Using MRI and AI to Improve Bladder Cancer Treatment Monitoring
Author Information
Author(s): Arita Yuki, Kwee Thomas C., Akin Oguz, Shigeta Keisuke, Paudyal Ramesh, Roest Christian, Ueda Ryo, Lema-Dopico Alfonso, Nalavenkata Sunny, Ruby Lisa, Nissan Noam, Edo Hiromi, Yoshida Soichiro, Shukla-Dave Amita, Schwartz Lawrence H.
Primary Institution: Memorial Sloan Kettering Cancer Center, New York, NY USA
Hypothesis
Can multiparametric MRI and artificial intelligence enhance the prediction and monitoring of treatment response in bladder cancer?
Conclusion
The study suggests that integrating quantitative imaging biomarkers and AI can significantly improve the assessment of treatment responses in bladder cancer.
Supporting Evidence
- Quantitative imaging biomarkers from MRI can outperform traditional methods for bladder cancer treatments.
- AI enhances the accuracy of MRI segmentation and feature extraction.
- Predictive models combining imaging biomarkers and clinical data can improve treatment outcomes.
- Multicenter studies validate the clinical utility of radiomics and quantitative imaging biomarkers.
- Standardized applications of MRI and AI are essential for reliable clinical practice.
Takeaway
This study shows that special MRI techniques and computer programs can help doctors see how well bladder cancer treatments are working, making it easier to help patients.
Methodology
The review discusses the use of multiparametric MRI and AI in assessing bladder cancer treatment responses, focusing on quantitative imaging biomarkers and radiomics.
Limitations
The integration of these techniques into clinical practice faces challenges such as standardization and validation across different settings.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website