Back to results
US 12,614,638 B2Granted
Method for assessing vasculature, obtaining angiographic parametric imaging (API) maps of vasculature and determining state of vasculature using machine-learning classifier
AssigneeThe Research Foundation for The State University of New York
InventorsCiprian Ionita, Mohammad Mahdi Shiraz Bhurwani
Life of this patent
Estimating the term…
Abstract
Methods and systems are provided for assessing a vasculature of an individual. In an embodiment of a method, one or more angiographic parametric imaging (API) maps of the vasculature are obtained, wherein each API map of the one or more API maps encodes a hemodynamic parameter. A state of the vasculature is determined using a machine-learning classifier applied to the one or more API maps.
Claims34
A method for assessing a vasculature of an individual, comprising:
- obtaining one or more angiographic parametric imaging (API) maps of the vasculature, wherein each API map of the one or more API maps encodes a hemodynamic parameter, and wherein the hemodynamic parameter comprises one or more of time to peak (TTP) mean transit time (MTT), time to arrival, peak height (PH), and/or area under the time-density curve (AUC);
- determining a state of the vasculature using a machine-learning classifier applied to the one or more API maps, wherein the machine-learning classifier is trained to determine a reperfusion state of the vasculature, an occlusion state of the vasculature, or both;
- and
- displaying, in real-time during an endovascular procedure, a vasculature state assessment based on the determined state of the vasculature to provide feedback for adjusting the endovascular procedure, wherein the vasculature state assessment includes a probability of achieving a relevant therapeutic outcome as defined by established clinical standards.
1 more element
An image processing apparatus, comprising:
- a memory for storing one or more angiographic parameter imaging (API) maps of a vasculature, wherein each API map of the one or more API maps encodes a hemodynamic parameter comprising one or more of time to peak (TTP), mean transit time (MTT), time to arrival, peak height (PH), and/or area under the time-density curve (AUC);
- and
- a processor in electronic communication with the memory, and wherein the processor is programmed to determine a state of the vasculature based on the one or more API maps stored in the memory, and wherein the processor determines the state of the vasculature using a machine-learning classifier trained to determine a reperfusion state of the vasculature, an occlusion state of the vasculature, or both;
- and
- wherein the processor is programmed to display a vasculature state assessment based on the determined state of the vasculature to provide feedback for adjusting the endovascular procedure, wherein the vasculature state assessment includes a probability of achieving a relevant therapeutic outcome as defined by established clinical standards.
2 more elements
Dependencies are inferred from the claim text.