CN114469052A - Quantitative calculation method and device for tumor shrinkage deformation after liver ablation - Google Patents

Quantitative calculation method and device for tumor shrinkage deformation after liver ablation Download PDF

Info

Publication number
CN114469052A
CN114469052A CN202210125369.XA CN202210125369A CN114469052A CN 114469052 A CN114469052 A CN 114469052A CN 202210125369 A CN202210125369 A CN 202210125369A CN 114469052 A CN114469052 A CN 114469052A
Authority
CN
China
Prior art keywords
tumor
ablation
liver
image
afterimage
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
CN202210125369.XA
Other languages
Chinese (zh)
Inventor
梁萍
董立男
刘方义
于杰
程志刚
韩治宇
罗艳春
穆梦娟
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.)
Fifth Medical Center of PLA General Hospital
Original Assignee
Fifth Medical Center of PLA General 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 Fifth Medical Center of PLA General Hospital filed Critical Fifth Medical Center of PLA General Hospital
Priority to CN202210125369.XA priority Critical patent/CN114469052A/en
Publication of CN114469052A publication Critical patent/CN114469052A/en
Pending 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
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
    • A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1073—Measuring volume, e.g. of limbs
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1076—Measuring physical dimensions, e.g. size of the entire body or parts thereof for measuring dimensions inside body cavities, e.g. using catheters
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
    • A61B5/4222—Evaluating particular parts, e.g. particular organs
    • A61B5/4244—Evaluating particular parts, e.g. particular organs liver
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4848—Monitoring or testing the effects of treatment, e.g. of medication
    • 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
    • G06F18/211—Selection of the most significant subset of features
    • G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
    • 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
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • 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
    • G06T2207/20112—Image segmentation details
    • 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

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Dentistry (AREA)
  • Radiology & Medical Imaging (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Gastroenterology & Hepatology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Endocrinology (AREA)
  • Physiology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Geometry (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

The quantitative calculation method and the device for the shrinkage degree of the tumor after the liver ablation can solve the problem of quantitative calculation of shrinkage deformation of tumors with different properties under different ablation conditions, and lay a foundation for accurate postoperative evaluation of tumor ablation. The method comprises the following steps: (1) selecting a multi-stage image by using an MRI image with clear tumor afterimage after ablation, respectively segmenting a liver before the operation, a tumor region, a tumor afterimage after the operation and an ablation region, and calculating the volumes of the tumor region before the operation, the tumor afterimage after the operation and the ablation region; (2) extracting image omics characteristics aiming at preoperative liver and tumor segmentation areas of each stage; (3) performing correlation test on all image omics characteristics, removing omics characteristics with correlation, adding clinical information of a patient, and performing characteristic dimension reduction screening by adopting a LASSO algorithm LASSO; (4) and establishing a regression model of tumor volume shrinkage by using ablation energy parameters and the characteristics of the image omics.

Description

Quantitative calculation method and device for tumor shrinkage deformation after liver ablation
Technical Field
The invention relates to the technical field of medical image processing, in particular to a quantitative calculation method for the shrinkage degree of a tumor after liver ablation and a quantitative calculation device for the shrinkage degree of the tumor after liver ablation.
Background
In recent years, image-guided percutaneous thermal ablation has become one of the promising minimally invasive treatment methods for solid tumors such as liver, kidney, and breast. The microwave ablation is conducted by ultrasonic, CT and other image guidance, the ablation needle is inserted into the tumor, and polar molecules in a local area are vibrated and rubbed to generate high temperature by releasing electromagnetic waves, so that the purpose of inactivating the tumor is finally achieved. However, unlike the clear visualization of the tumor and the treatment area during open surgery, minimally invasive ablation is performed under intraoperative two-dimensional image guidance, and assessment is made by comparing preoperative and postoperative images as to whether the treatment area completely covers the tumor and reaches a sufficient safety margin. However, due to the syneresis and deformation of the tumor during the ablation treatment of the patient, the accurate efficacy evaluation cannot be carried out only by the layer-by-layer comparison or rigid registration of the preoperative and postoperative two-dimensional images.
The error of the non-rigid registration method in the aspect of postoperative evaluation is lower than that of rigid registration, but the non-rigid registration method applied to the postoperative evaluation of ablation at home and abroad at present is limited by the universality problem of the tissue deformation energy functional construction, and particularly for the characteristic of uneven local tissue deformation after liver tumor ablation, a method for quantitatively calculating the tumor shrinkage deformation and a method for correcting the non-rigid registration evaluation error caused by tumor shrinkage do not exist.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a quantitative calculation method for shrinkage deformation of tumors after liver ablation, which can solve the problem of quantitative calculation of shrinkage deformation of tumors with different properties under different ablation conditions and lay a foundation for accurate postoperative evaluation of tumor ablation.
The technical scheme of the invention is as follows: the quantitative calculation method for the shrinkage deformation of the tumor after the liver ablation comprises the following steps:
(1) selecting a multi-stage image by using an MRI image with clear tumor afterimage after ablation, respectively segmenting a liver, a tumor region before the operation, the tumor afterimage after the operation and an ablation region, and calculating the volume of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
(2) extracting the image omics characteristics aiming at the preoperative tumor segmentation region of each stage;
(3) carrying out correlation test on all image omics characteristics, removing the omics characteristics with correlation, adding clinical information of a patient, and carrying out characteristic dimension reduction screening by adopting a LASSO algorithm LASSO;
(4) and establishing a regression model of tumor volume shrinkage by using ablation energy parameters and the characteristics of the imagemics.
The method comprises the steps of selecting T2 and multi-stage images such as an arterial stage and the like by utilizing an MRI image with clear tumor afterimage after ablation, respectively segmenting a preoperative tumor region, a postoperative tumor afterimage and an ablation region, and calculating the volumes of the three; extracting the image omics characteristics aiming at the preoperative tumor segmentation region of each stage; carrying out correlation test on all image omics characteristics, removing the omics characteristics with correlation, adding clinical information of patients, and carrying out feature dimension reduction screening by adopting a lasso algorithm; finally, establishing a regression model of tumor volume shrinkage by using ablation energy parameter combination omics characteristics; therefore, the problem of shrinkage deformation quantitative calculation of tumors with different properties under different ablation conditions can be solved, and a foundation is laid for accurate postoperative evaluation of tumor ablation.
Still provide tumour shrink degree ration accounting device after the liver ablation, it includes:
the image segmentation module is configured to select a multi-stage image by using an MRI image with clear tumor afterimage after ablation, segment a liver, a tumor region before the operation, a tumor afterimage after the operation and an ablation region respectively, and calculate the volumes of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
a feature extraction module configured to extract an imagemics feature for each stage of the pre-operative tumor segmentation region;
the characteristic screening module is configured for carrying out correlation test on all image omics characteristics, removing the omics characteristics with correlation, adding clinical information of a patient, and carrying out characteristic dimension reduction screening by adopting a LASSO algorithm LASSO;
a model building module configured to build a regression model of tumor volume shrinkage using the ablation energy parameters in combination with the omics features.
Drawings
Fig. 1 is a flowchart of a quantitative calculation method of tumor shrinkage degree after liver ablation according to the present invention.
Fig. 2 is an operation diagram of the quantitative calculation method of the degree of tumor shrinkage after liver ablation according to the present invention.
Fig. 3 is a diagram illustrating the effect of processing the liver region of the image before and after ablation by using a point cloud registration algorithm in the prior art.
Fig. 4 is a diagram illustrating an effect of correcting fig. 3 according to the present invention.
Detailed Description
As shown in fig. 1, the quantitative calculation method for shrinkage deformation of tumor after liver ablation is applied to the correction of three-dimensional registration, and includes the following steps:
(1) selecting a multi-stage image by using an MRI image with clear tumor afterimage after ablation, respectively segmenting a liver, a tumor region before the operation, the tumor afterimage after the operation and an ablation region, and calculating the volume of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
(2) extracting the image omics characteristics aiming at the preoperative tumor segmentation region of each stage;
(3) performing correlation test on all image omics characteristics, removing omics characteristics with correlation, adding clinical information of a patient, and performing characteristic dimension reduction screening by adopting a lasso algorithm LASSO (least absolute shrinkage and selection operator);
(4) and establishing a regression model of tumor volume shrinkage by using ablation energy parameters and the characteristics of the image omics.
The method comprises the steps of selecting T2 and multi-stage images such as an arterial stage and the like by utilizing an MRI image with clear tumor afterimage after ablation, respectively segmenting a liver and a tumor region before the operation, the tumor afterimage after the operation and an ablation area, and calculating the volumes of the liver, the tumor region, the tumor afterimage and the ablation area; extracting image omics characteristics aiming at preoperative liver and tumor segmentation areas of each stage; carrying out correlation test on all image omics characteristics, removing omics characteristics with correlation, adding clinical information of a patient, and carrying out characteristic dimension reduction screening by adopting a lasso algorithm; finally, establishing a regression model of tumor volume shrinkage by using ablation energy parameter combination omics characteristics; therefore, the problem of shrinkage deformation quantitative calculation of tumors with different properties under different ablation conditions can be solved, and a foundation is laid for accurate postoperative evaluation of tumor ablation.
200 cases of preoperative and postoperative data of the patient enhanced MRI image are collected, and the clear tumor afterimage in the postoperative image is taken as an inclusion standard. Preferably, in the step (1), the tumor volume V is calculated by performing three-dimensional tumor segmentation on preoperative T2, DWI, arterial phase and delayed phase respectivelybefore(ii) a Three-dimensional segmentation is carried out on the tumor afterimage of the postoperative delayed-phase enhanced MRI image, and the volume V of the tumor afterimage is calculatedafterAnd ablation zone volume Vablation(can be realized by image segmentation software such as ITK-snap; MITK, etc.); tumor shrinkage ratio (V) was calculated for each case of databefore-Vafter)/Vbefore。
Preferably, in the step (2), the MRI images of each phase are standardized; PyRadiomics is used for extracting 873 three-dimensional image omics characteristics of each phase tumor in T2, DWI, arterial phase and delay phase in preoperative MRI of each patient, wherein the number of shape characteristics is 13, the number of first-order characteristics is 180, and the number of texture characteristics is 680, namely 3492 image characteristics.
Preferably, in the step (3), the 617 image features are remained after the screening by using the correlation analysis.
Preferably, LASSO in step (3) is expressed as Y ═ Σ ω as a generalized linear modeliXi+ b, where i ═ 1,2,3, … … n, ωiIs each characteristic XiBy making the loss function formula (1)
Figure BDA0003500258350000051
And (3) minimizing, and enabling the unimportant characteristic coefficient to be 0 to realize the purpose of characteristic screening, wherein lambda is calculated in a ten-fold cross validation cycle optimization process, and is finally included in 23 tumor shrinkage related omics characteristics through LASSO characteristic screening. The method comprises the following steps:
exponential_firstorder_Minimum 1.04
gradient_glcm_Idn -0.002
gradient_glcm_Imc1 0.32
gradient_glcm_InverseVariance 0.51
gradient_glcm_MCC -0.55
gradient_glszm_SmallAreaLowGrayLevelEmphasis 2.41
Lbp-2D_glszm_SmallAreaEmphasis 0.69
logarithm_glcm_MaximumProbability -0.58
Wavelet-LLH_glcm_ClusterShade -1.0
Wavelet-LHL_firstorder_90Percentile 0.13
Wavelet-LHL_glszm_LowGrayLevelZoneEmphasis 1.33
Wavelet-LHH_firstorder_InterquartileRange 0.46
Wavelet-LHH_glszm_GrayLevelNonUniformity 0.86
Wavelet-LHH_glszm_LargeAreaEmphasis -0.87
Wavelet-LHH_glszm_SizeZoneNonUniformityNormalized 0.73
Wavelet-HLL_glcm_ClusterShade 0.89
Wavelet-HLL_glszm_LargeAreaLowGrayLevelEmphasis -0.59
Wavelet-HHL_glszm_GrayLevelNonUniformity 1.82
Wavelet-HHL_glszm_LowGrayLevelZoneEmphasis 0.36
Wavelet-HHL_glszm_ZoneEntropy 0.19
Wavelet-HHH_firstorder_Mean 0.13
Wavelet-HHH_glszm_SmallAreaLowGrayLevelEmphasis 0.67
Wavelet-LLL_glcm_MaximumProbability -1.56
the imageomics score, Rad score, was calculated for each case based on the screened texture features.
Preferably, in the step (3), the ten-fold cross validation is to divide all cases into 10, randomly select 1 of them as validation set, use the other 9 as training set, repeat the cross validation 10 times, and average 10 times to obtain the final prediction result.
According to the previous research and analysis of a team, the tissue contraction degree is influenced by microwave energy absorbed by the tissue, so that the image omics score is subjected to regression analysis by taking ablation energy parameters (microwave energy absorbed by an ablation area in unit volume is calculated according to ablation time, power and ablation volume) of each patient and clinical information (age, sex and the like) as tumor contraction influence factors, and a linear regression model is established to predict the tumor volume contraction degree Y.
Preferably, in the step (4), the image omics score and the ablation energy parameter and clinical information of each patient are used as tumor shrinkage influence factors for regression analysis, and a linear regression model is established to predict the tumor volume shrinkage degree Y; the ablation energy parameter is microwave energy absorbed by an ablation area in unit volume according to ablation time, power and ablation volume, and clinical information comprises age, gender, ratio of actual liver volume to standard liver volume and the like.
Preferably, the linear regression model in the step (4) is formula (2)
Y＝0.4*X1+1.02*X2+36.6 (2)
Wherein Y represents the degree of tumor shrinkage and X represents1Representing the energy absorbed per unit volume, X2Representative imaging omics scores.
Preferably, in the step (4), in the post-operation registration evaluation, the point cloud elastic registration Based on differential homoembryo is used as an evaluation method (in addition, the contraction method is also applicable to other traditional elastic registration methods, such as a Free-Form Deformation model (Free-Form Deformation model), a registration model Based on Kernel function (Kernel Functions-Based model), and the like), according to the degree of tumor volume contraction, the tumor boundary line of the primary non-rigid registration is uniformly and centripetally contracted along a normal vector in a three-dimensional space, and the registered tumor volume contraction correction is performed, and the minimum distance between the tumor boundary and the ablation region boundary in the space is used as a measure of the ablation efficacy.
The technical effect of the present invention with respect to the prior art is verified as follows.
Fig. 3 is a diagram illustrating the effect of processing the liver region of the image before and after ablation by using a point cloud registration algorithm in the prior art. And registering the liver regions before and after ablation by using a point cloud registration algorithm to obtain a transformation matrix. And (3) obtaining a registration result of the preoperative liver tumor region corresponding to the postoperative CT/MRI image region according to the liver surface transformation matrix, wherein the registration result is shown in figure 3. The point cloud initial registration result is shown, a three-dimensional result graph (the innermost side is an inactivated tumor ghost, the middle layer is a preoperative tumor registration transformation result, and the outermost layer is a postoperative ablation region) is arranged on the right side, and the difference between the initial registration result and the actual tumor form can be seen.
Fig. 4 is a diagram illustrating an effect of correcting fig. 3 according to the present invention. The method is used for predicting the liver tumor form change of the patient after the ablation operation, and the tumor form obtained in the figure 3 is corrected, so that the corrected tumor deformation basically coincides with the inactivated actual form. Therefore, compared with the prior art, the method can solve the problem of quantitative calculation of shrinkage deformation of tumors with different properties under different ablation conditions, and lays a foundation for accurate postoperative evaluation of tumor ablation.
It will be understood by those skilled in the art that all or part of the steps in the method of the above embodiments may be implemented by hardware instructions related to a program, the program may be stored in a computer-readable storage medium, and when executed, the program includes the steps of the method of the above embodiments, and the storage medium may be: ROM/RAM, magnetic disks, optical disks, memory cards, and the like. Therefore, corresponding to the method of the present invention, the present invention also includes a device for quantitatively calculating the degree of shrinkage of the tumor after liver ablation, which is generally expressed in the form of functional modules corresponding to the steps of the method. The device comprises:
still provide the tumour degree of contraction ration accounting device after the liver ablation, it includes:
the image segmentation module is configured to select a multi-stage image by using an MRI image with clear tumor afterimage after ablation, segment a liver, a tumor region before the operation, a tumor afterimage after the operation and an ablation region respectively, and calculate the volumes of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
a feature extraction module configured to extract an imagemics feature for each stage of the pre-operative tumor segmentation region;
the characteristic screening module is configured for carrying out correlation test on all image omics characteristics, removing the omics characteristics with correlation, adding clinical information of a patient, and carrying out characteristic dimension reduction screening by adopting a LASSO algorithm LASSO;
a model building module configured to build a regression model of tumor volume shrinkage using the ablation energy parameters in combination with the omics features.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent variations and modifications made to the above embodiment according to the technical spirit of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims (10)

1. The quantitative calculation method of the tumor shrinkage degree after liver ablation is characterized by comprising the following steps: which comprises the following steps:
(1) selecting a multi-stage image by using an MRI image with clear tumor afterimage after ablation, respectively segmenting a liver, a tumor region before the operation, the tumor afterimage after the operation and an ablation region, and calculating the volume of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
(2) extracting the image omics characteristics aiming at the preoperative tumor segmentation region of each stage;
(3) performing correlation test on all image omics characteristics, removing omics characteristics with correlation, adding clinical information of a patient, and performing characteristic dimension reduction screening by adopting a LASSO algorithm LASSO;
(4) and establishing a regression model of tumor volume shrinkage by using ablation energy parameters and the characteristics of the image omics.
2. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 1, characterized in that: in the step (1), tumor three-dimensional segmentation is carried out on preoperative T2, DWI, arterial phase and delay phase respectively, and tumor volume V is calculatedbefore(ii) a Three-dimensional segmentation is carried out on the tumor afterimage of the postoperative delayed-phase enhanced MRI image, and the volume V of the tumor afterimage is calculatedafterAnd ablation zone volume Vablation(ii) a Tumor shrinkage ratio (V) was calculated for each case of databefore-Vafter)/Vbefore。
3. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 2, characterized in that: in the step (2), the MRI image of each period is standardized; PyRadiomics is used for extracting 873 three-dimensional image omics characteristics of T2, DWI, arterial stage and each phase tumor in pre-operation MRI of each patient, wherein the three-dimensional image omics characteristics include 13 shape characteristics, 180 first-order characteristics and 680 texture characteristics.
4. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 3, characterized in that: in the step (3), the 617 image features are remained after screening by using correlation analysis.
5. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 4, characterized in that: the LASSO in step (3) is expressed as Y ═ Σ ω as a generalized linear modeliXi+ b, where i ═ 1,2,3, … … n, ωiIs each characteristic XiBy making the loss function formula (1)
Figure FDA0003500258340000021
And (3) minimizing, and enabling the unimportant characteristic coefficient to be 0 to realize the purpose of characteristic screening, wherein lambda is calculated in a ten-fold cross validation cycle optimization process, and is finally included in 23 tumor shrinkage related omics characteristics through LASSO characteristic screening.
6. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 5, characterized in that: in the step (3), the ten-fold cross validation is to divide all cases into 10, randomly select 1 of the cases as a validation set, use the other 9 cases as a training set, repeat the cross validation 10 times, average 10 times of results to obtain a final prediction result.
7. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 6, characterized in that: in the step (4), regression analysis is carried out on the score of the image omics, the ablation energy parameter and the clinical information of each patient as tumor shrinkage influence factors, and a linear regression model is established to predict the shrinkage degree Y of the tumor volume; the ablation energy parameter is microwave energy absorbed by an ablation area in unit volume according to ablation time, power and ablation volume, and clinical information comprises age, gender, actual liver volume and a standard liver volume ratio.
8. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 7, characterized in that: the linear regression model in the step (4) is a formula (2)
Y＝0.4*X1+1.02*X2+36.6 (2)
Wherein Y represents the degree of tumor shrinkage and X represents1Representing the energy absorbed per unit volume, X2Representative imaging omics scores.
9. The quantitative calculation method of tumor shrinkage degree after liver ablation according to claim 8, characterized in that: in the step (4), in the post-operation registration evaluation, the point cloud elastic registration based on differential homoembryo is used as an evaluation method, the preliminarily non-rigidly registered tumor boundary line is uniformly and centripetally contracted along a normal vector in a three-dimensional space according to the tumor volume contraction degree, the registered tumor volume contraction correction is carried out, and the minimum distance between the tumor boundary and the boundary of an ablation area in the space is used as a measurement standard of the ablation curative effect.
10. Liver melts postoperative tumour shrinkage degree ration accounting device, its characterized in that: it includes: the image segmentation module is configured to select a multi-stage image by using an MRI image with clear tumor afterimage after ablation, segment a liver, a tumor region before the operation, a tumor afterimage after the operation and an ablation region respectively, and calculate the volumes of the liver, the tumor region before the operation, the tumor afterimage after the operation and the ablation region;
a feature extraction module configured to extract an imagemics feature for each stage of the pre-operative tumor segmentation region;
the characteristic screening module is configured for carrying out correlation test on all image omics characteristics, removing the omics characteristics with correlation, adding clinical information of a patient, and carrying out characteristic dimension reduction screening by adopting a LASSO algorithm LASSO;
a model building module configured to build a regression model of tumor volume shrinkage using the ablation energy parameters in combination with the omics features.
CN202210125369.XA 2022-02-10 2022-02-10 Quantitative calculation method and device for tumor shrinkage deformation after liver ablation Pending CN114469052A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210125369.XA CN114469052A (en) 2022-02-10 2022-02-10 Quantitative calculation method and device for tumor shrinkage deformation after liver ablation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210125369.XA CN114469052A (en) 2022-02-10 2022-02-10 Quantitative calculation method and device for tumor shrinkage deformation after liver ablation

Publications (1)

Publication Number Publication Date
CN114469052A true CN114469052A (en) 2022-05-13

Family

ID=81479117

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210125369.XA Pending CN114469052A (en) 2022-02-10 2022-02-10 Quantitative calculation method and device for tumor shrinkage deformation after liver ablation

Country Status (1)

Country Link
CN (1) CN114469052A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670960A (en) * 2024-02-01 2024-03-08 江苏一影医疗设备有限公司 Image registration method, system and equipment based on lung CT-CBCT

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670960A (en) * 2024-02-01 2024-03-08 江苏一影医疗设备有限公司 Image registration method, system and equipment based on lung CT-CBCT

Similar Documents

Publication Publication Date Title
CN110782474B (en) Deep learning-based method for predicting morphological change of liver tumor after ablation
JP6567179B2 (en) Pseudo CT generation from MR data using feature regression model
US9672622B2 (en) Image fusion with automated compensation for brain deformation
Tobon-Gomez et al. Benchmark for algorithms segmenting the left atrium from 3D CT and MRI datasets
US8207992B2 (en) Composite images for medical procedures
CN110910406B (en) Method and system for evaluating three-dimensional space curative effect after liver tumor ablation
JP2018535732A (en) Pseudo CT generation from MR data using tissue parameter estimation
EP3788596B1 (en) Lower to higher resolution image fusion
Schumann et al. Fast automatic path proposal computation for hepatic needle placement
CN108460813A (en) A kind of Target delineations method and apparatus
CN113545844A (en) Simulation method and device for laser interstitial thermotherapy
Xu et al. ROI-based intraoperative MR-CT registration for image-guided multimode tumor ablation therapy in hepatic malignant tumors
CN114469052A (en) Quantitative calculation method and device for tumor shrinkage deformation after liver ablation
Nazem et al. Two-stage point-based registration method between ultrasound and CT imaging of the liver based on ICP and unscented Kalman filter: a phantom study
Foruzan et al. Multimodality liver registration of Open-MR and CT scans
KR20200095967A (en) Apparatus and method for measuring left atrium thickness of heart
CN113096166B (en) Medical image registration method and device
Sultana et al. A deformable multimodal image registration using PET/CT and TRUS for intraoperative focal prostate brachytherapy
Laura et al. Accurate physics-based registration for the outcome validation of minimal invasive interventions and open liver surgeries
Sandoval et al. Evaluation of computed tomography to ultrasound 2D image registration for atrial fibrillation treatment
JP6570460B2 (en) Evaluation apparatus, method and program
US11423553B2 (en) Calibration of image-registration based tracking procedures
Criscuolo et al. A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms
Zhang et al. A multiscale adaptive mask method for rigid intraoperative ultrasound and preoperative CT image registration
Elhawary et al. Intra-operative multimodal non-rigid registration of the liver for navigated tumor ablation

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