System and methods of prediction of ischemic brain tissue fate from multi-phase CT-angiography in patients with acute ischemic stroke using machine learning
The invention relates to systems and methods for predicting ischemic brain tissue fate from multi-phase CT-angiography. More specifically, systems and methods are provided that enable meaningful prediction of core, penumbra and perfusion from mCTA images using software that has been trained via machine learning to interpret mCTA images.
1 . A method of deriving and presenting information useful in diagnosing medium vessel occlusion (MeVO) in a current patient comprising the steps of:
from a plurality of CT images showing hypoperfused regions of the current patient;
i. quantifying, by one or more processors, a hypoperfused tissue volume in the current patient;
ii. comparing, by the one or more processors the hypoperfused tissue volume from step i to threshold volume parameters defining a MeVO event and determining if the hypoperfused tissue matches volume parameters of a MeVO event; and,
iii. if a MeVO event is determined, electronically displaying on a display device a MeVO event determination.
2 . The method as in claim 1 wherein steps i and ii include quantifying, by the one or more processors, a hypoperfused tissue shape in the current patient and comparing, by the one or more processors, the hypoperfused tissue shape to threshold shape parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue shape matches shape parameters of a MeVO event.
3 . The method as in any one of claim 1 wherein steps i and ii include quantifying, by the one or more processors, a hypoperfused tissue location in the current patient and comparing, by the one or more processors the hypoperfused tissue location to threshold location parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue location matches location parameters of a MeVO event.
4 . The method as in any one of claim 3 further comprising the steps of correlating, by the one or more processors, the hypoperfused tissue location to corresponding hypoperfused locations from historical patient data wherein historical patient data includes data marking past MeVO events; determining, by the one or more processors, a best fit of historical patient image data and electronically marking and displaying current patient images with MeVO location data derived from the historical patient image data.
5 . The method as in claim 4 wherein the historical patient data with past MeVO events includes data quantifying proximal voxel location relevant to a past MeVO event within a past patient record.
6 . The method as in claim 4 wherein historical patient data records have been previously analyzed to derive 2D and/or 3D relationships between level 1-3 vessels.
7 . The method as in claim 6 wherein the historical patient data records have been previously analyzed to define volumes of tissue as level 1, level 2 or level 3 tissue and wherein each volume of level 1, level 2 or level 3 tissue has at least one, equal, distal or proximal relationship with an adjacent volume of tissue.
8 . The method as in claim 7 further comprising the step of, after step iii, examining, by the one or more processors, changes in contrast densities in adjacent proximal volumes across two or more phases of CTA images for the current patient and based on those changes electronically marking and displaying changes in contrast density as normal flow or abnormal flow.
9 . The method as in claim 8 further comprising the step of discarding, by the one or more processors, volumes showing normal flow from further analysis.
10 . The method as in claim 9 further comprising the step of utilizing, by the one or more processors, volumes showing normal flow as a baseline for contrast density analysis.
11 . The method as in claim 10 further comprising the step of electronically marking and displaying, by the one or more processors, volumes showing abnormal flow for further analysis.
12 . The method as in claim 11 further comprising the step of analyzing, by the one or more processors, zones where contrast abruptly transitions from no contrast to significant contrast between adjacent images or vice versa to identify vessels of interest.
13 . The method as in claim 12 further comprising the step of electronically marking and displaying, by the one or more processors, zones where contrast abruptly transitions on CTA images of the current patient.
14 . The method as in any one of claim 1 wherein steps i and ii include quantifying, by the one or more processors, involved cortex.
15 . The method as in any one of claim 1 wherein steps i and ii include quantifying, by the one or more processors, hypoperfused tissue confluence in the current patient and comparing, by the one or more processors, the hypoperfused tissue confluence to hypoperfused tissue confluence parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue confluence matches hypoperfused tissue confluence of a MeVO event.
16 . The method as in claim 1 further comprising the steps of providing, by the one or more processors, at least one output selected from any one of or a combination of: a) presence or not of MeVO; b) zone of interest marking and c) vessel of interest.
17 . A method of deriving and presenting information useful in diagnosing medium vessel occlusion (MeVO) in a current patient comprising the steps of:
from a plurality of CTA images showing at least one hypoperfused region of the current patient;
i. identifying, by one or more processors, the at least one hypoperfused region and correlating, by the one or more processors, the at least one hypoperfused regions to one or more corresponding hypoperfused regions from within historical patient data; and,
ii. deriving and identifying, by the one or more processors, immediately proximal vessels/zones in the current patient based on best match(s) to the historical patient data and electronically marking and displaying the proximal vessel/zones as predicted MeVO locations on current patient CT images.
18 . The method as in claim 17 where the CT images are mCTA images.
19 . The method as in claim 17 further comprising the steps of quantifying, by the one or more processors, a hypoperfused tissue shape in the current patient and comparing, by the one or more processors, the hypoperfused tissue shape to threshold shape parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue shape matches shape parameters of a MeVO event.
20 . The method as in any one of claim 17 further comprising the steps of quantifying, by the one or more processors, a hypoperfused tissue location in the current patient and comparing, by the one or more processors, the hypoperfused tissue location to threshold location parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue location matches location parameters of a MeVO event.
21 . The method as in any one of claim 17 further comprising the steps of quantifying, by the one or more processors, involved cortex.
22 . The method as in any one of claim 17 further comprising the steps of quantifying, by the one or more processors, hypoperfused tissue confluence in the current patient and comparing, by the one or more processors, the hypoperfused tissue confluence to hypoperfused tissue confluence parameters defining a MeVO event and determining, by the one or more processors, if the hypoperfused tissue confluence matches hypoperfused tissue confluence of a MeVO event.
23 . The method as in any one of claim 17 further comprising the steps of correlating, by the one or more processors, the hypoperfused tissue location to corresponding hypoperfused locations from historical patient data wherein historical patient data includes data marking past MeVO events; determining, by the one or more processors, a best fit of historical patient image data and electronically marking and displaying current patient images with MeVO location data derived from the historical patient image data.
24 . The method as in claim 23 wherein the historical patient data with past MeVO events includes data quantifying proximal voxel location relevant to a past MeVO event within a past patient record.