Coronary DSA Vessel Extraction via Motion-Compensated Subtraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for extracting coronary vessels from fluoroscopic image sequences, such as angiography, face challenges due to the overlapping and transparent nature of internal structures, leading to inaccurate differentiation and motion estimation errors, especially with cardiac motion.
Innovation Solution
A method utilizing coronary digital subtraction angiography (DSA) that combines learning-based vessel segment detection and covariance-based motion estimation to accurately separate coronary vessel layers from background structures by warping mask images to match background regions in contrast images, employing a Lucas-Kanade-Fusion technique for robust motion compensation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional intensity based approaches are used to differentiate objects in fluoroscopic image sequences, then the method is simple and fast, but the accuracy deteriorates due to overlapping transparent structures
Solution Approach 1:
The patent segments the fluoroscopic image into multiple transparent layers representing different anatomical structures (coronary vessels, background structures, etc.). Each layer is processed independently to extract vessel information, overcoming the limitation of traditional single-layer intensity-based approaches that fail with overlapping transparent structures.
Solution Approach 2:
The patent introduces a learned transparency model as an intermediary that estimates the transparency characteristics of different tissues. This model guides the layer separation process by identifying which structures are transparent and should be separated, enabling accurate vessel extraction despite the transparent nature of biological tissues.
2Measurement precision
If mask images are directly subtracted from contrast images without motion compensation, then the process is fast, but the accuracy deteriorates due to cardiac and respiratory motion
Solution Approach 1:
The patent performs preliminary motion estimation and mask image warping before the subtraction operation. By pre-aligning the mask images to match the background in the contrast image through estimated motion fields, the subsequent subtraction accurately removes background structures without being affected by cardiac and respiratory motion.
Solution Approach 2:
The patent employs an iterative refinement process where the subtraction result feeds back into improving the motion estimation. The initial subtraction provides information about residual background structures, which is used to refine the motion field estimation, leading to better alignment and more accurate background removal in subsequent iterations.
3Measurement precision
If learning-based vessel detection is used, then vessel detection accuracy improves, but the computational complexity and processing time increase
Solution Approach 1:
The patent applies learning-based vessel detection selectively only in regions identified as containing vessels, rather than processing the entire image. By limiting the computationally intensive learning-based detection to relevant regions identified through preliminary processing, the method maintains high accuracy while reducing overall computational burden and enabling real-time processing.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables fully automatic and real-time extraction of coronary vessels with improved accuracy by effectively removing background structures and compensating for cardiac and respiratory motion, enhancing image clarity and reducing errors in vessel detection.
Implementation Method 1
Angiography is a medical imaging technique in which X-ray images are used to visualize internal blood filled structures
Implementation Method 2
Since blood has the same radiodensity as the surrounding tissues, these blood-filled structures cannot be differentiated from the surrounding tissue using conventional radiology
Implementation Method 3
Thus, in angiography, a contrast agent is added to the blood, usually via a catheter, to make the blood vessels visible via X-ray
Implementation Method 4
In many angiography procedures, X-ray images are taken over a period of time, which results in a sequence of fluoroscopic images, which show the motion of the blood over the period of time
Data Source
AI summary
A method and system for extracting coronary vessels fluoroscopic image sequences using coronary digital subtraction angiography (DSA) are disclosed. A set of mask images of a coronary region is received, and a sequence of contrast images for the coronary region is received. For each contrast image, vessel regions are detected in the contrast image using learning-based vessel segment detection and a background region of the contrast image is determined based on the detected vessel regions. Background motion is estimated between one of the mask images and the background region of the contrast image by estimating a motion field between the mask image and the background image and performing covariance-based filtering over the estimated motion field. The mask image is then warped based on the estimated background motion to generate an estimated background layer. The estimated background layer is subtracted from the contrast image to extract a coronary vessel layer for the contrast image.