Data processing apparatus and method

1. A medical image data processing apparatus, comprising:

hardware processing circuitry configured to

receive medical image data in respect of at least one subject, wherein the medical image data comprise sets of training data;

receive non-image data;

generate a filter based on the non-image data; and

apply the filter to the medical image data, wherein the filter is configured to limit a region of the medical image data,

wherein the processing circuitry is further configured to train a model, the model comprising a plurality of layers, and apply the filter with respect to outputs of a layer of the model as part of the training of the model.

2. The apparatus according to claim 1 , wherein:

the model comprises a neural network; and

the processing circuitry is further configured to generate the filter by training an auxiliary model to obtain at least one parameter value for the filter, and the auxiliary model comprises an auxiliary neural network.

3. The apparatus according to claim 2 , wherein the obtaining of the at least one parameter value for the filter by the processing circuitry comprises learning the at least one parameter value separately for each of a plurality of channels and/or feature maps using the auxiliary neural network.

4. The apparatus according to claim 1 , wherein the processing circuitry is further configured to apply the filter as part of a further layer of the model, the outputs of said layer being used as inputs to said further layer.

5. The apparatus according to claim 4 , wherein said further layer comprises a plurality of feature maps and/or channels, and the processing circuitry is further configured to apply the filter by using different parameter values and/or different functions for different ones of the feature maps and/or channels.

6. The apparatus according to claim 1 , wherein the processing circuitry is further configured to determine respective parameter values of the filter for each of a plurality of channels and/or feature maps.

7. The apparatus according to claim 1 , wherein the processing circuitry is further configured to at least one of:

determine parameter values for a plurality of filters, and apply the filters in respect of outputs of a plurality of different layers of the model as part of the training of the model; or

apply a process that causes a variation in a position of a peak or other characteristic of the filter for different ones of a plurality of channels and/or feature maps.

8. The apparatus according to claim 1 , wherein the received non-image data comprises or represents at least one of age, weight, sex, presence, or absence of a particular medical condition, at least one property of an imaging procedure or imaging apparatus, an output of another method, electronic health records (EHR), text data, structured data, metadata, DICOM data, or DICOM metadata.

9. The apparatus according to claim 1 , wherein the filter is a Gaussian filter.

10. The apparatus according to claim 9 , wherein the processing circuitry is further configured to determine parameters of the Gaussian filter based on the received non-image data.

11. The apparatus according to claim 10 , wherein the processing circuitry is further configured to provide a neural network that outputs parameters of the Gaussian filter based on the received non-image data as input.

12. The apparatus according to claim 1 , wherein

the filter represents a position of a feature of interest; or

the filter represents relative positions of two or more features of interest.

13. The apparatus according to claim 1 , wherein the processing circuitry is further configured to cause a display to display a visual representation of the filter on an image obtained from an image data set.

14. The apparatus according to claim 1 , wherein at least one of:

the filter comprises a differentiable function and/or a compact or efficiently parameterized smooth function;

the filter comprises a Gaussian function or a Student's T-distribution;

the filter comprises a product of at least two vectors, and/or a matrix; and

the non-image data comprises at least one of text data, metadata, audio data, and/or structured data.

15. The apparatus according to claim 1 , wherein the processing circuitry is further configured to apply the trained model to a data set to produce an output.

16. A medical image data processing apparatus, comprising:

hardware processing circuitry configured to

receive medical image data in respect of at least one subject;

receive non-image data;

generate a filter based on the non-image data; and

apply the filter to the medical image data, wherein the filter is configured to limit a region of the medical image data,

wherein the filter is a Gaussian filter; and

wherein the processing circuitry is further configured to determine a peak position and a variance of the Gaussian filter based on the received non-image data.

17. A medical image data processing apparatus, comprising:

hardware processing circuitry configured to

receive medical image data in respect of at least one subject;

receive non-image data;

generate a filter based on the non-image data; and

apply the filter to the medical image data, wherein the filter is configured to limit a region of the medical image data,

wherein the processing circuitry is further configured to generate the filter by using a penalty in a loss function to penalize spatial uniformity.

18. A method of processing medical image data, comprising:

receiving medical image data in respect of at least one subject, wherein the medical image data comprise sets of training data;

receiving non-image data;

generating a filter based on the non-image data; and

applying the filter to the medical image data, wherein the filter is configured to limit a region of the medical image data,

wherein the method further comprises

training a model, the model comprising a plurality of layers; and

applying the filter with respect to outputs of a layer of the model as part of the training of the model.