Model training apparatus and method

A processing method comprising:

• applying a first trained model to input data to obtain a first output based on the input data, wherein the input data comprises clinical data;
• and
• applying a second trained model different than the first trained model to the input data to obtain a second output based on the input data,
• wherein the first trained model is trained to obtain the first output and the second trained model is trained to obtain the second output in dependence on a hierarchical relationship between the first output and the second output, the hierarchical relationship comprising at least one of:
• a spatial hierarchy, a temporal hierarchy, an anatomical hierarchy, and a hierarchy of clinical conditions, such that a boundary of the second output is included within a boundary of the first output or a time extent of the second output is included within a time extent of the second output.

A processing apparatus comprising:

• processing circuitry configured to perform a training process comprising:
• training a first model to obtain a first output from input data, wherein the input data comprises clinical data, and
• training a second model different than the first model to obtain a second output from the input data;
• wherein training of the first model and training of the second model is in dependence on a hierarchical relationship between the first output and the second output, the hierarchical relationship comprising at least one of:
• a spatial hierarchy, a temporal hierarchy, an anatomical hierarchy, and a hierarchy of clinical conditions, such that a boundary of the second output is included within a boundary of the first output or a time extent of the second output is included within a time extent of the second output.

A method for training a first model and a second model using a training process, the training process comprising:

• training the first model to obtain a first output from input data, wherein the input data comprises clinical data;
• and
• training the second model different from the first model to obtain a second output from the input data;
• wherein training of the first model and training of the second model is in dependence on a hierarchical relationship between the first output and the second output, the hierarchical relationship comprising at least one of:
• a spatial hierarchy, a temporal hierarchy, an anatomical hierarchy, and a hierarchy of clinical conditions, such that a boundary of the second output is included within a boundary of the first output or a time extent of the second output is included within a time extent of the second output.