STN Shape Prediction via Statistical Model and PLSR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging technologies, particularly in clinical settings, are insufficient for accurately portraying the necessary information for precise localization and segmentation of small and complex brain structures like the subthalamic nucleus (STN), which is crucial for deep brain stimulation (DBS) procedures.
Innovation Solution
A method using a statistical shape model and partial least squares regression (PLSR) to predict the position and shape of the STN by exploiting its spatial relationship with adjacent structures that can be easily segmented on high-field MRI or conventional MRI images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current clinical imaging methods are used, then the imaging process is simple and widely available, but the measurement precision and detection capability for small brain structures like STN are insufficient
Solution Approach 1:
The patent segments the brain imaging process into multiple stages: acquiring multiple types of MRI images (T1, T2, FLAIR), performing separate segmentation of different brain structures, and integrating them into a composite atlas. This segmentation allows each structure to be optimized and processed independently, improving overall measurement precision for small structures like STN.
Solution Approach 2:
The patent introduces a composite atlas as an intermediary that integrates multiple MRI sequences and anatomical structures. This composite atlas serves as a reference framework that enhances the detection capability for small brain structures by providing contextual information from multiple imaging modalities and anatomical levels.
2Adaptability or versatility
If atlases from single individual or averages are used, then the atlas creation is straightforward, but the adaptability to specific patient anatomy is insufficient
Solution Approach 1:
The patent performs preliminary actions by acquiring and processing multiple types of MRI images (T1, T2, FLAIR) and segmenting various brain structures before creating the composite atlas. This preliminary processing establishes a comprehensive reference framework that can be adapted to individual patient anatomy, enhancing versatility without requiring complex real-time adjustments during patient evaluation.
Data Source
AI summary
A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.