Back to results
US 12,642,646 B2Granted
Systems and methods for vitreous disease severity measurement
AssigneeAlcon Inc.
InventorPaul R. Hallen
Life of this patent
Estimating the term…
Abstract
Certain aspects presented herein provide systems and methods utilizing one or more machine learning models in determining a severity of vitreous disease, and in particular, vitreous opacities. Such machine learning models are trained based on historical patient data to determine the severity of vitreous opacities afflicting a current patient. The severity determination may thereafter be utilized to inform treatment decisions for the current patient, including patient suitability for certain types of treatment.
Claims30
A system for generating vitreous opacity severity measurements, comprising:
- one or more ophthalmic diagnostic devices configured to generate one or more measurements of a vitreous opacity condition of a current patient, the one or more ophthalmic diagnostic devices including one or more of an optical coherence tomography (OCT) device, a scanning laser ophthalmoscopy (SLO) device, a dark field microscope, or a multi-spectral imaging device;
- a memory comprising executable instructions;
- a processor communicatively coupled with the one or more ophthalmic diagnostic devices and in data communication with the memory and configured to execute the instructions to generate, using one or more trained machine learning models, a severity assessment of the vitreous opacity condition based on the one or more measurements of the vitreous opacity condition of the current patient, wherein:
- the one or more trained machine learning models are trained based on at least one historical data set, wherein each entry in the at least one historical data set includes one or more measurements of a vitreous opacity condition for a historical patient, the measurements indicating one or more of a number, a size, a shape, a surface area, a relative transparency, a movement, a location, and a distance to a retina and/or a crystalline lens of one or more vitreous opacities of the historical patient;
- and
- the memory is further configured to execute the instructions to:
- map the one or more measurements of the vitreous opacity condition of the current patient to the severity assessment;
- and
- convert the one or more measurements of the vitreous opacity condition of the current patient and the severity assessment into a sample for retraining the one or more trained machine learning models.
6 more elements
A method of determining a severity of a vitreous opacity condition, comprising:
- generating, using one or more ophthalmic diagnostic devices, one or more measurements of a vitreous opacity condition of a current patient, the one or more ophthalmic diagnostic devices including one or more of an optical coherence tomography (OCT) device, a scanning laser ophthalmoscopy (SLO) device, a dark field microscope, or a multi-spectral imaging device;
- and
- generating, using one or more trained machine learning models, a severity assessment of the vitreous opacity condition based on the one or more measurements of the vitreous opacity condition of the current patient, wherein:
- the one or more trained machine learning models are trained based on at least one historical data set, wherein each entry in the at least one historical data set includes one or more measurements of a vitreous opacity condition for a historical patient, the measurements corresponding with one or more of a number, a size, a shape, a surface area, a relative transparency, a movement, a location, and a distance to a retina and/or a crystalline lens of one or more vitreous opacities of the historical patient;
- mapping the one or more measurements of the vitreous opacity condition of the current patient to the severity assessment;
- and
- converting the one or more measurements of the vitreous opacity condition of the current patient and the severity assessment into a sample for retraining the one or more trained machine learning models.
4 more elements
Dependencies are inferred from the claim text.