WO2023155310A1 - 一种cbist成像方法及成像系统 - Google Patents

一种cbist成像方法及成像系统 Download PDF

Info

Publication number
WO2023155310A1
WO2023155310A1 PCT/CN2022/092597 CN2022092597W WO2023155310A1 WO 2023155310 A1 WO2023155310 A1 WO 2023155310A1 CN 2022092597 W CN2022092597 W CN 2022092597W WO 2023155310 A1 WO2023155310 A1 WO 2023155310A1
Authority
WO
WIPO (PCT)
Prior art keywords
cancerous
electrical
frequency
impedance value
imaging
Prior art date
Application number
PCT/CN2022/092597
Other languages
English (en)
French (fr)
Inventor
姚佳烽
刘凯
尹鸿润
Original Assignee
济纶医工智能科技(南京)有限公司
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 济纶医工智能科技(南京)有限公司 filed Critical 济纶医工智能科技(南京)有限公司
Publication of WO2023155310A1 publication Critical patent/WO2023155310A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/053—Measuring electrical impedance or conductance of a portion of the body
    • A61B5/0536—Impedance imaging, e.g. by tomography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/30—Assessment of water resources

Definitions

  • the invention belongs to the field of medical detection, and in particular relates to a CBIST (colorful bioelectrical impedance spectrum) imaging method and imaging system.
  • CBIST colorful bioelectrical impedance spectrum
  • Electrical impedance detection is a technology that uses the electrical properties of biological tissues and organs and their changes to distinguish whether the organism is diseased.
  • EIT Electrical Impedance Tomography
  • BIOS Biological Impedance Spectroscopy
  • EIT technology injects a safe driving current into the organism, and reconstructs the conductivity change image inside the organism by measuring the response information on the surface of the organism.
  • BIS technology injects safe multi-frequency excitation current into organisms, collects impedance information of biological tissues at different frequencies by sweeping frequency, and quantitatively analyzes electrical characteristics of biological tissues by extracting effective electrical parameters in impedance.
  • the key problem to solve the above limitations is to combine the two to realize the visualization of the cancerous area, accurately identify the specific information of the cancerous area, and intuitively display the lesion in the visualized image.
  • the purpose of the present invention is to solve the problems in the above-mentioned prior art and provide a method of Colorful Biological Impedance Spectroscopy Tomography (CBIST). Visualize the area, find the nearest electrode as the excitation electrode through the EIT image feature, combine the EIT image feature and the BIS impedance spectrum feature to classify the cancerous area, and present the classification results in different colors in the final visualization image , to achieve accurate and intuitive classification and visualization of cancerous regions.
  • CBIST Colorful Biological Impedance Spectroscopy Tomography
  • CBIST-based imaging system including storage module, EIT imaging and processing module, BIS electrical feature extraction module, recognition module, display module;
  • the storage module maintains bidirectional communication with the EIT imaging module, identification module, and display module;
  • the storage module is used for storing voltage difference data and storing frequency-impedance magnitude-phase matrix of each cancerous region
  • the EIT imaging and processing module is used to read the data of the storage module to generate an EIT binary image and preliminarily judge the cancerous area on the EIT binary image and obtain the center coordinates of each cancerous area;
  • the BIS electrical feature extraction module is used to read the frequency-impedance amplitude-phase matrix of each cancerous region, calculate the frequency-electrical impedance value real part-electrical impedance value imaginary part, and calculate the BIS electrical feature;
  • the identification module provides classification information for different cancerous regions according to the calculated BIS electrical features calculated by the BIS electrical feature extraction module;
  • the display module is used to realize colorful display.
  • a CBIST imaging method comprising the following steps:
  • Step1 EIT imaging: the EIT imaging module reads the data of the storage module to generate an EIT binary image;
  • Step2 preliminarily judge the cancerous area on the EIT binary image and obtain the center coordinates of each cancerous area;
  • Step3 calculate its corresponding frequency-electrical impedance value real part-electrical impedance value imaginary part matrix for each cancerous region
  • Step4 according to the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix of each cancerous area, extract the BIS electrical characteristics corresponding to each cancerous area;
  • Step5 according to the results of Step4, perform category analysis on each cancerous region
  • Step6 imaging a colorful electrical impedance spectroscopy image.
  • Step2 also includes: according to the binary image obtained in Step1, each node coordinate (xi , y i ) in each cancerous area and the conductivity value ⁇ i corresponding to the node coordinates can be obtained, then the electrical conductivity of each cancerous area can be obtained center coordinates;
  • n represents the total number of nodes in the jth cancerous region, which can be known from the binary image obtained in Step1.
  • Step3 includes: For any jth cancerous region, calculating the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix corresponding to the cancerous region includes:
  • Step3-1 According to the Euclidean distance between the center coordinates (X j , Y j ) of the jth cancerous area and each electrode, determine the two electrodes with the closest Euclidean distance as the impedance spectrum excitation-measurement of the jth cancerous area electrode;
  • Step3-2 for any j-th cancerous area, use the impedance analyzer to select the excitation-measurement electrode in Step3-1 at different frequencies (f 1 , f 2 ,..., f i ,..., f q ) Collect the impedance amplitude and phase of the cancerous area to obtain: frequency-impedance amplitude-phase matrix, which can be expressed as:
  • Z i is the impedance amplitude corresponding to f i , is the phase angle corresponding to f i ;
  • Step3-3 calculate the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix corresponding to the cancerous area, using the following matrix representation:
  • Step4 also includes: BIS electrical characteristics are R C , C C ;
  • Step4-1 According to the frequency-impedance magnitude-phase matrix of Step3-2, calculate the data set:
  • j represents the imaginary part unit
  • Step4-2 using the data set: ( ⁇ 1 , ⁇ 2 ?? ⁇ q ), (Z′′′ 1 , Z′′′ 2 ?? Z′′′ q ) and the following formula can be obtained by data fitting R C , C C :
  • R L1 , C L1 , R L2 , C L2 , R O and C O represent the electrical characteristics of normal lungs that can be obtained through a healthy lung model, and are all known values.
  • Step5 determine the type information of different cancerous regions:
  • R C and C C For the BIS electrical signature of any jth cancerous region: R C and C C :
  • C C ⁇ C thresh it is lung small cell carcinoma; if C C > C thresh , it is lung squamous cell carcinoma;
  • C C ⁇ C thresh it is lung adenocarcinoma; if C C >C thresh , it is lung large cell carcinoma.
  • Step6 also includes:
  • Step6-1 convert the EIT binary image obtained in Step1 into a pseudo-color image
  • Step6-2 the pseudo-color map in Step6-1 identifies each cancerous area and the type corresponding to the cancerous area:
  • the application proposes a CBIST imaging method (the method itself is not a medical treatment method ), which can accurately and intuitively detect the location of the lung cancer area and identify the type of lung cancer, and the method It is non-invasive imaging, with fast imaging, no radiation, and no damage to the human body.
  • the detection equipment has the advantages of portability and easy operation. Not the medical treatment itself), and the method can obtain the location, shape and precise type information of the cancerous area, which can provide relevant information for clinicians.
  • the core invention of this application lies in: solving the BIS electrical characteristics of "lung cancer”. This is the biggest problem in applying CBIST imaging method to "lung".
  • the lung cancer electrical model that this application proposes is as follows:
  • the data obtained through Step3-2 namely: Z is known to have a set of data, ⁇ is known to have a set of data (corresponding to the data of Z), find Rc, Cc.
  • the type of the cancerous region can be known.
  • Fig. 1 is a diagram of the CBIST method used for lung cancer detection in the present invention.
  • Fig. 2 is a diagram of an electrical model of lung cancer in the present invention.
  • FIG. 3 is a design diagram of the CBIST-based imaging system of the present invention.
  • Display module 500 Display module 500 .
  • Embodiment 1 CBIST-based imaging system
  • CBIST is the abbreviation of Colorful Biological Impedance Spectroscopy Tomography. Its special feature is that it adopts the following design, and the present invention will be further described below in conjunction with the accompanying drawings.
  • the CBIST-based imaging system includes a storage module 100, an EIT imaging and processing module 200, a BIS electrical feature extraction module 300, an identification module 400, and a display module 500;
  • the storage module maintains bidirectional communication with the EIT imaging module, identification module, and display module;
  • the storage module is used for storing voltage difference data and storing frequency-impedance magnitude-phase matrix of each cancerous region
  • the EIT imaging and processing module is used to read the data of the storage module to generate an EIT binary image and preliminarily judge the cancerous area on the EIT binary image and obtain the center coordinates of each cancerous area;
  • the BIS electrical feature extraction module is used to read the frequency-impedance amplitude-phase matrix of each cancerous region, calculate the frequency-electrical impedance value real part-electrical impedance value imaginary part, and calculate the BIS electrical feature;
  • the identification module provides classification information for different cancerous regions according to the calculated BIS electrical features calculated by the BIS electrical feature extraction module;
  • the display module is used to realize colorful display.
  • a generalized CBIST-based imaging system further includes: an electrode group sensor; the electrode group sensor is used to collect chest boundary voltage values and impedance values.
  • Embodiment 2 A kind of CBIST imaging method
  • ECG electrodes have terminals for connection, and are used to connect with multiplexers through terminal lines, using an electrical impedance analyzer To measure, control the multiplexer module through the PC to switch the excitation and acquisition channels, inject the signal into the designated electrode pair of the micro EIT sensor in turn, and collect the voltage of the remaining electrodes and send it back to the PC), and calculate the Get the boundary voltage difference U.
  • the above collected data is stored in the storage module.
  • the CBIST imaging method comprises the following steps:
  • Step1 EIT imaging of the lungs based on the 16-electrode sensor:
  • the EIT imaging module reads the data (the data is stored in the storage module 100), and calculates the conductivity difference ⁇ of each pixel point that generates the EIT image:
  • ⁇ is the change in conductivity, which is the value to be measured
  • S is the sensitivity matrix, which can be obtained in advance through simulation
  • S T is the transpose matrix of the sensitive matrix S
  • U is the boundary voltage difference, which can be obtained by measurement
  • I is the identity matrix
  • ⁇ and ⁇ are regularization coefficients
  • diag(S T S) is the diagonal matrix of S T S.
  • Step2 thresholding the EIT image obtained in Step1 to obtain a more intuitive binary image of EIT imaging, thereby obtaining the position of the cancerous area:
  • the coordinates (x i , y i ) of each node in the cancerous area and the conductivity value ⁇ i corresponding to the node coordinates can be obtained, and then the center coordinates (X j , Y j ) is:
  • Step3 for any jth cancerous area, calculate the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix corresponding to the cancerous area:
  • Step3-1 According to the Euclidean distance between the center coordinates (X j , Y j ) of the jth cancerous area and each electrode, determine the two electrodes with the closest Euclidean distance as the impedance spectrum excitation-measurement of the jth cancerous area electrode;
  • Step3-2 use the PC to control the multiplexing module to switch the acquisition channel, and select the starting frequency point f 1 (usually 1000Hz in lung cancer detection) and cut-off frequency f q (usually 10MHz in lung cancer detection) Divide the frequency band between the start and cut-off frequency points exponentially and averagely to obtain the sampling frequency points (f 1 , f 2 ,..., f i ,..., f q ), for any j-th cancerous region through Step3
  • the excitation-measurement electrode selected in -1 uses an impedance analyzer to collect the impedance amplitude and phase of the cancerous area at a selected sampling frequency point, and obtains: a frequency-impedance amplitude-phase matrix, which can be expressed as:
  • Z i is the impedance amplitude corresponding to f i
  • Step3-3 calculate the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix corresponding to the cancerous area, using the following matrix representation:
  • Step4 in combination with the EIT position feature in Step2 and the frequency-electrical impedance value real part-electrical impedance value imaginary part matrix corresponding to each cancerous region obtained in Step3, extract the BIS electrical feature corresponding to each cancerous region:
  • j represents the imaginary part unit
  • R L1 , C L1 , R L2 , C L2 , R O and C O represent the electrical characteristics of normal lungs, which can be obtained through a healthy lung model, that is, they are all known values;
  • R C and C C represent the BIS electrical characteristics of the cancerous area, which can be obtained by fitting the impedance spectrum data.
  • R C , C C represents the electrical parameter value of the cancerous area to be obtained
  • Step5 determine the type information of different cancerous regions:
  • a complete classification feature can be formed.
  • the electrical feature division thresholds R thresh and C thresh of different cancerous areas can be obtained (R thresh , C thresh can be obtained based on machine learning and is a known value);
  • R C >R thresh if C C ⁇ C thresh, it is lung adenocarcinoma, if C C >C thresh, it is lung large cell carcinoma.
  • Step6 imaging a colorful electrical impedance spectroscopy image:
  • Step6-1 convert the EIT binary image obtained in Step1 into a pseudo-color image
  • Step6-2 the pseudo-color map in Step6-1 identifies each cancerous area and the type corresponding to the cancerous area:

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)

Abstract

本发明公开了一种CBIST成像方法及成像系统，其属于医疗检测领域。其技术要点在于：包括以下步骤：Step1,EIT成像；Step2,在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；Step3,对于每个癌变区域均计算其对应的频率-电阻抗值实部-电阻抗值虚部矩阵；Step4，根据每个癌变区域的频率-电阻抗值实部-电阻抗值虚部矩阵，提取每个癌变区域对应的BIS电气特征；Step5，根据Step4的结果，对每个癌变区域进行种类分析；Step6，成像多彩的电阻抗谱成像图。本发明旨在提供一种CBIST成像方法及成像系统，为临床医生提供相关信息。

Description

一种CBIST成像方法及成像系统 技术领域
本发明属于医疗检测领域，具体涉及一种CBIST(多彩生物电阻抗谱)成像方法及成像系统。
背景技术
电阻抗检测是一种利用生物组织与器官的电特性及其变化规律来分辨生物体是否病变的技术，其中，电阻抗断层成像(Electrical Impedance Tomography，EIT)和生物阻抗谱(Biological Impedance Spectroscopy，BIS)是目前应用最广泛的两种生物阻抗检测方法。EIT技术是向生物体注入安全的驱动电流，通过测量生物体体表的响应信息，重建生物体内部的电导率变化图像。BIS技术是向生物体注入安全的多频激励电流，以扫频方式采集生物组织不同频率下的阻抗信息，通过提取阻抗中有效的电学参数来定量分析生物组织的电学特性。这两种电阻抗检测方法均具有快速、免标记、易操作的特点，逐步成为肺检测研究中有效的分析工具。
参考文献1：任超世,李章勇,王妍,等.我国电阻抗断层成像实用化应用研究展望[J].航天医学与医学工程,2010(04):79-82；
参考文献2：王春艳.应用于肺部检测的电阻抗成像系统[D].天津大学，2007；
参考文献3：赵秋红.生物阻抗参数测量与特性分析[D].天津科技大学,2015.
从上述参考文献1-3可知，目前肺检测都是采用单一的EIT技术或单一的BIS技术。EIT技术在癌变区域可视化中获得了较好效果，而BIS技术则在精确识别癌变区域的具体信息上取得不错的进展。
但是，由于两种技术自身存在的局限性，单一检测方法很难同时将癌变区域可视化并精准直观的分辨出病变的具体情况。
而在很多情况下，对癌变区域可视化并给出病变具体信息都很有必要且具有重要意义。例如在肺癌早期筛查中，尽早识别出早期癌变区域的位置、形状并精确识别出种类信息有利于临床医生对早期肺癌患者进行针对性治疗，提高治愈率。
因此，在继承上述电阻抗检测方法优点的基础上，将二者融合实现对癌变区域可视化，精确辨别癌变区域具体信息，并将病变情况直观地显示在可视化图像中是解决上述局限的关键问题。
发明内容
本发明的目的是为了解决上述现有技术存在的问题，提供一种多彩生物电阻抗谱成像(Colorful Biological Impedance Spectroscopy Tomography,CBIST)方法，该方法是一种EIT与BIS融合的方法，能够对癌变区域可视化，并通过EIT图像特征寻找最近电极作为激励电极，结合EIT的图像特征与BIS的阻抗谱特征对癌变区域进行具体分类，并将获得的分类结果以不同的颜色呈现在最终的可视化图像中，实现癌变区域的精准直观分类并可视化。
本发明的通过以下技术方案来实现：
基于CBIST的成像系统，包括存储模块、EIT成像及处理模块、BIS电气特征提取模块、识别模块、显示模块；
所述存储模块与所述EIT成像模块、识别模块、显示模块均保持双向连通；
所述存储模块用于存储电压差数据以及存储每个癌变区域的频率-阻抗幅值-相位矩阵；
所述EIT成像及处理模块，用于读取存储模块的数据生成EIT二值化图像以及在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；
所述BIS电气特征提取模块，用于读取每个癌变区域的频率-阻抗幅值-相位矩阵、计算频率-电阻抗值实部-电阻抗值虚部、计算BIS电气特征；
所述识别模块，根据BIS电气特征提取模块计算得到的计算BIS电气特征，来对不同癌变区域给出其分类信息；
所述显示模块，用于实现多彩显示。
一种CBIST成像方法，包括以下步骤：
Step1,EIT成像：EIT成像模块读取存储模块的数据生成EIT二值化图像；
Step2,在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；
Step3,对于每个癌变区域均计算其对应的频率-电阻抗值实部-电阻抗值虚部矩阵；
Step4，根据每个癌变区域的频率-电阻抗值实部-电阻抗值虚部矩阵，提取每个癌变区域对应的BIS电气特征；
Step5，根据Step4的结果，对每个癌变区域进行种类分析；
Step6，成像多彩的电阻抗谱成像图。
进一步，Step2还包括：根据Step1所得的二值图像能够获得每个癌变区域内各节点坐标(x i，y i)和该节点坐标对应的电导率值σ i，则能够获得每个癌变区域的中心坐标；
对于任意第j个癌变区域而言，其中心坐标(X j,Y j)为：
Figure PCTCN2022092597-appb-000001
其中，n表示第j个癌变区域的节点总数，其能够从Step1所得的二值图像上得知。
进一步，Step3，包括：对于任意第j个癌变区域，计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵包括：
Step3-1：根据第j个癌变区域中心坐标(X j,Y j)与各电极之间的欧氏距离，确定欧氏距离最近的两个电极为第j个癌变区域的阻抗谱激励-测量电极；
Step3-2,对于任意第j个癌变区域通过Step3-1中选定激励-测量电极使用阻抗分析仪在不同频率下(f 1，f 2，...，f i，…，f q)下采集该癌变区域的阻抗幅值和相位进而获得：频率-阻抗幅值-相位矩阵，该矩阵可表达为：
Figure PCTCN2022092597-appb-000002
其中，Z i为与f i对应的阻抗幅值，
Figure PCTCN2022092597-appb-000003
为与f i对应的相位角；
Step3-3,计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵，采用下述矩阵表示：
Figure PCTCN2022092597-appb-000004
其中：
与频率f i对应的电阻抗值实部
Figure PCTCN2022092597-appb-000005
与频率f i对应的电阻抗值虚部
Figure PCTCN2022092597-appb-000006
进一步，Step4还包括：BIS电气特征为R C、C C；
Step4-1:根据Step3-2的频率-阻抗幅值-相位矩阵，计算数据集：
(ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)
对于任意第i个阻抗复值Z″′ i、第i个角频率ω i，求解方式如下：
Figure PCTCN2022092597-appb-000007
j表示虚部单位；
Step4-2,利用数据集：(ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)以及下式，通过数据拟合能够求取R C、C C：
Figure PCTCN2022092597-appb-000008
其中:R L1、C L1、R L2、C L2、R O和C O代表正常肺部电气特征能够通过健康肺模型获得，均为已知值。
进一步，Step5，判断出不同癌变区域的种类信息:
对于任意第j个癌变区域的BIS电气特征:R C和C C：
当R C＜R thresh时
若C C＜C thresh则为肺小细胞癌；若C C＞C thresh则为肺鳞癌；
当R C＞R thresh时
若C C＜C thresh则为肺腺癌；若C C＞C thresh则为肺大细胞癌。
进一步，Step6还包括：
Step6-1，将Step1所得的EIT二值化图像转化为伪彩图；
Step6-2，在Step6-1中的伪彩图标识每个癌变区域以及该癌变区域对应的种类：
结合Step5中得到的结果:对伪彩图中对应的每个癌变区域的像素值进行替换，从而实现多彩显示：不同色彩对应不同的癌变种类。
本发明技术方案的优点主要体现在：
第一，本申请提出了一种用于CBIST成像方法( 本申请的方法本身并非医疗治疗方法)， 该方法能精准、直观地实现对肺癌区域的位置检测并对肺癌种类进行识别，且该方法为非侵入式成像，成像较快、无辐射、对人体无损伤，检测设备具有便携、易操作等优点，可于社区肺癌筛查(本申请的方法本质上属于医疗器械的内部工作方法，并不是医疗治疗方法本身)，并且该方法可以获得癌变区域的位置、形状以及精确的种类信息，可为临床医生提供相关信息。
第二，本申请的核心发明在于：解决了“肺癌”的BIS电气特征。这个是CBIST成像方法应用在“肺部”最大的难题。
本申请提出的肺癌电气模型如下:
Figure PCTCN2022092597-appb-000009
其中:Z″′表示阻抗复值，Z″′＝Z′+Z″j；ω表示角频率，ω＝2πf；j表示虚部单位；R L1、C L1、R L2、C L2、R O、C O均为已知值；
未知值为：R C、C C。
通过Step3-2得到的数据，即：Z已知有一组数据，ω已知有一组数据(与Z的数据对应)，求Rc、Cc。
Figure PCTCN2022092597-appb-000010
通过Rc、Cc与阈值R thresh和C thresh的比较，从而能够知晓癌变区域的种类。
附图说明
下面结合附图中的实施例对本发明作进一步的详细说明，但并不构成对本发明的任何限制。
图1为本发明用于肺癌检测的CBIST方法图。
图2为本发明中的肺癌电学模型图。
图3是本发明的基于CBIST的成像系统的设计图。
附图标记说明如下：
存储模块100；
EIT成像及处理模块200；
BIS电气特征提取模块300；
识别模块400；
显示模块500。
具体实施方式
本发明的目的、优点和特点，将通过下面优选实施例的非限制性说明进行解释。这些实施例仅是应用本发明技术方案的典型范例，凡采取等同替换或者等效变换而形成的技术方案，均落在本发明要求保护的范围之内。
实施例1：基于CBIST的成像系统
CBIST是Colorful Biological Impedance Spectroscopy Tomography的简称，其特别之处在于采用以下设计，下面结合附图对本发明作进一步的说明。
基于CBIST的成像系统，包括存储模块100、EIT成像及处理模块200、BIS电气特征提取模块300、识别模块400、显示模块500；
所述存储模块与所述EIT成像模块、识别模块、显示模块均保持双向连通；
所述存储模块用于存储电压差数据以及存储每个癌变区域的频率-阻抗幅值-相位矩阵；
所述EIT成像及处理模块，用于读取存储模块的数据生成EIT二值化图像以及在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；
所述BIS电气特征提取模块，用于读取每个癌变区域的频率-阻抗幅值-相位矩阵、计算频率-电阻抗值实部-电阻抗值虚部、计算BIS电气特征；
所述识别模块，根据BIS电气特征提取模块计算得到的计算BIS电气特征，来对不同癌变区域给出其分类信息；
所述显示模块，用于实现多彩显示。
各个模块的作用见表1所示。
表1 基于CBIST的成像系统的构成
Figure PCTCN2022092597-appb-000011
Figure PCTCN2022092597-appb-000012
进一步，广义的基于CBIST的成像系统，还包括：电极组传感器；所述电极组传感器，用来采集胸腔边界电压值以及阻抗值。
实施例2：一种CBIST成像方法
采集数据：通过均匀分布在第4-5肋骨间的16个心电电极采集数据(心电电极具有用于连接的端子，用于通过端子线与多路复用器连接，使用电阻抗分析仪进行测量，通过PC端控制多路复用器模块实现激励、采集通道的切换，将信号依次注入到微型EIT传感器的指定电极对上，并采集剩余电极的电压传回PC端)，并通过计算获得边界电压差U。上述采集好的数据存储到存储模块中。
所述的CBIST成像方法，包括以下步骤：
Step1,基于16电极传感器对肺部进行EIT成像：
EIT成像模块读取数据(该数据存储在存储模块100)，计算生成EIT图像的各个像素点的电导率差值Δσ：
Δσ＝(S TS+μI+ηdiag(S TS)) -1S TU
上式中：
Δσ是电导率变化量，是待测值；
S是敏感矩阵，可以通过仿真预先获得；
S T是敏感矩阵S的转置矩阵；
U是边界电压差，可通过测量获得；
I为单位矩阵；
μ和η是正则化系数；
diag(S TS)是S TS的对角矩阵。
对电导率差值进行归一化处理，可以生成EIT二值化图像；
Step2，对Step1得到的EIT图像进行阈值化处理，得到更直观的EIT成像二值图像，从而获取癌变区域位置：
根据Step1所得的二值图像可以获得癌变区域内各节点坐标(x i，y i)和该节点坐标对应的电导率值σ i，则能够获得任意第j个癌变区域的中心坐标(X j,Y j)为：
Figure PCTCN2022092597-appb-000013
Step3，对于任意第j个癌变区域，计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵：
Step3-1：根据第j个癌变区域中心坐标(X j,Y j)与各电极之间的欧氏距离，确定欧氏距离最近的两个电极为第j个癌变区域的阻抗谱激励-测量电极；
Step3-2,通过PC电脑来控制多路复用模块切换采集通道，选定起始频点f 1(在肺癌检测中通常取1000Hz)与截止频点f q(在肺癌检测中通常取10MHz)并将起始和截止频点之间的频段进行指数平均划分，获得采样频点(f 1，f 2，...，f i，…，f q),对于任意第j个癌变区域通过Step3-1中选定的激励-测量电极使用阻抗分析仪在选定采样频点下采集该癌变区域的阻抗幅值和相位，获得：频率-阻抗幅值-相位矩阵，该矩阵可表达为：
Figure PCTCN2022092597-appb-000014
其中，Z i为与f i对应的阻抗幅值，
Figure PCTCN2022092597-appb-000015
为与f i对应的相位角(
Figure PCTCN2022092597-appb-000016
分别是与f i对应的采集的电压信号、激励的电流信号的相位角)；
Step3-3,计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵，采用下述矩阵表示：
Figure PCTCN2022092597-appb-000017
其中：
与频率fi对应的电阻抗值实部
Figure PCTCN2022092597-appb-000018
与频率fi对应的电阻抗值虚部
Figure PCTCN2022092597-appb-000019
Step4，结合Step2中的EIT位置特征与Step3得到的每个癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵，提取每个癌变区域对应的BIS电气特征:
如图2所示是一种肺癌电气模型，由于其他肺癌区域距离第j个癌变区域的激励-采集电极较远，因此自需考虑第j个癌变区域对阻抗谱数据的影响，可得到肺癌电气模型如下:
Figure PCTCN2022092597-appb-000020
其中:
Z″′表示阻抗复值，Z″′＝Z′+Z″j；
ω表示角频率，ω＝2πf；
j表示虚部单位；
R L1、C L1、R L2、C L2、R O和C O代表正常肺部电气特征，可以通过健康肺模型获得，即均为已知值；
R C和C C代表癌变区域的BIS电气特征，根据阻抗谱数据拟合可以获得。
对于R C、C C而言，其拟合时：Z″′、ω(ω＝2πf，f对应于Step3-2的f实测值)；根据肺癌电气模型与阻抗谱数据拟合得到癌变区域电气参数，即获得R C、C C，拟合方法如下：
Figure PCTCN2022092597-appb-000021
其中：
R C，C C表示待求癌变区域电气参数值；
Figure PCTCN2022092597-appb-000022
表示第i个频率下测量得到的阻抗复值；
Figure PCTCN2022092597-appb-000023
表示第i个频率下通过肺癌电气模型计算得到的阻抗复值。
Step5，判断出不同癌变区域的种类信息:
结合根据EIT图像获得的癌变区域中心与激励-采集电极距离可形成完备的分类特征，通过训练并测试机器学习模型得出不同癌变区域的电气特征划分阈值R thresh和C thresh(R thresh、C thresh基于机器学习能够获得，为已知值)；
任意第j个癌变区域的电气特征R C和C C：
当R C＜R thresh时，若C C＜C thresh则为肺小细胞癌，若C C＞C thresh则为肺鳞癌；
当R C＞R thresh时，若C C＜C thresh则为肺腺癌，若C C＞C thresh则为肺大细胞癌。
Step6，成像多彩的电阻抗谱成像图：
Step6-1，将Step1所得的EIT二值化图像转化为伪彩图；
Step6-2，在Step6-1中的伪彩图标识每个癌变区域以及该癌变区域对应的种类：
结合Step5中得到的结果:对伪彩图中对应的每个癌变区域的像素值(像素值不同，即色彩不同)进行替换，从而实现多彩显示：不同色彩对应不同的癌变种类。
以上所举实施例为本发明的较佳实施方式，仅用来方便说明本发明，并非对本发明作任何形式上的限制，任何所属技术领域中具有通常知识者，若在不脱离本发明所提技术特征的范围内，利用本发明所揭示技术内容所作出局部更动或修饰的等效实施例，并且未脱离本发明的技术特征内容，均仍属于本发明技术特征的范围内。

Claims (10)

  1. 一种CBIST成像方法，其特征在于，包括以下步骤：
    Step1,EIT成像：EIT成像模块读取存储模块的数据生成EIT二值化图像；
    Step2,在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；
    Step3,对于每个癌变区域均计算其对应的频率-电阻抗值实部-电阻抗值虚部矩阵；
    Step4，根据每个癌变区域的频率-电阻抗值实部-电阻抗值虚部矩阵，提取每个癌变区域对应的BIS电气特征；
    Step5，根据Step4的结果，对每个癌变区域进行种类分析；
    Step6，成像多彩的电阻抗谱成像图。
  2. 根据权利要求1所述的一种CBIST成像方法，其特征在于，Step2还包括：根据Step1所得的二值图像能够获得每个癌变区域内各节点坐标(x i，y i)和该节点坐标对应的电导率值σ i，则能够获得每个癌变区域的中心坐标；
    对于任意第j个癌变区域而言，其中心坐标(X j,Y j)为：
    Figure PCTCN2022092597-appb-100001
    其中，n表示第j个癌变区域的节点总数，其能够从Step1所得的二值图像上得知。
  3. 根据权利要求2所述的一种CBIST成像方法，其特征在于，Step3，包括：对于任意第j个癌变区域，计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵包括：
    Step3-1：根据第j个癌变区域中心坐标(X j,Y j)与各电极之间的欧氏距离，确定欧氏距离最近的两个电极为第j个癌变区域的阻抗谱激励-测量电极；
    Step3-2,对于任意第j个癌变区域通过Step3-1中选定激励-测量电极使用阻抗分析仪在不同频率下(f 1，f 2，...，f i，…，f q)下采集该癌变区域的阻抗幅值和相位进而获得：频率-阻抗幅值-相位矩阵，该矩阵可表达为：
    Figure PCTCN2022092597-appb-100002
    其中，Z i为与f i对应的阻抗幅值，
    Figure PCTCN2022092597-appb-100003
    为与f i对应的相位角；
    Step3-3,计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵，采用下述矩阵表示：
    Figure PCTCN2022092597-appb-100004
    其中：
    与频率f i对应的电阻抗值实部
    Figure PCTCN2022092597-appb-100005
    与频率f i对应的电阻抗值虚部
    Figure PCTCN2022092597-appb-100006
  4. 根据权利要求3所述的一种CBIST成像方法，其特征在于，Step4还包括：BIS电气特征为R C、R C；
    Step4-1:根据Step3-2的频率-阻抗幅值-相位矩阵，计算数据集：
    (ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)
    对于任意第i个阻抗复值Z″′ i、第i个角频率ω i，求解方式如下：
    Figure PCTCN2022092597-appb-100007
    j表示虚部单位；
    Step4-2,利用数据集：(ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)以及下式，通过数据拟合能够求取R C、C C：
    Figure PCTCN2022092597-appb-100008
    其中:R L1、C L1、R L2、C L2、R O和C O代表正常肺部电气特征能够通过健康肺模型获得，均为已知值。
  5. 根据权利要求4所述的一种CBIST成像方法，其特征在于，Step5，判断出不同癌变区域的种类信息:
    对于任意第j个癌变区域的BIS电气特征:R C和C C：
    当R C＜R thresh时
    若C C＜C thresh则为肺小细胞癌；若C C＞C thresh则为肺鳞癌；
    当R C＞R thresh时
    若C C＜C thresh则为肺腺癌；若C C＞C thresh则为肺大细胞癌。
  6. 根据权利要求5所述的一种CBIST成像方法，其特征在于，Step6还包括：
    Step6-1，将Step1所得的EIT二值化图像转化为伪彩图；
    Step6-2，在Step6-1中的伪彩图标识每个癌变区域以及该癌变区域对应的种类：
    结合Step5中得到的结果:对伪彩图中对应的每个癌变区域的像素值进行替换，从而实现多彩显示：不同色彩对应不同的癌变种类。
  7. 基于CBIST的成像系统，其特征在于，包括：存储模块、EIT成像及处理模块、BIS电气特征提取模块、识别模块、显示模块；
    所述存储模块与所述EIT成像模块、识别模块、显示模块均保持双向连通；
    所述存储模块用于存储电压差数据以及存储每个癌变区域的频率-阻抗幅值-相位矩阵；
    所述EIT成像及处理模块，用于读取存储模块的数据生成EIT二值化图像以及在EIT二值化图像上初步判断癌变区域并且得到每个癌变区域的中心坐标；
    所述BIS电气特征提取模块，用于读取每个癌变区域的频率-阻抗幅值-相位矩阵、计算频率-电阻抗值实部-电阻抗值虚部、计算BIS电气特征；
    所述识别模块，根据BIS电气特征提取模块计算得到的计算BIS电气特征，来对不同癌变区域给出其分类信息；
    所述显示模块，用于实现多彩显示。
  8. 根据权利要求7所述的一种基于CBIST的成像系统，其特征在于，计算频率-电阻抗值实部-电阻抗值虚部的方法为：
    A：根据第j个癌变区域中心坐标(X j,Y j)与各电极之间的欧氏距离，确定欧氏距离最近的两个电极为第j个癌变区域的阻抗谱激励-测量电极；
    B,对于任意第j个癌变区域通过选定的激励-测量电极使用阻抗分析仪在不同频率下(f 1，f 2，...，f i，…，f q)下采集该癌变区域的阻抗幅值和相位进而获得：频率-阻抗幅值-相位矩阵，该矩阵可表达为：
    Figure PCTCN2022092597-appb-100009
    其中，Z i为与f i对应的阻抗幅值，
    Figure PCTCN2022092597-appb-100010
    为与f i对应的相位角；
    C,计算该癌变区域对应的频率-电阻抗值实部-电阻抗值虚部矩阵，采用下述矩阵表示：
    Figure PCTCN2022092597-appb-100011
    其中：
    与频率f i对应的电阻抗值实部
    Figure PCTCN2022092597-appb-100012
    与频率f i对应的电阻抗值虚部
    Figure PCTCN2022092597-appb-100013
  9. 根据权利要求8所述的一种基于CBIST的成像系统，其特征在于，计算BIS电气特征的方法为：
    BIS电气特征为R C、C C，包括如下步骤：
    A:根据频率-阻抗幅值-相位矩阵，计算数据集：
    (ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)
    对于任意第i个阻抗复值Z″′ i、第i个角频率ω i，求解方式如下：
    Figure PCTCN2022092597-appb-100014
    j表示虚部单位；
    B,利用数据集：(ω 1，ω 2………ω q)、(Z″′ 1，Z″′ 2………Z″′ q)以及下式，通过数据拟合能够求取R C、C C：
    Figure PCTCN2022092597-appb-100015
    其中:R L1、C L1、R L2、C L2、R O和C O代表正常肺部电气特征能够通过健康肺模型获得，均为已知值。
  10. 根据权利要求8所述的一种基于CBIST的成像系统，其特征在于，
    识别模块“在根据BIS电气特征提取模块计算得到的计算BIS电气特征来对不同癌变区域给出其分类信息”的具体方式为：
    对于任意第j个癌变区域的BIS电气特征:R C和C C：
    当R C＜R thresh时
    若C C＜C thresh则为肺小细胞癌；若C C＞C thresh则为肺鳞癌；
    当R C＞R thresh时
    若C C＜C thresh则为肺腺癌；若C C＞C thresh则为肺大细胞癌。
PCT/CN2022/092597 2022-02-18 2022-05-13 一种cbist成像方法及成像系统 WO2023155310A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210153035.3A CN114519708B (zh) 2022-02-18 2022-02-18 一种cbist成像方法及成像系统
CN202210153035.3 2022-02-18

Publications (1)

Publication Number Publication Date
WO2023155310A1 true WO2023155310A1 (zh) 2023-08-24

Family

ID=81598438

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/092597 WO2023155310A1 (zh) 2022-02-18 2022-05-13 一种cbist成像方法及成像系统

Country Status (2)

Country Link
CN (1) CN114519708B (zh)
WO (1) WO2023155310A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115530791B (zh) * 2022-12-02 2023-03-10 中国医学科学院北京协和医院 基于盐水造影的心内分流电阻抗图像分析方法及系统
CN115035208B (zh) * 2022-06-10 2023-11-14 中国医学科学院北京协和医院 肺灌注与区域v/q无创成像方法、系统及设备
CN116869510B (zh) * 2023-07-10 2024-09-27 南京航空航天大学 基于生物阻抗谱的肺容积测量方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050135707A1 (en) * 2003-12-18 2005-06-23 Turek Matthew W. Method and apparatus for registration of lung image data
CN101194833A (zh) * 2006-12-08 2008-06-11 南京东影生物医学影像技术有限责任公司 电阻抗乳腺扫描诊断仪
CN111643079A (zh) * 2020-04-26 2020-09-11 南京航空航天大学 基于生物阻抗谱与电阻抗成像互为补偿的肿瘤细胞精准电阻抗检测方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101241094B (zh) * 2008-03-12 2011-03-23 天津大学 非接触式电阻抗传感器及基于该传感器的图像重建方法
CN101564294B (zh) * 2009-06-01 2011-04-20 中国人民解放军第四军医大学 一种结构信息融合的电阻抗断层成像方法
US10357178B2 (en) * 2015-12-16 2019-07-23 General Electric Company System and method for enhanced electrical impedance tomography
DE102017007224A1 (de) * 2017-08-02 2019-02-07 Drägerwerk AG & Co. KGaA Vorrichtung und Verfahren zu einer Bestimmung von Differenzkennzahlen auf Basis von EIT-Daten
CN108664928A (zh) * 2018-05-10 2018-10-16 西京学院 一种面向手掌bis大数据的椭圆特征模型及其特征选择的方法
CN111248909A (zh) * 2020-01-19 2020-06-09 上海交通大学 基于生物电阻抗断层成像的医疗成像系统、方法及设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050135707A1 (en) * 2003-12-18 2005-06-23 Turek Matthew W. Method and apparatus for registration of lung image data
CN101194833A (zh) * 2006-12-08 2008-06-11 南京东影生物医学影像技术有限责任公司 电阻抗乳腺扫描诊断仪
CN111643079A (zh) * 2020-04-26 2020-09-11 南京航空航天大学 基于生物阻抗谱与电阻抗成像互为补偿的肿瘤细胞精准电阻抗检测方法

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
YAO JIA-FENG, HU SONG-PEI, YANG LU, WU YANG, HAN WEI, LIU KAI: "Tongue tumor tissue recognition based on bioelectrical impedance spectroscopy", ACTA PHYSICA SINICA, vol. 70, no. 15, 1 January 2021 (2021-01-01), pages 158704, XP093086282, ISSN: 1000-3290, DOI: 10.7498/aps.70.20210297 *
YAO, JIAFENG: "Application Progress of Micro-scale Electrical Impedance Tomography in Tumor Cell Detection", MODERN MEDICINE AND HEALTH RESEARCH, vol. 6, no. 2, 28 January 2022 (2022-01-28), pages 6 - 9, XP009548594, ISSN: 2096-3718 *
YIN HONG-RUN, YE MING, WU YANG, LIU KAI, PAN HUA-PING, YAO JIA-FENG: "Biological tissue detection based on electrical impedance spectroscopic tomography", ACTA PHYSICA SINICA, vol. 71, no. 4, 1 January 2022 (2022-01-01), pages 048706, XP093086284, ISSN: 1000-3290, DOI: 10.7498/aps.71.20211600 *

Also Published As

Publication number Publication date
CN114519708A (zh) 2022-05-20
CN114519708B (zh) 2023-08-15

Similar Documents

Publication Publication Date Title
WO2023155310A1 (zh) 一种cbist成像方法及成像系统
Zou et al. A review of electrical impedance techniques for breast cancer detection
EP2175776B1 (en) Impedance measurement process
US11617518B2 (en) Method for detecting both pre-cancerous and cancerous tissues
US9066671B2 (en) System and method for early breast cancer detection using electrical property enhanced tomography
AU2010352406B2 (en) Method and device for quality assessment of an electrical impedance measurement on tissue
WO2001067098A1 (en) Electrical impedance measuring method for differentiating tissue types
JP2016028778A (ja) 極低周波電磁場を用いる疾病の診断およびスクリーニングのための装置
Sarode et al. Role of bioimpedance in cancer detection: A brief review
CN114287906A (zh) 一种便携式检测传感器、检测系统、检测方法
Meroni et al. Measurement of electrical impedance in different ex-vivo tissues
CN100596275C (zh) 用于术中乳腺癌病灶边缘界定的病理阻抗测量装置
Barrow et al. Impedance measurements for cervical cancer diagnosis
Meani et al. Electrical Impedance Spectroscopy for Ex-Vivo Breast Cancer Tissues Analysis
Hu et al. An electrode array sensor for tongue cancer detection with bioelectrical impedance spectroscopic tomography
Deng et al. Three-dimensional bioelectrical impedance spectroscopic tomography for visualization of breast tumor
JPH07250837A (ja) 組織タイプ認識方法およびそのための装置
Kossmann An Electrical Impedance Tomography Based Probe for Intraoperative Surgical Margin Assessment
KR102091828B1 (ko) 임피던스를 이용한 인공지능 기반 피부질환 진단시스템
Alsaid et al. Using Electrical Impedance Tomography and Machine Learning for Breast Cancer Detection
Grewal Multimodality based Tissue Classification Technique for Malignant Anomaly Detection
Zhenyu et al. Improvement in EIS diagnosis accuracy using a multi-frequency parameter analysis method: preliminary results
TWI725441B (zh) 生物訊號檢測分析方法
Emran Novel bioimpedance spectroscopic methods for examination of oral mucosal tissues
Fidaner et al. Wavelet Transform Analysis of Bio-impedance Spectroscopy for Accurate Cancer Detection

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: 22926623

Country of ref document: EP

Kind code of ref document: A1