Predicting Prostate Cancer Treatment Response with MRI
Author Information
Author(s): Kathrine Røe, Manish Kakar, Therese Seierstad, Anne H. Ree, Dag R. Olsen
Primary Institution: The Norwegian Radium Hospital, Oslo University Hospital
Hypothesis
The combination of several functional parameters increases the predictive power of therapy response in prostate cancer.
Conclusion
The study shows that combining early changes in multiple functional MRI parameters can provide valuable information about therapy response in prostate cancer.
Supporting Evidence
- The combination of ADC, Ktrans, volumes, and PSA predicted treatment response with a correlation coefficient of 0.85.
- ADC, volumes, and PSA as inputs revealed a correlation coefficient of 0.54.
- Ktrans, volumes, and PSA gave a correlation coefficient of 0.66.
Takeaway
Researchers used MRI to see how well prostate cancer treatments work. They found that looking at different MRI results together helps predict if the treatment is working.
Methodology
The study used an artificial neural network to analyze MRI data from mice with prostate cancer to predict treatment response.
Potential Biases
Potential for overfitting the neural network due to the complexity of the data.
Limitations
The study was conducted in a preclinical model, which may not fully represent human patients.
Participant Demographics
Male, sexually mature BALB/c nude mice, 6-8 weeks old.
Statistical Information
P-Value
p < 0.001
Statistical Significance
p < 0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website