Medical image processing device, medical imaging apparatus, and noise reduction method for medical image
The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.
1. A medical image processing device that inputs an image acquired by a medical imaging apparatus and outputs an image in which noise is reduced, the medical image processing device comprising:
a plurality of processors for noise reduction;
an analysis unit configured to analyze a pattern of a signal and noise of the input image and classify the input image; and
a processor selection unit configured to select one or a plurality of processors from the plurality of processors based on a classification result of the analysis unit and activate the selected processor,
wherein the analysis unit transforms the input image into frequency spatial data other than an image space, and classifies the input image using a spatial pattern of the frequency spatial data.
2. The medical image processing device according to claim 1 , wherein the analysis unit transforms the input image into sparse spatial data, and classifies the input image using signal values of a plurality of regions of the sparse spatial data or a ratio thereof.
3. The medical image processing device according to claim 1 , wherein
the analysis unit classifies the input image based on a characteristic value calculated by texture analysis of the input image.
4. The medical image processing device according to claim 1 , wherein
the analysis unit classifies the input image based on a pattern of an artifact included in the input image.
5. The medical image processing device according to claim 4 , wherein
the analysis unit classifies the input image based on presence or absence of a line-shaped artifact included in the input image and a line pattern.
6. The medical image processing device according to claim 1 , wherein
the input image is an image acquired by a magnetic resonance imaging apparatus, and is classified by information on a spatial distribution of a signal from a living body received by a receiving coil.
7. The medical image processing device according to claim 1 , wherein
the analysis unit acquires an imaging parameter together with the input image when the input image is acquired, and classifies the input image using the imaging parameter.
8. The medical image processing device according to claim 7 , wherein
the input image is an image acquired by a magnetic resonance imaging apparatus, and the imaging parameter includes a measurement matrix size and a reconstruction matrix size.
9. A medical imaging apparatus comprising:
an imaging unit configured to take an image of a subject and acquire a medical image; and
an image processing unit configured to process the medical image acquired by the imaging unit, wherein
the image processing unit includes the medical image processing device according to claim 1 .
10. A noise reduction method for reducing noise included in an image acquired by a medical imaging apparatus, the method comprising:
analyzing a pattern of the noise of the image and classifying an input image;
selecting a predetermined processor from a plurality of processors for noise reduction prepared for each classification based on a classification result of the classification; and
executing a noise reduction processing of the input image by the selected processor, wherein
the classification uses a high-speed imaging condition when the input image is acquired together with the analysis results in the classification of the input image.
11. The noise reduction method according to claim 10 , wherein
the analysis of the pattern of the noise includes at least one of (i) histogram analysis of the image, (ii) texture analysis of the image, and (iii) analysis of data after a frequency spatial transformation or a sparse spatial transformation, and the input image is classified based on one or a plurality of analysis results.
12. A noise reduction method for reducing noise included in an image acquired by a medical imaging apparatus, the method comprising:
analyzing a pattern of the noise of the image and classifying an input image;
selecting a predetermined processor from a plurality of processors for noise reduction prepared for each classification based on a classification result of the classification;
executing a noise reduction processing of the input image by the selected processor;
selecting no processor after the classification; and
displaying on a display device to select no processor.