Predictive Model Integrating Morphometric and Molecular Data for Prostate Cancer Recurrence

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical diagnostic tools for predicting prostate cancer recurrence and treatment outcomes are limited in accuracy and do not effectively utilize tissue-level architectural information, relying heavily on subjective Gleason scoring and serum-based PSA screening, which results in uncertain predictions for a significant portion of patients.

Innovation Solution

A predictive model that combines clinical, molecular, and computer-generated morphometric information using support vector machines and neural networks to analyze tissue images, providing a more objective and accurate assessment of prostate cancer recurrence and overall survival probabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional nomograms and PSA screening tests are used for prediction, then the diagnostic process is simple and quick, but the predictive accuracy is low and cannot effectively distinguish between patients with different outcomes

Engineering Contradiction:
Improvepredictive accuracyVSAvoiddiagnostic system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple data sources including digital pathology images, genomic data, clinical variables, and morphometric features into an integrated predictive model. This merging of heterogeneous data types enables significantly improved predictive accuracy for prostate cancer outcomes while compensating for the increased complexity through automated processing pipelines.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces computer-aided morphometric analysis as an intermediary layer between traditional pathology and clinical decision-making. This intermediary automatically extracts quantitative features from tissue images, providing objective measurements that bridge the gap between subjective visual assessment and predictive modeling requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If subjective Gleason scoring by pathologists is used, then the diagnostic process is quick and requires minimal equipment, but the measurement precision varies between different pathologists and is inconsistent

Engineering Contradiction:
Improvescoring consistencyVSAvoiddiagnostic time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical/subjective process of visual Gleason scoring with an automated computer-aided morphometric analysis system. This system uses image processing algorithms to objectively measure tissue architecture features, eliminating inter-observer variability while maintaining rapid diagnosis through automated processing of digital pathology images.

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

Solution Approach 2:

The patent creates a digital copy of the tissue sample through whole-slide imaging, allowing multiple independent analyses of the same specimen. This digital replication enables both automated morphometric measurements and preservation of the original slide, permitting repeated assessments without additional tissue processing time.

Inventive Principle:
Principle #26Copying

3Measurement precision

If detailed morphometric analysis of tissue images is performed, then the predictive accuracy improves significantly, but the computational resources and processing time required increase substantially

Engineering Contradiction:
Improvepredictive accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the most discriminative morphometric features from complete tissue image analysis using automated feature selection algorithms. By identifying and extracting only the key predictive features rather than analyzing all possible image parameters, the system achieves high predictive accuracy while substantially reducing computational resource requirements compared to exhaustive image analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

4Adaptability or versatility

If comprehensive multi-parameter predictive modeling is implemented, then the ability to predict both biochemical and clinical outcomes is improved, but the device complexity and data processing requirements increase

Engineering Contradiction:
Improveprediction scopeVSAvoidmodel complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent develops a unified predictive model framework that simultaneously predicts multiple outcomes including biochemical recurrence, clinical progression, and overall survival using the same integrated set of input features. This multi-functional model eliminates the need for separate predictive systems for different outcomes, managing complexity through a single comprehensive analytical platform.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2145276B1System and method for handling, diagnose and predict the occurrence of a medical condition
Publication Date: 2020.06.10 FUNDACAO D ANNA SOMMER CHAMPALIMAUD E DR CARLOS
  • EP2145276B1 patent drawingFigure 1A
  • EP2145276B1 patent drawingFigure 1B
  • EP2145276B1 patent drawingFigure 1C

AI summary

Methods and systems are provided that use clinical information, molecular information and computer-generated morphometric information in a predictive model for predicting the occurrence (e.g., recurrence) of a medical condition, for example, cancer. In an embodiment, a model that predicts prostate cancer recurrence is provided, where the model is based on features including one or more (e.g., all) of biopsy Gleason score, seminal vesicle invasion, extracapsular extension, preoperative PSA, dominant prostatectomy Gleason grade, the relative area of AR+ epithelial nuclei, a morphometric measurement of epithelial nuclei, and a morphometric measurement of epithelial cytoplasm. In another embodiment, a model that predicts clinical failure post-prostatectomy is provided, wherein the model is based on features including one or more (e.g., all) of dominant prostatectomy Gleason grade, lymph node invasion status, one or more morphometric measurements of lumen, a morphometric measurement of cytoplasm, and average intensity of AR in AR+/AMACR- epithelial nuclei.