3D Ultrasound Applicator Visualization via Probability Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In brachytherapy, determining the optimal positioning of a radiation source within a patient's body using two-dimensional ultrasound images is inefficient, particularly in developing countries where advanced imaging modalities are limited, requiring clinicians to acquire multiple images to ensure accurate visualization of the applicator in a three-dimensional ultrasound volume.
Innovation Solution
A device and method that automatically determine a final two-dimensional image by iteratively adjusting the scan direction based on probability maps, using an applicator pre-trained classification method to identify the best cross-sectional view of the applicator within a three-dimensional ultrasound volume, reducing the need for manual browsing through orthogonal planes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clinicians manually browse through multiple orthogonal ultrasound images to find the best view of the applicator, then they can ensure accurate visualization, but the time required for image acquisition and review increases significantly
Solution Approach 1:
The system automatically changes the orientation parameter of the ultrasound volume by computing multiple rotated views (e.g., axial, coronal, sagittal planes and oblique angles) to present the applicator from different perspectives, eliminating the need for manual browsing while maintaining visualization accuracy
Solution Approach 2:
The invention transforms the problem from two-dimensional image selection to three-dimensional volume rendering by generating virtual cross-sectional views through mathematical rotation and interpolation of the 3D ultrasound dataset, allowing optimal visualization without additional physical probe movements
2Loss of information
If multiple sets of ultrasound images are acquired to ensure the object of interest is visible, then complete information is obtained, but the clinical workflow efficiency decreases
Solution Approach 1:
A single three-dimensional ultrasound volume acquisition serves multiple purposes: it contains all necessary anatomical information and allows generation of any desired two-dimensional cross-sectional view through computational rotation, making one scan replace multiple traditional scanning planes
Solution Approach 2:
The complete 3D volume is acquired and processed in advance before the clinical decision-making moment, pre-computing all possible view orientations so that the clinician receives ready-to-use optimal images without needing to perform additional scanning or manual search during the procedure
3Ease of manufacture
If conventional ultrasound imaging methods are used in developing countries, then cost burden is reduced, but the complexity of acquiring and interpreting multiple images increases
Solution Approach 1:
The system performs automatic classification and optimization of the 3D ultrasound volume using machine learning algorithms that autonomously identify the applicator, determine optimal viewing angles, and generate the best 2D cross-sectional views without requiring advanced operator skills or manual intervention, reducing the complexity burden on clinicians in resource-constrained settings
Data Source
AI summary
The present invention relates to a device (2) and a method (100) for determining at least one final two-dimensional image or slice for visualizing an object of interest in a three-dimensional ultrasound volume. The method (100) for determining at least one final two-dimensional image, the method comprises the steps: a) providing (101) a three-dimensional image of a body region of a patient body, wherein an applicator configured for fixating at least one radiation source is inserted into the body region; b) providing (102) an initial direction, in particular by randomly determining the initial direction within the three-dimensional image; c) repeating (103) the following sequence of steps s1) to s4): s1) determining (104), via a processing unit, a set-direction within the three-dimensional image based on the initial direction for the first sequence or based on a probability map determined during a previous sequence; s2) extracting (105), via the processing unit, an image-set of two-dimensional images from the three-dimensional image, such that the two-dimensional images of the image-set are arranged coaxially and subsequently in the set-direction; s3) applying (106), via the processing unit, an applicator pre-trained classification method to each of the two-dimensional images of the image-set resulting in a probability score for each of the two-dimensional images of the image-set indicating a probability of the applicator being depicted, in particular fully depicted, in the respective two-dimensional image of the image-set in a cross-sectional view; and s4) determining (107), via the processing unit, a probability-map representing the probability scores of the two-dimensional images of the image-set with respect to the set-direction; wherein the method comprises the further step: d) determining (108), via a processing unit and after finishing the last sequence, the two-dimensional image associated with the highest probability score, in particular from the image-set determined during the last sequence, as the final two-dimensional image. The invention provides an efficient way to ensure that the ultrasound volume has the required clinical information by providing the necessary scan planes having the object of interest e.g. the applicator (6) in a three-dimensional ultrasound volume.