System and method for providing an analytical result based on a medical data set using ML algorithms

1 . A computing device to provide an analytical result based on an evaluation of a medical data set, the computing device comprising:

an interface linked, for data purposes, to a second computing device, the interface configured to

receive medical data sets and a request to provide an analytical result of the medical data set from the second computing device, and

provide the analytical result to the second computing device;

a memory including an algorithm repository and computer readable instructions, the algorithm repository including

at least one ML algorithm trained to provide an analytical result based on medical data sets, and

for each ML algorithm, a plurality of areas of application, each area of application of an ML algorithm corresponding to a different type of preprocessing of the medical data set prior to application of the ML algorithm; and

at least one processor configured to execute the computer readable instructions to cause the computing device to

select an ML algorithm from the memory based on the request,

acquire an item of status information of at least one of the computing device, the second computing device, or a data transmission between the computing device and the second computing device,

select an area of application for the selected ML algorithm based on the item of status information and at least one of the request or the medical data set,

request preprocessing of the medical data set in accordance with a respective preprocessing associated with the selected area of application to provide a preprocessed medical data set, and

apply the selected ML algorithm to the preprocessed medical data set to provide the analytical result.

2 . The computing device as claimed in claim 1 , wherein

the algorithm repository has a different version of the ML algorithm for each respective area of application of the ML algorithm, each different version is specific to the respective area of application,

the at least one processor is configured to cause the computing device to select the version of the ML algorithm which corresponds to the selected area of application, and

the at least one processor is configured to cause the computing device, on application of the ML algorithm, to apply the selected version of the ML algorithm to the preprocessed medical data set to provide the analytical result.

3 . The computing device as claimed in claim 1 , wherein

the plurality of areas of application in each case include performance characteristics of the ML algorithm during the respective preprocessing, and

the at least one processor is configured to cause the computing device to select the area of application additionally based on the performance characteristics.

4 . The computing device as claimed in claim 3 , wherein

the performance characteristics include at least one of an item of information characterizing a quality of the analytical result or an item of information characterizing a consumption of resources on application of the selected ML algorithm for the respective preprocessing.

5 . The computing device as claimed in claim 4 , wherein

the at least one processor is configured to cause the computing device to select the area of application based on the performance characteristics to optimize at least one of the quality of the analytical result to be provided or the consumption of resources for provision of the analytical result.

6 . The computing device as claimed in claim 1 , wherein the at least one processor is configured to cause the computing device to

determine, based on at least one of the status information or the selected area of application, whether the preprocessed data set is to be requested from the second computing device or a resource within the computing device, and

request, as a function of the determination, the preprocessed data set from the second computing device or from the resource within the computing device.

7 . The computing device as claimed in claim 1 , wherein the at least one processor is configured to cause the computing device to

request the preprocessed medical data set from the second computing device, and enable the second computing device to provide the preprocessed data set.

8 . The computing device as claimed in claim 1 , wherein

the at least one ML algorithm has, in each case, been trained by carrying out, in each case, at least one training step using the types of preprocessing corresponding to the plurality of areas of application.

9 . The computing device as claimed in claim 1 , wherein

the medical data set includes medical image data,

the analytical result is based on detection of medical anomalies in the medical image data, and

the preprocessing includes segmentation of the medical image data.

10 . The computing device as claimed in claim 9 , wherein

the medical image data is generated based on an imaging protocol,

the imaging protocol is associated with at least one area of application, and

the at least one processor is configured to cause the computing device to

acquire the imaging protocol of the medical image data, and

select the area of application additionally based on the acquired imaging protocol and the associated at least one area of application.

11 . The computing device as claimed in claim 1 , further comprising:

a training computing device configured to

carry out an evaluation of the provided analytical result, and

based on the evaluation, adapt at least one of the area of application or the ML algorithm by further training of the ML algorithm.

12 . The computing device as claimed in claim 1 , wherein the computing device is at least in part configured as at least one of an edge or cloud device.

13 . A computer-implemented method for providing an analytical result by evaluating a medical data set with a computing device, the computer-implemented method comprising:

receiving a request to provide an analytical result of the medical data set from a second computing device;

providing, in the computing device, an algorithm repository unit-having

at least one ML algorithm trained to provide analytical results based on medical data sets, and

for each ML algorithm, a plurality of areas of application, each area of application of an ML algorithm corresponding to a different type of preprocessing of the medical data set prior to application of the ML algorithm;

selecting an ML algorithm from the algorithm repository based on the request;

acquiring an item of status information of at least one of the computing device, the second computing device, or a data transmission between the computing device and the second computing device

selecting an area of application based on the item of status information and at least one of the request or the medical data set;

requesting preprocessing corresponding to the preprocessing associated with the selected area of application to provide a preprocessed data set; and

applying the ML algorithm to the preprocessed medical data set to provide the analytical result to the second computing device.

14 . The computing device as claimed in claim 1 , wherein

the medical data set includes medical image data,

the analytical result is based on detection of medical anomalies in the medical image data, and

the preprocessing includes preprocessing of the medical image data.

15 . A non-transitory computer-readable storage medium storing computer-executable program instructions that, when executed at a computing device, cause the computing device to perform the method of claim 13 .

16 . A computing device to provide an analytical result based on detection of medical anomalies in medical image data of a medical data set, the medical image data generated based on an imaging protocol, the computing device comprising:

an interface linked, for data purposes, to a second computing device, the interface configured to

receive medical data sets and a request to provide an analytical result of the medical data set from the second computing device, and

provide the analytical result to the second computing device;

a memory including an algorithm repository and computer readable instructions, the algorithm repository including

at least one ML algorithm trained to provide an analytical result based on medical data sets, and

for each ML algorithm, a plurality of areas of application, each area of application of an ML algorithm corresponding to a different type of preprocessing of the medical data set prior to application of the ML algorithm, and the imaging protocol associated with at least one area of application; and

at least one processor configured to execute the computer readable instructions to cause the computing device to

select an ML algorithm from the memory based on the request,

acquire the imaging protocol of the medical image data,

select an area of application for the selected ML algorithm based on the acquired imaging protocol and at least one of the request or the medical data set,

request preprocessing of the medical data set in accordance with a respective preprocessing associated with the selected area of application to provide a preprocessed data set, the preprocessing including segmentation of the medical imaging data, and

apply the selected ML algorithm to the preprocessed medical data set to provide the analytical result.