Integration and fusion of data from diagnostic measurements for glaucoma detection and progression analysis
Systems and methods for improving the reliability of glaucoma diagnosis and progression analysis are described. The measurements made from one type of diagnostic device are adjusted based on another measurement using a priori knowledge of the relationship between the two measurements including the relationship between structure and function, knowledge of disease progression, and knowledge of instrument performance at specific locations in the eye. The adjusted or fused measurement values can be displayed to the clinician, compared to normative data, or used as input in a machine learning classifier to enhance the diagnostic and progression analysis of the disease.
1. A method of improving the accuracy of ophthalmic diagnostic measurements of disease in the eye of a patient, said method comprising:
collecting optical coherence tomography (OCT) measurements of the eye of a patient using an optical coherence tomography device, said OCT measurements corresponding to scattering intensity as a function of depth in the eye;
collecting visual field test measurements on the eye of a patient using a perimetry device;
adjusting the values of a plurality of the measurements made from one of above collection steps based on the measurements from the other collection step and á priori knowledge of the relationship between the two types of measurements,
wherein said adjusting step includes one or both of:
(a) transforming the OCT measurements using a mathematical function based on the visual field test measurements obtained from corresponding regions of the eye; or
(b) transforming the visual field test measurements using a mathematical function based on the OCT measurement obtained from corresponding regions of the eye; and
storing or displaying the adjusted value.
2. A method as recited in claim 1 , wherein the adjustment is made only when a measurement falls within a predefined criteria.
3. A method as recited in claim 1 , wherein the adjusted value is compared to normative data.
4. A method as recited in claim 1 , wherein the adjusted value is used to determine the progression of disease.
5. A method as recited in claim 1 , wherein the adjusted parameters are used as input in a machine learning classifier.
6. A method as recited in claim 1 , wherein the machine learning classifier is an artificial neural network.
7. A method of facilitating the analysis of disease conditions in the eye of a patient comprising the steps of:
obtaining a set of structural measurements of the eye with an optical coherence tomography (OCT) device, said OCT measurements corresponding to scattering intensity as a function of depth in the eye;
obtaining a set of visual functions measurements with a perimetry device;
modifying the visual function measurements with information from the structural measurements taking into account a priori knowledge about the relationship between the two types of measurements, and wherein said modification includes transforming the visual function measurements using a mathematical function based on the OCT measurement obtained from corresponding regions of the eye; and
displaying a perimetry map based upon the modified visual function measurements.
8. A method as recited in claim 7 , wherein the modified visual function measurements are classified.
9. A method as recited in claim 8 , wherein the classification is based on the level of glaucoma present in the eye.
10. A method as recited in claim 7 , wherein the á priori knowledge includes a model of the anatomical relationship between retinal nerve fiber layer (RNFL) morphology and areas of the visual field.
11. A method as recited in claim 7 , wherein the á priori knowledge includes information related to difference in data distributions for the OCT and perimetry measurements.
12. A method as recited in claim 11 , wherein the differences in data distributions includes one or more of the following factors: measurement variability, sources of measurement errors and normative limits for each measurement.
13. A method as recited in claim 7 , wherein the modification of the visual function measurements increase some of the visual field defects and decrease some different visual field defects.
14. A method as recited in claim 7 , wherein the perimetry map is in the form of a Glaucoma Hemifield Test.
15. A method as recited in claim 7 , further including adjusting the visual function measurements to account for variability caused by age.
16. A method as recited in claim 7 , further including adjusting the visual function measurements to account for variability caused by refractive error.
17. A method as recited in claim 7 , further including adjusting the structural measurements to account for variability caused by age.
18. A method as recited in claim 7 , further including adjusting the structural measurements to account for variability caused by refractive error.
19. A method as recited in claim 7 , further including transforming the structural measurements using a statistical model to identify a subset of measurements used to modify the visual function measurements.
20. A method as recited in claim 7 , further including transforming the visual function measurements using a statistical model to identify a subset of measurements that are modified by the structural measurements.
21. A system for analyzing the disease condition of an eye of a patient said system comprising:
a processor for receiving a set of structural measurements of the eye collected with an optical coherence tomography (OCT) device, said OCT measurements corresponding to scattering intensity as a function of depth in the eye and receiving a set of visual function measurements collected with a perimetry device, said processor adjusting the values of a plurality of the measurements made from one of the two data sets based on the measurements from the other data set and a priori knowledge of the relationship between the two types of measurements, and wherein the adjustment of the values include one or both of:
(a) transforming the OCT measurements using a mathematical function based on the visual function measurements obtained from corresponding regions of the eye; or
(b) transforming the visual function measurements using a mathematical function based on the OCT measurement obtained from corresponding regions of the eye; and
a display for displaying one or more adjusted measurement values.
22. A system as recited in claim 21 , wherein the adjustment is made only when a measurement falls within a predefined criteria.
23. A system as recited in claim 21 , wherein the adjusted value is compared to normative data.
24. A system as recited in claim 21 , wherein the adjusted parameters are used as input in a machine learning classifier.
25. A system as recited in claim 21 , wherein the machine learning classifier is an artificial neural network.
26. The method as recited in claim 1 , wherein the values of the plurality of the measurements are adjusted based on a priori knowledge of the severity of the disease in the eye of the patient.
27. The method as recited in claim 7 , wherein visual function measurements are modifying based on a priori knowledge of the severity of the disease in the eye of the patient.
28. A system as recited in claim 21 , wherein the values of the plurality of the measurements are adjusted based on a priori knowledge of the severity of the disease in the eye of the patient.
29. A system as recited in claim 21 , wherein the adjusted values is used to determine the progression of disease.