CN116473592A - Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope - Google Patents
Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope Download PDFInfo
- Publication number
- CN116473592A CN116473592A CN202310407175.3A CN202310407175A CN116473592A CN 116473592 A CN116473592 A CN 116473592A CN 202310407175 A CN202310407175 A CN 202310407175A CN 116473592 A CN116473592 A CN 116473592A
- Authority
- CN
- China
- Prior art keywords
- chemotherapy
- image
- breast cancer
- ultrasonic
- ultrasonic positioning
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 208000026310 Breast neoplasm Diseases 0.000 title claims abstract description 45
- 206010006187 Breast cancer Diseases 0.000 title claims abstract description 44
- 230000000694 effects Effects 0.000 title claims abstract description 40
- 238000011227 neoadjuvant chemotherapy Methods 0.000 title claims abstract description 26
- 238000002512 chemotherapy Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000002604 ultrasonography Methods 0.000 claims abstract description 19
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 16
- 210000004088 microvessel Anatomy 0.000 claims abstract description 12
- 239000008280 blood Substances 0.000 claims abstract description 10
- 238000003384 imaging method Methods 0.000 claims abstract description 10
- 239000002872 contrast media Substances 0.000 claims description 25
- 210000004204 blood vessel Anatomy 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 16
- 230000004807 localization Effects 0.000 claims description 15
- 230000010412 perfusion Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 230000017531 blood circulation Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000001000 micrograph Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 5
- 238000011226 adjuvant chemotherapy Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000000692 Student's t-test Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 3
- 230000001575 pathological effect Effects 0.000 claims description 3
- 229920013655 poly(bisphenol-A sulfone) Polymers 0.000 claims description 3
- 238000002601 radiography Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000012353 t test Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims description 2
- 238000012285 ultrasound imaging Methods 0.000 claims description 2
- 230000000877 morphologic effect Effects 0.000 claims 1
- 230000000004 hemodynamic effect Effects 0.000 abstract description 5
- 238000004393 prognosis Methods 0.000 abstract description 4
- 238000002560 therapeutic procedure Methods 0.000 abstract description 2
- 230000000593 degrading effect Effects 0.000 abstract 1
- 230000002792 vascular Effects 0.000 description 11
- 230000002093 peripheral effect Effects 0.000 description 6
- 230000008081 blood perfusion Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000541 pulsatile effect Effects 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 208000003721 Triple Negative Breast Neoplasms Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000002601 intratumoral effect Effects 0.000 description 2
- 208000022679 triple-negative breast carcinoma Diseases 0.000 description 2
- 206010006272 Breast mass Diseases 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 201000007741 female breast cancer Diseases 0.000 description 1
- 201000002276 female breast carcinoma Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 210000005075 mammary gland Anatomy 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002504 physiological saline solution Substances 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0825—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the breast, e.g. mammography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0891—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/48—Diagnostic techniques
- A61B8/481—Diagnostic techniques involving the use of contrast agent, e.g. microbubbles introduced into the bloodstream
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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
- G06T2207/10056—Microscopic 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Hematology (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Vascular Medicine (AREA)
- Physiology (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a method for evaluating the curative effect of breast cancer neoadjuvant chemotherapy by using an ultrasonic positioning microscope, which comprises the following steps: s1, collecting a low-dose ultrasonic contrast image; performing low-dose ultrasound contrast on breast tumor of a breast cancer patient under the new auxiliary chemotherapy and performing image acquisition; s2, MATLAB image processing; performing ultrasonic positioning microscope micro-blood vessel imaging treatment offline by MATLAB to obtain an ultrasonic super-resolution map and a flow velocity map of the micro-blood vessel; s3, calculating and analyzing; and respectively calculating the morphology and hemodynamic parameters of the microvessels through an ultrasonic super-resolution chart and a flow velocity chart of the microvessels, and finally evaluating the curative effect of the novel auxiliary chemotherapy according to dynamic changes of microvessel parameters in tumors extracted before, during and after chemotherapy. Provides a new method and thought for accurately and noninvasively evaluating the curative effect of the novel auxiliary chemotherapy in the early stage of clinic, provides guidance for upgrading and degrading the breast cancer treatment and developing a novel therapy, provides scientific basis for clinically and individually adjusting the treatment scheme, and has important value for improving the treatment and prognosis of patients.
Description
Technical Field
The invention relates to the technical field of ultrasonic positioning imaging, in particular to a method for evaluating the curative effect of new auxiliary chemotherapy for breast cancer by using an ultrasonic positioning microscope.
Background
Female breast cancer is a tumor with highest global cancer incidence rate beyond lung cancer, so that physical and mental health of females is seriously influenced, and novel auxiliary chemotherapy is used as a common treatment mode of breast cancer, and timely evaluation of the chemotherapy curative effect is of great significance for improving treatment and prognosis of patients. The study proves that the size, shape, structure, distribution and the like of the micro-blood vessels of the breast cancer influence the tumor progress along with the time-space change of the treatment process of the neoadjuvant chemotherapy, and early identification of the reconstruction of the micro-blood vessels is beneficial to the evaluation of the curative effect of the neoadjuvant chemotherapy of the breast cancer.
The current commonly used microvascular detection technology mainly comprises ultrasonic radiography and dynamic contrast enhancement magnetic resonance, can display the neovascular and blood perfusion modes of breast tumors, and can generate quantitative indexes for evaluating the curative effect of the novel auxiliary chemotherapy; however, the resolution of the traditional ultrasonic imaging is affected by diffraction limit, and the blood vessel of micron order (50-100 microns) cannot be imaged clearly; the Chinese patent publication No. CN115482229A discloses a method and a device for recognizing breast tumor by conventional ultrasonic and ultrasonic contrast images; the two-way convolutional neural network (two-way deep convolutional neural network) is used for respectively processing two-dimensional information and three-dimensional information, and the two types of characteristics obtained by processing are fused, so that higher-level characteristic expression is obtained, and the accuracy of the identification result is improved; however, the definition of the image is poor, and the clear image which accords with the actual situation can not be obtained through the algorithm processing in the later period; in addition, MRI examination is expensive, and single examination time is long, which limits its application in evaluation of the efficacy of neoadjuvant chemotherapy.
Therefore, a low-cost, accurate and noninvasive new auxiliary chemotherapy efficacy evaluation means for breast cancer is clinically needed at present.
Disclosure of Invention
Aiming at the problems that a blood vessel detection technology adopted in cancer chemotherapy evaluation in the prior art cannot carry out clear imaging on blood vessels with the micron level (50-100 microns), is high in inspection cost and is not beneficial to the evaluation of the curative effect of the breast cancer neoadjuvant chemotherapy, the invention provides a method for evaluating the curative effect of the breast cancer neoadjuvant chemotherapy by using an ultrasonic positioning microscope, carries out positioning, tracking and other procedures on ultrasonic microbubbles in breast cancer tumors, noninvasively identifies and displays a microvascular system, breaks through an ultrasonic diffraction limit to generate microvascular images in the tumor, extracts parameters of corresponding microvascular morphology (blood vessel diameter, blood vessel spacing, blood vessel density ratio and blood vessel tortuosity) and dynamic change process of microvascular reconstruction in the process of the neoadjuvant chemotherapy, and explores the corresponding microvascular reconstruction rules of different curative effects; can provide a new method for early and accurate prediction for the evaluation of the curative effect of the breast cancer new auxiliary chemotherapy, provides technical guidance for the clinical personalized adjustment of the treatment scheme, and improves the prognosis of breast cancer patients.
A method for evaluating the curative effect of breast cancer neoadjuvant chemotherapy by using an ultrasonic positioning microscope, comprising the following steps:
s1, collecting a low-dose ultrasonic contrast image; respectively carrying out low-dose ultrasonic radiography on breast tumor of a breast cancer patient before, during and after the new auxiliary chemotherapy and carrying out image acquisition;
s2, MATLAB image processing; performing ultrasonic positioning microscope micro-blood vessel imaging treatment offline by MATLAB to obtain an ultrasonic super-resolution map and a flow velocity map of the micro-blood vessel;
s3, calculating and analyzing; and finally, according to intratumoral microvascular parameters (namely blood vessel morphology and blood flow dynamic parameters) extracted before, during and after chemotherapy, taking a pathological result as a gold standard, carrying out statistical analysis, and exploring a novel method and a novel standard for early noninvasively evaluating the curative effect of the novel auxiliary chemotherapy of the breast cancer.
Preferably, the step 2 specifically includes: step S21, background and noise signal processing; s22, ultrasonic positioning treatment; step S23, tracking the microbubble signal.
Preferably, the step S21 is background and noise signal processing; exporting image data in an ultrasonic diagnostic apparatus in a DICOM format, carrying out singular value decomposition processing on each frame of image in each data set, and then processing a tissue background signal and an image noise signal by selecting different singular value thresholds;
preferably, the step S22 is ultrasonic positioning treatment; to reject noise and detect potential microbubble signals, the coordinates of the individual contrast signals are located, firstly ultrasound localization microscopy images are obtained by gaussian fitting, and then each observed Point Spread Function (PSF) is compared with a calibration PSF according to its area (a), intensity (I) and shape/eccentricity (E); these parameters are used to discard potential non-microbubble signals and noise; all observed PSFs with the corresponding three attributes are summarized into three matrices; all values in each matrix are normalized; the position of the separated signals is calculated by a "centroid" method; the centroid of each local signal is calculated by calculating the intensity weighted centroid, and all the positions from all the images are assembled into the final super resolution image.
Preferably, in the step S23, the microbubble signal is tracked; in order to calculate the flow velocity of the super-resolution microvessels, tracking microvesicle signals between adjacent frames, matching the nearest contrast signals between the adjacent frames by using a Kuhn-Munkres algorithm, taking the distance between each microvesicle between the adjacent frames as a weight, matching the adjacent microvesicles between the adjacent frames based on the idea of bipartite graph to minimize the total weight, and finally removing the matching of overlarge distance and zero distance by setting a threshold value to realize the tracking of the contrast signals in a two-dimensional plane and generate a super-resolution flow velocity graph of the microvessels.
Preferably, in the step S21, the singular value decomposition filtering is used to remove the image background signal in the singular value decomposition process, which may be represented as m=udv, where U and V are orthogonal matrices, and U is a spatial singular vector; v is a time vector corresponding to the space singular vector; d is a characteristic value matrix; the spatial singular vectors of the Nz rows Nx columns that are reordered to form may be regarded as a virtual picture taken from the data.
Preferably, the specific process of gaussian fitting in step S22 is that firstly, a calibrated ultrasound imaging Point Spread Function (PSF) is subjected to gaussian fitting to obtain a template gaussian kernel, and then normalized two-dimensional cross-correlation is performed on the template gaussian kernel and a contrast agent image sequence after noise treatment:
where f represents the processed contrast agent image,t represents the template gaussian kernel image, c represents the cross-correlation coefficient, x, y represents the two-dimensional spatial position, f (x, y) represents the pixel value at the (x, y) coordinate in the contrast agent image, u, v represent the amount of translation of the contrast agent template image in the contrast agent image along the x, y axes, respectively,representing an average value of pixels of the contrast agent image in the covered region as the template gaussian kernel image translates in the contrast agent image; after the correlation coefficient is obtained, a threshold value is set to remove a part with a lower correlation coefficient, then the coordinate of the local maximum value of the correlation coefficient is used as the center coordinate of the contrast agent, the positioning of the two-dimensional space contrast signal is realized, and finally the positioned points in each frame are accumulated to obtain an ultrasonic positioning microscope image.
Preferably, the vessel morphology parameters include vessel diameter to vessel spacing, vessel density ratio, and vessel tortuosity.
Preferably, the hemodynamic parameters include average speed, blood perfusion index value, perfusion ratio, and directional entropy.
Preferably, the statistical analysis process in step S3 includes: (1) All characteristic parameters evaluate the correlation analysis of the curative effect of the novel adjuvant chemotherapy, which specifically comprises the steps of checking the metering data by t-test and checking the counting data by chi-square to verify the difference of all the parameters between the effective group and the ineffective group of the chemotherapy; (2) Evaluating the effect of the ultrasonic positioning microscope on the effect evaluation of the novel auxiliary chemotherapy, which specifically comprises the steps of combining all parameters of significance for the chemotherapy, drawing an ROC curve of the ultrasonic positioning microscope, and calculating sensitivity, specificity, accuracy and AUC; (3) Analyzing the microvascular reconstruction law in the new auxiliary chemotherapy process, specifically comprising the dynamic change process of extracting microvascular parameters by an ultrasonic positioning microscope in different stages of characterization and summarizing the microvascular reconstruction law corresponding to different curative effects of the new auxiliary chemotherapy.
Compared with the prior art, the invention has the following beneficial effects:
the method evaluates the curative effect of the new auxiliary chemotherapy by detecting the micro-vascular reconstruction through an ultrasonic positioning microscope, focuses on the problem of the front hot spot of the evaluation of the curative effect of the new auxiliary chemotherapy of the breast cancer, monitors the dynamic change process of the micro-vascular reconstruction in the process of the new auxiliary chemotherapy of the triple negative breast cancer by utilizing the new technology of the ultrasonic positioning microscope, explores the new method and imaging indexes for early prediction of the curative effect of the new auxiliary chemotherapy of the triple negative breast cancer, provides a new method and thought for the accurate noninvasive evaluation of the curative effect of the new auxiliary chemotherapy in the early clinical stage, provides guidance for the promotion and degradation of the breast cancer treatment and the development of the new therapy, provides scientific basis for the clinical personalized adjustment of the treatment scheme, and has important value for improving the treatment and prognosis of patients. The application of the ultrasound in the field of evaluation of the curative effect of the breast cancer neoadjuvant chemotherapy is further expanded, and the ultrasound is hopefully popularized to the evaluation of the curative effect of various malignant tumors. Has wide clinical transformation prospect, meets the important requirements of health of people in China, and has good economic and social benefits.
Drawings
FIG. 1 is a schematic block diagram of a method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope in accordance with the present invention;
FIG. 2 is a technical roadmap of a method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope in accordance with the invention;
FIG. 3 is a super-resolution graph and a super-resolution flow rate graph before chemotherapy obtained by a method for assessing the efficacy of neoadjuvant chemotherapy of breast cancer with an ultrasound localization microscope according to the present invention.
Detailed Description
The drawings in the embodiments of the present invention will be combined; the technical scheme in the embodiment of the invention is clearly and completely described:
in one embodiment of the present invention, as shown in fig. 1 and 2, a method for evaluating the efficacy of neoadjuvant chemotherapy for breast cancer by using an ultrasound localization microscope comprises the steps of:
carrying out ultrasonic detection on the breast tumor part of the patient subjected to the new auxiliary chemotherapy by using a MindrayResonaR9T ultrasonic diagnostic instrument and an L20-5U linear array probe (bandwidth is 6-23 MHz), and fully exposing the breast when the patient is supine and the arm is lifted in the scanning process; the breast mass is scanned for transverse and longitudinal planes. After the two-dimensional mode clearly shows the tumor long diameter, and the section is kept, 0.5ml of targeted microbubbles are injected by a 19-gauge elbow vein indwelling needle through a bolus, 5ml of physiological saline wash pipe is immediately injected, and when the contrast agent starts filling the mammary gland, 1000 frames of ultrasonic contrast images of the tumor area are continuously acquired at a frame rate of 80Hz for ultrasonic positioning microscope data analysis; a Mechanical Index (MI) of 0.08 was used to avoid microbubble destruction during ultrasound contrast examination; other imaging parameters were set as follows: gain 10dB, dynamic range 100; converting the data beam into in-phase/quadrature (IQ) data through a commercial ultrasonic platform, and performing ultrasonic positioning microscopic microvascular imaging processing offline by using MATLAB (MathWorksInc., natick, MA, USA); due to motion during the scan, an established two-stage motion correction is applied to correct for tissue motion.
In the specific processing, image data in an ultrasonic diagnostic apparatus are exported in a DICOM format, singular value decomposition processing is carried out on each frame of image in each data set, and a time-space domain singular value decomposition filtering is adopted to remove image background signals during processing, wherein M=UDV is expressed, U and V are orthogonal matrixes, and U is a space singular vector; v is a time vector corresponding to the space singular vector; d is a characteristic value matrix; the spatial singular vectors of the Nz rows Nx columns formed by the reordering can be regarded as a virtual picture obtained from the data; then, the tissue background signal and the image noise signal are processed by selecting different singular value thresholds; performing super-localization processing on each ultrasonic image, in order to locate the coordinates of a single contrast signal, firstly performing Gaussian fitting on a calibrated ultrasonic imaging Point Spread Function (PSF) to obtain a template Gaussian kernel, and then performing normalized two-dimensional cross-correlation on the template Gaussian kernel and a processed contrast agent image sequence:
wherein f represents the processed contrast agent image, t represents the template gaussian kernel image, c represents the cross-correlation coefficient, x, y represents the two-dimensional spatial position, and f (x, y) represents the (x, y) coordinates in the contrast agent imagePixel values, u, v, represent the amount of translation of the contrast agent template image in the contrast agent image along the x, y axes, respectively,representing an average value of pixels of the contrast agent image in the covered region as the template gaussian kernel image translates in the contrast agent image; after the correlation coefficient is obtained, setting a threshold value to remove a part with a lower correlation coefficient, taking the coordinate of the local maximum value of the correlation coefficient as the center coordinate of the contrast agent to realize the positioning of the two-dimensional space contrast signal, and finally accumulating the positioned points in each frame to obtain an ultrasonic positioning microscope image; after obtaining the ultrasound localization microscope image, each observed Point Spread Function (PSF) is compared to a calibration PSF based on its area (a), intensity (I) and shape/eccentricity (E). These parameters are used to discard potential non-microbubble signals and noise; all observed PSFs with the corresponding three attributes are summarized into three matrices; all values in each matrix are normalized. The position of the separated signals is calculated by a "centroid" method; the centroid of each local signal is calculated by calculating the intensity weighted centroid, and all the locations from all the images are assembled into the final super-resolution map.
In order to calculate the flow velocity of the super-resolution microvessels, tracking microvesicle signals between adjacent frames, matching the nearest contrast signals between the adjacent frames by using a Kuhn-Munkres algorithm, taking the distance between each microvesicle between the adjacent frames as a weight, matching the adjacent microvesicles between the adjacent frames based on the idea of bipartite graph to minimize the total weight, and finally removing the matching of overlarge distance and zero distance by setting a threshold value to realize the tracking of the contrast signals in a two-dimensional plane and generate a super-resolution flow velocity graph of the microvessels.
As shown in fig. 3, the ultrasonic contrast image a is processed by the method to obtain a super-resolution map B and a super-resolution flow velocity map C, and in order to further improve the accuracy of calculation, an image a (an internal image of a square frame in fig. 3A) of a key part can be cut out from the ultrasonic contrast image a, and the super-resolution map B and the super-resolution flow velocity map C are processed by the method; for calculating a vascular morphology parameter and a hemodynamic parameter;
the specific calculation is as follows:
1. vascular morphology parameter extraction and analysis
Vessel diameter and vessel spacing were obtained by calculating Full Width Half Maximum (FWHM) values by gaussian fitting, defined as follows:
wherein sigma is the standard deviation.
The Vascular Density (VD) reflects the amount of vascular distribution in a given region, defined as follows:
where Vesselpixels is the vascular pixel and over allpixels is the total pixel.
The vessel density ratio (VesselDensityRatio, VDR) is defined as the ratio of peripheral vessel density to central vessel density:
wherein, the peripheral vascular density is the peripheral vascular density, and the central vd is the central vascular density.
For the tortuosity of a blood vessel (VascularTortuosity, VT), the Distance Metric (DM) is defined as the ratio between the actual path length (AL) of the blood vessel and the straight line distance (SL) between two end points of the blood vessel:in general, the greater the DM value, the higher the tortuosity of the blood vessel.
2. Hemodynamic parameter extraction and analysis
The average velocity of blood flow (AverageVelocity) is typically calculated using histogram statistics, the blood flow perfusion index (PerfusionIndex, PI), and the PI value reflects pulsatile blood flow conditions, i.e. reflects the blood flow perfusion capacity. The greater the pulsatile blood flow, the more pulsatile components and the greater the PI value. Thus, it can be expressed as:
PI=V m *area
wherein V is m Mean blood flow velocity, area, is the area.
The perfusion ratio is the ratio of the perfusion index of the tumor margin to the perfusion index of the central microvasculature:
wherein, the peripheral PI is the peripheral micro-vascular perfusion index, and the central PI is the central micro-vascular perfusion index.
The directional entropy (DirectionEntropy) is defined as follows:
when the information entropy characteristics judge the activity of the microvessels, the higher the entropy value is, the higher the activity of the microvessels is.
And respectively calculating 1 and vessel morphology parameters through an ultrasonic super-resolution map and a flow velocity map of the micro-blood vessel: (1) vessel diameter and vessel spacing: realizing the evaluation of the distribution of blood vessels in breast tumor before and after chemotherapy. (2) Vascular density: reflecting the density of blood vessels in the tumor before and after chemotherapy. (3) Vascular density ratio: ratio of peripheral vessel density to central vessel density. (4) Vascular tortuosity: reflecting the form of blood vessel growth inside the tumor. 2. Hemodynamic parameters: (1) average speed: reflecting the change in blood flow velocity in the tumor before and after chemotherapy. (2) Blood perfusion index value: reflecting the blood perfusion capacity, and judging the change of blood flow richness in the tumor. (3) Perfusion ratio: reflecting the change of the perfusion capacity of tumor margin and central microvascular before and after chemotherapy. (4) Directional entropy: reflects the activity of the micro-blood vessels and judges the curative effect of chemotherapy.
According to the parameters of the intratumoral microvessels extracted before, during and after chemotherapy, taking pathological results as gold standards, and carrying out statistical analysis; the method comprises (1) evaluating correlation analysis of the curative effect of the neoadjuvant chemotherapy by all characteristic parameters, wherein the method specifically comprises the steps of checking the metering data by t-test and checking the counting data by chi-square to verify the difference of all the parameters between the effective group and the ineffective group of the chemotherapy; (2) Evaluating the effect of the ultrasonic positioning microscope on the effect evaluation of the novel auxiliary chemotherapy, which specifically comprises the steps of combining all parameters of significance for the chemotherapy, drawing an ROC curve of the ultrasonic positioning microscope, and calculating sensitivity, specificity, accuracy and AUC; (3) Analyzing the microvascular reconstruction law in the process of the new auxiliary chemotherapy, which comprises the steps of representing the dynamic change process of the microvascular parameter extracted by an ultrasonic positioning microscope in different treatment stages, summarizing the microvascular reconstruction law corresponding to different treatment effects of the new auxiliary chemotherapy;
the analysis and statistics process is used to explore new methods and new standards for non-invasively evaluating the curative effect of the breast cancer new adjuvant chemotherapy in early stage.
The foregoing description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to apply equivalents and modifications according to the technical scheme and the modified concept of the present invention within the scope of the present invention.
Claims (10)
1. A method for evaluating the curative effect of breast cancer neoadjuvant chemotherapy by using an ultrasonic positioning microscope is characterized in that: the method comprises the following steps:
s1, collecting a low-dose ultrasonic contrast image; respectively carrying out low-dose ultrasonic radiography on breast tumor of a breast cancer patient before, during and after the new auxiliary chemotherapy and carrying out image acquisition;
s2, MATLAB image processing; performing ultrasonic positioning microscope micro-blood vessel imaging treatment offline by MATLAB to obtain an ultrasonic super-resolution map and a flow velocity map of the micro-blood vessel;
s3, calculating and analyzing; and finally, according to the parameters of the microvessels in tumors extracted before, during and after chemotherapy, taking a pathological result as a gold standard, carrying out statistical analysis, and exploring a novel method and a novel standard for early noninvasive evaluation of the curative effect of the breast cancer novel adjuvant chemotherapy.
2. The method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 1, wherein: the step 2 specifically includes: step S21, background and noise signal processing; s22, ultrasonic positioning treatment; step S23, tracking the microbubble signal.
3. A method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 2, wherein: step S21, background and noise signal processing; the image data in the ultrasonic diagnostic apparatus is exported in DICOM format, singular value decomposition processing is carried out on each frame of image in each data set, and then the tissue background signal and the image noise signal are processed by selecting different singular value thresholds.
4. A method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 2, wherein: s22, ultrasonic positioning treatment; firstly, obtaining an ultrasonic positioning microscope image through Gaussian fitting, and then comparing each observed Point Spread Function (PSF) with a calibration PSF according to the area (A), the intensity (I) and the shape/eccentricity (E) of the ultrasonic positioning microscope image; these parameters are used to discard potential non-microbubble signals and noise; all observed PSFs with the corresponding three attributes are summarized into three matrices; all values in each matrix are normalized; the position of the separated signals is calculated by a "centroid" method; the centroid of each local signal is calculated by calculating the intensity weighted centroid, and all the positions from all the images are assembled into the final super resolution image.
5. A method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 2, wherein: step S23, tracking the microbubble signals; pairing the contrast signals with the nearest adjacent two frames by using a Kuhn-Munkres algorithm, taking the distance between each microbubble of the adjacent two frames as a weight, pairing the microbubbles of the adjacent two frames based on the idea of bipartite graph to minimize the total weight, and finally removing the matching with the overlarge distance and the zero distance by setting a threshold value so as to realize the tracking of the contrast signals in a two-dimensional plane and generate a super-resolution flow velocity graph of the microvessels.
6. A method of assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 3, wherein: in the step S21, the singular value decomposition filtering of the time-space domain singular value decomposition is adopted to remove the image background signal, which can be represented as m=udv, where U and V are orthogonal matrices and U is a space singular vector; v is a time vector corresponding to the space singular vector; d is a characteristic value matrix; the spatial singular vectors of the Nz rows Nx columns that are reordered to form may be regarded as a virtual picture taken from the data.
7. The method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 4, wherein: the specific process of gaussian fitting in step S22 is that firstly, a calibrated ultrasound imaging Point Spread Function (PSF) is subjected to gaussian fitting to obtain a template gaussian kernel, and then normalized two-dimensional cross correlation is performed on the template gaussian kernel and a contrast agent image sequence after noise processing:
wherein f represents the processed contrast agent image, t represents the template gaussian kernel image, c represents the cross-correlation coefficient, x, y represents the two-dimensional spatial position, f (x, y) represents the pixel value at the (x, y) coordinate in the contrast agent image, u, v represents the amount of translation of the contrast agent template image in the contrast agent image along the x, y axes, respectively,representing an average value of pixels of the contrast agent image in the covered region as the template gaussian kernel image translates in the contrast agent image; after the correlation coefficient is obtained, a threshold value is set to remove a part with a lower correlation coefficient, then the coordinate of the local maximum value of the correlation coefficient is used as the center coordinate of the contrast agent, the positioning of the two-dimensional space contrast signal is realized, and finally the positioned points in each frame are accumulated to obtain an ultrasonic positioning microscope image.
8. The method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 1, wherein: the blood vessel morphological parameters comprise blood vessel diameter and blood vessel interval, blood vessel density ratio and blood vessel tortuosity.
9. The method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 1, wherein: the blood flow dynamic parameters comprise average speed, blood flow perfusion index value, perfusion ratio and directional entropy.
10. The method for assessing the efficacy of neoadjuvant chemotherapy for breast cancer using an ultrasound localization microscope according to claim 1, wherein: the statistical analysis process in the step S3 includes:
(1) All characteristic parameters evaluate the correlation analysis of the curative effect of the novel adjuvant chemotherapy, which specifically comprises the steps of checking the metering data by t-test and checking the counting data by chi-square to verify the difference of all the parameters between the effective group and the ineffective group of the chemotherapy;
(2) Evaluating the effect of the ultrasonic positioning microscope on the effect evaluation of the novel auxiliary chemotherapy, which specifically comprises the steps of combining all parameters of significance for the chemotherapy, drawing an ROC curve of the ultrasonic positioning microscope, and calculating sensitivity, specificity, accuracy and AUC;
(3) Analyzing the microvascular reconstruction law in the new auxiliary chemotherapy process, specifically comprising the dynamic change process of extracting microvascular parameters by an ultrasonic positioning microscope in different stages of characterization and summarizing the microvascular reconstruction law corresponding to different curative effects of the new auxiliary chemotherapy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310407175.3A CN116473592A (en) | 2023-04-17 | 2023-04-17 | Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310407175.3A CN116473592A (en) | 2023-04-17 | 2023-04-17 | Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116473592A true CN116473592A (en) | 2023-07-25 |
Family
ID=87214914
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310407175.3A Pending CN116473592A (en) | 2023-04-17 | 2023-04-17 | Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116473592A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116687353A (en) * | 2023-08-01 | 2023-09-05 | 宁波杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107361791A (en) * | 2017-07-21 | 2017-11-21 | 北京大学 | A kind of rapid super-resolution blood flow imaging method |
WO2018222724A1 (en) * | 2017-05-31 | 2018-12-06 | Mayo Foundation For Medical Education And Research | Methods for super-resolution ultrasound imaging of microvessels |
CN114146890A (en) * | 2021-12-03 | 2022-03-08 | 深圳先进技术研究院 | Ultrasonic sound control method and sound tweezers device |
CN114202512A (en) * | 2021-11-22 | 2022-03-18 | 复旦大学附属中山医院 | Ultrasonic contrast quantitative analysis method, system and computer readable storage medium for dynamic follow-up tumor local radiotherapy and chemotherapy effect |
CN114419016A (en) * | 2022-01-25 | 2022-04-29 | 华润武钢总医院 | Ultrasonic super-resolution method and system for differential diagnosis of benign and malignant thyroid nodules |
CN114403924A (en) * | 2022-01-19 | 2022-04-29 | 复旦大学附属中山医院 | Method for evaluating AIP hormone treatment curative effect based on ultrasonic contrast |
-
2023
- 2023-04-17 CN CN202310407175.3A patent/CN116473592A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018222724A1 (en) * | 2017-05-31 | 2018-12-06 | Mayo Foundation For Medical Education And Research | Methods for super-resolution ultrasound imaging of microvessels |
CN107361791A (en) * | 2017-07-21 | 2017-11-21 | 北京大学 | A kind of rapid super-resolution blood flow imaging method |
CN114202512A (en) * | 2021-11-22 | 2022-03-18 | 复旦大学附属中山医院 | Ultrasonic contrast quantitative analysis method, system and computer readable storage medium for dynamic follow-up tumor local radiotherapy and chemotherapy effect |
CN114146890A (en) * | 2021-12-03 | 2022-03-08 | 深圳先进技术研究院 | Ultrasonic sound control method and sound tweezers device |
CN114403924A (en) * | 2022-01-19 | 2022-04-29 | 复旦大学附属中山医院 | Method for evaluating AIP hormone treatment curative effect based on ultrasonic contrast |
CN114419016A (en) * | 2022-01-25 | 2022-04-29 | 华润武钢总医院 | Ultrasonic super-resolution method and system for differential diagnosis of benign and malignant thyroid nodules |
Non-Patent Citations (2)
Title |
---|
万财凤;王琳;刘雪松;方华;李凤华;: "超声造影评估乳腺癌新辅助化疗疗效的临床价值", 临床超声医学杂志, no. 10, 30 October 2017 (2017-10-30), pages 652 - 655 * |
隋怡晖;郭星奕;郁钧瑾;ALEXANDER A.SOLOVEV;他得安;许凯亮: "生成对抗网络加速超分辨率超声定位显微成像方法研究", 物理学报, vol. 71, no. 022, 31 December 2022 (2022-12-31), pages 224301 - 1 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116687353A (en) * | 2023-08-01 | 2023-09-05 | 宁波杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
CN116687353B (en) * | 2023-08-01 | 2023-12-19 | 宁波杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107230206B (en) | Multi-mode data-based 3D pulmonary nodule segmentation method for hyper-voxel sequence lung image | |
CN107361791B (en) | Rapid super-resolution blood flow imaging method | |
CN113781439B (en) | Ultrasonic video focus segmentation method and device | |
US11557072B2 (en) | Clustering algorithm-based multi-parameter cumulative calculation method for lower limb vascular calcification indexes | |
CN107451983A (en) | The three-dimensional fusion method and system of CT images | |
JP2003529421A (en) | Magnetic Resonance Angiography by Automating Vessel Segmentation | |
Caresio et al. | Quantitative analysis of thyroid tumors vascularity: A comparison between 3‐D contrast‐enhanced ultrasound and 3‐D Power Doppler on benign and malignant thyroid nodules | |
Kumar et al. | State-of-the-art review on automated lumen and adventitial border delineation and its measurements in carotid ultrasound | |
CN110288698B (en) | Meniscus three-dimensional reconstruction system based on MRI | |
CN116473592A (en) | Method for evaluating curative effect of breast cancer neoadjuvant chemotherapy by using ultrasonic positioning microscope | |
CN114419016A (en) | Ultrasonic super-resolution method and system for differential diagnosis of benign and malignant thyroid nodules | |
CN112348794A (en) | Ultrasonic breast tumor automatic segmentation method based on attention-enhanced U-shaped network | |
Su et al. | Ultrasound image assisted diagnosis of hydronephrosis based on CNN neural network | |
CN116091466A (en) | Image analysis method, computer device, and storage medium | |
Lei et al. | In vivo ultrasound localization microscopy imaging of the Kidney’s microvasculature with block-matching 3-D denoising | |
CN114209278A (en) | Deep learning skin disease diagnosis system based on optical coherence tomography | |
Kutbay et al. | A computer-aided diagnosis system for measuring carotid artery intima-media thickness (IMT) using quaternion vectors | |
CN116580033B (en) | Multi-mode medical image registration method based on image block similarity matching | |
CN114403924B (en) | Method for evaluating AIP hormone treatment effect based on ultrasonic radiography | |
Simmons et al. | Segmentation of neuroanatomy in magnetic resonance images | |
CN111062979B (en) | Visualization method and visualization system for acquiring physical characteristic parameters of thrombus based on medical image | |
Hu et al. | Diffusion-weighted imaging-magnetic resonance imaging information under class-structured deep convolutional neural network algorithm in the prognostic chemotherapy of osteosarcoma | |
CN107705308A (en) | Brain tumor image partition method based on multi-modal magnetic resonance | |
CN113689469A (en) | Method for automatically identifying ultrasonic contrast small liver cancer focus and ultrasonic system | |
Roy-Cardinal et al. | Homodyned K-distribution parametric maps combined with elastograms for carotid artery plaque assessment |
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 |