| CPC G16H 40/20 (2018.01) [G06F 9/45558 (2013.01); G06F 16/5854 (2019.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01); G06F 2009/45583 (2013.01); G06F 2009/45595 (2013.01); H04L 67/10 (2013.01)] | 16 Claims |
|
1. A computer-implemented method, comprising:
obtaining one or more medical datasets of a patient; performing a configuration of a generation of a medical report including a selection of a report template of the medical report from a report repository;
selecting, using a selection algorithm, one or more algorithms from an algorithm repository including multiple candidate algorithms based on the one or more medical datasets, a user input, and the configuration of the generation of the medical report, the selecting including:
providing the one or more medical datasets as an input to one or more further algorithms,
triggering execution of the one or more further algorithms, at least one of the one or more further algorithms being configured to perform a landmark detection of physiological features in the one or more medical datasets, and
selecting the one or more algorithms based on meta data associated with the multiple candidate algorithms and the physiological features obtained from the landmark detection by comparing the meta data and the physiological features, the comparing including a semantic reasoning based on a knowledge graph associated with one or more of:
physiological features;
body regions;
diseases:
imaging modalities; or
types of medical datasets,
providing the one or more medical datasets as an input to the one or more algorithms;
executing the one or more algorithms using a respective dedicated container of a cloud-computing service, the one or more algorithms configured to evaluate the one or more medical datasets and the respective dedicated container of each of the one or more algorithms being instantiated upon execution of each of the one or more algorithms;
generating the medical report based on an output of at least one of the one or more algorithms;
transmitting the output of the one or more algorithms to a human-machine interface as a first user output;
receiving feedback associated with the output of the one or more algorithms from the human-machine interface;
triggering, based on the feedback, a re-execution of at least one of the one or more algorithms using the respective dedicated container of the cloud-computing service, the feedback being an input into the at least one of the at one or more algorithms;
generating an updated medical report based on an updated output of the at least one of the one or more algorithms;
transmitting the updated medical report to the human-machine interface as a second user output; and training the selection algorithm using recurrent training based on the user input.
|