3D Liver Reconstruction With Vascular Territory Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for reconstructing three-dimensional liver images from two-dimensional images are not automated, requiring significant time and effort from experts, and fail to accurately identify the three-dimensional structure of blood vessels in the liver.
Innovation Solution
A method using deep learning to automatically reconstruct a three-dimensional liver image from a two-dimensional image, classifying regions into liver parenchyma, hepatic veins, portal veins, and background, and further dividing the liver parenchyma into specific territories occupied by different hepatic veins.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional manual reconstruction methods are used, then experts can reconstruct 3D liver images, but it takes much time and effort
Solution Approach 1:
The patent replaces the manual mechanical reconstruction process with an automated deep learning-based image processing system. The system uses neural networks to automatically reconstruct 3D liver images from 2D CT images, eliminating the need for manual expert intervention while maintaining high accuracy in vascular structure identification.
Solution Approach 2:
The system enables self-service automation where the image processing device autonomously performs the complete reconstruction workflow including segmentation, 3D rendering, and vascular structure identification without requiring continuous expert input. The automated algorithm independently processes images and generates accurate 3D reconstructions.
2Measurement precision
If conventional manual reconstruction methods are used, then 3D liver images can be obtained, but the process is not automated and requires expert intervention
Solution Approach 1:
The patent substitutes manual expert operations with an automated deep learning system that performs image processing, segmentation, and classification. The system automatically identifies and classifies liver parenchyma, hepatic veins, portal veins, and tumors, achieving high precision without expert intervention.
Solution Approach 2:
The reconstruction system operates autonomously by automatically processing 2D liver images through multiple neural network models to generate classified 3D reconstructions. The system self-manages the entire workflow from input image processing to output generation without requiring manual expert operations.
3Ease of manufacture
If 2D liver images are used for analysis, then imaging is simpler, but it is difficult to accurately identify three-dimensional vascular structures
Solution Approach 1:
The patent transforms 2D liver images into 3D reconstructed images using deep learning-based volumetric rendering. This dimensional transformation enables accurate identification of three-dimensional vascular structures while maintaining the simplicity of 2D image acquisition. The system generates pseudo-3D or true 3D reconstructions that preserve spatial relationships of hepatic veins and portal veins.
Data Source
AI summary
Provided is a method of reconstructing a three-dimensional (3D) liver image, which includes: receiving, by an image processing device, a two-dimensional (2D) liver image; inputting, by the image processing device, the 2D liver image into an image model; and reconstructing, by the image processing device, a 3D liver image corresponding to the 2D liver image using the image model, wherein a region of the 3D liver image is classified into a region of liver parenchyma, a region of a hepatic vein, a region of a portal vein, and a region of a background, when a mass is included in the region of the 3D liver image, the region of the 3D liver image is further classified to include a region of mass, and the region of the liver parenchyma is divided into at least one of a region occupied by a left portal vein, a region occupied by a right portal vein, a region occupied by a left hepatic vein, a region occupied by a middle hepatic vein, a region occupied by a right hepatic vein, a region occupied by an inferior hepatic vein, and a region occupied by vascular branches.