Automated Target Anatomy Localization Using Landmark Confidence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical imaging preparation is time-consuming and prone to errors due to the difficulty in precisely and quickly determining the position of target anatomy, especially when it is hidden from the camera, leading to reliability issues and increased workload for medical assistants.
Innovation Solution
A computer-implemented method that uses a series of images to determine the position of anatomically related landmarks and calculates a confidence level to accurately locate the target anatomy, even when obscured, by utilizing previous images with high confidence levels and image analysis algorithms like deep convolutional neural networks to ensure precise positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to determine the position of target anatomy, then personnel can perform the task, but the process is time-consuming and prone to errors
Solution Approach 1:
The patent replaces manual mechanical positioning methods with an automated computer-implemented method that uses image processing and machine learning algorithms to detect landmarks and determine target anatomy position, thereby increasing both speed and reliability
Solution Approach 2:
The system enables self-service by automatically capturing images, detecting landmarks, calculating positions, and providing guidance without requiring manual intervention from medical personnel for the positioning determination process
2Measurement precision
If the target anatomy is hidden from the camera, then imaging can be performed, but the position determination becomes unreliable
Solution Approach 1:
The system performs preliminary actions by capturing a series of images before the target anatomy becomes hidden, detecting landmarks in advance when they are visible, and storing this information for later use when the anatomy is obscured
Solution Approach 2:
The patent uses anatomical landmarks as intermediaries that can be detected even when the target anatomy itself is hidden. These landmarks serve as proxy markers that allow indirect determination of the target position through spatial relationships
3Reliability
If multiple tasks are required for preparation, then comprehensive preparation can be achieved, but the workload and time required increase
Solution Approach 1:
The patent merges multiple separate preparation tasks into a single integrated computer-implemented process that simultaneously performs image capture, landmark detection, position calculation, and guidance provision, thereby reducing total preparation time while maintaining quality
Solution Approach 2:
The system performs multiple functions through a single automated method: capturing images, detecting landmarks, determining positions, calculating confidence levels, and providing guidance - replacing multiple manual operations with one multi-functional system
Data Source
AI summary
A computer-implemented method for preparing a subject in medical imaging, comprising: obtaining a series of images of a region of interest comprising at least a part of the subject, wherein the series of images comprises at least a first image and at least a subsequent, second image (S10); determining a position of at least one landmark from the series of images, wherein the at least one landmark is anatomically related to a target anatomy (S20); determining a confidence level assigned to the position of the at least one landmark (S30); determining the position of the target anatomy based on the position of the at least one landmark, and the confidence level (S40); providing the position of the target anatomy for preparing the subject in medical imaging (S50).