Automatic segmentation and multimodal image fusion for stereoelectroencephalographic (SEEG) analysis in virtual reality (SAVR)
Aspects of the subject disclosure may include, for example, co-registering MRI data with CT data to derive merged data, the MRI data and the CT data being associated with an anatomical part of a patient, the MRI data being obtained prior to implantation of a plurality of electrodes into the anatomical part and the CT data being obtained after the implantation of the plurality of electrodes, performing segmentation on the merged data to identify locations of the plurality of electrodes, resulting in identified locations, localizing a region of interest in the merged data based on the identified locations of the plurality of electrodes and based on activity recordings relating to the anatomical part, and generating a model of the anatomical part by performing multimodal image fusion of the activity recordings and the merged data to derive an output for VR viewing or manipulation. Additional embodiments are disclosed.
1 . A device, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
co-registering magnetic resonance imaging (MRI) data with computerized tomography (CT) data to derive merged data, the MRI data and the CT data being associated with an anatomical part of a patient, the MRI data being obtained prior to implantation of a plurality of electrodes into the anatomical part and the CT data being obtained after the implantation of the plurality of electrodes;
performing segmentation on the merged data to identify locations of the plurality of electrodes, resulting in identified locations;
localizing a region of interest in the merged data based on the identified locations of the plurality of electrodes and based on activity recordings relating to the anatomical part; and
generating a model of the anatomical part by performing multimodal image fusion of the activity recordings and the merged data to derive an output for virtual reality (VR) viewing or manipulation.
2 . The device of claim 1 , wherein the performing the multimodal image fusion further includes overlaying of information from additional imaging data.
3 . The device of claim 2 , wherein the additional imaging data relates to gray matter, white matter, cerebral spinal fluid, skull structure, blood vessels, fiber tracks, or a combination thereof.
4 . The device of claim 1 , wherein the anatomical part comprises a brain, and wherein the activity recordings comprise seizure data.
5 . The device of claim 1 , wherein the region of interest comprises a seizure onset zone (SOZ).
6 . The device of claim 1 , wherein the plurality of electrodes comprises stereoelectroencephalographic (SEEG) electrodes.
7 . The device of claim 1 , wherein the operations further comprise receiving the MRI data.
8 . The device of claim 1 , wherein the operations further comprise receiving the CT data.
9 . The device of claim 1 , wherein the performing the segmentation comprises iterative thresholding to identify recording locations of each electrode of the plurality of electrodes.
10 . The device of claim 9 , wherein the performing the segmentation further comprises replacing or representing each identified electrode with a respective synthetic electrode.
11 . The device of claim 1 , wherein the operations further comprise facilitating, via a graphical user interface (GUI), naming or labeling of the plurality of electrodes subsequent to the segmentation.
12 . The device of claim 1 , wherein the operations further comprise aligning the identified locations to a common space.
13 . The device of claim 1 , wherein the model comprises a three-dimensional (3D) model or a four-dimensional (4D) model.
14 . The device of claim 13 , wherein the 4D model comprises a 3D model and time, thereby enabling animated 3D modeling.
15 . A method, comprising:
co-registering, by a processing system including a processor, magnetic resonance imaging (MRI) data with computerized tomography (CT) data to derive combined data, the MRI data and the CT data being associated with an anatomical part of a patient, the MRI data being obtained prior to implantation of a plurality of electrodes into the anatomical part and the CT data being obtained after the implantation of the plurality of electrodes;
performing, by the processing system, segmentation on the combined data to identify locations of the plurality of electrodes, resulting in identified locations;
localizing, by the processing system, a region of interest in the combined data based on the identified locations of the plurality of electrodes and based on activity recordings relating to the anatomical part; and
creating, by the processing system, a model of the anatomical part by performing multimodal image fusion of the activity recordings and the combined data to derive an output for virtual reality (VR) viewing or manipulation.
16 . The method of claim 15 , wherein the performing the segmentation comprises iterative erosions to identify recording locations of each electrode of the plurality of electrodes.
17 . The method of claim 16 , wherein the performing the segmentation further comprises grouping recording locations to their corresponding electrodes.
18 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
merging magnetic resonance imaging (MRI) data with computerized tomography (CT) data, resulting in merged data, the MRI data and the CT data being associated with an anatomical part of a patient, the MRI data being obtained prior to implantation of a plurality of electrodes into the anatomical part and the CT data being obtained after the implantation of the plurality of electrodes;
performing segmentation on the merged data to identify locations of the plurality of electrodes, resulting in identified locations;
determining a region of interest in the merged data based on the identified locations of the plurality of electrodes and based on activity recordings relating to the anatomical part; and
generating a model of the anatomical part by performing multimodal image fusion of the activity recordings and the merged data to derive an output for virtual reality (VR) viewing or manipulation.
19 . The non-transitory machine-readable medium of claim 18 , wherein the region of interest comprises a seizure onset zone (SOZ).
20 . The non-transitory machine-readable medium of claim 19 , wherein the operations further comprise causing the region of interest to be highlighted or graphically delineated so as to provide a visualization of the SOZ.