View source for 20240016378. MACHINE LEARNING TO ASSESS THE CLINICAL SIGNIFICANCE OF VITREOUS FLOATERS simplified abstract (Alcon Inc.)

=MACHINE LEARNING TO ASSESS THE CLINICAL SIGNIFICANCE OF VITREOUS FLOATERS=


==Organization Name==

[[:Category:Alcon Inc.|Alcon Inc.]]


[[Category:Alcon Inc.]]

==Inventor(s)==

[[:Category:Zsolt Bor of San Clemente CA (US)|Zsolt Bor of San Clemente CA (US)]][[Category:Zsolt Bor of San Clemente CA (US)]]

[[:Category:Alireza Malek Tabrizi of Fremont CA (US)|Alireza Malek Tabrizi of Fremont CA (US)]][[Category:Alireza Malek Tabrizi of Fremont CA (US)]]

==MACHINE LEARNING TO ASSESS THE CLINICAL SIGNIFICANCE OF VITREOUS FLOATERS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240016378 titled 'MACHINE LEARNING TO ASSESS THE CLINICAL SIGNIFICANCE OF VITREOUS FLOATERS

==Simplified Explanation==

The abstract of this patent application describes a method for training a machine learning model to estimate the clinical significance of floaters in a patient's eye. The method involves evaluating images of the eye to identify shaded regions corresponding to floaters, measuring these shaded regions, and processing the measurements using a machine learning model to obtain an estimated significance. The machine learning model is then updated by comparing the estimated significance to a human-assigned clinical significance. Additionally, the model can be updated by evaluating the estimated category with respect to visibility threshold data.

* The method involves evaluating images of the patient's eye to identify shaded regions corresponding to floaters.
* The shaded regions are measured and processed using a machine learning model to estimate the clinical significance of the floaters.
* The machine learning model is updated by comparing the estimated significance to a human-assigned clinical significance.
* The model can also be updated by evaluating the estimated category with respect to visibility threshold data.
* The method can use various types of images, such as SLO images or en face retinal OCT images.

Potential applications of this technology:
* Improving the diagnosis and treatment of patients with floaters in their eyes.
* Enhancing the efficiency and accuracy of clinical assessments by providing an automated estimation of the clinical significance of floaters.
* Assisting healthcare professionals in making informed decisions regarding the management of floaters.

Problems solved by this technology:
* Floaters in the eye can be subjective and challenging to assess clinically. This technology provides an objective and automated method for estimating the clinical significance of floaters.
* The method reduces the reliance on human assessment, which can be time-consuming and prone to variability.
* It allows for continuous monitoring and tracking of floaters over time, providing valuable information for patient management.

Benefits of this technology:
* Provides a more standardized and consistent approach to assessing the clinical significance of floaters.
* Enables early detection and intervention for patients with significant floaters, potentially improving outcomes.
* Reduces the burden on healthcare professionals by automating part of the assessment process.
* Facilitates research and data analysis by providing a quantitative measure of the clinical significance of floaters.


==Original Abstract Submitted==

particular embodiments disclosed herein provide a method for training a machine learning model to estimate the clinical significance of floaters in a patient's eye. one or more images, such as slo images or en face retinal oct images, are evaluated to identify shaded regions corresponding to floaters. the shaded regions are measured and the measurements processed using a machine learning model to obtain an estimated significance. the machine learning model is then updated according to a comparison of the estimated significance to a human-assigned clinical significance. the machine learning model may additionally or alternatively be updated by evaluating the estimated category with respect to visibility threshold data, such as one or more visibility threshold surfaces defined with respect to two or more variables.



[[Category:A61B3/10]]
[[Category:A61B3/00]]