Abstract
Purpose To examine the role of artificial intelligence (AI) in multiparametric magnetic resonance (MR) imaging for precision oncology, with a focus on automated tumor segmentation, treatment response prediction, and workflow efficiency.
Method A literature review was conducted to examine current evidence on AI applications in multiparametric MR imaging for oncology. Studies evaluating deep learning models for tumor segmentation, longitudinal imaging analysis, and treatment response prediction were synthesized using a thematic analysis approach.
Results Three primary themes emerged: (a) AI-driven tumor segmentation improved accuracy, reproducibility, and efficiency across multiparametric MR sequences; (b) deep learning models enhanced prediction of treatment response through longitudinal pre- and posttreatment imaging analysis; and (c) AI-supported workflows reduced radiologist workload while improving clinical decision-making and personalized care.
Discussion The findings suggest that AI is transforming precision oncology by improving the consistency and efficiency of multiparametric MR image analysis. Advanced deep learning models, particularly nnU-Net, demonstrated strong performance in automated tumor segmentation, while longitudinal imaging analyses enabled earlier prediction of therapeutic response. Together, these advances support more personalized treatment planning and more efficient clinical workflows, although continued validation across diverse patient populations and imaging protocols is needed.
Conclusion AI-enhanced multiparametric MR imaging has significant potential to improve tumor characterization, treatment response assessment, and workflow efficiency in precision oncology. Continued research should focus on clinical validation and broader implementation to support routine use in oncologic imaging.
DOI
https://doi.org/10.52519/00265
Graduation Date
Summer 8-7-2026
Document Type
Poster
Degree Name
Master of Science in Radiologic Science
Program
The School of Health Professions
Faculty Advisor
Kevin R. Clark
Director, Graduate Program
William A. Undie
Dean
Kimberly Hoggatt Krumwiede
Recommended Citation
Marwaha, M. K. AI-Driven Multi-Modal MR for Precision Oncology. [poster]. University of Texas MD Anderson Cancer Center; 2026. https://doi.org/10.52519/00265
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
