Disclosure of Invention
The embodiment of the specification provides a method and a system for extracting a target region based on brain image data, which are used for solving the following technical problems: the method can eliminate or reduce the participation of human factors, simplify the calculation process, shorten the time consumption and realize the simple and rapid evaluation of the core infarct area and/or the low perfusion area.
The embodiment of the present specification provides a method for extracting a target region based on brain image data, including the following steps:
acquiring craniocerebral perfusion image data to be processed, wherein the perfusion image data is one frame or multiple frames of craniocerebral perfusion image data;
inputting the craniocerebral perfusion image data to be processed into a segmentation model to obtain a segmentation result image of the craniocerebral perfusion image data to be processed;
analyzing the segmentation result image by a connected domain method to obtain a target region of the to-be-processed craniocerebral perfusion image data, wherein the target region comprises a core infarct area and/or a low perfusion area.
Preferably, the inputting the to-be-processed craniocerebral perfusion image data into a segmentation model to obtain a segmentation result image of the to-be-processed craniocerebral perfusion image data further includes: preprocessing the craniocerebral perfusion image data to be processed, wherein the preprocessing specifically comprises the following steps:
and performing image cropping and/or image scaling and/or pixel spacing adjustment and/or sequence time interval adjustment on the craniocerebral perfusion image data to be processed.
Preferably, the analyzing the segmentation result image by the connected domain method to obtain the target region of the to-be-processed craniocerebral perfusion image data further includes: and carrying out noise reduction processing on the segmentation result image.
Preferably, the craniocerebral perfusion image data to be processed is a matrix formed based on a craniocerebral perfusion image data sequence.
Preferably, the segmentation model is a model obtained in advance based on a neural network method, and specifically includes:
inputting the artificially marked craniocerebral perfusion image data into a neural network model, and training according to the characteristics of an artificially marked region of the craniocerebral perfusion image data to obtain a segmentation model, wherein the neural network model comprises a convolution neural network model, the artificially marked region comprises a background and/or a core infarct region and/or a low perfusion region, and the characteristics of the craniocerebral perfusion image data comprise the symmetrical structure of the left and right brains and/or the gray scale change of the left and right brains.
An embodiment of the present specification provides a system for extracting a target region based on brain image data, including:
the data preprocessing module is used for acquiring the craniocerebral perfusion image data to be processed, wherein the perfusion image data is one frame or multiple frames of craniocerebral perfusion image data;
the segmentation module is used for inputting the to-be-processed craniocerebral perfusion image data into a segmentation model to obtain a segmentation result image of the to-be-processed craniocerebral perfusion image data;
and the data post-processing module is used for analyzing the segmentation result image by a connected domain method to obtain a target area of the to-be-processed craniocerebral perfusion image data, wherein the target area comprises a core infarct area and/or a low perfusion area.
Preferably, the inputting the to-be-processed craniocerebral perfusion image data into a segmentation model to obtain a segmentation result image of the to-be-processed craniocerebral perfusion image data further includes: preprocessing the craniocerebral perfusion image data to be processed, wherein the preprocessing specifically comprises the following steps:
and performing image cropping and/or image scaling and/or pixel spacing adjustment and/or sequence time interval adjustment on the craniocerebral perfusion image data to be processed.
Preferably, the analyzing the segmentation result image by the connected domain method to obtain the target region of the to-be-processed craniocerebral perfusion image data further includes: and carrying out noise reduction processing on the segmentation result image.
Preferably, the craniocerebral perfusion image data to be processed is a matrix formed based on a craniocerebral perfusion image data sequence.
Preferably, the segmentation model is a model obtained in advance based on a neural network method, and specifically includes:
inputting the artificially marked craniocerebral perfusion image data into a neural network model, and training according to the characteristics of an artificially marked region of the craniocerebral perfusion image data to obtain a segmentation model, wherein the neural network model comprises a convolution neural network model, the artificially marked region comprises a background and/or a core infarct region and/or a low perfusion region, and the characteristics of the craniocerebral perfusion image data comprise the symmetrical structure of the left and right brains and/or the gray scale change of the left and right brains.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
in the embodiment of the description, the craniocerebral perfusion image data to be processed is input into a segmentation model, and a segmentation result image of the craniocerebral perfusion image data to be processed is obtained; and further analyzing the segmentation result image by a connected domain method to obtain a target region of the to-be-processed craniocerebral perfusion image data, wherein the target region comprises a core infarct area and/or a low perfusion area, automation can be realized, the target region is directly displayed on the craniocerebral perfusion image, the calculation flow is simplified, time consumption is shortened, and the evaluation of the core infarct area and/or the low perfusion area is simply and quickly realized.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
Perfusion imaging with CTP (CT perfusion) and MRP (MR perfusion) has become a routine means to examine cerebral blood perfusion in stroke patients. Brain perfusion imaging is performed by continuously and dynamically scanning a selected interest layer, obtaining a time density curve of each pixel of a selected layer, and obtaining the time density curve through mathematical model processing: the functional imaging method is used for evaluating the perfusion state of brain tissue and is a functional imaging method based on hemodynamic parameters such as Cerebral Blood Volume (CBV), Cerebral blood flow, Mean Transit Time (MTT), and time to peak, and perfusion image expression. In practical application, perfusion imaging is mainly used for evaluating a core infarct area and a low perfusion area to screen indications of vascular interventional therapy, so that how to quickly acquire the core infarct area and/or the low perfusion area of craniocerebral perfusion image data to be processed has important significance.
Fig. 1 is a schematic flowchart of a method for extracting a target region based on brain image data according to an embodiment of the present disclosure. The method specifically comprises the following steps:
step S101: acquiring craniocerebral perfusion image data to be processed, wherein the perfusion image data is one frame or a plurality of frames of craniocerebral perfusion image data.
In the embodiment of the present application, the craniocerebral perfusion image data to be processed includes, but is not limited to: CTP craniocerebral perfusion image data and MRP craniocerebral perfusion image data. The craniocerebral perfusion image data to be processed is one frame or a plurality of frames.
Step S103: inputting the craniocerebral perfusion image data to be processed into a segmentation model to obtain a segmentation result image of the craniocerebral perfusion image data to be processed.
Inputting the to-be-processed craniocerebral perfusion image data acquired in the step S101 into a segmentation model, analyzing the to-be-processed craniocerebral perfusion image data based on the segmentation model, and acquiring a segmentation result image of the to-be-processed craniocerebral perfusion image data, wherein the segmentation result image represents that each pixel point in the to-be-processed craniocerebral perfusion image data belongs to a background, a core infarct area or a low perfusion area. In one embodiment of the present application, after the craniocerebral perfusion image data to be processed is input into the segmentation model, the segmentation model outputs an image with the same size as the image of the craniocerebral perfusion image data to be processed. After each frame of craniocerebral perfusion image data to be processed is input into the segmentation model, a mask image corresponding to each frame of craniocerebral perfusion image data is output, and the number of the mask images is at least one. In one embodiment of the present application, a CTP brain perfusion image sequence, each sequence is 8 frames, each frame has a size of 512 × 512, and 2 mask images of 512 × 512 are output after being input into the segmentation model, wherein 0 in mask image 1 represents a background and 1 represents a core infarct area; in mask image 2, 0 represents background and 1 represents low perfusion.
In the embodiment of the present application, the segmentation model is a model obtained in advance based on a neural network method. Specifically, after a series of cerebral perfusion image data are labeled manually, the cerebral perfusion image data are input into a neural network model, training is carried out according to the characteristics of the manually labeled area of the cerebral perfusion image data, the mapping relation between the cerebral perfusion image data and the manually labeled area is obtained, and a segmentation model is obtained through training. In the embodiment of the present application, the human marker marks the craniocerebral perfusion image data according to the practical application, and the human marker area includes but is not limited to: a core infarct region and/or hypoperfusion region and/or background of the craniocerebral perfusion image data. Features of the artificially labeled regions of the craniocerebral perfusion image data include, but are not limited to: symmetric structure of the left and right brains and/or gray scale variation of the left and right brains. By using the segmentation model provided by the application, the craniocerebral perfusion image data to be processed is input into the segmentation model, and then the segmentation result of the craniocerebral perfusion image data is output. It should be particularly noted that the segmentation model in the present application may perform single-frame craniocerebral perfusion image data segmentation, and may also perform multi-frame craniocerebral perfusion image data segmentation at the same time to obtain a segmentation result image.
In one embodiment of the present application, the craniocerebral perfusion image data of the whole brain is labeled manually and then input into a neural network model for training to obtain a segmentation model. In practical applications, the segmentation model can be used to obtain a segmentation result image of the brain perfusion image data of the CTP or MRP.
In one embodiment of the application, a mask image of a DWI sequence of an MR is obtained after the DWI sequence has been artificially marked. And inputting the CTP sequence and the mask image of the registered DWI sequence into a neural network model for training to obtain a segmentation model. In practical applications, the segmentation model can be used to obtain a segmentation result image of the brain perfusion image data of the CTP or MRP.
In the embodiment of the application, the brain perfusion image data of the CTP or MRP is subjected to difference processing, so that the brain perfusion image data of the CTP or MRP keeps the same pixel pitch and the time interval between sequences keeps consistent. In one embodiment of the present specification, the pixel pitch of the CTP or MRP brain perfusion image data is adjusted to 250mm/512 and the time interval between sequences is adjusted to 1s by using difference processing. Then, labeling the background and the target area on the feature map of the brain perfusion image of the CTP or MRP processed by the difference value, specifically, labeling the core infarct area on the rCBV (Relative cerebral blood flow) map, and labeling the low perfusion area on the Tmax (peak-to-peak response time) map. The marked brain perfusion image data is input into a neural network model for learning, and the segmentation model obtained by training can output pixel points belonging to a background/core infarct area/low perfusion area in the brain perfusion image after the brain perfusion image data is input. It should be particularly noted that, when the neural network model performs the training of the segmentation model, the features learned by the neural network model include, but are not limited to: pixel points and adjacent pixel points and/or the symmetric structure of the left and right brains and/or the gray level change of the left and right brains.
In the embodiment of the present application, the neural network model includes, but is not limited to: a convolutional neural network model. It should be noted that the segmentation model is preferably an end-to-end trained neural network, and non-end-to-end trained neural networks are also considered in the same manner.
Step S105: analyzing the segmentation result image by a connected domain method to obtain a target region of the to-be-processed craniocerebral perfusion image data, wherein the target region comprises a core infarct area and/or a low perfusion area.
Due to the influence of factors such as image quality and equipment, isolated target region pixel points may exist in a segmentation result image, and such pixel points belong to noise interference, so that the noise needs to be removed to avoid the influence of the noise interference on the subsequent determination of the symmetry axis/symmetry plane.
In an embodiment of the present application, the segmentation result image of the to-be-processed craniocerebral perfusion image data is analyzed by a connected domain method, and the pixel points of the isolated target region are corrected to the pixel points belonging to the background, so as to determine the target region of the to-be-processed craniocerebral perfusion image data. In one embodiment of the present application, the target area includes, but is not limited to: the core infarct zone, the low perfusion zone.
By adopting the method provided by the embodiment of the specification, automation can be realized, the target area can be directly displayed on the craniocerebral perfusion image, the calculation process is simplified, the time consumption is shortened, and the evaluation of the core infarct area and/or the low perfusion area can be simply and quickly carried out.
The methods or concepts provided by the embodiments of the present application can also be applied to other perfusion images to determine a target region, such as cardiac perfusion images.
An embodiment of the present application further provides a better implementation manner, and fig. 2 is a schematic flow chart of a method for extracting a target region based on brain image data according to an embodiment of the present application. The method specifically comprises the following steps:
step S201: acquiring craniocerebral perfusion image data to be processed.
In the present application, the acquired craniocerebral perfusion image data to be processed can be conveniently read in a matrix form. For example, a matrix with CTP sequences read in [8,50,512 ] represents 50 sequences, each sequence is 8 frames, and each frame has a size of 512 × 512.
Step S203: and preprocessing the craniocerebral perfusion image data to be processed.
Due to differences in the types and types of the skull image imaging devices, differences may exist in the sizes, pixel pitches, and the like of the craniocerebral perfusion image data, and therefore preprocessing needs to be performed on the craniocerebral perfusion image data to be processed. In the embodiments of the present application, the pretreatment method includes, but is not limited to: image cropping and/or image scaling and/or pixel pitch adjustment and/or sequence time interval adjustment. The format, size, pixel spacing and time interval between sequences of the preprocessed craniocerebral perfusion image data are consistent with the image format, size, pixel spacing and time interval between sequences required by a segmentation model of the subsequent step.
Step S205: inputting the preprocessed craniocerebral perfusion image data into a segmentation model to obtain a segmentation result image of the preprocessed craniocerebral perfusion image data.
Step S207: and carrying out noise reduction processing on the segmentation result image.
Step S209: and analyzing the segmentation result image subjected to the noise reduction treatment by a connected domain method to obtain a target region of the to-be-treated craniocerebral perfusion image data.
In practical application, the method provided by the specification can further calculate the volume of the myocardial infarction and/or the volume of the low perfusion area based on the target area obtained by the extraction method. In an embodiment of the present disclosure, the method provided in the present disclosure is used to obtain a core infarct area and a hypoperfusion area in the craniocerebral perfusion image data, and then calculate a core infarct volume and/or a hypoperfusion area volume in each frame by taking a frame as a unit, where a sum of all the core infarct volumes is the core infarct volume in the whole brain, and a sum of all the hypoperfusion area volumes is the hypoperfusion area volume in the whole brain.
In another embodiment of the present disclosure, the method provided by the present disclosure is used to obtain the core infarct area and hypoperfusion zone in the craniocerebral perfusion image data, and further calculate the volume of the core infarct and/or the volume of the hypoperfusion zone in the whole brain.
Based on the same idea, an embodiment of the present specification further provides a system for extracting a target region based on brain image data, and fig. 3 is a schematic diagram of the system for extracting a target region based on brain image data, which is provided by the embodiment of the present specification, and the system includes:
the data preprocessing module 301 obtains craniocerebral perfusion image data to be processed, wherein the perfusion image data is one frame or multiple frames of craniocerebral perfusion image data;
the segmentation module 303 is configured to input the to-be-processed craniocerebral perfusion image data into a segmentation model, and obtain a segmentation result image of the to-be-processed craniocerebral perfusion image data;
the data post-processing module 305 analyzes the segmentation result image by a connected domain method to obtain a target region of the to-be-processed craniocerebral perfusion image data, wherein the target region includes a core infarct area and/or a low perfusion area.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and the relevant points can be referred to the partial description of the embodiments of the method.
The apparatus, the electronic device, the nonvolatile computer storage medium and the method provided in the embodiments of the present description correspond to each other, and therefore, the apparatus, the electronic device, and the nonvolatile computer storage medium also have similar advantageous technical effects to the corresponding method.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.