[go: up one dir, main page]

WO2017117710A1 - Système et procédé d'imagerie pour endoscopie - Google Patents

Système et procédé d'imagerie pour endoscopie Download PDF

Info

Publication number
WO2017117710A1
WO2017117710A1 PCT/CN2016/070148 CN2016070148W WO2017117710A1 WO 2017117710 A1 WO2017117710 A1 WO 2017117710A1 CN 2016070148 W CN2016070148 W CN 2016070148W WO 2017117710 A1 WO2017117710 A1 WO 2017117710A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
infrared
visible light
infrared image
generate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/070148
Other languages
English (en)
Chinese (zh)
Inventor
库马阿兔
黄士维
刘楷哲
汪彦佑
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Show Chwan Memorial Hospital
Original Assignee
Show Chwan Memorial Hospital
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Show Chwan Memorial Hospital filed Critical Show Chwan Memorial Hospital
Priority to PCT/CN2016/070148 priority Critical patent/WO2017117710A1/fr
Publication of WO2017117710A1 publication Critical patent/WO2017117710A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons

Definitions

  • the present application relates to an endoscope imaging system and method. More specifically, the present application relates to an endoscope imaging system that analyzes a focused area of an infrared image and superimposes it on a visible light image to display a superimposed image. And methods.
  • Endoscopic surgery is typically performed under visible light, where visible light allows the user to see the surface of the surgical anatomy during the procedure.
  • a special light source such as an infrared source is required.
  • the patient will be injected with Indocyanine green (ICG) dye before surgery, so that the surgeon can see the infrared in the infrared image mode during the operation, such as lymph node resection and bile duct surgery.
  • ICG Indocyanine green
  • the operator needs to continuously switch between the infrared image mode and the visible image mode, which not only causes inconvenience to the operator, but also prolongs the operation time and increases the chance of infection of the patient. .
  • the solution to the above problem is to directly implant the infrared image into the visible light image.
  • the displayed image will be indistinguishable to the operator, thus improving the difficulty of the operation. degree.
  • an endoscope imaging technology that can automatically superimpose an infrared image beyond a visible light image, and can selectively and accurately display a key area and automatically track a key area in a subsequent image.
  • an object of the present application is to provide an endoscope imaging system suitable for displaying images in a patient, which includes an endoscope photography module, an image processing module, a storage unit, an analysis module, and a display module.
  • the endoscope photography module includes a light source, an infrared imager, and an image capture module.
  • the light source is used to illuminate the patient.
  • Infrared imaging The instrument is configured to capture a target area within the patient and produce an infrared image signal.
  • the image capture module is configured to capture a target area and generate a visible light image signal.
  • the image processing module is electrically connected to the endoscope photography module, and receives the infrared image signal and the visible light image signal to generate an infrared image and a visible light image, and associates the infrared image with the visible light image.
  • the storage unit is electrically connected to the image processing module for storing infrared images and visible light images.
  • the analysis module is electrically coupled to the image processing module and configured to analyze the infrared image to generate at least one focus area and superimpose the focus area onto the visible light image associated with the infrared image to produce a superimposed image.
  • the display module is electrically connected to the analysis module and configured to display the superimposed image.
  • the analysis module divides the infrared image into a plurality of key regions according to the intensity distribution of the infrared image, and each of the key regions respectively corresponds to different intensity ranges.
  • the analysis module may superimpose the plurality of key regions in a color block manner to the visible light image associated with the infrared image to generate the superimposed image.
  • the analysis module may further extract edges of the plurality of key regions, and superimpose the edges of the plurality of focus regions in a color line manner to the visible light image associated with the infrared image to generate the superimposed image.
  • the analysis module may further calculate a matching point between two consecutive frames in the visible light image, and generate a transformation matrix according to the matching point, and apply the transformation matrix to the frame that has generated at least one key area and corresponds to the previous frame
  • the infrared image is superimposed and the converted at least one focus area is superimposed on the infrared image corresponding to the subsequent picture frame to generate another superimposed image continuous with the superimposed image.
  • the analysis module can calculate an error value of the matching point, and if the error value exceeds a predetermined range, the infrared imager can be configured to retake the target object and generate another infrared image signal.
  • an endoscope imaging method suitable for the aforementioned endoscope imaging system, comprising the steps of: illuminating a target area in a patient with a light source; and using an infrared imager and an image capturing module Shoot the target area in the patient's body and divide The infrared image signal and the visible light image signal are generated;
  • the image processing module is configured to receive the infrared image signal and the visible light image signal and generate the infrared image and the visible light image, and associate the infrared image with the visible light image; and store the infrared image and the visible light image in the storage unit;
  • the analysis module is configured to analyze the infrared image to generate at least one key area, and superimpose the key area on the visible light image associated with the infrared image to generate the superimposed image; and display the superimposed image in the display module.
  • the analysis module further divides the infrared image into a plurality of key areas according to the intensity distribution of the infrared image, and each of the key areas respectively correspond to different Strength range.
  • the analysis module superimposes the plurality of key regions in a color block manner to the visible light image associated with the infrared image to generate the superimposed image.
  • the analysis module further extracts edges of the plurality of key regions, and superimposes the edges of the plurality of key regions in a color line manner to the visible light image associated with the infrared image to generate the superimposed image.
  • the analysis module further calculates a matching point between the consecutive two frames in the visible light image, and generates a conversion according to the matching point.
  • the analysis module calculates an error value of the matching point, and if the error value exceeds a predetermined range, the infrared imager is configured to retake the target object and generate another infrared image signal.
  • the endoscope imaging system and method of the present application can provide a clear field of view and accurately mark the organ region in the superimposed image provided to the operator, thereby eliminating the need to repeat the visible light image mode. And the time it takes to switch between infrared image modes, Further improve the safety, accuracy and speed of the operation.
  • the time and system resources for retrieving the infrared image can be saved, and the key areas can be selectively and accurately displayed, and the subsequent images can be automatically tracked. Key areas can further improve image processing speed and save system resources.
  • FIG. 1 is a block diagram showing an embodiment of an endoscope imaging system in accordance with the present application.
  • FIG 2 is an example of an infrared image of an embodiment of an endoscope imaging system in accordance with the present application.
  • FIG 3 is an illustration of a visible light image of an embodiment of an endoscope imaging system in accordance with the present application.
  • FIG. 4 is an example of a processed infrared image of an embodiment of an endoscope imaging system in accordance with the present application.
  • FIG. 5 is an example of a superimposed image produced by an embodiment of an endoscope imaging system in accordance with the present application.
  • FIG. 6 is an illustration of a processed infrared image produced by another embodiment of an endoscope imaging system in accordance with the present application.
  • FIG. 7 is an illustration of a processed infrared image produced in accordance with yet another embodiment of an endoscope imaging system of the present application.
  • FIG. 8 is a schematic diagram of calculating matching points for an endoscope imaging system in accordance with the present application.
  • FIG. 11 is a flow chart showing an embodiment of an endoscope imaging method according to the present application.
  • FIG. 12 is a flow chart showing another embodiment of an endoscope imaging method according to the present application.
  • the term "and/or” includes any and all combinations of one or more of the associated listed items.
  • the "at least one of” statements are prefixed to the list of components, the entire list component is modified rather than the individual components in the list.
  • FIG. 1 is a block diagram of an embodiment of an endoscope imaging system according to the present application.
  • the endoscope imaging system 1 of the present application is suitable for displaying images in a patient, and includes an endoscope photography module 102, an image processing module 108, a storage unit 110, an analysis module 116, a display module 118, and a power module 120.
  • the endoscope photography module 102 includes a light source 100, an infrared imager 104, and an image capture module 106.
  • the light source 100 is configured to illuminate a patient, and the infrared imager 104 is configured to capture a target area in the patient's body, wherein the light source 100 can include a visible light source and an infrared light source, and the infrared imager 104 receives the infrared light illuminated by the target area reflected light source 100, And generate infrared image signals.
  • Infrared image acquisition uses a photographic or photographic device to capture light waves in the infrared light field generated by the object being reflected by an infrared light source.
  • FIG. 2 is an example of an infrared image of an embodiment of an endoscope imaging system according to the present application.
  • the patient Before the operation, the patient will inject the Indocyanine green (ICG) dye several hours ago, so that the surgeon can see the image in the infrared image mode during the operation, such as lymph node resection and bile duct surgery.
  • Dye-labeled areas containing lymph nodes or bile ducts As shown in the figure, the area A in which the fluorescence is displayed is the effect of the fluorescent dye, but not the organ area, such as the area B.
  • the image capture module 106 is configured to capture a target area and generate a visible light image signal.
  • the image processing module 108 is electrically connected to the endoscope camera module, and receives the infrared image signal and the visible light image signal, and generates the infrared image 112 and the visible light image 114, and associates the infrared image 112 with the visible light image 114.
  • the visible light image 114 is usually an image with a continuous picture frame, where the association between the single picture frames is generated, that is, the infrared image 112 and the visible light image 114 of the first picture frame, and the method can be referred to.
  • FIG. 3 is an example of a visible light image of an embodiment of an endoscope imaging system in accordance with the present application.
  • the operator usually uses visible light images, but there are some shortcomings in which the organs in the patient cannot be seen.
  • the storage unit 110 is electrically connected to the image processing module 108 for storing the infrared image 112 and the visible light image 114.
  • the analysis module 116 is electrically coupled to the image processing module 108 and configured to analyze the infrared image 112 to generate at least one region of focus.
  • FIG. 4 is an example of a processed infrared image of an embodiment of an endoscope imaging system in accordance with the present application.
  • the infrared image 112 itself is a grayscale image
  • FIG. 4 shows the infrared image 112 in blue by the same gray-scale, and the aforementioned region A corresponds to the converted high-luminance region.
  • A', and area B corresponds to the low-luminance area B'.
  • the grayscale image will be stored in the storage unit 110.
  • the analysis module 108 can analyze the infrared image 112. Specifically, the analysis module 108 can divide the infrared image 112 into multiple key regions according to the gray value distribution of the infrared image 112, and each key point The regions each correspond to a different range of gray values. As shown in the figure, the infrared image 112 is analyzed by the analysis module 108 and divided into two key regions of the gray value range. For the operator, the interested portion is only the organ region A displayed with high brightness. ', therefore, the key area can be divided into two parts, such as area A" and area B".
  • the method for dividing the area of the infrared image 112 can be referred to the "Current methods in medical image segmentation 1, "Annual Review of Biomedical Engineering 2000” by DL Pham et al., which is a technique familiar to those skilled in the art. Therefore, it is not described here.
  • the focus area is superimposed on the visible light image 114 associated with the infrared image 112 to generate a superimposed image
  • the display module 118 is electrically coupled to the analysis module 116 to display the superimposed image.
  • the area A" and the area B" are displayed in a uniform color block, providing the operator with a clear field of view and accurate marking of the organ area, eliminating the need for duplication. Switching between visible light image mode and infrared light image mode takes time to further improve the safety, accuracy and speed of the operation.
  • FIG. 6 is an example of a processed infrared image produced by another embodiment of an endoscope imaging system in accordance with the present application.
  • the analysis module 116 can divide the infrared image 112 into three intensity ranges according to the intensity distribution of the infrared image 112, in other words, the number of key regions is three.
  • the area of lower brightness is displayed in white, and the area of the organ can be divided into area A1 and area A2.
  • the user can set different numbers and different intensity ranges (ie, the gray value range of the grayscale image) according to requirements, so as to increase the flexibility of the system, and is not limited to the description in the specification of the present application.
  • FIG. 7 is an example of a processed infrared image produced by still another embodiment of the endoscope imaging system of the present application.
  • the analysis module 116 can further extract the edges of the plurality of key areas, such as the edges of the areas A1 and A2 in FIG. 6, the color line area as shown in the figure. A1' and A2', and the edges of the plurality of focus areas are superimposed in color lines to the visible light image 114 associated with the infrared image 112 to generate a superimposed image.
  • the analysis module 116 may first generate an image containing only color lines and store it in the storage unit 110, or may directly superimpose the visible light image 112 to generate a superimposed image, which is not limited thereto. It is worth mentioning that the method of extracting the edge of the key area can be referred to the "Study and comparison of various image edge detection techniques” (Study and comparison of various image edge detection techniques, International Journal of Image Processing 2009). It is also a technique well known to those skilled in the art, and therefore will not be described here.
  • FIG. 8 is a schematic diagram of calculating matching points according to the endoscope imaging system of the present application.
  • the visible light image 114 is generally an image with a continuous frame, although the infrared image 112 and the visible light image 114 of the first frame have been processed, in order to display a continuous image, the second frame is required.
  • the visible light image 114 is analyzed to produce another superimposed image.
  • the analysis module 116 performs a matching point calculation on the visible light image between successive frames to generate a conversion matrix.
  • the calculation of the matching point needs to first extract the feature points from the visible light image between successive frames, and then calculate according to the offset of the feature points to obtain the conversion matrix.
  • the matching point CP can pass any feature detection or feature comparison
  • an algorithm refer to Li, Jing, and Nigel M. Allinson et al. for a comprehensive review of local local features for computer vision. "Neurocomputing 71.10 (2008): 1771- 1787), an example of matching point calculation is shown in Figure 8.
  • the transformation matrix can be calculated accordingly.
  • the transformation matrix can be a rigid body or non-rigid body transformation matrix between successive frames, which can be optimized by least squares (see Zitova, Barbara, and Jan). According to Flusser et al., "Image registration methods: a survey, Image and vision computing 21.11 (2003): 977-1000), the transformation matrix shown in the figure is calculated as follows:
  • FIG. 9 and FIG. 10 are examples of superimposed images generated by another embodiment of the endoscope imaging according to the present application and another embodiment.
  • this matrix By applying this matrix to the aforementioned infrared image represented by a color patch or a color line, a superimposed image as shown in FIG. 9 or FIG. 10 can be produced.
  • This superimposed image can replace the previously generated superimposed image to form a superimposed image with continuous images.
  • the error value of the matching point is further calculated in the process of matching point calculation.
  • the analysis module 116 determines that the error value is too large, that is, the matching point offset is too large, or it is difficult to find the same matching point, the configuration system recaptures the infrared image in the patient.
  • FIG. 11 is a flow chart illustrating an embodiment of an endoscope imaging method according to the present application. As shown, the endoscope imaging method is applicable to the above-described endoscope imaging system, which includes the following steps:
  • Step S101 illuminating a target area in the patient's body with a light source
  • Step S102 taking an infrared imager and an image capturing module to capture a target area in the patient, and respectively generating an infrared image signal and a visible light image signal.
  • the infrared imager may first capture the fluorescent image and then switch to the image. Taking a module to capture a visible light image;
  • Step S103 After receiving the infrared image signal and the visible light image signal, the image processing module generates an infrared image and a visible light image, and associates the infrared image with the visible light image;
  • Step S104 storing the infrared image and the visible light image by using the storage unit;
  • Step S105 analyzing the infrared image by the analysis module to generate a key area, and superimposing the key area on the visible light image to generate a superimposed image;
  • Step S106 Display the superimposed image by the display module.
  • the present application also provides an endoscope imaging method. Please refer to FIG. 12, which is a flow chart of another embodiment of an endoscope imaging method according to the present application. As shown, the endoscope imaging method is applicable to the above-described endoscope imaging system, which is continued from step S104 of the previous embodiment, and includes the following steps:
  • Step S201 After obtaining the infrared image, the analysis module divides the infrared image into a plurality of key regions according to the intensity distribution of the infrared image. Specifically, the analysis module 116 may count the infrared image 112 according to the intensity distribution of the infrared image 112. The intensity range is divided, and the image captured by the infrared image is mainly in the area of interest of the physician.
  • Step S202 superimposing a plurality of key regions on the visible light image to generate a superimposed image, wherein the key regions may be represented by color blocks in the superimposed image.
  • the method may first proceed to step S203, the analysis module further extracts edges of the plurality of key regions, and superimposes edges of the plurality of focus regions to the visible light image in a color line manner to generate Superimposed image.
  • Step S204 displaying the superimposed image by the display module. For this reason, only the visible light image of the first frame is currently processed. In order to display the continuous image, the visible image 114 of the second frame needs to be analyzed to generate another Add image.
  • Step S205 capturing a target area in the patient's body by using an image capturing module to generate a visible light image signal
  • Step S206 After receiving the visible light image signal, the image processing module generates a visible light image, and the analysis module further calculates a matching point and an error value between the adjacent frames;
  • Step S207 The configuration analysis module determines whether the error value of the matching point is greater than a predetermined range. If yes, the process proceeds to step S208, the infrared imager is used to capture the target area of the patient to generate an infrared image signal, and the image processing module is configured to generate a new infrared image. (Step S209), that is, once an error has occurred in the use of the visible light image matching region, which is different from the original region of interest or the matching, it is necessary to perform the infrared image capturing and the infrared image segmentation again. And returning to step S201; if it is determined that the error value of the matching point is within the predetermined range, proceeding to step S210, configuring the analysis module to calculate a conversion matrix according to the matching point;
  • Step S211 The analysis module is configured to apply the transformation matrix to the plurality of key regions of the front frame. It should be noted that the endoscope imaging method of the present application can perform image matching only on the first image of the infrared image. To the visible light collection, the function of the subsequent image alignment is performed by the visible light image matching, so that the subsequent pictures can have the function of displaying the characteristic area, and then the process proceeds to step S203, or directly returns to step S202.
  • the endoscope imaging system and method of the present application can provide a clear field of view and accurately mark the organ region in the superimposed image provided to the operator, thereby eliminating the need to repeat the visible light image mode. And the time it takes to switch between infrared image modes further enhances the safety, accuracy and speed of the operation.
  • the system by detecting matching points and errors and calculating the conversion matrix, it is possible to omit the time of retrieving the infrared image.
  • the inter- and system resources can automatically track key areas in subsequent images, further improving image processing speed and saving system resources.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Endoscopes (AREA)

Abstract

L'invention concerne un procédé et un système d'imagerie (1) pour endoscopie, applicables pour afficher une image de l'intérieur du corps d'un patient. Le système comprend un module de caméra d'endoscope (102), un module de traitement d'image (108), une unité de mémoire (110), un module d'analyse (116) et un module d'affichage (118). Le module de caméra d'endoscope (102) comprend une source de lumière (100), un dispositif d'imagerie infrarouge (104) et un module de capture d'image (106). Le dispositif d'imagerie infrarouge (104) et le module de capture d'image (106) peuvent être configurés pour photographier une région cible et générer un signal d'image infrarouge et un signal d'image de lumière visible. Le module de traitement d'image (108) reçoit le signal d'image infrarouge et le signal d'image de lumière visible, et génère une image infrarouge et une image de lumière visible. Le module d'analyse (116) analyse l'image infrarouge, génère au moins une zone clé, et recouvre la région clé sur l'image de lumière visible pour générer une image superposée affichée sur le module d'affichage (118).
PCT/CN2016/070148 2016-01-05 2016-01-05 Système et procédé d'imagerie pour endoscopie Ceased WO2017117710A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/070148 WO2017117710A1 (fr) 2016-01-05 2016-01-05 Système et procédé d'imagerie pour endoscopie

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/070148 WO2017117710A1 (fr) 2016-01-05 2016-01-05 Système et procédé d'imagerie pour endoscopie

Publications (1)

Publication Number Publication Date
WO2017117710A1 true WO2017117710A1 (fr) 2017-07-13

Family

ID=59273336

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/070148 Ceased WO2017117710A1 (fr) 2016-01-05 2016-01-05 Système et procédé d'imagerie pour endoscopie

Country Status (1)

Country Link
WO (1) WO2017117710A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021051222A1 (fr) * 2019-09-16 2021-03-25 北京数字精准医疗科技有限公司 Système d'endoscope, source de lumière mixte, dispositif d'acquisition de vidéo et processeur d'image

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030187319A1 (en) * 2002-03-29 2003-10-02 Olympus Optical Co., Ltd. Sentinel lymph node detecting apparatus, and method thereof
CN102319059A (zh) * 2011-10-28 2012-01-18 北京天助基业科技发展有限公司 近红外荧光造影手术引导装置及其应用
CN103065131A (zh) * 2012-12-28 2013-04-24 中国航天时代电子公司 一种复杂场景下自动目标识别跟踪方法及系统
WO2014176375A2 (fr) * 2013-04-23 2014-10-30 Cedars-Sinai Medical Center Systèmes et procédés d'enregistrement simultané d'une image en lumière visible et d'une image en lumière infrarouge à partir de fluorophores
CN104217413A (zh) * 2014-09-11 2014-12-17 昆明云锗高新技术有限公司 可见光图像上叠加红外光图像的方法
WO2015037340A1 (fr) * 2013-09-10 2015-03-19 ソニー株式会社 Dispositif de traitement d'image, procédé de traitement d'image et programme

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030187319A1 (en) * 2002-03-29 2003-10-02 Olympus Optical Co., Ltd. Sentinel lymph node detecting apparatus, and method thereof
CN102319059A (zh) * 2011-10-28 2012-01-18 北京天助基业科技发展有限公司 近红外荧光造影手术引导装置及其应用
CN103065131A (zh) * 2012-12-28 2013-04-24 中国航天时代电子公司 一种复杂场景下自动目标识别跟踪方法及系统
WO2014176375A2 (fr) * 2013-04-23 2014-10-30 Cedars-Sinai Medical Center Systèmes et procédés d'enregistrement simultané d'une image en lumière visible et d'une image en lumière infrarouge à partir de fluorophores
WO2015037340A1 (fr) * 2013-09-10 2015-03-19 ソニー株式会社 Dispositif de traitement d'image, procédé de traitement d'image et programme
CN104217413A (zh) * 2014-09-11 2014-12-17 昆明云锗高新技术有限公司 可见光图像上叠加红外光图像的方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021051222A1 (fr) * 2019-09-16 2021-03-25 北京数字精准医疗科技有限公司 Système d'endoscope, source de lumière mixte, dispositif d'acquisition de vidéo et processeur d'image

Similar Documents

Publication Publication Date Title
CN110325100B (zh) 内窥镜系统及其操作方法
CN113573654B (zh) 用于检测并测定病灶尺寸的ai系统、方法和存储介质
WO2023103467A1 (fr) Procédé, appareil et dispositif de traitement d'images
CN111295127B (zh) 检查支持装置、内窥镜装置及记录介质
JP6368870B2 (ja) 画像解析装置、画像解析システム、及び画像解析装置の作動方法
JP2023076644A (ja) 内視鏡システム
CN110619318B (zh) 基于人工智能的图像处理方法、显微镜、系统和介质
CN105072968A (zh) 图像处理装置、内窥镜装置、程序和图像处理方法
WO2020054543A1 (fr) Dispositif et procédé de traitement d'image médicale, système d'endoscope, dispositif de processeur, dispositif d'aide au diagnostic et programme
WO2015105951A1 (fr) Système et procédé permettant une imagerie par fluorescence intra-opératoire dans une lumière ambiante
KR20160118037A (ko) 의료 영상으로부터 병변의 위치를 자동으로 감지하는 장치 및 그 방법
US8902305B2 (en) System and method for managing face data
JPWO2019130868A1 (ja) 画像処理装置、プロセッサ装置、内視鏡システム、画像処理方法、及びプログラム
CN116188554A (zh) 一种基于双目立体测量内镜的三维成像方法及装置
JP2010220794A (ja) 内視鏡画像回転装置および方法並びにプログラム
JPWO2019087969A1 (ja) 内視鏡システム、報知方法、及びプログラム
WO2014132475A1 (fr) Dispositif, procédé et programme de traitement d'image et dispositif d'endoscope
CN115311405A (zh) 一种双目内窥镜的三维重建方法
US12475389B2 (en) Training data generation device, recording method, and inference device
JPWO2019203006A1 (ja) 内視鏡装置、内視鏡プロセッサ装置及び内視鏡画像表示方法
WO2017117710A1 (fr) Système et procédé d'imagerie pour endoscopie
CN112867430B (zh) 医疗图像处理系统及学习方法
Liedlgruber et al. Endoscopic image processing-an overview
TWI581750B (zh) 內視鏡成像系統及方法
US10307209B1 (en) Boundary localization of an internal organ of a subject for providing assistance during surgery

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16882857

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16882857

Country of ref document: EP

Kind code of ref document: A1