# US 2021/0174501 A1 · Medical data processing apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0174501 A1 - Document ID: US20210174501A1 - Status: Published application - Kind: A1 - Application number: 17/082,114 - Filed: 2020-10-28 - Published: 2021-06-10 - Earliest claimed: 2019-12-04 - Assignees: Canon Medical Systems Corporation - Applicants: Canon Medical Systems Corporation - Inventors: Hidenori TAKESHIMA - Web page: https://patentgrep.com/patent/US20210174501A1 ## CPC - G06T 7/0012: {Biomedical image inspection} - 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)} - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 5/60: using machine learning, e.g. neural networks - G06T 2207/10088: Magnetic resonance imaging [MRI] - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20216: Image averaging - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) ## Abstract A medical image processing apparatus includes processing circuitry. The processing circuitry generates a plurality of first medical images by applying a plurality of first machine learning models having different elements to a set of raw data, or applying a first machine learning model to a set of raw data a plurality of times while changing elements. The processing circuitry outputs a second medical image and a first reliability relating to the second medical image based on the first medical images. ## Claims ### Claim 1 A medical data processing apparatus comprising a circuitry configured to: generate a plurality of first medical images by applying a plurality of first machine learning models having different elements to a set of raw data, or applying a first machine learning model to a set of raw data a plurality of times while changing elements; and output a second medical image and a first reliability relating to the second medical image based on the first medical images. ### Claim 2 (depends on 1) The medical data processing apparatus according to claim 1, wherein the second medical image is generated by using the first medical images. ### Claim 3 (depends on 1) The medical data processing apparatus according to claim 1, wherein the first reliability is information corresponding to variations between the first medical images. ### Claim 4 (depends on 1) The medical data processing apparatus according to claim 1, wherein the first reliability includes a reliability of every same image area of the first medical images. ### Claim 5 (depends on 1) The medical data processing apparatus according to claim 1, wherein the first reliability evaluates a change in pixel values in same image areas over the first medical images. ### Claim 6 (depends on 1) The medical data processing apparatus according to claim 1, wherein: the processing circuitry outputs the first reliability and the second medical image by applying a second machine learning model to the first medical images; and the second machine learning model is trained based on the first medical images, which are inputs, and the second medical image based on the first medical images and the first reliability relating to the second medical image, which are outputs. ### Claim 7 (depends on 6) The medical data processing apparatus according to claim 6, wherein: the first medical images as the inputs are a plurality of MR medical images corresponding to the number of excitations in magnetic resonance imaging; and the second medical image as the outputs is an addition average image or an addition image based on the MR medical images. ### Claim 8 (depends on 1) The medical data processing apparatus according to claim 1, further comprising a display configured to display the second medical image and the first reliability. ### Claim 9 (depends on 1) The medical data processing apparatus according to claim 1, wherein the processing circuitry applies a third machine learning model to the second medical image and the first reliability, and outputs a processing result of image recognition by the third machine learning model for the second medical image and a second reliability relating to the processing result. ### Claim 10 (depends on 9) The medical data processing apparatus according to claim 9, wherein if the image recognition is an organ classification, the second reliability relates to a reliability of a classification result. ### Claim 11 (depends on 9) The medical data processing apparatus according to claim 9, wherein if the image recognition is a disease determination, the second reliability relates to a reliability of a determination result. ### Claim 12 (depends on 9) The medical data processing apparatus according to claim 9, wherein if the second reliability is lower than a threshold value, the processing circuitry instructs control circuitry of magnetic resonance imaging to perform additional acquisition. ### Claim 13 A medical image processing apparatus comprising processing circuitry configured to: obtain a medical image and a first reliability relating to the medical image; and apply a machine learning model that performs image recognition to the medical image and the first reliability, and output a processing result of the image recognition for the medical image and a second reliability relating to the processing result. ### Claim 14 A medical image processing apparatus comprising processing circuitry configured to: obtain raw data; perform iterative reconstruction on the raw data, thereby generating a plurality of medical images which are intermediate products and/or final products; and apply a machine learning model to the generated medical images, thereby generating one medical image.