Kidney Classification via Cortical Segmentation and MRI Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating kidney transplant success are invasive and lack non-invasive solutions for early detection of rejection, which is critical for timely medical intervention in kidney transplants.
Innovation Solution
A computer-aided diagnostic system that analyzes dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted magnetic resonance imaging (DW-MRI) data to classify kidneys as acutely rejected or non-rejected by segmenting renal cortex image data and applying learned models to determine perfusion features, while compensating for motion and intensity variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If biopsy is used to determine kidney transplant rejection, then diagnostic accuracy is improved, but patient invasiveness worsens
Solution Approach 1:
The patent replaces the mechanical biopsy procedure with a non-invasive magnetic resonance imaging (MRI) based diagnostic system. The system uses DCE-MRI and DW-MRI imaging modalities to capture kidney images, then applies computer-aided analysis with learned models to detect rejection without physical tissue sampling, thereby eliminating the harmful effects of invasive biopsy while maintaining diagnostic accuracy
Solution Approach 2:
The patent changes the diagnostic parameters from tissue-based histological analysis to imaging-based physiological parameter analysis. By measuring perfusion parameters (blood flow, blood volume, mean transit time) and diffusion parameters from MRI images, the system achieves accurate rejection detection through non-invasive physiological measurements rather than invasive tissue sampling
2Object-affected harmful factors
If non-invasive imaging methods are used to evaluate kidney transplant, then patient invasiveness is improved, but measurement precision worsens
Solution Approach 1:
The patent segments the kidney into functional regions (cortex and medulla) for separate analysis. By dividing the kidney tissue into distinct anatomical and functional segments, the system can measure perfusion and diffusion parameters specific to each region, improving the precision of rejection detection while maintaining non-invasive imaging methodology
Solution Approach 2:
The patent introduces computer-aided diagnostic systems with learned models as intermediaries between the non-invasive MRI images and the rejection diagnosis. These intelligent systems process complex imaging data, extract relevant features, and provide accurate rejection classification, bridging the gap between non-invasive imaging and precise diagnostic requirements
3Reliability
If manual biopsy and analysis are used, then diagnostic reliability is improved, but productivity worsens
Solution Approach 1:
The patent implements automated computer-aided diagnostic systems that perform self-service analysis of kidney images. The learned models automatically process DCE-MRI and DW-MRI data, extract perfusion and diffusion parameters, segment kidney regions, and provide rejection diagnoses without manual intervention, thereby maintaining high diagnostic reliability while dramatically improving evaluation speed and productivity
Solution Approach 2:
The patent enables continuous monitoring of kidney transplant function through repeated non-invasive MRI scans. The automated analysis system can continuously evaluate perfusion and diffusion parameters over time, providing ongoing surveillance of graft health without the intermittent disruption caused by manual biopsy procedures, thus improving both productivity and diagnostic reliability
Data Source
AI summary
A computer aided diagnostic system and automated method to classify a kidney. Image data for a medical scan that includes image data of a kidney may be received. The kidney image data may be segmented from other image data of the medical scan. One or more iso-contours may be registered for the kidney image data, and renal cortex image data may be segmented from the kidney image data based on the one or more registered iso-contours. The kidney may be classified by analyzing one or more features determined from the segmented renal cortex image data using a learned model associated with the one or more features.