3D Body Surface Model Estimation for Automated Patient Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual patient positioning in medical imaging is time-consuming and costly due to variations in patient body shapes and sizes, and existing solutions require prior medical imaging scans for alignment.
Innovation Solution
A computer-implemented method and system that estimate a patient's body surface model from three-dimensional camera data, including anatomical landmarks and body regions, to automate the patient positioning process by segmenting sensor image data, categorizing body pose, parsing anatomical features, and estimating the body surface model within the medical imaging scanner's coordinate frame.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual patient positioning is used to accommodate variations in body shapes and sizes, then positioning accuracy can be achieved, but the process becomes time-consuming and costly
Solution Approach 1:
The patent creates a 3D digital copy of the patient's body surface using depth camera data. This digital model replicates the patient's unique body geometry, allowing automated positioning calculations to be performed on the copy rather than requiring manual measurement and positioning of the actual patient, thereby reducing time while maintaining accuracy
Solution Approach 2:
The patent replaces the manual mechanical positioning process with an automated computer vision system. Instead of technicians physically positioning patients based on visual estimation, the system uses depth cameras to capture 3D data and algorithms to automatically determine optimal positioning, eliminating the time-consuming manual process while preserving positioning precision
2Productivity
If motion-sensing devices are used for patient alignment, then positioning efficiency is improved, but the system requires prior medical imaging scans as a prerequisite
Solution Approach 1:
The patent extracts the essential positioning information directly from the depth camera data capturing the patient's body surface geometry. By taking out only the necessary surface features and anatomical landmarks needed for positioning, the system eliminates the requirement for prior full medical imaging scans, reducing system complexity while maintaining positioning efficiency
Solution Approach 2:
The patent performs preliminary 3D body surface scanning and anatomical landmark detection before the actual positioning process. This preliminary action captures all necessary positioning information in advance, allowing the subsequent positioning to proceed without requiring additional prior medical imaging scans, thus improving efficiency while managing system complexity
3Loss of time
If automated positioning is implemented without prior scans, then time and costs are reduced, but measurement precision may be compromised
Solution Approach 1:
The patent introduces a 3D body surface model as an intermediary between the depth camera data and the organ position estimation. This model serves as a mediator that captures detailed surface geometry and anatomical landmarks, enabling accurate inference of internal organ positions without requiring direct prior imaging scans, thus maintaining precision while reducing time
Solution Approach 2:
The patent transitions from 2D medical imaging scans to 3D depth camera data for body surface modeling. By utilizing the additional depth dimension, the system captures comprehensive spatial information about body surface geometry and anatomical landmarks, enabling accurate automated positioning and organ position estimation without relying on prior 2D scans, thereby maintaining measurement precision while reducing time and costs
Data Source
AI summary
A method for estimating a body surface model of a patient includes: (a) segmenting, by a computer processor, three-dimensional sensor image data to isolate patient data from environmental data; (b) categorizing, by the computer processor, a body pose of the patient from the patient data using a first trained classifier; (c) parsing, by the computer processor, the patient data to an anatomical feature of the patient using a second trained classifier, wherein the parsing is based on a result of the categorizing; and (d) estimating, by the computer processor, the body surface model of the patient based on a result of the parsing. Systems for estimating a body surface model of a patient are described.