Cross-Scanner Prostate MRI CAD for Aggressive Cancer Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for diagnosing aggressive prostate cancer using MRI images are less reliable than human radiologists and are not robust across different types of MR scanners, leading to missed diagnoses or unnecessary aggressive treatments.
Innovation Solution
A system and method that utilize a control module to analyze MRI images of the prostate, calculating scores based on apparent diffusion coefficient and contrast agent wash-in/wash-out rates to identify aggressive cancer regions, using logistic regression to determine the presence of cancer, and providing diagnostic feedback to physicians.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If image processing methods are used to recognize signs of aggressive cancer in MRI images, then biopsy targeting is improved, but reliability decreases compared to experienced radiologists
Solution Approach 1:
The patent introduces an intermediary system that combines multiple MRI sequences (T2-weighted, diffusion-weighted, dynamic contrast-enhanced) with automated image processing and radiomics analysis to bridge the gap between raw imaging data and reliable cancer detection, achieving radiologist-level or superior reliability while maintaining ease of operation
Solution Approach 2:
The system performs multiple functions simultaneously: it processes multiple MRI sequences, extracts radiomics features, applies machine learning algorithms, and generates biopsy targeting recommendations, making it a universal solution that works across different scanner types and protocols
2Device complexity
If pre-existing image processing methods are developed using a limited number of MR scanners, then development complexity is reduced, but reliability decreases when used with different MR scanner types
Solution Approach 1:
The system changes parameters by incorporating data from multiple MRI sequences and adjusting radiomics feature extraction to account for variations in scanner types, magnetic field strengths, and imaging protocols, enabling reliable performance across diverse equipment
Solution Approach 2:
The system performs preliminary actions by pre-processing and standardizing images from different scanners before analysis, applying normalization and calibration steps that prepare the data in advance to ensure consistent results across various hardware platforms
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a system and a method for computer-aided detection (CAD) of aggressive prostate cancers. The automatic diagnosis of aggressive prostate cancers is difficult and methods that work with some MRI scanners do not work as well when implemented on images from different scanners. By studying a data base containing MRI data and biopsy results from 265 patients, acquired by 4 different types of MRI scanners, using machine learning techniques, the inventors established a method for automatically determining the presence of aggressive cancers, this methods showing high sensitivity and specificity when implemented on another database containing MRI data from 270 patients, acquired by different MRI scanners than the first database. The method involves feeding MRI images to a system calculating a score for a portion of the prostate and determines that the portion contains an aggressive cancer based on whether a criterion depending on the score is verified.