Prostate Cancer Predictive Model Using Morphometric Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive tools for prostate cancer, such as the Gleason scoring system, are subjective and lack diverse biomarkers, leading to inaccurate stratification of patients with intermediate-risk disease, resulting in unnecessary treatments and inadequate prediction of indolent tumors.
Innovation Solution
A system using clinical, molecular, and computer-generated morphometric information to develop predictive models that assess the likelihood of prostate cancer being indolent or progressing, incorporating features like minimum spanning tree and fractal dimension from tissue images, and molecular data to provide more objective treatment planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the Gleason scoring system is used to evaluate prostate cancer, then pathologists can assess the level of advancement and aggression of the disease, but the scoring system is subjective and different pathologists may make conflicting interpretations
Solution Approach 1:
The patent replaces the subjective mechanical visual assessment by pathologists with an automated image analysis system using computer algorithms to objectively evaluate tissue architecture and generate morphometric features, thereby eliminating inter-observer variability while maintaining diagnostic accuracy
Solution Approach 2:
The patent transforms the subjective Gleason scoring process into objective quantitative morphometric parameters (e.g., glandular architecture metrics, cellular density measurements) that can be precisely measured and consistently reproduced across different pathologists and laboratories
2Adaptability or versatility
If traditional predictive tools are used for prostate cancer, then treatment decisions can be made, but the tools lack diverse biomarkers and cannot accurately stratify patients with intermediate-risk disease
Solution Approach 1:
The patent combines multiple data sources including clinical parameters, molecular biomarkers, and computer-generated morphometric features from tissue images into an integrated predictive model, creating a comprehensive assessment tool that leverages the strengths of each data type to improve patient stratification accuracy
Solution Approach 2:
The patent creates a composite predictive model that integrates heterogeneous data types (clinical, molecular, morphometric) analogous to composite materials, where each component contributes unique information that enhances the overall predictive performance beyond what any single data type could achieve alone
3Reliability
If aggressive treatment is provided to all prostate cancer patients, then disease control may be improved, but unnecessary treatments are administered to patients with indolent tumors
Solution Approach 1:
The patent applies predictive modeling and risk stratification before treatment decisions are made, allowing clinicians to identify patients with indolent disease who are unlikely to benefit from aggressive treatment, thereby preventing unnecessary interventions and their associated side effects while maintaining appropriate treatment for high-risk patients
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Clinical information, molecular information and/or computer-generated morphometric information is used in a predictive model for predicting the occurrence of a medical condition. In an embodiment, a model predicts whether a patient is likely to have a favorable pathological stage of prostate cancer, where the model is based on features including one or more (e.g., all) of preoperative PSA, Gleason Score, a measurement of expression of androgen receptor (AR) in epithelial and stromal nuclei and/or a measurement of expression of Ki67-positive epithelial nuclei, a morphometric measurement of a ratio of area of epithelial nuclei outside gland units to area of epithelial nuclei within gland units, and a morphometric measurement of area of epithelial nuclei distributed away from gland units. In some embodiments, quantitative measurements of protein expression in cell lines are utilized to objectively assess assay (e.g., multiplex immunofluorescence (IF)) performance and/or to normalize features for use within a predictive model.