CN115937196A - Medical image analysis system, analysis method and computer-readable storage medium - Google Patents
Medical image analysis system, analysis method and computer-readable storage medium Download PDFInfo
- Publication number
- CN115937196A CN115937196A CN202310009071.7A CN202310009071A CN115937196A CN 115937196 A CN115937196 A CN 115937196A CN 202310009071 A CN202310009071 A CN 202310009071A CN 115937196 A CN115937196 A CN 115937196A
- Authority
- CN
- China
- Prior art keywords
- image data
- image
- scanning time
- value
- ctp
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a medical image analysis system, an analysis method and a computer-readable storage medium. The medical image analysis system comprises a data acquisition unit, a data acquisition unit and a data processing unit, wherein the data acquisition unit is configured to acquire CTP image data of the head of a patient; a preprocessing unit configured to register the CTP image data to obtain a registered image; an image positioning unit configured to determine CTA image data from the registered image, segment the CTA image data to obtain a first lesion region, and obtain a second lesion region on the registered image based on the first lesion region; and the analysis unit is configured to acquire a CT value of the second lesion area, and perform fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second lesion area.
Description
Technical Field
The present invention relates to the field of medical images, and more particularly, to a medical image analysis system, an analysis method, and a computer-readable storage medium.
Background
Acute ischemic stroke has the characteristics of high morbidity, high disability rate and high fatality rate. For a suspected acute ischemic stroke patient, the neurological deficit condition of the patient is usually clinically evaluated firstly to determine whether the patient belongs to light, medium or heavy stroke, and stroke clinicians with different degrees can adopt different types of treatment means such as intravenous thrombolysis or intravascular mechanical embolectomy treatment. In recent years, much attention has been paid to studies on imaging characteristics of thrombus represented in medical images, causes of acute stroke, prognostic effects of mechanical thrombus removal treatment of patients, and histological components.
Recent studies show that the higher the permeability of thrombus, the shorter the opening time of mechanical thrombus removal treatment in blood vessels, and the better the functional outcome, i.e. the better the prognosis effect of the treatment. The extracted thrombus imaging features of the prior research comprise the CT value (HU) of the thrombus on a CT flat scan, and the difference value (delta) between the mean value of the CT values of a thrombus region and the mean value of the CT values of a contralateral blood vessel region in arterial phase CT (computed tomography, CTA) Hu ) And Δ in multicycle CTA Hu Change over time. At present, no information characteristic for directly calculating the blood flow change in the thrombus along with the time based on the CT image exists. The existing measuring method of the thrombus imaging characteristics is a semi-automatic measuring mode, namely, a doctor needs to manually position the thrombus on a CT image of a traditional post-processing workstation and draw out the thrombus outline to calculate a corresponding value. The limitation of manual thrombus positioning and manual delineation of thrombus Region of interest (ROI) contour is that it requires manual layer-by-layer labeling of all CT image layers containing thrombus regions, which is time-consuming, especially for CT scan data with multiple scan times, the work is very heavy and complicated, and the capability of naked eye to distinguish thrombus regions and CT values on CT images is increased by ten timesThe limited number of points, the inconsistency caused by the cognitive difference between people, and thus the measurement with high precision is very challenging.
Disclosure of Invention
The invention provides a medical image analysis system, an analysis method and a computer readable storage medium, which can directly calculate the information characteristics of blood flow in thrombus along with time change based on CT images, provide more parameter information or characteristic information about the thrombus of a patient for a doctor, and provide help for the doctor to specify a treatment scheme.
In order to solve the above technical problem, an embodiment of the present invention provides a medical image analysis system, including: a data acquisition unit configured to acquire patient's head CTP image data; a preprocessing unit configured to register the CTP image data to obtain a registered image; an image positioning unit configured to obtain CTA image data from the registered image, segment the CTA image data to obtain a first lesion region, and obtain a second lesion region on the registered image based on the first lesion region; and the analysis unit is configured to acquire a CT value of the second lesion area, and perform fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second lesion area.
Optionally, the method further comprises: determining image data with a CT value larger than 150Hu on CTP image data, and determining a skull region based on a maximum communication algorithm; registering the image data of each scanning time of the CTP image data with the image data of the first scanning time based on a rigid registration method to obtain the registration image.
Optionally, the method further comprises: determining an artery point in the registered image according to the registered image; acquiring a first time density curve of the artery point in the CTP image data; screening the registered image data corresponding to the peak on the first time density curve as the CTA image.
Optionally, the method further comprises: acquiring a CT value of a second focus area, and averaging the CT values of the second focus area; and drawing a scatter diagram by taking the average value as a vertical coordinate and the CTP scanning time of the scanning time corresponding to the second lesion area as a horizontal coordinate.
Optionally, the method further comprises: and determining a fitting method of the scatter points on the scatter diagram according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time.
Optionally, the method further comprises: when the difference value between the peak point and the lowest point is more than 30Hu, and the ratio of the scanning time corresponding to the peak point to the whole scanning time is less than three-fourths, fitting the scatter diagram by adopting a Gaussian fitting algorithm; and when the difference value between the peak point and the lowest point is not more than 30Hu, or the ratio of the scanning time corresponding to the peak point to the whole scanning time is not less than three-fourths, fitting the scatter diagram by adopting a linear fitting algorithm.
Optionally, the method further comprises: and the prognosis estimation unit is configured to automatically estimate the recovery degree of the patient after the patient receives mechanical embolectomy treatment according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects: the full-automatic extraction system of the cerebral thrombosis attenuation time density curve is provided, the problems of time consumption, inconsistency of manual measurement difference, relatively rough precision and the like in the existing semi-automatic measurement method are solved, and an effective tool is provided for risk analysis of medical scientific research workers and patients with cerebrovascular diseases.
Drawings
Fig. 1 is a schematic structural diagram of a medical image analysis system provided by an embodiment of the invention;
FIG. 2 is a flow chart of a medical image analysis method provided by an embodiment of the invention;
FIG. 3 is a diagram of one embodiment of a medical image analysis method according to the present invention;
fig. 4 is a computer device according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that for a person skilled in the art, the present application can also be applied to other similar scenarios according to these drawings without inventive effort. Unless otherwise apparent from the context of language or otherwise indicated, like reference numerals refer to like structures or operations throughout.
It should be understood that as used herein, the terms "device," "unit," "system" and "system" are intended to refer to a method for distinguishing between different components, elements, components, parts or assemblies, but may be replaced by other terms, if the other terms are to achieve the same purpose.
As used in this application and the appended claims, the terms "a," "an," and "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that a specifically identified step or element is included, that the step or element does not constitute an exclusive list, and that a method or apparatus may include other steps or elements.
Flowcharts are used herein to illustrate the operations performed by the system of embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in the reverse order or simultaneously. Meanwhile, other operations may be added to these processes, or one or more operations may be removed from these processes.
Example one
Fig. 1 schematically shows a structural schematic diagram of the medical image analysis system provided in this embodiment. As can be seen from fig. 1, the medical image analysis system provided by the present embodiment includes: a data acquisition unit 101, a preprocessing unit 102, an image positioning unit 103, an analysis unit 104 and a prognosis estimation unit 105.
Specifically, the data acquisition unit is configured to acquire head CTP image data of a patient, specifically, the CTP perfusion scan operation of the patient is to inject contrast agent into the vein of the patient to be checked, and the selected layer is scanned through a plurality of layers continuously to obtain a time density curve of each pixel of the layer, wherein the time density curve reflects the concentration change of the contrast agent in the organ, so that the change of the organ perfusion volume is reflected. The organ of interest in this embodiment is the head of a patient, and CTP perfusion scanning is performed on the head of the patient, that is, a selected layer of the head is continuously scanned at each scanning time point, so that the change of the perfusion volume of the selected layer of the head at a plurality of different scanning times can be obtained, wherein the number of layers is related to the number of rows of detectors of the CT scanning apparatus, and the selected layer is one of all the layers.
The preprocessing unit is configured to register the CTP image data to obtain a registered image, and specifically, before the CTP image is registered, the CTP data may be sorted according to parameters such as scanning time and brain level position to obtain sorted multi-stage image data. The preprocessing unit is further configured to perform image registration operation, specifically, to process CTP image data at any scanning time, preferably, the image data at any scanning time may select image data with a clearer skull in an image at a first scanning time or all image data, the selected image is used as reference image data, a CT value of the reference CTP image data is determined, pixel points with CT values larger than 150Hu in the image data are screened out, CT value data with CT values larger than 150Hu in the CTP image data at each scanning time is processed based on a maximum link algorithm, a skull region corresponding to the reference image data is obtained, and a rigidity change matrix of each acquisition period during CT perfusion scanning is estimated by using the skull region. Therefore, the CTP image data of each scanning time is registered by using a rigid registration method, specifically, a rigid change matrix is used for registering the CTP image data of each scanning time, and a whole brain image of each scanning time after registration is obtained as a registration image. Optionally, in order to quantitatively measure the registration performance, information is normalized and mutually between skull region in the reference image and image data of other stages, quantitative evaluation of the registration result is performed, and according to the evaluation result, selection of a threshold of a CT value is optimized, the threshold of the CT value in the present application is 150Hu, it is understood that the above-mentioned CT threshold is only one preferred data provided by the present scheme, and according to the registration result or clinical experience of a clinician, the threshold of the above-mentioned CT value can be optimized to obtain the registration result meeting the quantitative evaluation index of the registration result.
Meanwhile, the process of extracting the skull region can remove all non-skull regions including brain tissues and surrounding metal artifacts and/or motion artifacts, so that the registration result of the CTP image is more accurate.
An image localization unit configured to determine CTA image data from the registered image, segment the CTA image data to obtain a first lesion region, and obtain a second lesion region on the registered image based on the first lesion region. Specifically, the specific step of determining CTA image data from CTP image data comprises: determining an artery point in a registration image, and providing an artery point extraction method based on CTP image data, which comprises the following steps: acquiring a blood vessel region image; screening out a vein region by utilizing a 1/4 region below a brain region; extracting the brightest point in the vein area as a vein point, and calculating a vein curve; setting a scanning time threshold according to the vein phase, and screening out an artery candidate region according to the scanning time threshold; carrying out space position constraint of registration on the artery candidate region to obtain an artery region; and extracting the brightest point in the artery area as an artery point, and calculating an artery curve. The method realizes the high-automatic and high-accuracy extraction of the artery in the CTP image. . Acquiring a first time density curve of the artery point in the CTP image data, and screening the registration image data corresponding to a peak value on the first time density curve as CTA image data. And (3) carrying out automatic positioning and segmentation of a focus area based on CTA image data to obtain a first focus area, wherein the first focus area is a thrombus area. The segmentation algorithm can be based on a 3D Res-Unet deep learning model, and more accurate and complete thrombus 3D volume can be obtained by using the deep learning model. After obtaining the thrombus segmentation area on the CTA image data, applying a segmentation area mask of the thrombus on the registered CTP image data so as to obtain a mask of the thrombus at all scanning times, and taking the mask at all scanning times as a second lesion area.
And the analysis unit is configured to acquire a CT value of the second lesion area, and perform fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second lesion area. Specifically, the CT value of the second lesion region at each scanning time may be obtained, and the CT value of the second lesion region is averaged; and drawing a scatter diagram by taking the average value as a vertical coordinate and the scanning time of the CTP image data corresponding to the second focus area as a horizontal coordinate.
And determining a fitting method of the scatter points on the scatter diagram according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time, so as to draw a time density curve, obtain image characteristics capable of representing thrombus blood flow information and display the image characteristics to a user. Specifically, the highest point of the CT value of the scatter diagram is regarded as a peak point, it can be understood that the peak point is a maximum average point, the lowest point is a minimum average point, the scanning time corresponding to the peak point is denoted as Tmax, if Tmax occurs three fourths of the total scanning duration and the difference between the CT value of the peak point and the CT value of the lowest point is greater than 30Hu, a gaussian fitting algorithm is used to implement curve fitting, the obtained time density curve is called uTAC, when the CT difference between the CT value of the peak point and the CT value of the lowest point is not greater than 30Hu, or Tmax occurs three fourths of the total scanning duration, a linear fitting algorithm is used to fit the scatter diagram, a linear fitting algorithm is used to implement curve fitting, and the obtained time density curve is called lTAC.
Specific reference may be made to fig. 3 for a specific embodiment of the method for analyzing medical images provided by the present invention. The ordinate is the average value of the CT value of the second focus area, and the ordinate is marked as attention; acquiring a CT value of a peak point on a discrete graph, namely a CT value of a peak point, namely a value of a vertical coordinate corresponding to a point a and a 'in fig. 3, and a CT value of a lowest point, namely a value of a vertical coordinate corresponding to a point b and a' in fig. 3, and a scanning time on a corresponding horizontal coordinate according to an analysis method provided by an analysis unit; the proportion in which Tmax occurs at the total scan duration may be determined by or based on the abscissa corresponding to the points a ', b ' and c '. And respectively determining the fitting mode of the scatter points according to the calculated results.
The time density curve of the corresponding thrombus position is obtained by the fitting curve obtained by different fitting modes in fig. 3. The speed of the contrast agent in the thrombus in the uTAC flowing through the thrombus is slower than the state shown in an ITAC curve, which indicates that the permeability of the thrombus is lower and worse, and through clinical empirical analysis and medical technical knowledge, the higher the permeability of the thrombus is, the better the permeability is, the shorter the mechanical embolectomy surgical treatment time is, the shorter the thrombus opening time is, and the corresponding patient prognosis effect is better.
The medical image analysis system provided in fig. 1 may further include a prognosis estimation unit configured to automatically estimate, according to the peak point and the lowest point on the scatter diagram and the ratio of the scanning time corresponding to the peak point to the whole scanning time, the degree of recovery of the patient after receiving the mechanical embolectomy treatment, which may be specifically estimated by the determination conditions: the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time can represent the component characteristics or the tissue characteristics of the thrombus. If the interpolation value of the peak point and the lowest point is more than 30Hu, and the ratio of the scanning time corresponding to the peak point to the whole scanning time is less than three quarters, the permeability of the thrombus is low, otherwise, the permeability of the thrombus is high. The permeability of the thrombus is high, more components of the thrombus are thrombus rich in fiber components, and the probability that the thrombus is derived from cardiogenic sources is higher; the permeability of the thrombus is low, and the more the composition of the thrombus is red blood cell-rich thrombus, the softer the plug mass. The lower the permeability of the thrombus, the easier the thrombus remover passes through the thrombus block, the shorter the mechanical thrombus removal surgery treatment time is, the shorter the thrombus opening time is, and the corresponding patient prognosis effect is better. Specifically, the approximation degree can represent the approximation degree of the difference value between the peak point and the lowest point on the scatter diagram and 30Hu and the approximation degree of the scanning time corresponding to the peak point on the scatter diagram and three quarters of the scanning time, and different scores can be scored according to the approximation degree, so that the prognosis score can be obtained. And making more accurate postoperative prognosis judgment according to the prognosis scoring result.
The prognosis judgment unit and the judgment condition for thrombus characteristics in the analysis unit can be preset according to experience values of clinicians, preferably artificial intelligence model training is carried out based on patient information in existing big data medical records, the range or value of interpolation of the maximum average value and the minimum average value is simulated and trained, meanwhile, the proportional relation between the scanning time corresponding to the maximum average value and the whole scanning time is simulated and trained, and the optimal curve fitting judgment condition can be determined based on optimal output.
Fig. 2 is a schematic flow chart of a medical image analysis method according to an embodiment of the present invention.
Specifically, the method comprises the steps of acquiring head CTP image data of a patient, specifically, carrying out CTP perfusion scanning on the patient, i.e. carrying out intravenous injection on a contrast agent in the patient to be checked, and carrying out continuous multiple times of same-layer scanning on a selected layer to obtain a time density curve of each pixel of the layer, wherein the time density curve reflects the concentration change of the contrast agent in the organ, so that the change of the organ perfusion volume is reflected. The organ of interest in this embodiment is the head of a patient, and CTP perfusion scanning is performed on the head of the patient, that is, a selected layer of the head is continuously scanned at each scanning time point, so that the change of the perfusion volume of the selected layer of the head at a plurality of different scanning times can be obtained, wherein the number of the layers is related to the number of rows of detectors of the CT scanning device, and the selected layer is one of all the layers.
And (3) registering the CTP image data to obtain a registered image, specifically, before registering the CTP image, sequencing the CTP data according to parameters such as scanning time, brain layer position and the like to obtain sequenced multi-stage image data. The preprocessing unit is further configured to perform an image registration operation, specifically, process CTP image data at any scanning time, and preferably, the image data at any scanning time may select image data with clear skull in an image at a first scanning time or all image data, the selected image is used as reference image data, determine a CT value of the reference CTP image data, screen out pixel points with CT values greater than 150Hu in the image data, and process CT value data with CT values greater than 150Hu in the CTP image data at each scanning time based on a maximum communication algorithm to obtain a skull region corresponding to the reference image data, and estimate a rigidity change matrix of each acquisition period during CT perfusion scanning with the skull region. Therefore, the CTP image data of each scanning time is registered by using a rigid registration method, specifically, the CTP image data of each scanning time is registered by using a rigid change matrix, and a registered whole brain image is obtained as a registration image. Optionally, in order to quantitatively measure the registration performance, standardized reciprocal information is used between the skull region in the reference image and the image data of other stages to perform quantitative evaluation on the registration result, and the threshold of the CT value is optimized according to the evaluation result, where the threshold of the CT value is 150Hu in the present application, and it is understood that the CT threshold is only one preferred data provided by the present scheme, and the threshold of the CT value may be optimized according to the registration result or the clinical experience of a clinician to obtain the registration result meeting the quantitative evaluation index of the registration result.
Meanwhile, the process of extracting the skull region can remove all non-skull regions including brain tissues and surrounding metal artifacts and/or motion artifacts, so that the registration result of the CTP image is more accurate.
CTA image data is determined according to the registration image, the CTA image data is segmented to obtain a first lesion area, and a second lesion area on the registration image is obtained based on the first lesion area. Specifically, the specific step of determining CTA image data from CTP image data comprises: determining an artery point in a registration image, and providing an artery point extraction method based on CTP image data, which comprises the following steps: acquiring a blood vessel region image; screening out a vein region by utilizing a 1/4 region below a brain region; extracting the brightest point in the vein area as a vein point, and calculating a vein curve; setting a scanning time threshold according to the vein phase, and screening out an artery candidate region according to the scanning time threshold; carrying out space position constraint of registration on the artery candidate region to obtain an artery region; and extracting the brightest point in the artery area as an artery point, and calculating an artery curve. The method realizes the high-automatic and high-accuracy extraction of the artery in the CTP image. . Acquiring a first time density curve of the artery point in the CTP image data, and screening the registration image data corresponding to a peak value on the first time density curve as CTA image data. And (3) carrying out automatic positioning and segmentation of a focus area based on CTA image data to obtain a first focus area, wherein the first focus area is a thrombus area. The segmentation algorithm can be based on a 3D Res-Unet deep learning model, and more accurate and complete thrombus 3D volume can be obtained by using the deep learning model. After obtaining the thrombus segmentation area on the CTA image data, applying a segmentation area mask of the thrombus on the registered CTP image data so as to obtain a mask of the thrombus at all scanning times, and taking the mask at all scanning times as a second lesion area.
And acquiring a CT value of the second focus region, and fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second focus region. Specifically, the CT value of the second lesion area at each scanning time may be obtained, and the CT value of the second lesion area is averaged; and drawing a scatter diagram by taking the average value as a vertical coordinate and the scanning time of CTP image data corresponding to the second lesion area as a horizontal coordinate.
And determining a fitting method of the scatter points on the scatter diagram according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time, so as to draw a time density curve, obtain image characteristics capable of representing thrombus blood flow information and display the image characteristics to a user. Specifically, the highest point of the CT value of the scatter diagram is regarded as a peak point, it can be understood that the peak point is a maximum average point, the lowest point is a minimum average point, the scanning time corresponding to the peak point is denoted as Tmax, if Tmax occurs in the first three quarters of the total scanning time and the difference between the CT value of the peak point and the CT value of the lowest point is greater than 30Hu, curve fitting is achieved by adopting a gaussian fitting algorithm, the obtained time density curve is called uTAC, and when the difference between the CT value of the peak point and the CT value of the lowest point is not greater than 30Hu or Tmax occurs in the last three quarters of the total scanning time, the scatter diagram is fitted by adopting a linear fitting algorithm, curve fitting is achieved by adopting the linear fitting algorithm, and the obtained time density curve is called lTAC.
According to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time, the recovery degree of the patient after the patient receives the mechanical embolectomy treatment is automatically scored, and the specific evaluation conditions can be as follows: the proportion of the peak point and the lowest point on the scatter diagram and the scanning time corresponding to the peak point in the whole scanning time can represent the component characteristics or the tissue characteristics of the thrombus. If the interpolation value of the peak point and the lowest point is more than 30Hu, and the proportion of the scanning time corresponding to the peak point to the whole scanning time is less than three quarters, the permeability of the thrombus is low, otherwise, the permeability of the thrombus is high. The permeability of the thrombus is high, so that the thrombus is more red blood cell-rich thrombus; the permeability of the thrombus is low, and the thrombus is more fibrous-rich in the components of the thrombus. The higher the permeability of the thrombus, the better the mechanical thrombus removal surgery treatment time is, the shorter the thrombus opening time is, and the better the corresponding patient prognosis effect is. Specifically, the approximation degree can represent the approximation degree of the difference value between the peak point and the lowest point on the scatter diagram and 30Hu and the approximation degree of the scanning time corresponding to the peak point on the scatter diagram and three quarters of the scanning time, and different scores can be scored according to the approximation degree, so that the prognosis score can be obtained. And making more accurate postoperative prognosis judgment according to the prognosis scoring result.
The determination conditions for the prognosis determination unit and for the thrombus characteristics in the analysis unit may be preset according to experience values of clinicians, preferably, artificial intelligence model training is performed based on patient information in existing big data medical records, a range or a value of interpolation between a maximum average value and a minimum average value is simulated and trained, meanwhile, a proportional relationship between scanning time corresponding to the maximum average value and the whole scanning time is simulated and trained, and an optimal curve fitting determination condition may be determined based on optimal output.
Fig. 4 is a computer device according to an embodiment of the present invention.
Specifically, the computer device further includes a communication interface 402 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 complete communication with each other through the communication bus 404. The communication bus 404 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 404 may be divided into an address bus, a data bus, a control bus, and the like. The communication interface 402 is used for communication between the above-mentioned computer and other devices.
The Processor 401 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 401 is the control center of the computer device and connects the various parts of the whole computer device by various interfaces and lines.
The memory 403 may be used for storing the computer program, and the processor 401 may implement various functions of the electronic device by running or executing the computer program stored in the memory 403 and calling data stored in the memory 403.
The memory 403 may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The invention also provides a readable storage medium having stored therein a computer program which, when executed by a processor, may implement the medical image analysis method described above. Since the readable storage medium provided by the present invention and the medical image analysis method described above belong to the same inventive concept, they have all the advantages of the medical image analysis method described above, and thus the detailed description thereof is omitted.
The readable storage media of embodiments of the invention may take any combination of one or more computer-readable media. The readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this context, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
While the present invention is described above, it is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A medical image analysis system, comprising:
a data acquisition unit configured to acquire patient's head CTP image data;
a preprocessing unit configured to register the CTP image data to obtain a registered image;
an image positioning unit configured to obtain CTA image data from the registration image, for the CTA
Segmenting image data to obtain a first focus area, and obtaining a second focus area on the registration image based on the first focus area;
and the analysis unit is configured to acquire a CT value of the second lesion area, and perform fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second lesion area.
2. The medical image analysis system according to claim 1, wherein the preprocessing unit is configured to:
determining image data with a CT value larger than 150Hu on CTP image data, and determining a skull region based on a maximum communication algorithm;
registering the image data of each scanning time of the CTP image data with the image data of the first scanning time based on a rigid registration method to obtain the registration image.
3. The medical image analysis system according to claim 1, wherein the image localization unit is configured to:
determining an artery point in the registered image according to the registered image;
acquiring a first time density curve of the artery point in the CTP image data;
screening the registered image data corresponding to the peak on the first time density curve as the CTA image data.
4. The medical image analysis system according to claim 1, wherein the analysis unit is configured to:
acquiring a CT value of the second focus area, and averaging the CT values of the second focus area; and drawing a scatter diagram by taking the average value as a vertical coordinate and the scanning time of the CTP image data corresponding to the second focus area as a horizontal coordinate.
5. The medical image analysis system according to claim 4, further comprising: and determining a fitting method of the scatter points on the scatter diagram according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time.
6. The medical image analysis system according to claim 5, wherein:
when the difference value between the peak point and the lowest point is more than 30Hu, and the ratio of the scanning time corresponding to the peak point to the whole scanning time is less than three-fourths, fitting the scatter diagram by adopting a Gaussian fitting algorithm; and when the difference value between the peak point and the lowest point is not more than 30Hu, or the ratio of the scanning time corresponding to the peak point to the whole scanning time is not less than three-fourths, fitting the scatter diagram by adopting a linear fitting algorithm.
7. The medical image analysis system according to claim 5, further comprising:
and the prognosis estimation unit is configured to automatically estimate the recovery degree of the patient after the patient receives mechanical embolectomy treatment according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time.
8. A method of medical image analysis, comprising:
CTP image data of the head of a patient is acquired;
registering the CTP image data to obtain a registered image;
determining CTA image data according to the registration image, segmenting the CTA image data to obtain a first lesion area, and obtaining a second lesion area on the registration image based on the first lesion area;
and acquiring a CT value of the second lesion area, and fitting according to the CT value and the scanning time of the corresponding registration image to obtain a time density curve of the second lesion area.
9. The medical image analysis method according to claim 8, further comprising:
acquiring a CT value of the second focus area, and averaging the CT values of the second focus area; taking the average value as a vertical coordinate, taking the scanning time of the CTP image data of the scanning time corresponding to the second lesion area as a horizontal coordinate, and drawing a scatter diagram;
and determining a fitting method of the scatter points on the scatter diagram according to the peak point and the lowest point on the scatter diagram and the proportion of the scanning time corresponding to the peak point in the whole scanning time.
10. A computer-readable storage medium storing a computer program, comprising:
the computer program, when executed by a processor, implements the method of any one of claims 8-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310009071.7A CN115937196A (en) | 2023-01-04 | 2023-01-04 | Medical image analysis system, analysis method and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310009071.7A CN115937196A (en) | 2023-01-04 | 2023-01-04 | Medical image analysis system, analysis method and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115937196A true CN115937196A (en) | 2023-04-07 |
Family
ID=86654314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310009071.7A Pending CN115937196A (en) | 2023-01-04 | 2023-01-04 | Medical image analysis system, analysis method and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937196A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116649993A (en) * | 2023-04-21 | 2023-08-29 | 北京绪水互联科技有限公司 | Multi-period scanning image quality control method and device, electronic equipment and storage medium |
-
2023
- 2023-01-04 CN CN202310009071.7A patent/CN115937196A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116649993A (en) * | 2023-04-21 | 2023-08-29 | 北京绪水互联科技有限公司 | Multi-period scanning image quality control method and device, electronic equipment and storage medium |
| CN116649993B (en) * | 2023-04-21 | 2024-05-14 | 北京绪水互联科技有限公司 | Multi-period scanning image quality control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9036878B2 (en) | Method for delineation of tissue lesions | |
| CN109410221B (en) | Cerebral perfusion image segmentation method, device, server and storage medium | |
| CN107280696B (en) | Method and camera for determining collateral information describing blood flow in collateral branch | |
| CA3095408C (en) | Systems and methods for automated detection and segmentation of vertebral centrum(s) in 3d images | |
| Deshpande et al. | Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature | |
| JP2008022928A (en) | Image analysis apparatus and image analysis program | |
| RU2752690C2 (en) | Detecting changes in medical imaging | |
| WO2004026140A2 (en) | Display of image data information | |
| CN102419864B (en) | Method and device for extracting skeletons of brain CT (computerized tomography) image | |
| KR20200075152A (en) | Method and device for automatic vessel extraction of fundus photography using registration of fluorescein angiography | |
| CN114419181A (en) | CTA image reconstruction method and device, display method and device | |
| CN115937196A (en) | Medical image analysis system, analysis method and computer-readable storage medium | |
| KR20200093502A (en) | Method and device for automatic vessel extraction of fundus photography using registration of fluorescein angiography | |
| CN110060261B (en) | Blood vessel segmentation method based on optical coherence tomography system | |
| Sukanya et al. | Region based coronary artery segmentation using modified Frangi's vesselness measure | |
| KR102517529B1 (en) | Method and apparatus for predicting amyloid PET positivity in patient with suspected cerebral amyloid angiopathy marker | |
| KR100332072B1 (en) | An image processing method for a liver and a spleen from tomographical image | |
| CN116491968A (en) | Acute ischemic stroke collateral circulation assessment method based on single-phase CTA | |
| CN111971751A (en) | System and method for evaluating dynamic data | |
| CN113706541B (en) | Image processing method and device | |
| CN113724264B (en) | Image segmentation method, system and readable storage medium | |
| CN114119688A (en) | Single-mode medical image registration method before and after coronary angiography based on deep learning | |
| Napier et al. | A CAD system for brain haemorrhage detection in head CT scans | |
| RU2815435C2 (en) | Method of contouring abnormal zones on results of percussion tomographic scanning | |
| CN117036372B (en) | Robust laser speckle image blood vessel segmentation system and segmentation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |