The Role of AI Techniques in Diagnosing Health Conditions with Integration of AI

• Published in: 2024 4th International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) pp. 167 - 172
• Main Authors: Viignesh, M. Ragul, Josphin Selsia, A, Bhuvaneswari, M., Pathak, Sudanshu, Yadav, Kanchan, Amirthayogam, G.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14-05-2024
• Subjects: Analytical models; CAM Models; Clinical Applications; Computational modeling; Deep learning; Deep Learning Models; Explainable AI; Human-Centered XAI; Interpretability; Medical Imaging; Medical services; Plagiarism; Radiomics; Reviews; Saliency; XAI Methods
• DOI: 10.1109/ICACITE60783.2024.10617043

Deep learning models for artificial intelligence (AI) have found wide-ranging applications in a variety of fields, most notably healthcare imaging and healthcare chores. Because medical decision-making is so vital, artificial intelligence must be able to mimic human judgment and interpretation abilities. Explainable AI (XAI) becomes an important element, with the goal of revealing how deep learning models function behind the scenes and how decisions are made. The latest XAI methods in healthcare and related medical imaging applications are examined in this study. In order to improve understanding in medical imaging domains, the study highlights techniques that are used to systematically classify different forms of XAI. A particular focus is on tackling difficult XAI problems in medical applications, including recommendations for the creation of better interpretable models using deep learning in medical text and picture analytics. Furthermore, the study delineates possible avenues for exploration in clinical themes, with a particular emphasis on applications related to medical imaging, offering developers and researchers valuable information to consider.