Method for providing an aggregate algorithm for processing medical data and method for processing medical data

Abstract

An embodiment of the disclosure relates to a method for providing an aggregate algorithm for processing medical data and a method for processing the medical data. A multitude of local algorithms is trained by machine learning, wherein the training of each respective local algorithm is performed on a respective local system using respective local training data, wherein a respective algorithm dataset concerning the respective local algorithm is transferred to an aggregating system that generates the aggregate algorithm based on the algorithm datasets.

Description

technical field [0001] The invention relates to a method for providing an aggregation algorithm for processing medical data, in particular medical image data, and a method for processing medical data. Furthermore, the present invention relates to a system, a computer program and a computer readable storage medium. Background technique [0002] Interest and research in the field of artificial intelligence and machine learning has been growing in recent years. Techniques such as deep learning have enabled major quality leaps in fully automated algorithms for segmenting and classifying image data, allowing such algorithms to be used in medical data processing, especially in the processing of medical image data middle. The most common approach in machine learning is supervised learning, which requires training data to train the algorithm. Often, it is necessary to at least manually identify features in the training data that need to be detected and / or defined, and optionally ...

AI Technical Summary

Problems solved by technology

Therefore, seemingly similar distributions can lead to huge differences in the resulting trained algorithms

Although the documentation recommends checking this fact by using local training with r

Images