MEDICAL DATA PROCESSING APPARATUS, MEDICAL DATA PROCESSING METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

1 . A medical data processing apparatus comprising processing circuitry configured to:

acquire medical data; and

generate output data by using a composite function consisting of one or more functions on the medical data, the one or more functions performing arithmetic processing of a fixed coefficient associated with information of interest in the medical data.

2 . The medical data processing apparatus according to claim 1 , wherein the information of interest is information in the medical data that affects output from the composite function or information in the medical data that is identified to affect output from the composite function during training of the composite function.

3 . The medical data processing apparatus according to claim 1 , wherein in the composite function, the medical data is multiplied by the fixed coefficient as the arithmetic processing.

4 . The medical data processing apparatus according to claim 1 , wherein the fixed coefficient is data relating to the medical data and a value based on data relating to medical physics or magnetic resonance physics.

5 . The medical data processing apparatus according to claim 1 , wherein the medical data is at least one of MR (magnetic resonance) data, CT (computed tomography) data, ultrasonic data, PET (positron emission tomography) data, SPECT (single photon emission computed tomography) data, vital data, or biopsy data.

6 . The medical data processing apparatus according to claim 1 , wherein the medical data is at least one of time-series data, image data, waveform data, examination data, or data having three or more dimensions.

7 . The medical data processing apparatus according to claim 1 , wherein

the medical data is MRS data, and

the fixed coefficient is a base spectrum or a spectrum corresponding to a chemical shift of a molecule.

8 . The medical data processing apparatus according to claim 1 , wherein

the medical data is MRS data, and

the composite function performs, on the MRS data, arithmetic processing of the fixed coefficient relating to molecular information in which a user is interested.

9 . The medical data processing apparatus according to claim 1 , wherein

the medical data is MRS data, and

the composite function is trained by training data, whereby the fixed coefficient relating to unknown molecular information is set for the MRS data.

10 . The medical data processing apparatus according to claim 1 , wherein

the medical data is an MR image, and

the composite function performs, on the MR image, the arithmetic processing of the fixed coefficient relating to a region of interest of an image.

11 . The medical data processing apparatus according to claim 1 , wherein

the medical data is an MR image, and

the composite function is trained by training data, whereby the fixed coefficient relating to extraction of an unknown image region is set for the MR image.

12 . The medical data processing apparatus according to claim 1 , wherein

the composite function is a neural network, and

a function for performing the arithmetic processing of the fixed coefficient is a layer of the neural network that includes the fixed coefficient as a parameter.

13 . The medical data processing apparatus according to claim 12 , wherein

the medical data is MRS data, and

if there are multiple pieces of molecular information in which a user is interested in the MRS data, the fixed coefficient relating to composite data of the multiple pieces of molecular information is set in the layer, or the fixed coefficient corresponding to each of the pieces of molecular information is set in each channel in the layer.

14 . The medical data processing apparatus according to claim 12 , wherein

the medical data is an MR image, and

if there are a plurality of image regions in which a user is interested in the MR image, the fixed coefficient relating to composite data of the plurality of image regions is set in the layer, or the fixed coefficient corresponding to each of the image regions is set in each channel in the layer.

15 . The medical data processing apparatus according to claim 1 , wherein

the composite function is a neural network, and

a configuration of an output layer of the neural network is switched, whereby the output data is applied to multiple tasks.

16 . The medical data processing apparatus according to claim 1 , wherein the output data is a result of any of medical classification processing, image reconstruction processing, denoising processing, segmentation processing, or super-resolution processing performed on the medical data.

17 . The medical data processing apparatus according to claim 1 , wherein the fixed coefficient is a value corresponding to data relating to magnetic field inhomogeneity of an MRI (magnetic resonance imaging) apparatus that has collected the medical data or a value corresponding to transmission and reception sensitivity data of a coil.

18 . A medical data processing method comprising:

acquiring medical data; and

generating output data by using a composite function consisting of one or more functions on the medical data, the one or more functions performing arithmetic processing of a fixed coefficient associated with information of interest in the medical data.

19 . A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method comprising:

acquiring medical data; and

generating output data by using a composite function consisting of one or more functions on the medical data, the one or more functions performing arithmetic processing of a fixed coefficient associated with information of interest in the medical data.