Back to results
US 2022/0031226 A1Published application
Mesial temporal lobe epilepsy classifier based on volume and shape of subcortical brain regions
AssigneeKoninklijke Philips N.V.
InventorsLyubomir Georgiev Zagorchev, Miranda Rasmussen, Shiv Sabesan
Life of this patent
Estimating the term…
Abstract
In one embodiment, a method that determine parameters corresponding to shape and volume of the one or more brain structures from the one or more meshes (36) and provides the parameters to a classifier to estimate a probability of a brain abnormality based on the parameters.
Claims15
A non-transitory computer readable medium comprising instructions that, when executed by one or more processors, causes the one or more processors to:
- receive a magnetic resonance image scan of a brain of a subject;
- access a deformable brain model, the deformable brain model comprising a plurality of meshes;
- adapt the deformable brain model to the magnetic resonance image scan of the brain of the subject such that the plurality of meshes are adapted to correspond to one or more structures of the brain of the subject;
- determine parameters corresponding to shape and volume of the one or more brain structures from the plurality of meshes;
- and
- provide the parameters to a classifier to estimate a probability of a brain abnormality based on the parameters, wherein the classifier is a trained classifier.
3 more elements
A system, comprising:
- a memory comprising instructions;
- and
- one or more processors configured by the instructions to:
- receive a magnetic resonance image scan of a brain of a subject;
- access a deformable brain model, the deformable brain model comprising a plurality of meshes;
- adapt the deformable brain model to the magnetic resonance image scan of the brain of the subject such that the plurality of meshes are adapted to correspond to one or more structures of the brain of the subject;
- determine parameters corresponding to shape and volume of the one or more brain structures from the plurality of adapted meshes;
- and
- estimate a probability of a brain abnormality based on the parameters.
6 more elements
(canceled)
A method implemented by one or more processors, the method comprising:
- at the one or more processors:
- receiving a magnetic resonance image scan of a brain of a subject;
- accessing a deformable brain model, the deformable brain model comprising a plurality of meshes;
- adapting the deformable brain model to the magnetic resonance image scan of the brain of the subject such that the plurality of meshes are adapted to correspond to one or more structures of the brain;
- determining parameters corresponding to shape and volume of the one or more brain structures from the one or more meshes;
- and
- estimating a probability of a brain abnormality based on the parameters.
4 more elements
Dependencies are inferred from the claim text.