Cross-Modality Image Registration for Surgical Navigation Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer-assisted surgery navigation systems face challenges in registering pre-operative images from one imaging modality to intra-operative images of a different modality, particularly due to differences in imaging techniques like MRI and CT, which affect the accuracy of surgical instrument navigation.
Innovation Solution
The method involves transforming pre-operative images from one imaging modality to an estimate in another modality using neural networks, registering these estimates to intra-operative navigable images, and utilizing camera tracking systems for precise surgical navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If pre-operative images from one imaging modality (e.g., MRI) are directly registered to intra-operative images of a different modality (e.g., CT), then the registration process is simplified, but the accuracy of surgical instrument navigation deteriorates due to differences in imaging techniques
Solution Approach 1:
The patent introduces a third imaging modality as an intermediary reference frame. Pre-operative images from the first modality are transformed into the third modality, and intra-operative images from the second modality are also transformed into the third modality. This intermediary transformation enables accurate cross-modality registration by providing a common reference space, resolving the contradiction between simplified registration and navigation accuracy.
2Measurement precision
If multiple imaging modalities are acquired and transformed to a common reference frame, then the accuracy of image alignment is improved, but the radiation exposure and cost increase
Solution Approach 1:
The patent performs the transformation of pre-operative images to the third imaging modality before the surgical procedure begins. This preliminary transformation allows the system to use the transformed pre-operative images throughout the surgery without requiring additional intra-operative scanning, thereby reducing radiation exposure while maintaining alignment accuracy.
3Measurement precision
If real-time tracking of surgical instruments is implemented using camera tracking systems, then the precision of surgical navigation is improved, but the system complexity and computational requirements increase
Solution Approach 1:
The patent creates a virtual copy of the patient's anatomy in the third imaging modality that serves as a reference framework. The camera tracking system then tracks the position of surgical instruments relative to this virtual model, rather than requiring complex direct registration between multiple real imaging modalities during surgery. This copying approach simplifies the real-time tracking system while maintaining high navigation precision.
Data Source
AI summary
A computer platform is provided for computer assisted navigation during surgery. The computer platform includes at least one processor that is operative to transform pre-operative images of a patient obtained from a first imaging modality to an estimate of the pre-operative images of the patient in a second imaging modality that is different than the first imaging modality. The at least one processor is further operative to register the estimate of the pre-operative images of the patient in the second imaging modality to intra-operative navigable images or data of the patient.