# US 10,872,411 B2 · Diagnostic imaging assistance apparatus and system, and diagnostic imaging assistance method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,411 B2 - Document ID: US10872411B2 - Status: Granted - Kind: B2 - Application number: 16/340,401 - Filed: 2017-10-26 - Published: 2019-08-01 - Granted: 2020-12-22 - Earliest claimed: 2016-11-01 - Assignees: Hitachi High-Tech Corporation - Applicants: Hitachi High-Technologies Corporation - Inventors: Hideharu Hattori; Kenko Uchida; Sadamitsu Aso; Toshinari Sakurai; Yasuki Kakishita - Web page: https://patentgrep.com/patent/US10872411B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G01N 15/00: Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials - G01N 33/48: Biological material, e.g. blood, urine (G01N33/02, G01N33/26, G01N33/44, G01N33/46 take precedence); Haemocytometers (counting blood corpuscules distributed over a surface by scanning the surface G06M11/02) - G06T 1/0007: {Image acquisition} - G06V 20/698: {Matching; Classification} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 30/40: for processing medical images, e.g. editing - G16H 40/67: for remote operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06T 2207/10056: Microscopic image - G06T 2207/20081: Training; Learning - G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro - G06T 2207/30096: Tumor; Lesion - G06V 20/695: {Preprocessing, e.g. image segmentation} - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A diagnostic imaging assistance apparatus according to the present invention performs a process of inputting images of a tissue and a cell, a process of extracting feature amounts of a wide view and a narrow view from a target image to be processed, a process of classifying whether the target images having different views are normal or abnormal from the feature amounts, and a process of classifying a lesion likelihood using a classification result. ## Claims ### Claim 1 A diagnostic imaging assistance apparatus comprising: an input unit configured to receive wide view image data and narrow view image data in a same image as image data obtained by capturing a slice of a tissue or a cell of a diagnostic object; a feature extraction unit configured to process the image data input to the input unit to extract a feature amount on an image of the tissue from the wide view image data and extract a feature amount on an image of the cell from the narrow view image data; a single view determination unit configured to classify whether the tissue is normal or abnormal from the feature amount of the wide view image data extracted by the feature extraction unit, and classify whether the cell is normal or abnormal from the feature amount of the narrow view image data; a multiple view determination unit configured to classify a lesion likelihood of the diagnostic object from a classification result of the wide view image data and a classification result of the narrow view image data classified by the single view determination unit; a drawing unit configured to actualize a region containing the tissue or the cell classified as abnormal by the multiple view determination unit on the image data; and a recording unit configured to store an image of which the region containing the tissue or the cell classified as abnormal is actualized by the drawing unit. ### Claim 2 (depends on 1) The diagnostic imaging assistance apparatus according to claim 1, further comprising a learning unit configured to create a first identifier to classify whether the tissue in the image data input to the input unit is a normal tissue or an abnormal tissue using the feature amount of the wide view image data of a slice of the tissue extracted by the feature extraction unit and a result obtained by classifying whether the tissue is normal or abnormal by the single view determination unit, and a second identifier to classify whether the cell in the image data input to the input unit is a normal cell or an abnormal cell using the feature amount of the narrow view image data of a slice of the cell extracted by the feature extraction unit and a result obtained by classifying whether the cell is normal or abnormal by the single view determination unit. ### Claim 3 (depends on 1) The diagnostic imaging assistance apparatus according to claim 1, wherein the single view determination unit calculates a deformed degree of the tissue from the feature amount of the wide view image data to classify whether the tissue is normal or abnormal, and calculates a deformed degree of the cell from the feature amount of the narrow view image data to classify whether the cell is normal or abnormal. ### Claim 4 (depends on 1) The diagnostic imaging assistance apparatus according to claim 1, wherein the drawing unit surrounds a region containing the tissue or the cell classified as abnormal by the multiple view determination unit with a frame on the image data to actualize the region containing the tissue or the cell. ### Claim 5 (depends on 1) The diagnostic imaging assistance apparatus according to claim 1, further comprising an output unit including a display screen, wherein the wide view image data and the narrow view image data in which a region containing the tissue or the cell classified as abnormal by the multiple view determination unit is actualized in the drawing unit are displayed on the display screen of the output unit side by side. ### Claim 6 A diagnostic imaging assistance method comprising: inputting wide view image data obtained by capturing a tissue of a diagnostic object to an input unit; processing the wide view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the tissue; classifying whether the tissue is normal or abnormal by a single view determination unit from the feature amount of the wide view image data extracted by the feature extraction unit; inputting narrow view image data in a same image as the wide view containing a cell captured from the tissue classified as abnormal by the single view determination unit to the input unit, the narrow view image data and the wide view image data comprising image data; processing the narrow view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the cell; classifying whether the cell is normal or abnormal by the single view determination unit from the feature amount of the narrow view image data extracted by the feature extraction unit; classifying a lesion likelihood of the diagnostic object by a multiple view determination unit from a classification result of the wide view image data and a classification result of the narrow view image data classified by the single view determination unit; actualizing a region containing the tissue or the cell classified as abnormal by the single view determination unit on the image data in a drawing unit; and storing the image data obtained by actualizing the region containing the tissue or the cell classified as abnormal in a recording unit. ### Claim 7 (depends on 6) The diagnostic imaging assistance method according to claim 6, wherein a learning unit creates a first identifier to classify whether the tissue in the image data input to the input unit is a normal tissue or an abnormal tissue using the feature amount of the wide view image data of a slice of the tissue extracted by the feature extraction unit and a result obtained by classifying whether the tissue is normal or abnormal by the single view determination unit, and a second identifier to classify whether the cell in the image data input to the input unit is a normal cell or an abnormal cell using the feature amount of the narrow view image data of a slice of the cell extracted by the feature extraction unit and a result obtained by classifying whether the cell is normal or abnormal by the single view determination unit. ### Claim 8 (depends on 6) The diagnostic imaging assistance method according to claim 6, wherein the single view determination unit calculates a deformed degree of the tissue from the feature amount of the wide view image data to classify whether the tissue is normal or abnormal, and calculates a deformed degree of the cell from the feature amount of the narrow view image data to classify whether the cell is normal or abnormal. ### Claim 9 (depends on 6) The diagnostic imaging assistance method according to claim 6, wherein the drawing unit surrounds a region containing the tissue or the cell classified as abnormal by the multiple view determination unit with a frame on the image data to actualize the region containing the tissue or the cell. ### Claim 10 (depends on 6) The diagnostic imaging assistance method according to claim 6, wherein the wide view image data and the narrow view image data in which a region containing the tissue or the cell classified as abnormal by the multiple view determination unit is actualized in the drawing unit are displayed on a display screen of an output unit side by side. ### Claim 11 A diagnostic imaging assistance method comprising: inputting narrow view image data obtained by capturing a cell of a diagnostic object to an input unit; processing the narrow view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the cell; classifying whether the cell is normal or abnormal by a single view determination unit from the feature amount of the narrow view image data extracted by the feature extraction unit; capturing an image of a tissue containing a cell classified as abnormal by the single view determination unit to input wide view image data of the tissue to the input unit, the narrow view image data and the wide view image data comprising image data; processing the wide view image data input to the input unit by a feature extraction unit to extract a feature amount on the image of the tissue; classifying whether the tissue is normal or abnormal by the single view determination unit from the feature amount of the wide view image data extracted by the feature extraction unit; classifying a lesion likelihood of the diagnostic object by a multiple view determination unit from a classification result of the narrow view image data and a classification result of the wide view image data classified by the single view determination unit; actualizing a region containing the cell or the tissue classified as abnormal by the single view determination unit on the image data in a drawing unit; and storing the image data obtained by actualizing the region containing the cell or the tissue classified as abnormal in a recording unit. ### Claim 12 (depends on 11) The diagnostic imaging assistance method according to claim 11, wherein a learning unit creates a first identifier to classify whether the cell in the image data input to the input unit is a normal cell or an abnormal cell using the feature amount of the narrow view image data of a slice of the cell extracted by the feature extraction unit and a result obtained by classifying whether the cell is normal or abnormal by the single view determination unit, and a second identifier to classify whether the tissue in the image data input to the input unit is a normal tissue or an abnormal tissue using the feature amount of the wide view image data of a slice of the tissue extracted by the feature extraction unit and a result obtained by classifying whether the tissue is normal or abnormal by the single view determination unit. ### Claim 13 (depends on 11) The diagnostic imaging assistance method according to claim 11, wherein the single view determination unit calculates a deformed degree of the cell from the feature amount of the narrow view image data to classify whether the cell is normal or abnormal, and calculates a deformed degree of the tissue from the feature amount of the wide view image data to classify whether the tissue is normal or abnormal. ### Claim 14 (depends on 11) The diagnostic imaging assistance method according to claim 11, wherein the drawing unit surrounds a region containing the tissue or the cell classified as abnormal by the multiple view determination unit with a frame on the image data to actualize the region containing the tissue or the cell. ### Claim 15 (depends on 11) The diagnostic imaging assistance method according to claim 11, wherein the wide view image data and the narrow view image data in which a region containing the tissue or the cell classified as abnormal by the multiple view determination unit is actualized in the drawing unit are displayed on a display screen of an output unit side by side. ### Claim 16 (depends on 1) A remote diagnostic assistance system, comprising: an image acquisition device including an image capturing unit to capture image data and a display unit; and a server including the diagnostic imaging assistance apparatus according to claim 1, wherein the image acquisition device transmits the image data to the server, the server receives the transmitted image data, processes the image data by the diagnostic imaging assistance apparatus, stores images of a tissue and a cell determined and a determination result in a memory, and transmits the images and the determination result to the image acquisition device, and the image acquisition device displays the determination result and the images of the tissue and the cell determined which are transmitted from the server on the display unit. ### Claim 17 (depends on 1) A network entrusting service provision system comprising: an image acquisition/processing device including an image capturing unit to capture image data; a server including the diagnostic imaging assistance apparatus according to claim 1; and a display device, wherein the image acquisition/processing device transmits the image data to the server, the server receives the transmitted image data, processes the image data by the diagnostic imaging assistance apparatus, stores images of a tissue and a cell determined and an identifier in a memory, and transmits an identifier to the image acquisition/processing device, and the diagnostic imaging assistance apparatus according to claim 1 in the image acquisition/processing device determines images of other tissues and cells using the received identifier transmitted from the server, and displays a determination result on the display device.