MLchartDataset catalogue

Patent · US2020193241A1 · A1 · US

Surgical instrument detection system and computer program

(11) Publication number
US2020193241A1
(21) Application number
16/617,742
(22) Filing date
2018-05-30
(30) Priority date
2017-05-31
(43) Publication date
2020-06-18
(51) IPC
A61B 34/00; A61B 34/20; G06V 10/44; G06V 10/56; A61B 17/28
(52) CPC
  • G06V Image or video recognition or understanding: 10/44, 10/56, 10/751, 20/00, 2201/034
  • A61B Diagnosis; surgery; identification: 17/28, 2034/2055, 2034/2065, 2090/0805, 34/20, 34/25, 90/08, 90/90
  • G06F Electric digital data processing: 18/24
  • G06K Graphical data reading; presentation of data; record carriers; handling record carriers: 9/342, 9/4652, 9/6202, 9/6267
  • G06T Image data processing or generation, in general: 7/00, 7/0008, 7/11
(73) Assignee
Eizo Corp
(72) Inventors
Takuya Katayama; Nobuaki SUGII
(54) Title
Surgical instrument detection system and computer program
(57) Abstract

A surgical instrument detection system is provided that can determine the kinds of surgical instruments without special processing, such as application of an optically readable symbol, to the surgical instruments. A surgical instrument detection system 100 includes: an image input section 31 to input an image taken by a camera 1; an object extraction section 32 to clip an object image of a small steel article from the input image; a determination section 33 to input the object image to a learned classification model 331 and determine a kind of the small steel article based on features included in the object image; and an output image generation section 34 to generate an image representing the result of determination by the determination section and output such image to a monitor 2.

Full text
View on Google Patents

Claims (1)

  1. A surgical instrument detection system, comprising: an image input section to input an image taken by a camera; an object extraction section to clip an object image of a surgical instrument from the input image; a determination section to input the object image to a learned classification model and determine a kind of the surgical instrument based on features included in the object image; and an output image generation section to generate an image representing the result of determination by the determination section and output such image to a monitor. 2. The surgical instrument detection system of claim 1, wherein the output image generation section outputs an image representing the kind of the surgical instrument overlaid on the object image in the taken image. 3. The surgical instrument detection system of claim 1, wherein the object extraction section clips the object image based on comparison of a color space vector for each pixel in a background image and the taken image. 4. The surgical instrument detection system of claim 1, wherein the object extraction section inputs the taken image to a learned object extraction model and clips the object image based on features included in the taken image. 5. The surgical instrument detection system of claim 1, wherein the object extraction section converts pixel data of the taken image to data in an HSV color space and clips the object image based on edge information on hue and saturation. 6. The surgical instrument detection system of claim 1, further comprising a comparison section to compare the kinds and number of surgical instruments after surgery with the kinds and number of surgical instruments before surgery, wherein the output image generation section generates an image representing the result of comparison by the comparison section and outputs such image to the monitor. 7. A computer readable storage medium comprising a program causing a processor of a computer to execute surgical instrument detection, wherein the surgical instrument detection comprises instructions for inputting an image taken by a camera; clipping an object image of a surgical instrument from the input image; determining, by inputting the object image to a learned classification model, a kind of the surgical instrument based on features included in the object image; and generating an image representing the result of determination and outputting such image to a monitor. 8. A surgical instrument detection method executed by a processor of a computer, the method comprising: inputting an image taken by a camera; clipping an object image of a surgical instrument from the input image; determining, by inputting the object image to a learned classification model, a kind of the surgical instrument based on features included in the object image; and generating an image representing the result of determination and outputting such image to a monitor.

Description

The present invention relates to a system to detect a surgical instrument used in surgery and the like.

Many surgical instruments, such as forceps and tweezers, are used in surgery. Since leaving a surgical instrument in the patient's body during surgery is medical malpractice that should not occur, it is thoroughly ensured that the kind and number of surgical instruments are counted before surgery and whether all surgical instruments are complete is checked after surgery.

However, surgical instruments come in a wide variety of kinds and many of them look very alike only with a slight difference in shape and size. It is thus difficult even for an experienced nurse to accurately distinguish the kinds of surgical instruments by visual observation.

A surgical appliance preparation system is conventionally proposed that can identify the kinds of surgical appliances (including small steel articles) using optically readable symbols, such as bar codes, given to the surgical appliances (PTL 1). It should be noted that the surgical appliance preparation system disclosed in PTL 1 is used for preparation of surgical appliances used in surgery before surgery and is not to check whether the surgical appliances are complete after surgery.

PTL 1: JP 6-142105A

However, giving such an optically readable symbol to each surgical instrument requires special processing, causing an increase in production costs of the surgical instruments. It also takes time and effort for reading the symbol from each surgical instrument with a reader.

Record as JSON
{
  "publication_number": "US2020193241A1",
  "country": "US",
  "kind": "A1",
  "title": "Surgical instrument detection system and computer program",
  "abstract": "A surgical instrument detection system is provided that can determine the kinds of surgical instruments without special processing, such as application of an optically readable symbol, to the surgical instruments. A surgical instrument detection system 100 includes: an image input section 31 to input an image taken by a camera 1; an object extraction section 32 to clip an object image of a small steel article from the input image; a determination section 33 to input the object image to a learned classification model 331 and determine a kind of the small steel article based on features included in the object image; and an output image generation section 34 to generate an image representing the result of determination by the determination section and output such image to a monitor 2.",
  "claims": [
    "1. A surgical instrument detection system, comprising: an image input section to input an image taken by a camera; an object extraction section to clip an object image of a surgical instrument from the input image; a determination section to input the object image to a learned classification model and determine a kind of the surgical instrument based on features included in the object image; and an output image generation section to generate an image representing the result of determination by the determination section and output such image to a monitor. 2. The surgical instrument detection system of claim 1, wherein the output image generation section outputs an image representing the kind of the surgical instrument overlaid on the object image in the taken image. 3. The surgical instrument detection system of claim 1, wherein the object extraction section clips the object image based on comparison of a color space vector for each pixel in a background image and the taken image. 4. The surgical instrument detection system of claim 1, wherein the object extraction section inputs the taken image to a learned object extraction model and clips the object image based on features included in the taken image. 5. The surgical instrument detection system of claim 1, wherein the object extraction section converts pixel data of the taken image to data in an HSV color space and clips the object image based on edge information on hue and saturation. 6. The surgical instrument detection system of claim 1, further comprising a comparison section to compare the kinds and number of surgical instruments after surgery with the kinds and number of surgical instruments before surgery, wherein the output image generation section generates an image representing the result of comparison by the comparison section and outputs such image to the monitor. 7. A computer readable storage medium comprising a program causing a processor of a computer to execute surgical instrument detection, wherein the surgical instrument detection comprises instructions for inputting an image taken by a camera; clipping an object image of a surgical instrument from the input image; determining, by inputting the object image to a learned classification model, a kind of the surgical instrument based on features included in the object image; and generating an image representing the result of determination and outputting such image to a monitor. 8. A surgical instrument detection method executed by a processor of a computer, the method comprising: inputting an image taken by a camera; clipping an object image of a surgical instrument from the input image; determining, by inputting the object image to a learned classification model, a kind of the surgical instrument based on features included in the object image; and generating an image representing the result of determination and outputting such image to a monitor."
  ],
  "description_excerpt": "The present invention relates to a system to detect a surgical instrument used in surgery and the like.\n\nMany surgical instruments, such as forceps and tweezers, are used in surgery. Since leaving a surgical instrument in the patient's body during surgery is medical malpractice that should not occur, it is thoroughly ensured that the kind and number of surgical instruments are counted before surgery and whether all surgical instruments are complete is checked after surgery.\n\nHowever, surgical instruments come in a wide variety of kinds and many of them look very alike only with a slight difference in shape and size. It is thus difficult even for an experienced nurse to accurately distinguish the kinds of surgical instruments by visual observation.\n\nA surgical appliance preparation system is conventionally proposed that can identify the kinds of surgical appliances (including small steel articles) using optically readable symbols, such as bar codes, given to the surgical appliances (PTL 1). It should be noted that the surgical appliance preparation system disclosed in PTL 1 is used for preparation of surgical appliances used in surgery before surgery and is not to check whether the surgical appliances are complete after surgery.\n\nPTL 1: JP 6-142105A\n\nHowever, giving such an optically readable symbol to each surgical instrument requires special processing, causing an increase in production costs of the surgical instruments. It also takes time and effort for reading the symbol from each surgical instrument with a reader.",
  "cpc": [
    "G06V 10/44",
    "A61B 17/28",
    "A61B 2034/2055",
    "A61B 2034/2065",
    "A61B 2090/0805",
    "A61B 34/20",
    "A61B 34/25",
    "A61B 90/08",
    "A61B 90/90",
    "G06F 18/24",
    "G06K 9/342",
    "G06K 9/4652",
    "G06K 9/6202",
    "G06K 9/6267",
    "G06T 7/00",
    "G06T 7/0008",
    "G06T 7/11",
    "G06V 10/56",
    "G06V 10/751",
    "G06V 20/00",
    "G06V 2201/034"
  ],
  "ipc": [
    "A61B 34/00",
    "A61B 34/20",
    "G06V 10/44",
    "G06V 10/56",
    "A61B 17/28"
  ],
  "assignees": [
    "Eizo Corp"
  ],
  "inventors": [
    "Takuya Katayama",
    "Nobuaki SUGII"
  ],
  "filing_date": "2018-05-30",
  "publication_date": "2020-06-18",
  "priority_date": "2017-05-31",
  "application_number": "US-201816617742-A",
  "family_id": "64455477",
  "cited_by_count": 13
}

Record 2,107 of 8,000 in Patents full text (MLC-0201). Request the full dataset.