Liver Segmentation in Multiphase CT via Histogram Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CT image segmentation methods for liver imaging are unreliable due to lack of clinical evaluation, sensitivity to input, and inefficiency in handling contrast-enhanced images, often requiring special acquisition protocols and being time-consuming.
Innovation Solution
A method using multiphase histogram analysis to identify the liver region of interest, followed by advanced region growing and registration of segmented liver volumes to compensate for patient breathing, allowing for accurate segmentation without manual model fitting or special acquisition protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional CT image segmentation methods are used, then liver segmentation can be performed, but the methods are unreliable due to lack of clinical evaluation and sensitivity to input
Solution Approach 1:
The patent performs preliminary actions by acquiring multiple phases of contrast-enhanced CT images (arterial, portal venous, and equilibrium phases) before segmentation. This preliminary multi-phase acquisition provides comprehensive clinical evaluation data that improves segmentation reliability, as the liver parenchyma shows different enhancement patterns across phases, enabling more accurate differentiation from surrounding structures.
Solution Approach 2:
The patent changes parameters by utilizing different contrast enhancement phases with varying timing and intensity. Each phase provides different Hounsfield unit ranges and enhancement patterns, allowing the segmentation algorithm to adapt to multiple parameter states of the liver tissue, thereby improving reliability through multi-parametric evaluation rather than relying on a single phase.
2Measurement precision
If special acquisition protocols are used for liver segmentation, then segmentation accuracy can be improved, but the acquisition process becomes more complex and time-consuming
Solution Approach 1:
The patent applies universality by using a multi-phase contrast-enhanced CT acquisition protocol that serves multiple functions: it provides diagnostic information for liver lesions, characterizes vascular structures, and enables accurate liver segmentation. This single multi-phase protocol replaces the need for separate specialized acquisition protocols for different purposes, reducing overall complexity while maintaining high segmentation accuracy.
Solution Approach 2:
The patent merges multiple acquisition phases (arterial, portal venous, equilibrium) into a single integrated segmentation workflow. By combining the information from all phases, the system achieves high segmentation accuracy without requiring separate specialized protocols for each phase, thereby reducing the perceived complexity through unified processing.
3Productivity
If conventional segmentation methods are used, then liver segmentation can be performed, but the process is time-consuming and not efficient for clinical practice
Solution Approach 1:
The patent applies segmentation by dividing the liver volume into anatomical segments (Couinaud classification) based on vascular structures identified across multiple contrast phases. This segmentation approach enables automated processing of complex liver anatomy without requiring manual tracing, significantly improving productivity while reducing time loss compared to conventional manual or single-phase automated methods.
Solution Approach 2:
The patent replaces manual mechanical segmentation processes with automated computational algorithms that process multi-phase CT images. The automated system performs thresholding, region growing, and anatomical segmentation without manual intervention, dramatically improving segmentation efficiency and reducing the time required for clinical workflow.
4Device complexity
If only one phase of contrast-enhanced examination is used, then the segmentation process is simpler, but the method does not correspond to general practice and reliability is reduced
Solution Approach 1:
The patent applies dynamics by utilizing the temporal evolution of contrast enhancement across multiple phases. The liver parenchyma exhibits dynamic enhancement patterns (arterial wash-in, portal venous peak, equilibrium phase) that provide temporal information for more reliable segmentation. This dynamic multi-phase approach corresponds to general clinical practice while maintaining manageable process complexity through automated processing.
Data Source
AI summary
Systems, method and apparatus in which some embodiments of automatic segmentation of a liver parenchyma from multiphase contrast-enhanced computed-tomography images includes analyzing an intensity change in the images belonging to the different phases in order to determine the region-of-interest of the liver, thereafter segmenting starting from the region-of-interest and incorporating anatomical information to prevent oversegmentation, and thereafter combining the information of all available images.