Back to results
US 2026/0134541 A1Published application
System for machine learning and mri-based evaluation of lumbar regions
AssigneeAclarion, Inc.
InventorJeffrey Thramann
Life of this patent
Estimating the term…
Abstract
A machine learning system is provided to train and use machine learning models to detect lumbar regions of interest on MRI images that correspond to lumbar regions of interest on SPECT/CT images for the same patient and lumbar region.
Claims15
A computer-implemented method for machine learning training for detection of lumbar regions of interest, the computer-implemented method comprising:
- under control of a computer system comprising one or more processors configured to execute specific computer-executable instructions,
- obtaining a plurality of Single Photon Emission Computed Tomography/Computed Tomography (SPECT/CT) images, wherein each SPECT/CT image of the plurality of SPECT/CT images is associated with a different patient of a plurality of patients, wherein a first subset of the plurality of SPECT/CT images represent patient lumbar regions with a lumbar region of interest, and wherein a second subset of the plurality of SPECT/CT images represent patient lumbar regions without a lumbar region of interest;
- obtaining a plurality of magnetic resonance imaging (MRI) images, wherein each MRI image of the plurality of MRI images is associated with a corresponding SPECT/CT image of the plurality of SPECT/CT images;
- labeling each MRI image of the plurality of MRI images based on the corresponding SPECT/CT image of the plurality of SPECT/CT images, wherein a label for a first MRI image indicates a presence of a lumbar region of interest in the first MRI image based on a presence of a lumbar region of interest in the corresponding SPECT/CT image;
- and
- training a machine learning model using the plurality of MRI images, wherein the machine learning model is trained to generate model output regrading a presence of data representing a lumbar region of interest in model input.
3 more elements
A lumbar disc evaluation system comprising:
- a magnetic resonance imaging (MRI) machine configured to generate a first MRI image representing a lumbar region of a patient;
- computer-readable memory storing a machine learning model trained to generate lumbar region evaluation output representing whether an MRI image input is associated with a lumbar region of interest;
- and
- one or more processors in communication with the computer-readable memory, wherein the one or more processors are programmed by executable instructions to:
- obtain the first MRI image generated by the MRI machine;
- and
- generate a first lumbar region evaluation output based on evaluation of at least a portion of the first MRI image using the machine learning model.
4 more elements
Dependencies are inferred from the claim text.