Awareness and Acceptance of Artificial Intelligence in Medical Imaging with Emerging Implications for Precision Drug Therapy

Abstract

Background: Artificial intelligence (AI) is rapidly transforming the field of medical imaging by enhancing diagnostic accuracy, improving workflow efficiency, and supporting clinical decision-making. In recent years, AI applications have extended beyond image interpretation to include therapeutic response evaluation and imagingguided precision drug therapy. The successful implementation of AI technologies in radiology practice largely depends on the awareness, attitudes, and acceptance of radiology professionals who are directly involved in diagnostic and treatment monitoring processes. Aim: To assess the awareness and acceptance of artificial intelligence among radiology professionals and to explore its emerging implications in medical imaging-guided precision drug therapy. Materials and Methods: A cross-sectional descriptive study was conducted among 100 radiology professionals, including radiologists, radiographers, CT and MRI technologists, and radiology students or interns working in hospitals and diagnostic imaging centres. Data were collected using a structured, self-administered questionnaire that comprised demographic details and items related to knowledge, attitudes, and acceptance of AI applications in diagnostic imaging and therapeutic response evaluation. Descriptive statistical analysis was performed, and results were expressed as frequencies and percentages. Results: The study revealed that 78% of participants were aware of AI applications in medical imaging, whereas only 32% had received formal training related to AI technologies. Most respondents demonstrated basic knowledge (52%), while 28% reported good knowledge of AI-based imaging applications. A majority agreed that AI could improve diagnostic accuracy (72%), enhance workflow efficiency (70%), and reduce workload (68%) in radiology departments. Furthermore, 65% of participants believed that AI could support therapeutic response evaluation and precision drug therapy planning. Regarding acceptance, 74% were willing to use AI tools in clinical practice, 76% supported integration of AI into routine workflow, and 82% expressed interest in AI training programs. However, concerns related to job security (40%) and ethical issues such as data privacy and system reliability (35%) were also reported. Conclusion: Radiology professionals demonstrated high awareness and positive acceptance of artificial intelligence in medical imaging, with growing recognition of its role in therapeutic response monitoring and precision drug therapy. Nevertheless, limited formal training and concerns regarding ethical and professional implications highlight the need for structured educational initiatives and institutional support. Enhancing workforce preparedness will be essential for the effective integration of AI technologies into imaging-guided personalized treatment strategies and future healthcare practice.

Ähnliche Arbeiten