Prostate Cancer Staging with Spatially Registered MRI and Supervised Target Detection

Solution Overview

Problem

Current methods for non-invasive prostate cancer staging and tumor detection using MRI are limited by variability, require extensive radiologist expertise, and fail to accurately assess tumor aggressiveness and metastases, often relying on fixed spatial windows and single metric summaries, which can miss small lesions and vary in effectiveness across patients.

Innovation Solution

The use of spatially registered multi-parametric MRI with supervised target algorithms and multispectral signatures, combined with a Whitening-DeWhitening transform, to non-invasively detect and score tumors, measure their size, and highlight metastases, employing color displays to enhance tumor visibility and heterogeneity assessment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If fixed spatial windows and single metric summaries are used for tumor detection, then the method is simple to implement, but small lesions are missed and detection accuracy decreases

Engineering Contradiction:
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent divides the prostate volume into multiple small, non-overlapping cubic segments (e.g., 5mm³ voxels) rather than using fixed spatial windows. Each segment is independently evaluated using multi-parametric MRI features, allowing detection of small lesions throughout the entire volume without missing areas that would be overlooked by fixed window approaches.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from single metric summaries to multi-dimensional analysis by evaluating multiple MRI parameters (T2-weighted, DWI, DCE) simultaneously across all segmented volumes. This multi-parametric approach adds dimensions of analysis that improve detection accuracy while maintaining computational feasibility through systematic segmentation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If multi-parametric MRI with spatially registered images is used, then sensitivity and specificity increase, but device complexity and processing requirements increase

Engineering Contradiction:
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

By segmenting the prostate into small cubic volumes, the patent simplifies the processing of multi-parametric MRI data. Each small segment requires less computational resources to analyze than the entire prostate volume, making the complex multi-parametric analysis more manageable while improving detection reliability through comprehensive coverage.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality analysis by evaluating each segmented volume independently with its own multi-parametric features. This localized approach allows the system to handle complexity at the segment level rather than requiring simultaneous processing of the entire prostate, improving both reliability and computational efficiency.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If invasive biopsy procedures are used for Gleason scoring, then accurate tumor aggressiveness assessment is achieved, but patient discomfort and potential complications increase

Engineering Contradiction:
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical invasive biopsy procedure with a non-invasive MRI-based computational analysis system. By using multi-parametric MRI features and machine learning algorithms to assess Gleason scores, the system eliminates needle insertions and associated patient discomfort while maintaining accurate tumor aggressiveness assessment.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual model of the prostate tumor characteristics using MRI data, which serves as a copy of the actual tissue properties. This virtual representation allows Gleason scoring to be performed on the copied data rather than requiring physical tissue sampling, eliminating invasive procedures while preserving diagnostic accuracy.

Inventive Principle:
Principle #26Copying

4Measurement precision

If radiologist expertise is required for tumor detection, then detection accuracy improves, but the method is difficult to standardize and reproduce across different clinicians

Engineering Contradiction:
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements a self-service system where the computational algorithm automatically performs tumor detection and Gleason scoring without requiring radiologist intervention. The system uses machine learning models trained on MRI data to independently evaluate each segmented volume, providing standardized results that are reproducible across different clinical settings without relying on individual radiologist expertise.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent transforms the detection process from subjective radiologist assessment to objective parameter-based analysis. By converting MRI data into quantitative parameters and applying consistent computational thresholds across all cases, the system achieves both high detection accuracy and full standardization, eliminating variability between different clinicians.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20200015734A1“One Stop Shop” for Prostate Cancer Staging using Imaging Biomarkers and Spatially Registered Multi-Parametric MRI
Publication Date: 2020.01.16
  • US20200015734A1 patent drawing
  • US20200015734A1 patent drawing
  • US20200015734A1 patent drawing

AI summary

The purpose of this embodiment is to describe a “one stop shop” for staging prostate cancer and a novel application of supervised target detection algorithms to spatially registered multiparametric MRI images in order to non-invasively detect, locate, and score prostate cancer at the voxel level and measure the tumor volume and assign color to the spatially registered MRI to highlight and display tumors, and detect metastases (specifically in the seminal vesicle). To test the approach advanced by the embodiment, a retrospective study analyzes MRI from 26 patients that had also undergone robotic prostatectomy. Whole-mount sections were stained for histopathologic evaluation and matched to the MRI. The stained sections were independently reviewed by pathologists. All slices of various types of MRI were spatially registered and stitched together. Signatures or image-based biomarkers from registered multiparametric MRI training sets were extracted. The untransformed and “whitened-dewhitened” transformed signatures (based on the statistics of the normal prostate) from a battery of Gleason scores were applied to the stitched hypercubes. Each voxel in the supervised target map was polled to find the signature that achieved the highest Gleason score likelihood. The Gleason scoring and volume measurements were quantitatively validated by comparing the results from 10 patients with prostate adenocarcinoma to the pathologist's assessment of the histology. High correlation between supervised target detection using “whitened-dewhitened” transformed signatures and histology was observed (p<0.02). Assigning red, green, and blue to the registered MRI hypercubes effectively displays tumors relative to normal prostate tissue. With only minor modifications, supervised target detection and transformation of target signatures and color display may be used to find metastases, specifically to the seminal vesicles. This novel application of supervised target detection algorithms to spatially registered multi-parametric MRI non-invasively detects, locates, and scores prostate cancer at each voxel level and measures the tumor volume.