CN111839444A - 一种基于图像识别匹配的肠镜镜头静止检测方法 - Google Patents

一种基于图像识别匹配的肠镜镜头静止检测方法 Download PDF

Info

Publication number
CN111839444A
CN111839444A CN201910339637.6A CN201910339637A CN111839444A CN 111839444 A CN111839444 A CN 111839444A CN 201910339637 A CN201910339637 A CN 201910339637A CN 111839444 A CN111839444 A CN 111839444A
Authority
CN
China
Prior art keywords
still
gray
lens
frame
image
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.)
Pending
Application number
CN201910339637.6A
Other languages
English (en)
Inventor
王玉峰
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.)
Yang Guozhen
Original Assignee
Tianjin Yujin Artificial Intelligence Medical Technology Co ltd
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 Tianjin Yujin Artificial Intelligence Medical Technology Co ltd filed Critical Tianjin Yujin Artificial Intelligence Medical Technology Co ltd
Priority to CN201910339637.6A priority Critical patent/CN111839444A/zh
Publication of CN111839444A publication Critical patent/CN111839444A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/31Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the rectum, e.g. proctoscopes, sigmoidoscopes, colonoscopes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/00002Operational features of endoscopes
    • A61B1/00004Operational features of endoscopes characterised by electronic signal processing
    • A61B1/00009Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/00002Operational features of endoscopes
    • A61B1/00043Operational features of endoscopes provided with output arrangements
    • A61B1/00055Operational features of endoscopes provided with output arrangements for alerting the user
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/00002Operational features of endoscopes
    • A61B1/00057Operational features of endoscopes provided with means for testing or calibration
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/04Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances

Abstract

本发明公开一种基于图像识别匹配的肠镜镜头静止检测方法,包括步骤:在肠镜视频中,读取每帧目标图像,转化为灰度图,然后归一化成512*512,并切割成4*4小块;计算每一个小块的灰度均值,得到一个16个数值的均值集合;计算前一帧与当前帧灰度均值集合的差,进而求出变化比例;若连续N帧变化比例低于阈值,则认为镜头发生静止。本发明能有效判断医生在给患者进行肠镜检查手术时的有效退镜检查时间是否达到了预定的时间以上,且能够予以提醒。

Description

一种基于图像识别匹配的肠镜镜头静止检测方法
技术领域
本发明涉及图像检测技术领域,特别是涉及一种基于图像识别匹配的肠镜镜头静止检测方法。
背景技术
结直肠癌在我国的发病率和死亡率近些年来呈现明显的上升趋势。早发现、早治疗是目前降低结直肠癌死亡率的主要策略。肠镜检查是发现结直肠息肉及肿瘤最有效的检查方法之一,也是结直肠肿瘤筛选的主要方法。使用肠镜检查发现结肠息肉,由于患者的肠道准备情况、操作者的结肠镜检查技术熟练程度、结肠息肉的形状和大小等情况的不同,以及检查时退镜时间不够充分都可能对结肠镜的检查结果产生影响。腺瘤性息肉作为癌前病变,其发现率被认为是衡量结肠镜检查质量的主要指标之一。结肠镜检查对早癌的早期发现、早期诊断及早期治疗有着重要的作用,若出现漏检,可能会延误医治的最佳时机,因此,最大限度地降低漏诊从某种意义上讲可以降低患者的死亡率。
相关研究发现,在结肠镜检查时,随着退镜检查时间的延长,息肉发现率逐渐增加,当退镜时间大于6分钟时,息肉的发现率最高,随着退镜时间的延长,腺瘤性息肉的发现率以及平均每个受检者的息肉发现数目亦增加。肠镜检查时退镜时间不低于6分钟可以增加结直肠息肉的发现概率,延长退镜时间对于提高结直肠镜检查质量,减少结直肠癌发病具有重要意义。
需要说明的是,退镜时间在这里指的是有效退镜检查时间,在退镜检查过程中,由于非正常检查相关原因而引起的肠镜画面静止部分时间是不计入其内的,因此,在开发的“结肠镜智能质控工作站”中,有必要对于这部分时间进行检测,以判断医生在给患者进行肠镜检查手术时的有效退镜检查时间是否达到了6分钟以上。
发明内容
本发明的目的是针对现有技术中存在的技术缺陷,而提供一种基于图像识别匹配的肠镜镜头静止检测方法,用于实时检测在退镜检查过程中由于非正常检查相关原因而引起的肠镜画面静止现象,从而有效判断医生在给患者进行肠镜检查手术时的有效退镜检查时间是否达到了预定时间以上,并能够予以提醒,提高操作者的结直肠镜检查质量。
为实现本发明的目的所采用的技术方案是:
一种基于图像识别匹配的肠镜镜头静止检测方法,包括步骤:
在肠镜视频中,读取每帧目标图像,转化为灰度图,然后归一化成512*512,并切割成4*4小块;
计算每一个小块的灰度均值,得到一个16个数值的均值集合;
计算前一帧与当前帧灰度均值集合的差,进而求出变化比例;
若连续N帧变化比例低于阈值,则认为镜头发生静止。
进一步的,检测出肠镜镜头静止时,向前端Web界面传递静止帧相关参数。
优选的,若连续N帧变化比例低于15%,则给出肠镜镜头处于静止状态的提示。
优选的,所述静止帧相关参数包括静止总帧数及视频总帧数,前端根据静止帧数计算相应的静止时间。
其中,所述静止时间=静止帧数/视频帧率*检查时间。
与现有技术相比,本发明的有益效果是:
本发明提出的一种基于图像识别匹配的肠镜镜头静止检测方法,用于实时检测在退镜检查过程中由于非正常检查相关原因而引起的肠镜画面静止现象,从而有效判断医生在给患者进行肠镜检查手术时的有效退镜检查时间是否达到了预定的时间以上,且能够予以提醒,提高操作者的结直肠镜检查质量,从而降低结肠镜检查病变漏诊率。
附图说明
图1为基于图像识别匹配的肠镜镜头静止检测方法流程图。
具体实施方式
以下结合附图和具体实施例对本发明作进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
如图1所示,本发明基于图像识别匹配的肠镜镜头静止检测方法流程图,其中包括:
步骤101,数据搜集。在肠镜视频中找出在退镜检查过程中由于非正常检查相关原因而引起的肠镜画面静止部分。
步骤102,OpenCV图像分析与处理。使用opencv读取含有画面静止部分的视频,循环读取每一帧,将其转化为灰度图,归一化成512*512,并切割成4*4小块;
计算每一个小块的灰度均值,得到一个16个数值的均值集合,使用该算法计算前后帧灰度均值集合的差,使用python中的matplotlib库,绘制曲线,得出视频画面静止部分变化阈值低于15%;
步骤103,图像匹配检测。使用OpenCV编写程序,每隔一百帧图像,进行一次灰度直方图匹配,与步骤102获得的阈值15%进行比较,当小于等于15%时,说明这两幅图像相似度很高,当连续250帧判断均为小于等于15%时,说明近10秒内肠镜图像一直处于同一画面,判定为“肠镜镜头静止”。
步骤104,参数传递到前端。当步骤103中检测出肠镜镜头静止时,统计静止帧数,当检查结束后,向前端Web界面传递相关参数,包括静止总帧数及视频总帧数。前端根据静止帧数计算相应的静止时间。
其中,静止时间=静止帧数/视频帧率*检查时间。
以上所述仅是本发明的优选实施方式,应当指出的是,对于本技术领域的普通技术人员来说,在不脱离本发明原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。

Claims (5)

1.一种基于图像识别匹配的肠镜镜头静止检测方法,其特征在于,包括步骤:
在肠镜视频中,读取每帧目标图像,转化为灰度图,然后归一化成512*512,并切割成4*4小块;
计算每一个小块的灰度均值,得到一个16个数值的均值集合;
计算前一帧与当前帧灰度均值集合的差,进而求出变化比例;
若连续N帧变化比例低于阈值,则认为镜头发生静止。
2.如权利要求1所述基于图像识别匹配的肠镜镜头静止检测方法,其特征在于,检测出肠镜镜头静止时,向前端Web界面传递静止帧相关参数。
3.如权利要求1所述基于图像识别匹配的肠镜镜头静止检测方法,其特征在于,若连续N帧变化比例低于15%,则给出肠镜镜头处于静止状态的提示。
4.如权利要求1所述基于图像识别匹配的肠镜镜头静止检测方法,其特征在于,所述静止帧相关参数包括静止总帧数及视频总帧数,前端根据静止帧数计算相应的静止时间。
5.如权利要求4所述基于图像识别匹配的肠镜镜头静止检测方法,其特征在于,所述静止时间=静止帧数/视频帧率*检查时间。
CN201910339637.6A 2019-04-25 2019-04-25 一种基于图像识别匹配的肠镜镜头静止检测方法 Pending CN111839444A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910339637.6A CN111839444A (zh) 2019-04-25 2019-04-25 一种基于图像识别匹配的肠镜镜头静止检测方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910339637.6A CN111839444A (zh) 2019-04-25 2019-04-25 一种基于图像识别匹配的肠镜镜头静止检测方法

Publications (1)

Publication Number Publication Date
CN111839444A true CN111839444A (zh) 2020-10-30

Family

ID=72951406

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910339637.6A Pending CN111839444A (zh) 2019-04-25 2019-04-25 一种基于图像识别匹配的肠镜镜头静止检测方法

Country Status (1)

Country Link
CN (1) CN111839444A (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597981A (zh) * 2021-03-04 2021-04-02 四川大学 基于深度神经网络的肠镜退镜质量智能监控系统及方法
CN113962998A (zh) * 2021-12-23 2022-01-21 天津御锦人工智能医疗科技有限公司 肠镜检查的有效退镜时间评估方法、装置及存储介质
CN117255222A (zh) * 2023-11-20 2023-12-19 上海科江电子信息技术有限公司 一种数字电视监测的方法、系统及应用

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101576952A (zh) * 2009-03-06 2009-11-11 北京中星微电子有限公司 一种检测静止目标的方法和装置
US20120099773A1 (en) * 2010-10-20 2012-04-26 General Electric Company Method to Achieve Frame Rate or Resolution in Diagnostic Ultrasound
CN109598716A (zh) * 2018-12-05 2019-04-09 上海珍灵医疗科技有限公司 基于计算机视觉的肠镜退镜速度实时监测方法和系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101576952A (zh) * 2009-03-06 2009-11-11 北京中星微电子有限公司 一种检测静止目标的方法和装置
US20120099773A1 (en) * 2010-10-20 2012-04-26 General Electric Company Method to Achieve Frame Rate or Resolution in Diagnostic Ultrasound
CN109598716A (zh) * 2018-12-05 2019-04-09 上海珍灵医疗科技有限公司 基于计算机视觉的肠镜退镜速度实时监测方法和系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597981A (zh) * 2021-03-04 2021-04-02 四川大学 基于深度神经网络的肠镜退镜质量智能监控系统及方法
CN113962998A (zh) * 2021-12-23 2022-01-21 天津御锦人工智能医疗科技有限公司 肠镜检查的有效退镜时间评估方法、装置及存储介质
CN117255222A (zh) * 2023-11-20 2023-12-19 上海科江电子信息技术有限公司 一种数字电视监测的方法、系统及应用

Similar Documents

Publication Publication Date Title
EP3848891B1 (en) Computer vision-based method and system for monitoring speed of intestinal lens removal in real time
US9324145B1 (en) System and method for detection of transitions in an image stream of the gastrointestinal tract
CN111839444A (zh) 一种基于图像识别匹配的肠镜镜头静止检测方法
CN107256552B (zh) 息肉图像识别系统及方法
EP1875855B1 (en) Image processing apparatus, image processing method, and image processing program
US8055033B2 (en) Medical image processing apparatus, luminal image processing apparatus, luminal image processing method, and programs for the same
US8639002B2 (en) Medical image processing apparatus and method for controlling medical image processing apparatus
US9342881B1 (en) System and method for automatic detection of in vivo polyps in video sequences
EP2188779A1 (en) Extraction method of tongue region using graph-based approach and geometric properties
CN107529963B (zh) 图像处理装置、图像处理方法和存储介质
WO2020215810A1 (zh) 一种基于图像识别的结肠镜手术中窄带成像检测方法
US20130064436A1 (en) Medical image processing apparatus and method of operating medical image processing apparatus
US20200090548A1 (en) Image processing apparatus, image processing method, and computer-readable recording medium
WO2020215807A1 (zh) 一种基于深度学习提高结肠镜腺瘤性息肉检出率的方法
KR102163108B1 (ko) 영상에서 관심 대상 실시간 검출 방법 및 시스템
CN115760858A (zh) 基于深度学习的肾脏病理切片细胞识别方法及系统
CN112597981B (zh) 基于深度神经网络的肠镜退镜质量智能监控系统及方法
CN113962998A (zh) 肠镜检查的有效退镜时间评估方法、装置及存储介质
CN111839429A (zh) 一种基于图像识别判断结肠镜检查是否完整的检测方法
CN108968892B (zh) 一种肠镜下盲区监测的系统及方法
CN111028219B (zh) 一种结肠图像识别方法、装置以及相关设备
Wang et al. Computer-aided detection of retroflexion in colonoscopy
EP4241650A1 (en) Image processing method, and electronic device and readable storage medium
CN107529962B (zh) 图像处理装置、图像处理方法和记录介质
CN114693912B (zh) 具有眼球追踪功能的内镜检查系统、存储介质及设备

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 300457 s1405, s1404, s1414, s1415 and s1424, experimental building 14, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Binhai New Area Economic and Technological Development Zone, Tianjin

Applicant after: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd.

Address before: Unit 80, room n212, experimental building, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin, 300457

Applicant before: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd.

TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20240128

Address after: No. 402, Gate 2, Building 1, Shunning Lane, Hongqi South Road, Nankai District, Tianjin, 300000

Applicant after: Yang Guozhen

Country or region after: China

Address before: 300457 s1405, s1404, s1414, s1415 and s1424, experimental building 14, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Binhai New Area Economic and Technological Development Zone, Tianjin

Applicant before: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd.

Country or region before: China