# US 11,896,362 B2 · Medical image processing apparatus, method of medical image processing, and nonvolatile computer readable storage medium storing therein medical image processing program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,896,362 B2 - Document ID: US11896362B2 - Status: Granted - Kind: B2 - Application number: 17/819,648 - Filed: 2022-08-15 - Published: 2023-03-23 - Granted: 2024-02-13 - Earliest claimed: 2021-09-17 - Assignees: Canon Medical Systems Corporation - Applicants: Canon Medical Systems Corporation - Inventors: Hideaki Kutsuna - Web page: https://patentgrep.com/patent/US11896362B2 ## CPC - A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging - G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)} - G01R 33/48: NMR imaging systems - G01R 33/4826: {in three dimensions} - G06N 3/02: Neural networks - G06T 2207/10088: Magnetic resonance imaging [MRI] - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A medical image processing apparatus according to the present embodiment includes processing circuitry. The processing circuitry inputs a first magnetic resonance image reconstructed with super-resolution processing on magnetic resonance data and a second magnetic resonance image obtained by imaging the same object as that of the first magnetic resonance image and with artifacts suppressed compared with the first magnetic resonance image, to a leaned model, the learned model being configured to output a third magnetic resonance image having the same resolution as that of the first magnetic resonance image and with the artifacts suppressed, generates the third magnetic resonance image based on the first magnetic resonance image and the second magnetic resonance image, using the learned model. ## Claims ### Claim 1 A medical image processing apparatus comprising: processing circuitry configured to input a first magnetic resonance image reconstructed with super-resolution processing on magnetic resonance data and a second magnetic resonance image obtained by imaging a same object as an object of the first magnetic resonance image and with artifacts suppressed compared with the first magnetic resonance image, to a learned model, the learned model being configured to output a third magnetic resonance image having a same resolution as a resolution of the first magnetic resonance image and with the artifacts suppressed, and generate the third magnetic resonance image based on the first magnetic resonance image and the second magnetic resonance image, using the learned model. ### Claim 2 (depends on 1) The medical image processing apparatus according to claim 1, wherein the processing circuitry reconstructs the first magnetic resonance image based on the magnetic resonance data after the super-resolution processing, and reconstructs the second magnetic resonance image based on the magnetic resonance data so that the artifacts occurring by reconstruction with the super-resolution processing are suppressed. ### Claim 3 (depends on 2) The medical image processing apparatus according to claim 2, wherein the processing circuitry executes zero-filling on a no-signal high-frequency region outside the magnetic resonance data placed in a k-space as the super-resolution processing, and reconstructs the first magnetic resonance image based on the magnetic resonance data subjected to the zero-filling. ### Claim 4 (depends on 1) The medical image processing apparatus according to claim 1, wherein the processing circuitry executes the super-resolution processing with a first filter applied to the magnetic resonance data to reconstruct the first magnetic resonance image, and executes the super-resolution processing with a second filter having a stronger filter strength than a filter strength of the first filter applied to the magnetic resonance data to reconstruct the second magnetic resonance image. ### Claim 5 (depends on 4) The medical image processing apparatus according to claim 4, wherein the first filter is a weak filter reducing a strength of an end of a high-frequency region in the magnetic resonance data more weakly than a filter strength of the second filter or a non-filter passing the magnetic resonance data, and the high-frequency region is a frequency region in which a contribution to edge information in the first magnetic resonance image is dominant. ### Claim 6 (depends on 4) The medical image processing apparatus according to claim 4, wherein the second filter is a strong filter making a strength of an end of a high-frequency region in the magnetic resonance data stronger than a filter strength of the first filter and corresponds to a low-pass filter having a stronger filter strength than the filter strength of the first filter, and the high-frequency region is a frequency region in which a contribution to edge information in the first magnetic resonance image is dominant. ### Claim 7 (depends on 1) The medical image processing apparatus according to claim 1, wherein the processing circuitry executes the super-resolution processing with a first filter having a certain filter strength applied to the magnetic resonance data to reconstruct the first magnetic resonance image, and reconstructs the second magnetic resonance image based on the magnetic resonance data without using the super-resolution processing. ### Claim 8 (depends on 1) The medical image processing apparatus according to claim 1, wherein the processing circuitry executes interpolation on a reconstructed image reconstructed based on the magnetic resonance data as the super-resolution processing to generate the first magnetic resonance image. ### Claim 9 (depends on 1) The medical image processing apparatus according to claim 1, wherein the processing circuitry executes interpolation on a reconstructed image reconstructed based on the magnetic resonance data as the super-resolution processing to generate the second magnetic resonance image. ### Claim 10 (depends on 1) A magnetic resonance imaging apparatus comprising: the medical image processing apparatus according to claim 1; and imaging control circuitry configured to collect the magnetic resonance data by magnetic resonance imaging on a subject. ### Claim 11 A method of medical image processing comprising: inputting a first magnetic resonance image reconstructed with super-resolution processing on magnetic resonance data and a second magnetic resonance image obtained by imaging a same object as an object of the first magnetic resonance image and with artifacts suppressed compared with the first magnetic resonance image, to a learned model, the learned model outputting a third magnetic resonance image having a same resolution as a resolution of the first magnetic resonance image and with the artifacts suppressed; and generating the third magnetic resonance image based on the first magnetic resonance image and the second magnetic resonance image, using the learned model. ### Claim 12 (depends on 11) The method of medical image processing according to claim 11, further comprising: reconstructing the first magnetic resonance image based on the magnetic resonance data after the super-resolution processing; and reconstructing the second magnetic resonance image based on the magnetic resonance data so that the artifacts occurring by reconstruction with the super-resolution processing are suppressed. ### Claim 13 (depends on 12) The method of medical image processing according to claim 12, further comprising: executing the super-resolution processing with a first filter applied to the magnetic resonance data to reconstruct the first magnetic resonance image; and executing the super-resolution processing with a second filter having a stronger filter strength than a filter strength of the first filter applied to the magnetic resonance data to reconstruct the second magnetic resonance image. ### Claim 14 A nonvolatile computer readable storage medium storing therein a medical image processing program comprising instructions that cause a computer to implement inputting a first magnetic resonance image reconstructed with super-resolution processing on magnetic resonance data and a second magnetic resonance image obtained by imaging a same object as an object of the first magnetic resonance image and with artifacts suppressed compared with the first magnetic resonance image, to a learned model, the learned model outputting a third magnetic resonance image having a same resolution as a resolution of the first magnetic resonance image and with the artifacts suppressed; and generating the third magnetic resonance image based on the first magnetic resonance image and the second magnetic resonance image, using the learned model. ### Claim 15 (depends on 14) The nonvolatile computer readable storage medium storing therein the medical image processing program comprising instructions according to claim 14 that cause the computer to further implement reconstructing the first magnetic resonance image based on the magnetic resonance data after the super-resolution processing; and reconstructing the second magnetic resonance image based on the magnetic resonance data so that the artifacts occurring by reconstruction with the super-resolution processing are suppressed.