Biliary Tree Quantification via Volumetric Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnostic techniques for assessing the biliary tree, such as MRCP and ERCP, are invasive and non-invasive but lack accuracy in detecting small duct PSC, leading to underdiagnosis of liver diseases like Primary Sclerosing Cholangitis due to sub-optimal views and depth information issues.
Innovation Solution
A method and apparatus for generating quantitative data from volumetric medical imaging scan data, including segmentation and parametric modeling of biliary tree structures to provide enhanced structural parameters like center-line positions, orientations, and branching points, using multi-scale Hessian-based tubular enhancement and pattern detection to improve visualization and detection of strictures and dilatations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If MRCP or ERCP procedures are used to assess the biliary tree, then the clinician can obtain views of biliary ducts, but the diagnostic accuracy is reduced due to sub-optimal views and lack of depth information
Solution Approach 1:
The patent transforms 2D projection data into 3D volumetric representations of the biliary tree. By reconstructing the biliary structures in three dimensions, the system recovers depth information that is lost in conventional 2D MRCP and ERCP images, enabling clinicians to assess spatial relationships and ductal morphology with significantly improved accuracy.
Solution Approach 2:
The patent segments the biliary tree into distinct tubular structures from the volumetric data. This segmentation process separates the biliary ducts from surrounding tissues and organs, creating clear, isolated 3D models that enhance diagnostic accuracy by eliminating the overlap and occlusion problems present in conventional imaging.
2Measurement precision
If ERCP is used to detect small duct PSC, then the clinician can obtain detailed biliary views, but the procedure becomes invasive and carries risks
Solution Approach 1:
The patent creates accurate 3D digital copies of the biliary tree structures from non-invasive MRCP data. These virtual models replicate the anatomical details previously only obtainable through invasive ERCP, allowing clinicians to diagnose small duct PSC without subjecting patients to the risks of sedation, anesthesia, and procedural complications associated with ERCP.
Solution Approach 2:
The patent replaces the mechanical invasive ERCP procedure with a computational 3D reconstruction system. Instead of physically inserting endoscopes and catheters into the patient's body, the system uses image processing algorithms to generate detailed biliary tree models from external imaging data, eliminating all invasive elements while preserving diagnostic capability.
3Ease of operation
If conventional 2D visualization methods are used, then the data presentation is simple, but the clinician cannot assess spatial relationships and depth of biliary structures
Solution Approach 1:
The patent enhances 2D display devices to present 3D volumetric data of the biliary tree. By rendering three-dimensional structures on conventional 2D screens using techniques such as shaded surface displays and cross-sectional views, the system preserves spatial information and depth perception while maintaining ease of operation on standard medical imaging equipment.
Data Source
Figure 1~9
Figure 2~5
Figure 3
AI summary
A method (200) and apparatus (1100) for generating quantitative data for biliary tree structures from volumetric medical imaging scan data. The method comprises performing segmentation (230; 300) of a volume of the medical imaging scan data to identify tubular biliary structures within the volume of the medical imaging scan data; for at least one segmented tubular biliary structure within the volume of the medical imaging scan data, computing (240; 800) at least one set of quantitative structural parameters for at least one location along the length of the tubular biliary structure; and outputting (250) quantitative biliary tree data comprising the at least one set of quantitative structural parameters for the at least one segmented tubular biliary structure.