3D Nodule Segmentation Mesh Reconstruction for Instrument Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical systems face challenges in accurately segmenting nodules within anatomical images, leading to inaccuracies in determining the spatial relationship between medical instruments and targets during procedures, which affects the precision of navigation and treatment.
Innovation Solution
Utilizing a neural network model for image segmentation to infer a segmentation mask and generate a polygon mesh representing the nodule's geometry, enhancing the accuracy of nodule segmentation and spatial relationship determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image segmentation techniques are used, then the system is simpler and faster, but the segmentation accuracy and measurement precision deteriorate
Solution Approach 1:
The patent replaces traditional mechanical/image-processing segmentation methods with a neural network-based intelligent system. The neural network model learns complex patterns in medical images to accurately segment nodules, achieving high measurement precision while automating the process through AI rather than manual or rule-based methods.
Solution Approach 2:
The patent transforms the segmentation approach by changing from fixed threshold-based parameters to adaptive neural network parameters that learn optimal segmentation criteria from training data. This allows the system to adjust to varying nodule characteristics and improve accuracy across different cases.
2Measurement precision
If traditional image segmentation techniques are used, then the processing is faster and requires less computational resources, but the spatial relationship determination accuracy deteriorates
Solution Approach 1:
The patent performs preliminary training of the neural network model using large datasets before actual segmentation tasks. This pre-computation phase enables the model to make accurate spatial relationship determinations during actual use, balancing high precision with efficient inference-time processing.
3Productivity
If manual segmentation methods are used, then the system is simpler, but the productivity and consistency of segmentation deteriorate
Solution Approach 1:
The patent implements self-service through automated neural network-based segmentation that operates independently without manual intervention. The system automatically segments nodules, determines spatial relationships, and generates results consistently, eliminating variability and improving productivity while maintaining high automation levels.
Data Source
AI summary
This disclosure provides methods, devices, and systems for planning and performing medical procedures. The present implementations more specifically relate to analyzing objects in 3D images. In some aspects, a segmentation system may receive image data representing a 3D image of an anatomy, select a seed location for a target in the 3D image, and infer a segmentation mask associated with the seed location from at least a portion of the received image data based on a neural network model trained to segment a class of objects associated with the target. The system further extracts a polygon mesh from the segmentation mask to produce a 3D model of the target. The system can determine a spatial relationship between an instrument and the target based on a position of the 3D model relative to the 3D image. The system can also estimate a geometry of the target based on the 3D model.