US 12,230,017 B2
Automated and assisted identification of stroke using feature-based brain imaging
Karl A. Kasischke, Riverview, FL (US); and William Scott Burgin, Tampa, FL (US)
Assigned to University of South Florida, Tampa, FL (US)
Filed by University of South Florida, Tampa, FL (US)
Filed on Jul. 31, 2023, as Appl. No. 18/362,219.
Application 18/362,219 is a continuation of application No. 18/017,144, previously published as PCT/US2021/047102, filed on Aug. 23, 2021.
Claims priority of provisional application 63/069,684, filed on Aug. 24, 2020.
Prior Publication US 2023/0377319 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/776 (2022.01); G06T 7/00 (2017.01); G06T 19/20 (2011.01); G06V 10/25 (2022.01); G06V 10/26 (2022.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01); G06V 20/64 (2022.01)
CPC G06V 10/776 (2022.01) [G06T 7/0012 (2013.01); G06T 19/20 (2013.01); G06V 10/25 (2022.01); G06V 10/26 (2022.01); G06V 10/7715 (2022.01); G06V 10/774 (2022.01); G06V 20/64 (2022.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20036 (2013.01); G06T 2207/30016 (2013.01); G06T 2207/30104 (2013.01); G06T 2210/41 (2013.01); G06T 2219/2012 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for automated identification of volumes of interest in brain image data, the system comprising:
one or more processors; and
computer memory storing instructions that, when executed by the processors, cause the processors to perform operations comprising:
receiving image data of a brain having voxel values, wherein the voxel values represent an interruption in blood supply of the brain when imaged;
populating an array of cells with the voxel values;
applying a segmenting analysis to the array to generate a segmented array including one or more volumetric geometries representing structures within the brain;
applying a morphological neighborhood analysis to the segmented array to generate a features relationship array, wherein the features relationship array includes features of interest in the brain indicative of stroke;
identifying three-dimensional (3D) connected volumes of interest in the segmented array based on connectivity data amongst the one or more volumetric geometries in the segmented array; and
generating an output, for display at a user device, indicating the identified 3D connected volumes of interest.