Method for a brain region location and shape prediction

摘要

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.

主权项

1. A method for operating an electronic device to generate a patient-specific brain image atlas, comprising:
receiving a patient's brain image having a region of interest that is produced using an imaging modality, wherein the patient's brain image is associated with a patient having characteristics; accessing a database of additional metadata-annotated brain images including images different than the patient's brain image, wherein the database includes:
registered first imaging modality brain image sets and associated metadata from each of a plurality of individuals, wherein the image sets include predicted regions of interest that correspond to the regions of interest in the patient's brain image and predictor regions that are anatomically different than and associated with the predicted regions; andregistered second imaging modality brain image sets and associated metadata from at least some of the plurality of individuals, wherein the second modality is different than the first modality, and wherein the image sets include predicted regions of interest that correspond to the regions of interest in the patient's brain image and predictor regions that are anatomically different than and associated with the predicted regions; andregistered additional modality brain image sets and associated metadata from at least some of the plurality of individuals, wherein the additional modality is different than the first and second modalities, and wherein the image sets include predicted regions of interest that correspond to the regions of interest in the patient's brain image and predictor regions that are anatomically different than and associated with the predicted regions; selecting one or more of the additional brain images from the database based on a correlation of the metadata elements of the one or more additional images to the patient's characteristics and the imaging modality of the patient's brain image for the clinical purpose of deep brain stimulation electrode placement to have predictor regions associated with predicted regions of interest that correspond to the regions of interest in the patient's brain image; processing, using the electronic device, the patient's brain image to segment one or more predictors corresponding to registered predictors of the selected one or more additional brain images; processing, using the electronic device, the patient's brain image and the selected one or more additional brain images as a function of the segmented one or more predictors in the patient's brain image and registered predictors of the selected one or more additional brain images, to predict one or more of the shape, location, size or orientation of the region of interest in the patient's brain image; and processing, using the electronic device, the patient's brain image as a function of the predicted one or more of the shape, location, size or orientation of the region of interest to incorporate the predicted one or more of the shape, location, size or orientation of the region of interest into the patient's brain image to generate a patient-specific atlas having enhanced regions of interest.