Method for training a prediction model, method for determining laser irradiation parameters, and device for retinal treatment
By training a prediction model to determine laser irradiation parameters using retinal images and other physiological parameters, the problem of insufficient individualized parameter recording in retinal therapy has been solved, thereby improving the reliability and safety of retinal therapy.
CN122373975APending Publication Date: 2026-07-10OD-OS MAKUGE GMBH
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202480073331.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-09-22
- Filing Date
- 2024-09-20
- Publication Date
- 2026-07-10
AI Technical Summary
Technical Problem
Current technology makes it difficult to individually record the necessary parameters for patients during retinal laser treatment, resulting in insufficient reliability and safety of the treatment.
Method used
By training a predictive model, using the patient's retinal images and other physiological parameters such as those of the skin, hair, iris, cornea, lens, and vitreous body, thresholds for laser irradiation parameters are determined, and individualized treatment is performed using neural networks or mapping functions.
Benefits of technology
This enables reliable, effective, and safe treatment of the retina with fewer procedures, reducing data collection time and costs while improving treatment accuracy and safety.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122373975A_ABST
Abstract
The invention relates to a method for training a prediction model (1, 2) which assigns one or more laser irradiation parameters (10a, 10b, 10c) to current state parameters (3a, 3b, 3c, 4a, 4b, 4c) of a patient (5) for retinal treatment, characterized in that, as training data for a plurality of patients (9a, 9b, 9c), in each case at least one parameter (6a, 6b, 6c) determined independently of the patient's retina (in particular a skin parameter, a hair parameter, an iris parameter, a patient age, a physiologically relevant life habit or a previous illness) and at least one retinal image (7a, 7b, 7c) of the patient acquired by an imaging method are used as training input parameters; and, on the other hand, a threshold value for a laser irradiation parameter (8a, 8b, 8c) is used as a training result parameter, which, when exceeded, leads to a permanent damaging tissue change. The invention further relates to such a prediction model and its use in patient retinal irradiation.
Need to check novelty before this filing date? Find Prior Art