Related Experiment Video
Updated: Nov 23, 2025
08:05
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
887
Radiomic features for prostate cancer grade detection through formal verification.
Antonella Santone1, Maria Chiara Brunese1, Federico Donnarumma1
1Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, Campobasso, Italy.
La Radiologia Medica
|January 4, 2021
Summary
This study introduces a novel method using magnetic resonance imaging (MRI) radiomic features to detect prostate cancer grade. The approach achieved high accuracy, demonstrating its potential for non-invasive cancer grading.
Area of Science:
- Radiology
- Oncology
- Computer Science
Background:
- Prostate cancer is a leading cancer in men, often asymptomatic early.
- Accurate grading is crucial for treatment decisions.
- Non-invasive detection methods are highly desirable.
Purpose of the Study:
- To develop and validate a methodology for detecting prostate cancer grade.
- To utilize non-invasive, shape-based radiomic features from MRI.
- To assess the feasibility of automated cancer grading.
Main Methods:
- A dataset of 112 patient coronal MRI scans was used.
- Magnetic resonance slices were converted into a formal model.
- Model checking was employed to verify cancer grade-related properties.
Main Results:
- The methodology achieved an average specificity of 0.97.
- An average sensitivity of 1 was obtained.
- The approach demonstrated high performance in distinguishing cancer grades.
Conclusions:
- Radiomics combined with formal verification is effective for Gleason grade group detection.
- This non-invasive method shows promise for prostate cancer management.
- The study highlights the potential of integrating imaging features with formal methods.
