Automated 3D CT Lung Nodule Growth Rate Determination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer-aided detection and diagnostic systems for lung nodules in 3D CT scans lack accuracy in determining growth rates without human intervention, relying on manual methods that are time-consuming and prone to errors, and existing deep learning systems only focus on detection and localization rather than automated and accurate growth rate determination.
Innovation Solution
A system utilizing trained 3D deep neural networks for automated detection, segmentation, and registration of abnormalities in 3D data sets, including a detection module for identifying VOIs, a segmentation module for classifying voxels, and a registration module for mapping corresponding VOIs across time series data sets, enabling fully automated determination of growth rates with accuracy comparable to medical experts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual detection and segmentation methods are used, then measurement precision is improved, but loss of time increases and device complexity increases
Solution Approach 1:
The patent replaces manual mechanical detection and segmentation processes with an automated deep learning system. The neural network automatically detects abnormalities, segments them into voxels, registers them across time series, and calculates growth rates without human intervention, thereby eliminating time loss while maintaining precision comparable to manual methods
Solution Approach 2:
The system performs self-service by automatically executing the complete workflow from detection to growth rate calculation. The deep learning model independently identifies abnormalities, segments them, tracks them across multiple scans, and computes growth parameters without requiring operator intervention or switching between different software applications
2Ease of operation
If conventional image processing techniques are used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent replaces conventional image processing techniques with deep learning-based automated detection and segmentation. The neural network directly processes 3D CT data to identify and segment abnormalities, eliminating the need for manual seed point selection and region growing algorithms, thereby achieving both ease of operation and high measurement precision
3Productivity
If automated deep learning systems are used, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent segments the complex automated system into distinct functional modules: a detection module for identifying abnormalities, a segmentation module for dividing into voxels, a registration module for aligning across time series, and a growth rate calculation module. This modular architecture manages system complexity while maintaining high productivity through automation
Data Source
AI summary
A method for automated determination of a growth rate of an object in 3D data sets is described wherein the method may comprise: a first trained 3D detection deep neural network (DNN) determining one or more first VOIs in a current 3D data set and second VOIs in prior 3D data set, a VOI being associated with an abnormality; a registration algorithm, preferably a registration algorithm based on a trained 3D registration DNN, determining a mapping between the one or more first and second VOIs, the mapping providing for a first VOI in the current 3D data set a corresponding second VOI in the prior 3D data set; a second trained 3D segmentation DNN segmenting voxels of a first VOI into first voxels representing the abnormality and voxels of a corresponding second VOI into second voxels representing the abnormality; and, determining a first volume of the abnormality on the basis of the first voxels and a second volume of the abnormality on the basis of the second voxels and using the first and second volume to determine a growth rate.