Ultrasound Image Segmentation via B-Mode and B-Flow Edge Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ultrasound imaging systems face challenges in accurately segmenting structures due to drop-outs, shadowing, and noise in B-mode images, which affect the accuracy of tissue and blood element differentiation.
Innovation Solution
The system generates both B-mode and B-flow ultrasound images and applies simultaneous edge detection to these images to enhance segmentation accuracy, leveraging coded excitation techniques to improve image SNR and resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If B-mode ultrasound imaging is used for structure segmentation, then tissue intensity information is obtained, but image quality deteriorates due to drop-outs, shadowing, and noise
Solution Approach 1:
The patent combines B-mode ultrasound images with B-flow ultrasound images to perform segmentation. The B-mode image provides tissue intensity information while the B-flow image provides blood flow information. By merging these two complementary image types and applying edge detection to both simultaneously, the system overcomes the limitations of B-mode alone (drop-outs, shadowing, noise) and achieves more reliable and accurate segmentation of anatomical structures.
2Ease of manufacture
If conventional B-mode image segmentation is used, then processing simplicity is maintained, but segmentation accuracy deteriorates due to acoustical artifacts
Solution Approach 1:
The system merges B-mode and B-flow image processing pipelines, applying edge detection algorithms to both image types simultaneously. While this increases processing complexity compared to conventional B-mode-only segmentation, it significantly improves segmentation accuracy by providing complementary information that compensates for acoustical artifacts. The combined approach leverages tissue intensity from B-mode and blood flow information from B-flow to achieve more accurate anatomical structure segmentation.
Data Source
AI summary
Methods and systems for segmenting structures in medical images are provided. The methods and systems drive a plurality of transducer element, and collect receive signals from the transducer array at a receive beamformer to form beam summed signals. The methods and systems generate a first ultrasound image of a region of interest (ROI) having tissue elements and blood elements, and generate a second ultrasound image of the ROI having tissue elements and blood elements. The tissue elements of the first ultrasound image having a higher intensity than the blood elements. The blood elements of the second ultrasound image having a higher intensity than the tissue elements. The methods and systems further perform segmentation by simultaneously applying edge detection on the first and second ultrasound images for the ROI.