CN110619644B - Data processing system and electronic equipment for acquiring tumor position and contour in CT image - Google Patents

Data processing system and electronic equipment for acquiring tumor position and contour in CT image Download PDF

Info

Publication number
CN110619644B
CN110619644B CN201910882016.2A CN201910882016A CN110619644B CN 110619644 B CN110619644 B CN 110619644B CN 201910882016 A CN201910882016 A CN 201910882016A CN 110619644 B CN110619644 B CN 110619644B
Authority
CN
China
Prior art keywords
image
tumor
data processing
qsofm
particle
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.)
Active
Application number
CN201910882016.2A
Other languages
Chinese (zh)
Other versions
CN110619644A (en
Inventor
袁双虎
李玮
孟祥伟
于清溪
刘宁
魏玉春
李莉
李潇箫
刘长民
于金明
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.)
Shandong Cancer Hospital & Institute (shandong Cancer Hospital)
Shandong University
Original Assignee
Shandong Cancer Hospital & Institute (shandong Cancer Hospital)
Shandong University
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 Shandong Cancer Hospital & Institute (shandong Cancer Hospital), Shandong University filed Critical Shandong Cancer Hospital & Institute (shandong Cancer Hospital)
Priority to CN201910882016.2A priority Critical patent/CN110619644B/en
Publication of CN110619644A publication Critical patent/CN110619644A/en
Priority to NL2025775A priority patent/NL2025775B1/en
Application granted granted Critical
Publication of CN110619644B publication Critical patent/CN110619644B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The utility model provides a data processing system and an electronic device for obtaining the tumor position and contour in a CT image, which collect the CT image, and use a particle swarm optimization algorithm to segment the collected CT image to obtain a segmented CT image data matrix; building a QSOFM classifier model, and performing model training by using the segmented CT image data matrix; identifying the canceration type of the tumor in the CT image by utilizing a QSOFM classifier model, and acquiring the position and contour information of the canceration tumor in the CT image based on a multi-connected region segmentation method; the segmentation of the image is more detailed, the redundant data is reduced, the tumor recognition rate of the automatic puncture device in the CT image is higher, the tumor position is more quickly and accurately positioned, the automation degree of the automatic puncture device is improved, and a foundation is laid for computer-assisted treatment.

Description

Data processing system and electronic equipment for acquiring tumor position and contour in CT image
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to a data processing system and an electronic device for acquiring a tumor position and a tumor contour in a CT image.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, there are various tumor identification methods based on images, and most of the methods have superior identification effects, and the most commonly used methods are identification methods based on convolutional neural networks, traditional sliding window methods, feature value methods, and the like.
The inventor of the present disclosure finds in research that, with further development of computer technology and robotics, some basic medical operations are slowly replaced by mechanical devices, for example, a radiotherapy room in a hospital needs to perform a puncture treatment on a tumor when performing radiotherapy treatment on the tumor, and these devices cannot perform effective data processing on an acquired CT image to obtain tumor position and contour information in the CT image, so that development of automatic puncture devices is limited. Therefore, how to rapidly and accurately perform data processing and analysis on the CT image, and implement positioning identification and contour segmentation on the tumor in the CT image to improve the automation level of the medical automation equipment is a technical problem which needs to be solved urgently.
Disclosure of Invention
In order to solve the defects of the prior art, the data processing system and the electronic equipment for acquiring the tumor position and contour in the CT image are provided, the image is divided more finely by utilizing a particle swarm optimization algorithm, a quantum-based self-organizing feature mapping neural network classifier model and a multi-connected region division-based method, redundant data are reduced, the tumor position and contour in the CT image can be acquired rapidly, and the automation level of a medical automation device is improved.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
in a first aspect, the present disclosure provides a data processing system for acquiring tumor locations and edge contours in CT images;
a data processing system for acquiring tumor location and edge contours in CT images, comprising the steps of:
the preprocessing module is configured to acquire a CT image, and perform image segmentation on the acquired CT image by utilizing a particle swarm optimization algorithm to obtain a segmented CT image data matrix;
the model building module is configured to build a QSOFM classifier model and perform model training by using the segmented CT image data matrix;
and the data processing module is configured to identify the canceration type of the tumor in the CT image by utilizing the QSOFM classifier model, and acquire the position and the contour information of the canceration tumor in the CT image based on a multi-connected region segmentation method.
As some possible implementation manners, the preprocessing module segments the acquired CT image by using a particle swarm optimization algorithm, specifically:
(1-1) establishing an energy minimization control point generalization function of image segmentation and generating a particle swarm;
(1-2) calculating a fitness function of the particle swarm algorithm to generate a fitness value of each particle;
(1-3) comparing the fitness value of each particle with the individual optimal value of the particle and the individual optimal value of the particle group, and replacing the individual optimal value of the particle and the individual optimal value of the particle group if the fitness value of the particle is more optimal;
(1-4) generating an auxiliary optimum point according to an orthogonal experimental mechanism;
(1-5) calculating a linear decreasing weight;
(1-6) calculating new positions and speeds of the particle swarm, and calculating fitness values of the new positions and speeds;
(1-7) if the number of iterations of the particle swarm exceeds the maximum number of iterations, terminating the search process of the particle swarm;
(1-8) obtaining an energy minimization control point of the problem according to the individual optimal value of the particle swarm;
(1-9) segmenting the image according to the energy minimization control point.
As some possible implementation manners, the training method of the QSOFM classifier model specifically includes:
(2-1) initializing system parameters of a QSOFM classifier model, and setting the parameters;
(2-2) performing cluster training on the QSOFM classifier model by using the CT image data matrix processed by the particle swarm optimization algorithm to obtain the QSOFM classifier model which can be used for classification and identification;
(2-3) randomly selecting a plurality of tumor CT images, and judging whether the tumors on the CT images are normal, cancerated or unknown by using the trained QSOFM classifier model.
As a further limitation, in the step (2-1), parameter setting is performed according to the number of competing nodes being 255, the radius of the field being 5, the learning rate being 1.0, the threshold being 2.0, the number of unsupervised training steps being 100, and the number of supervised training steps being 100.
As a further limitation, in the step (2-3), a plurality of CT images are arbitrarily selected, a to-be-tested CT image sample matrix is constructed, a characteristic data matrix is generated after calculation by a particle swarm optimization algorithm, and the characteristic data matrix is input into the QSOFM classifier model.
As some possible implementation manners, the data processing module is further configured to segment and number connected domains of high-grayscale regions of the CT image after the segmentation by the particle swarm optimization algorithm.
As a further limitation, when dividing the connected regions, the centroid of each connected region is calculated, the connected regions are divided according to the centroid positions, and the connected regions are selected by using the circumscribed rectangle frame and numbered in sequence.
As a further limitation, the numbered images are copied into the same number of copies as the number of the connected regions, the images are numbered in sequence, and the connected regions with the same number as the images are filled; wherein the numbering convention for images is the same as for connected regions.
Further, when the connected regions after numbering are sequentially filled, the selected connected regions are filled under the condition that other connected regions are not influenced;
further, after the filling of the image is completed, the filled image is input into a QSOFM classifier model, and the image processing result is recorded and displayed as a normal image number, and a connected region corresponding to the number represents the position of a tumor in the CT image.
As a further limitation, the connected region of the recorded number is retained, and other connected regions are filled and processed to obtain the image number of which all the image processing results are displayed as normal, and the filled image is compared with the original CT image to obtain the position and contour information of the tumor in the original CT image.
In a second aspect, the present disclosure provides a readable storage medium, on which a program is stored, which when executed by a processor, implements the data processing method of the data processing system for acquiring tumor location and contour in CT images according to the present disclosure.
In a third aspect, the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data processing method of the data processing system for acquiring a tumor position and contour in a CT image according to the present disclosure.
Compared with the prior art, the beneficial effect of this disclosure is:
according to the method, the segmentation of the image is more detailed and the redundant data is reduced by utilizing a particle swarm optimization algorithm, a quantum-based self-organizing feature mapping neural network classifier model (QSOFM classifier model) and a multi-connected region segmentation-based method, so that the tumor identification rate of the medical automatic equipment in the CT image is higher, and the tumor position is more quickly and accurately positioned.
The QSOFM classifier model is built based on the quantum neural network, so that the CT image is processed and identified at a higher processing speed and in a larger storage space, the retrieval time is reduced, and the retrieval effect is optimized.
According to the method, under the condition that a tumor exists, the CT image is further segmented, the tumor position information and the edge contour information in the CT image are obtained, the automation degree of the automatic puncture device is improved, and a foundation is laid for computer-assisted therapy.
Drawings
Fig. 1 is a schematic structural diagram of a data processing system for acquiring tumor location and contour information in a CT image according to embodiment 1 of the present disclosure.
Fig. 2 is a flowchart illustrating a particle swarm optimization algorithm for segmenting a CT image according to embodiment 1 of the present disclosure.
Fig. 3 is a flowchart of the training and recognition of QSOFM classifier models according to embodiment 1 of the present disclosure.
Fig. 4 is a flowchart of a data processing method of a data processing system for acquiring tumor location and contour information in a CT image according to embodiment 1 of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example 1:
as shown in fig. 1 to 4, embodiment 1 of the present disclosure provides a data processing system for acquiring a tumor location and an edge contour in a CT image, which includes the following steps:
the preprocessing module is configured to acquire a CT image, and perform image segmentation on the acquired CT image by utilizing a particle swarm optimization algorithm to obtain a segmented CT image data matrix;
the model building module is configured to build a QSOFM classifier model and perform model training by using the segmented CT image data matrix;
and the data processing module is configured to identify the canceration type of the tumor in the CT image by utilizing the QSOFM classifier model, and acquire the position and the contour information of the canceration tumor in the CT image based on a multi-connected region segmentation method.
The QSOFM classifier model is a two-layer network model and comprises an input layer and a competition layer. The input layer is a sample space used for receiving external signals; the competition layer, which may also be referred to as an output layer, is a one-dimensional or two-dimensional planar array of a plurality of neurons. And neurons in the output layer adopt an interaction pattern of "close neighbor excitation, far neighbor inhibition".
The preprocessing module utilizes particle swarm optimization algorithm to calculate and segment the acquired tumor CT image, and specifically comprises the following steps:
(1-1) establishing an energy minimization control point generalization function of image segmentation and generating a particle swarm;
(1-2) calculating a fitness function of the particle swarm algorithm to generate a fitness value of each particle;
(1-3) associating the fitness value of each particle with the individual optimum value (p) of the particleibest) And the individual optimum value (g) of the population of particlesbest) Comparing, and replacing the individual optimal value of the particle and the individual optimal value of the particle swarm if the fitness value of the particle is better;
let the D-dimensional space have m particles which form a particle group, and at the k-th iteration, the position vector and the velocity vector of the ith particle are respectively Xi[k]And Vi[k]WhereinThe position vectors correspond to potential solutions to the problem, all the groups of particles according to pibestAnd gbestAnd guiding the spatial search in the solution, wherein the calculation formula is as follows:
Vi[k+1]＝ωVi[k]+c1r1(pibest-Xi[k])+c2r2(gbest-Xi[k]) (1)
Xi[k+1]＝Xi[k]+Vi[k+1] (2)
wherein c is1And c2Is an individual and social cognitive coefficient, r1And r2Is a random number, ω is an inertial weight, and the variation is:
Figure BDA0002206148590000071
(1-4) generating an auxiliary optimal point X according to an orthogonal test schemebestBy XbestIn place of gbest；
Let PiIndicating the ith control point with the smallest energy in the ith search window SWiIn (q)i,jFor the jth candidate energy minimum control point, a generalization function of the energy minimum control points is established as follows:
Figure BDA0002206148590000072
wherein alpha, beta, gammaline、γedgeAnd gammatermAre all weight coefficients; c represents an edge function of the target image; cxyRepresents the partial derivative of the C function in the x direction and then the partial derivative of the y; cxRepresents the partial derivative of the C function in the x direction; cyRepresenting the partial derivative of the C function in the y direction.
(1-5) calculating a linear decreasing weight;
(1-6) calculating new positions and velocities of the particle swarm through formulas (3) and (4), and calculating fitness values of the new positions and velocities;
(1-7) if the number of iterations of the particle swarm exceeds the maximum number of iterations, terminating the search process of the particle swarm;
(1-8) obtaining an energy minimization control point of the problem according to the individual optimal value of the particle swarm;
(1-9) segmenting the image according to the energy minimization control point.
The construction method of the QSOFM classifier model specifically comprises the following steps:
(2-1) initializing system parameters of a QSOFM classifier model, and setting the parameters according to the number of competitive nodes of 255, the radius of the field of 5, the learning rate of 1.0, the threshold of 2.0, the number of unsupervised training steps of 100 and the number of supervised training steps of 100;
(2-2) performing cluster training on the QSOFM classifier model by using the CT image data matrix processed by the particle swarm optimization algorithm to obtain the QSOFM classifier model which can be used for classification and identification;
(2-3) randomly selecting a plurality of tumor CT images, constructing a CT image sample matrix to be tested, generating a characteristic data matrix after calculation of a particle swarm optimization algorithm, inputting the characteristic data matrix into a QSOFM classifier model, and judging whether the tumor on the CT image is a normal type, a canceration type or an unknown type by using the trained QSOFM classifier model.
The data processing module is also used for segmenting and numbering the connected domain of the high-gray-value region of the CT image segmented by the particle swarm optimization algorithm.
When the connected regions are divided, calculating the core of each connected region, dividing the connected regions according to the core positions, selecting the connected regions by using an external rectangular frame, numbering the connected regions in sequence, wherein the numbering mode is as follows: a 1, 2, 3, 4 ·;
copying the marked image into the same number of parts as the number of the connected regions, and numbering the images in sequence, wherein the numbering mode is as follows: b, filling a connected region with the same number as the image;
when the connected regions after numbering are sequentially filled, filling the selected connected regions under the condition of not influencing other connected regions;
after the image is filled, the filled image is input into a QSOFM classifier model, and the image processing result is recorded and displayed as a normal image number, and a connected region corresponding to the number represents the position of a tumor in a CT image.
And reserving the connected regions with the recorded numbers, filling and processing other connected regions to obtain all image processing results, displaying the image processing results as normal image numbers, and comparing the filled images with the original CT image to obtain the position and contour information of the tumor in the original CT image.
Example 2:
the embodiment 2 of the present disclosure provides a readable storage medium, on which a program is stored, which when executed by a processor, implements the data processing method of the data processing system for acquiring a tumor position and an edge contour in a CT image according to the embodiment 1 of the present disclosure.
Example 3:
an embodiment 3 of the present disclosure provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, where the processor implements a data processing method of the data processing system for acquiring a tumor position and an edge contour in a CT image according to embodiment 1 of the present disclosure when executing the program.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (7)

1. A data processing system for acquiring tumor location and edge contours in CT images, comprising:
the preprocessing module is configured to acquire a CT image, and perform image segmentation on the acquired CT image by utilizing a particle swarm optimization algorithm to obtain a segmented CT image data matrix;
the model building module is configured to build a QSOFM classifier model and perform model training by using the segmented CT image data matrix;
the data processing module is configured to identify the tumor canceration type in the CT image by using a QSOFM classifier model, and acquire the position and contour information of a canceration tumor in the CT image based on a multi-connected region segmentation method, and particularly, the data processing module is further used for segmenting and numbering the connected regions of the high-gray-value region of the CT image segmented by using a particle swarm optimization algorithm;
when the connected regions are divided, calculating the core of each connected region, dividing the connected regions according to the positions of the cores, selecting the connected regions by using an external rectangular frame, and numbering the connected regions;
copying the marked image into the number of parts which is the same as that of the connected regions, numbering the parts, and filling the connected regions with the same number as that of the image;
when the connected regions after numbering are sequentially filled, filling the selected connected regions under the condition of not influencing other connected regions;
after the image is filled, the filled image is input into a QSOFM classifier model, and the image processing result is recorded and displayed as a normal image number, and a connected region corresponding to the number represents the position of a tumor in a CT image.
2. The data processing system for acquiring tumor location and edge contour in CT image as claimed in claim 1, wherein said preprocessing module utilizes particle swarm optimization to segment the acquired CT image, specifically:
(1-1) establishing an energy minimization control point generalization function of image segmentation and generating a particle swarm;
(1-2) calculating a fitness function of the particle swarm algorithm to generate a fitness value of each particle;
(1-3) comparing the fitness value of each particle with the individual optimal value of the particle and the individual optimal value of the particle group, and replacing the individual optimal value of the particle and the individual optimal value of the particle group if the fitness value of the particle is more optimal;
(1-4) generating an auxiliary optimum point according to an orthogonal experimental mechanism;
(1-5) calculating a linear decreasing weight;
(1-6) calculating new positions and speeds of the particle swarm, and calculating fitness values of the new positions and speeds;
(1-7) if the number of iterations of the particle swarm exceeds the maximum number of iterations, terminating the search process of the particle swarm;
(1-8) obtaining an energy minimization control point of the problem according to the individual optimal value of the particle swarm;
(1-9) segmenting the image according to the energy minimization control point.
3. The data processing system for acquiring tumor locations and edge contours in CT images of claim 1, wherein the training of the QSOFM classifier model is specifically:
(2-1) initializing system parameters of a QSOFM classifier model, and setting the parameters;
(2-2) performing cluster training on the QSOFM classifier model by using the CT image data matrix processed by the particle swarm optimization algorithm to obtain the QSOFM classifier model which can be used for tumor classification and identification;
(2-3) randomly selecting a plurality of tumor CT images, and judging whether the tumors on the CT images are normal, cancerated or unknown by using the trained QSOFM classifier model.
4. The data processing system for acquiring tumor location and edge contour in CT image as claimed in claim 3, wherein in said step (2-1), parameter setting is performed based on the number of competing nodes being 255, the radius of the field being 5, the learning rate being 1.0, the threshold being 2.0, the number of unsupervised training steps being 100 and the number of supervised training steps being 100;
or in the step (2-3), a plurality of CT images are selected at will, a CT image sample matrix to be tested is constructed, a characteristic data matrix is generated after calculation of a particle swarm optimization algorithm, and the characteristic data matrix is input into the QSOFM classifier model.
5. The data processing system of claim 4, wherein the connected regions with recorded numbers are retained, and other connected regions are filled and processed to obtain the normal image numbers of all image processing results, and the filled image is compared with the original CT image to obtain the position and contour information of the tumor in the original CT image.
6. A readable storage medium on which a program is stored which, when being executed by a processor, carries out a data processing method of a data processing system for acquiring a tumor location and an edge contour in a CT image according to any one of claims 1 to 5.
7. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor when executing the program implements a data processing method of a data processing system for acquiring a tumor location and an edge contour in a CT image according to any one of claims 1 to 5.
CN201910882016.2A 2019-09-18 2019-09-18 Data processing system and electronic equipment for acquiring tumor position and contour in CT image Active CN110619644B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910882016.2A CN110619644B (en) 2019-09-18 2019-09-18 Data processing system and electronic equipment for acquiring tumor position and contour in CT image
NL2025775A NL2025775B1 (en) 2019-09-18 2020-06-08 Data processing system for acquiring tumor position and contour in ct image and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910882016.2A CN110619644B (en) 2019-09-18 2019-09-18 Data processing system and electronic equipment for acquiring tumor position and contour in CT image

Publications (2)

Publication Number Publication Date
CN110619644A CN110619644A (en) 2019-12-27
CN110619644B true CN110619644B (en) 2022-01-28

Family

ID=68923491

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910882016.2A Active CN110619644B (en) 2019-09-18 2019-09-18 Data processing system and electronic equipment for acquiring tumor position and contour in CT image

Country Status (2)

Country Link
CN (1) CN110619644B (en)
NL (1) NL2025775B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111419194A (en) * 2020-04-30 2020-07-17 山东大学 Fluorescent laser and OCT (optical coherence tomography) -based combined imaging device and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021552A (en) * 2014-05-28 2014-09-03 华南理工大学 Multi-objective particle swarm parameter optimization method based on graph segmentation process
CN104732213A (en) * 2015-03-23 2015-06-24 中山大学 Computer-assisted lump detecting method based on mammary gland magnetic resonance image
CN105405136A (en) * 2015-11-04 2016-03-16 南方医科大学 Self-adaptive spinal CT image segmentation method based on particle swarm optimization
CN106952275A (en) * 2017-03-16 2017-07-14 南京师范大学 A kind of cell image segmentation method based on PSO Neural Network
CN107845098A (en) * 2017-11-14 2018-03-27 南京理工大学 Liver cancer image full-automatic partition method based on random forest and fuzzy clustering
CN108921049A (en) * 2018-06-14 2018-11-30 华东交通大学 Tumour cell pattern recognition device and equipment based on quantum gate transmission line neural network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021552A (en) * 2014-05-28 2014-09-03 华南理工大学 Multi-objective particle swarm parameter optimization method based on graph segmentation process
CN104732213A (en) * 2015-03-23 2015-06-24 中山大学 Computer-assisted lump detecting method based on mammary gland magnetic resonance image
CN105405136A (en) * 2015-11-04 2016-03-16 南方医科大学 Self-adaptive spinal CT image segmentation method based on particle swarm optimization
CN106952275A (en) * 2017-03-16 2017-07-14 南京师范大学 A kind of cell image segmentation method based on PSO Neural Network
CN107845098A (en) * 2017-11-14 2018-03-27 南京理工大学 Liver cancer image full-automatic partition method based on random forest and fuzzy clustering
CN108921049A (en) * 2018-06-14 2018-11-30 华东交通大学 Tumour cell pattern recognition device and equipment based on quantum gate transmission line neural network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Segmentation of Pulmonary Parenchyma in CT lung Images based on 2D Otsu optimized by PSO;R.Helen et al;《2011 International Conference on Emerging Trends in Electrical and Computer Technology》;20110502;全文 *
基于QSOFM的胃粘膜肿瘤细胞图像识别;甘岚 等;《计算机应用研究》;20160630;全文 *

Also Published As

Publication number Publication date
CN110619644A (en) 2019-12-27
NL2025775B1 (en) 2021-12-14
NL2025775A (en) 2021-05-17

Similar Documents

Publication Publication Date Title
CN107154043B (en) Pulmonary nodule false positive sample inhibition method based on 3DCNN
Zhang et al. A hybrid biogeography-based optimization and fuzzy C-means algorithm for image segmentation
Liu et al. An evolutionary autonomous agents approach to image feature extraction
Zhu et al. Anatomynet: Deep 3d squeeze-and-excitation u-nets for fast and fully automated whole-volume anatomical segmentation
CN110992351B (en) sMRI image classification method and device based on multi-input convolution neural network
CN111709485B (en) Medical image processing method, device and computer equipment
Shokouhifar et al. An artificial bee colony optimization for mri fuzzy segmentation of brain tissue
Taherdangkoo et al. Segmentation of MR brain images using FCM improved by artificial bee colony (ABC) algorithm
CN112232407A (en) Neural network model training method and device for pathological image sample
Sharma et al. Deep learning model for automatic classification and prediction of brain tumor
US11804029B2 (en) Hierarchical constraint (HC)-based method and system for classifying fine-grained graptolite images
CN116884623B (en) Medical rehabilitation prediction system based on laser scanning imaging
Shan et al. Lung cancer diagnosis based on an ann optimized by improved teo algorithm
Tang et al. Multi-atlas brain parcellation using squeeze-and-excitation fully convolutional networks
CN110619644B (en) Data processing system and electronic equipment for acquiring tumor position and contour in CT image
CN107492101B (en) Multi-modal nasopharyngeal tumor segmentation algorithm based on self-adaptive constructed optimal graph
CN116188428A (en) Bridging multi-source domain self-adaptive cross-domain histopathological image recognition method
CN116029994A (en) Brain glioma MR image segmentation method based on edge loss and knowledge fusion decision
CN115310491A (en) Class-imbalance magnetic resonance whole brain data classification method based on deep learning
Yuan Image processing method based on FGCA and artificial neural network
Pan et al. Leukocyte image segmentation using novel saliency detection based on positive feedback of visual perception
CN113192053A (en) Cervical tumor target area intelligent delineation method, equipment and medium based on deep learning
Kaur et al. A Study of Particle Swarm Optimization based K-means Clustering for Detection of Dental Caries in Dental X-ray Images.
Zohra et al. Adjustment of active contour parameters in Brain MRI segmentation using evolution strategies
Singh et al. An efficient brain tumor detection using modified tree growth algorithm and random forest method

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
GR01 Patent grant
GR01 Patent grant