Abstract
Recent advancements in artificial intelligence (AI) have revolutionized the field of radiography by enabling automated detection of pathologies in radiographic images. This thesis explores the utilization of AI algorithms for the automated detection of various pathologies in radiographic images, aiming to enhance diagnostic accuracy, efficiency, and patient outcomes. The study focuses on developing and implementing AI-based models that can accurately detect and classify common pathologies, such as fractures, tumors, and abnormalities in different anatomical regions. The research begins with a comprehensive review of the existing literature on AI applications in radiography, highlighting the evolution of AI technologies in medical imaging and their potential impact on diagnostic radiology. The literature review also discusses the challenges, limitations, and ethical considerations associated with the integration of AI in radiographic imaging. The methodology section outlines the research design, data collection methods, and AI algorithms used for the automated detection of pathologies in radiographic images. The study utilizes a dataset of radiographic images annotated by expert radiologists to train and validate the AI models. Various deep learning techniques, including convolutional neural networks (CNNs) and transfer learning, are employed to develop robust and accurate pathology detection models. The findings of the study demonstrate the effectiveness of AI algorithms in detecting and classifying pathologies in radiographic images with high accuracy and sensitivity. The AI models exhibit promising results in identifying fractures, tumors, and other abnormalities, outperforming traditional image analysis methods in terms of efficiency and diagnostic accuracy. In the discussion section, the implications of the study findings are analyzed in relation to clinical practice, patient care, and the future of radiography. The potential benefits of integrating AI-based pathology detection systems in radiology departments are highlighted, including improved workflow efficiency, reduced diagnostic errors, and enhanced patient outcomes. In conclusion, this thesis contributes to the growing body of research on AI applications in radiography by demonstrating the feasibility and effectiveness of utilizing AI for automated detection of pathologies in radiographic images. The study underscores the potential of AI technologies to transform diagnostic radiology practices and improve healthcare delivery. Future research directions and recommendations for the implementation of AI-based pathology detection systems in clinical settings are also discussed. Keywords Artificial intelligence, Radiography, Pathology detection, Deep learning, Convolutional neural networks, Medical imaging, Diagnostic radiology, Healthcare technology.

Thesis Overview