# US 8,542,896 B2 · Medical image processing device and medical image processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,542,896 B2 - Document ID: US8542896B2 - Status: Granted - Kind: B2 - Application number: 13/124,452 - Filed: 2009-10-20 - Published: 2011-09-22 - Granted: 2013-09-24 - Earliest claimed: 2009-10-20 - Assignees: Hitachi Medical Corporation - Applicants: Shino Tanaka; Takashi Shirahata; Takayuki Kadomura; Tetsuo Nakazawa - Inventors: Shino Tanaka; Takashi Shirahata; Takayuki Kadomura; Tetsuo Nakazawa - Web page: https://patentgrep.com/patent/US8542896B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/10072: Tomographic images - G06T 2207/10132: Ultrasound image - G06T 2207/20221: Image fusion; Image merging - G06T 2207/30032: Colon polyp - G06T 2207/30096: Tumor; Lesion - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract There is provided a medical image processing device and a medical image processing method that can extract and display lesion candidate regions having different sizes and similarity forms at a time through a series of processing. Therefore, with respect to a first medical image, a first evaluation for the curved surface form of the first medical image is made to extract first lesion candidate regions. With respect to each of the first lesion candidate regions extracted by a first extracting unit, a second evaluation for the curved surface form thereof is made to extract a second lesion candidate region. The second lesion candidate region extracted by a second extracting unit is superimposed and displayed on a second medical image. ## Claims ### Claim 1 A medical image processing device for extracting from a medical image, and displaying, lesion candidate regions on a surface of an organ, the medical image processing device comprising: a first extracting unit that makes a first evaluation of a curved surface form of the organ by using an initial parameter, and extracts first lesion candidate regions from volume image data based on the first evaluation; a second extracting unit that makes a second evaluation of a curved surface form of the organ by using a parameter reset based on a region size of each of the first lesion candidate regions, and re-extracts second lesion candidate regions from volume image data based on the second evaluation; and a display unit that superimposes and displays the second lesion candidate regions extracted by the second extracting unit on a second medical image. ### Claim 2 (depends on 1) The medical image processing device according to claim 1, characterized in that the first extracting unit and the second extracting unit make the first evaluation and the second evaluation by using a form exponent for estimating a state of the curved surface form. ### Claim 3 (depends on 2) The medical image processing device according to claim 2, characterized in that the first extracting unit and the second extracting unit calculate the form exponent by using a predetermined parameter. ### Claim 4 (depends on 3) The medical image processing device according to claim 3, characterized in that the form exponent is Shape Index, and the predetermined parameter is a differential distance for determining a differential value at a point of interest. ### Claim 5 (depends on 3) The medical image processing device according to claim 3, characterized in that the second extracting unit calculates the form exponent by using a differential distance corresponding to a region size of each of the first lesion candidate regions. ### Claim 6 (depends on 1) The medical image processing device according to claim 1, characterized in that the first extracting unit and the second extracting unit calculate a predetermined feature amount for the extracted lesion candidate regions, and by extracting regions in which the calculated feature amount falls into a predetermined threshold value range, delete a false-positive region from the extracted lesion candidate regions. ### Claim 7 (depends on 6) The medical image processing device according to claim 6, characterized in that the second extracting unit executes expansion processing on regions obtained by deleting the false-positive region from the first lesion candidate regions to make the second evaluation. ### Claim 8 (depends on 1) The medical image processing device according to claim 1, characterized in that the first medical image and the second medical image are panoramic images of a hollow organ region created by using volume image data. ### Claim 9 (depends on 1) The medical image processing device according to claim 1, characterized in that the first medical image and the second medical image are virtual endoscopic images of a hollow organ region created by using volume image data. ### Claim 10 (depends on 1) The medical image processing device according to claim 1, characterized in that the first medical image is a panoramic image of a hollow organ region created by using volume image data, and the second medical image is a virtual endoscopic image of the hollow organ region created by using the volume image data. ### Claim 11 (depends on 1) The medical image processing device according to claim 1, characterized in that the display unit further superimposes and displays the second lesion candidate regions extracted by the second extracting unit on the second medical image in a display style corresponding to a form of the second lesion candidate region. ### Claim 12 (depends on 1) The medical image processing device according to claim 1, characterized in that the display unit further superimposes and displays the second lesion candidate regions extracted by the second extracting unit on the second medical image in a display style corresponding to a region size of the second lesion candidate region. ### Claim 13 (depends on 1) The medical image processing device according to claim 1, further comprising an specifying unit that specifies a range concerning the region size of the lesion candidate region to be superimposed and displayed on the second medical image, wherein the display unit further superimposes and displays, on the second medical image, a second lesion candidate region having a region size within the range specified by the specifying unit out of the second lesion candidate regions extracted by the second extracting unit. ### Claim 14 A medical image processing method for extracting from a medical image, and displaying, lesion candidate regions on a surface of an organ, the medical image processing method comprising: a first extracting step that makes a first evaluation of a curved surface form of the organ by using an initial parameter, and extracts first lesion candidate regions from volume image data based on the first evaluation; a second extracting step that makes a second evaluation of a curved surface form of the organ by using a parameter reset based on a region size of each of the first lesion candidate regions, and re-extracts second lesion candidate regions from volume image data based on the second evaluation; and a display step that superimposes and displays the second lesion candidate regions, extracted in the second extraction step, on a second medical image. ### Claim 15 (depends on 14) The medical image processing method according to claim 14, characterized in that the display step further superimposes and displays the second lesion candidate regions extracted by the second extracting step in a display style corresponding to a form or region size of the second lesion candidate.