Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186391,
        author = {Aryan A. Dalvi and Pruthvi R. Patel and Prasad V. Reddy and Prof. Swati R. Bhatt},
        title = {Gen-AI For Medical Diagnosis and Drug Discovery Using UNETR},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {1678-1682},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186391},
        abstract = {Generative Artificial Intelligence (GenAI) is poised to revolutionize medicine, yet its adoption is challenged by significant barriers in clinical diagnosis and drug discovery. Deep learning has shown promise, but two major issues limit its clinical application: the "black-box" nature of AI predictions and concerns regarding their reliability and accuracy. This review paper surveys an integrated framework that connects high-fidelity medical image segmentation for diagnosis with de novo molecule generation for therapeutic design. We analyze advanced architectures like the UNETR (UNEt TRansformers) for volumetric segmentation and explore the role of specialized platforms like MONAI in their implementation. To address model opacity, the importance of Explainable AI (XAI) techniques in building trust and validating computational drug discovery is examined. This integrated approach surveys a path forward that addresses not only performance but also the critical needs for efficiency, transparency, and interpretability across the diagnosis-to-treatment pipeline.},
        keywords = {Generative AI, Medical Diagnosis, Drug Discovery, Deep Learning, UNETR, Medical Image Segmentation, MONAI, Explainable AI (XAI), De Novo Molecule Generation.},
        month = {November},
        }