Carl Zeiss Meditec Ag

Hendrik Burwinkel

Christoph Hauger

Stefan Saur

Holger Matz

Michael Trost

The invention relates to a computer-implemented method and a corresponding system for a machine-learning-supported determining of refractive power for a measure for correcting the eyesight of a patient. The method involves providing a scan result of an eye, wherein the scan result represents an image of an anatomical structure of the eye. The method also involves supplying the scan result as input data to a first machine-learning system in the form of a convolutional neural network, and using output values of the first machine-learning system as input data for a second machine-learning system in the form of a multi-layer perceptron, and a target refraction value for the second machine-learning system is used as an additional input value for the second machine-learning system. Finally, the method involves determining parameters for the measure for correcting the eyesight of a patient via an immediate and direct cooperation of the first machine-learning system and the second machine-learning system.

Machine-learning-based determining of refractive power for measures for correcting eyesight from OCT images

A computer implemented method for determining a refractive power value of an intraocular lens to be inserted is described. The method includes measuring ophthalmological patient data, receiving a target refraction value, determining a first refractive power value of an intraocular lens to be inserted, with the measured ophthalmological patient data and the target refraction value being used as input data, determining, by means of a trained machine learning system, a second refractive power value of the intraocular lens to be inserted, the measured ophthalmological patient data and the received target refraction value being used as input data for the trained machine learning system, and determining the final refractive power value of the intraocular lens to be inserted from the first refractive power value and the second refractive power value by means of an individual boosting factor value.

Training domain-based AI boosting of an IOL determination

The invention relates to a computer-assisted method for position determination for an intraocular lens supported by machine learning. The method comprises providing a scan result for an eye. The scan result here represents an image of an anatomical structure of the eye. The method further comprises use of a trained machine learning system for the direct determination of a final location of an intraocular lens to be fitted, wherein digital data of the scan of the eye is used as the input data for the machine learning system.

Growing community of inventors

Munich, Germany

Hendrik Burwinkel