Multi-volume sequence image data processing method, computer equipment and readable storage medium

Abstract

The invention provides a multi-volume sequence image data processing method, computer equipment and a readable storage medium, and the method comprises the steps: firstly, obtaining to-be-processed multi-volume sequence image data, the multi-volume sequence image data comprising a first number of medical image data; secondly, performing first classification processing on the multi-volume sequence image data to obtain second multi-volume sequence image data to be classified; thirdly, performing position calculation processing on the second multi-volume sequence image data to obtain position sequence data; then, carrying out transformation processing and calculation processing on the second multi-volume sequence image data according to the position sequence data to obtain a period number, a step number and frequency domain image data; and finally, classifying the multi-volume sequence image data or the second multi-volume sequence image data into a second number of first-volume sequence image data according to the number of cycles and the number of steps, so that the method can accurately split the multi-volume sequence into a plurality of subsequences, and has relatively high robustness.

Description

Technical Field

[0001] The present invention relates to the field of image data processing, and in particular to a multi-volume sequence image data processing method, a computer device and a readable storage medium. Background Art

[0002] Digital Imaging and Communications in Medicine (DICOM) is an international standard for the storage and communication of medical image information and is widely used in the field of medical imaging. A DICOM image sequence consists of a series of images. Each DICOM image contains several DICOM tags. Different images in the same sequence have the same SeriesInstanceUID tag.

[0003] Generally speaking, a DICOM sequence shows a 3D scan. When all DICOM images are superimposed in a certain order, a spatial stereoscopic image will be presented, which is the stereoscopic observation result of the scanned body. We call it Volume (which means both stereo and volume). If a sequence contains multiple Volume images, we call this sequence a multi-volume sequence.

[0004] In DICOM multi-volume sequence images, multiple sequence files that should be separated are often placed in the same sequence due to the settings of scanning device parameters, or human reasons and habits. For example, a DWI sequence contains DWI subsequences with multiple b values. This mixture of subsequences brings splitting costs to downstream image processing. For example, in scientific research and artificial intelligence training, it is necessary to split the subsequences with different b values ​​into separate volumes, because a single volume is required in the data analysis and artificial intelligence model construction process.

[0005] The challenges faced in subsequence splitting of multi-volume sequences are mainly in three aspects:

[0006] First, there are different ways of interleaving multi-volume sequences. Taking DWI multi-volume sequences as an example, some DWI multi-volume sequences put images with the same b value next to each other, while others put images with different b values ​​at the same time next to each other.

[0007] Second, some multi-volume sequences are formed by superimposing the results of multiple scans, but the starting and ending points of these repetitive scans are not strictly the same, which means that they will show a deviated periodicity.

[0008] Third, some multi-volume sequences may have a missing frame or an extra frame due to artificial reasons, which destroys the uniformity of the distance between two adjacent images.

[0009] At present, the existing technology uses the following methods to deal with multi-volume sequence splitting, including:

[0010] One is a splitting method that relies on the image's own logic. Taking the DWI sequence as an example, this method knows that the b value is stored in a DICOM tag. It only needs to obtain the b value of the tag to distinguish each volume. This method is the most accurate method, but the disadvantages of this method are: on the one hand, many manufacturers do not support fixed tags, or different models of the same manufacturer have different parameters; on the other hand, the splitting of many sequences, such as the splitting of CTP, does not have similar iconic parameters.

[0011] Another common method is to split the DICOM images according to the interval of their spatial position. This method is the simplest method, but it is not suitable for multi-volume sequences where two sub-sequences are interspersed alternately, and it has weak anti-interference performance. When the spatial position of an image is disturbed, it is very easy to fail.

[0012] Another method is to use machine learning to decompose, which is to divide each frame of the image into several categories. This method is highly adaptable, but the cost is high, and different training processes are required for different multi-volume sequences. Summary of the invention

[0013] The purpose of the embodiments of the present invention is to provide a multi-volume sequence image data processing method based on the defects in the multi-volume sequence splitting method in the prior art, which quantifies the overall periodicity and step characteristics of the entire sequence based on the frequency domain characteristics of the spatial position of the image sequence, and accurately and robustly splits the multi-volume sequence on the basis of the quantification.

[0014] A first aspect of the present invention provides a method for processing multi-volume sequence image data, the method comprising:

[0015] Acquire multi-volume sequence image data to be processed, wherein the multi-volume sequence image data includes a first number of medical image data; wherein the medical image data is medical digital imaging or communication image data;

[0016] performing a first classification process on the multi-volume sequence image data to obtain second multi-volume sequence image data to be classified;

[0017] performing position calculation processing on the second multi-volume sequence image data to obtain position sequence data;

[0018] transforming the second multi-volume sequence image data according to the position sequence data to obtain a frequency domain sequence and frequency domain image data;

[0019] Performing amplitude zeroing processing on the frequency domain image data according to the frequency domain sequence to obtain amplitude zeroing frequency domain image data;

[0020] Calculating the number of cycles according to the amplitude-zeroed frequency domain image data;

[0021] According to the number of cycles, the step number calculation process is performed on the amplitude-zeroed frequency domain image data to obtain the step number of the amplitude-zeroed frequency domain image data;

[0022] The multi-volume sequence image data or the second multi-volume sequence image data is classified into a second number of first volume sequence image data according to the number of cycles and the number of steps.

[0023] Preferably, the first classification process includes:

[0024] Traversing each medical image data in the multi-volume sequence image data; wherein the medical image data includes an ImagePatientOrientation tag, an ImagePatientPosition tag, and an InstanceNumber tag;

[0025] Adding an availability tag to each of the medical image data, and assigning a value of disable or enable to the availability tag according to the ImagePatientOrientation tag, the ImagePatientPosition tag and / or the InstanceNumber tag of each of the medical image data;

[0026] The second multi-volume sequence image data is obtained according to the medical image data to which the availability label is added.

[0027] Further preferably, the performing position calculation processing on the second multi-volume sequence image data to obtain position sequence data is specifically:

[0028] For each medical image data whose availability tag value is enable in the second multi-volume sequence image data, calculating relative position data of the medical image data;

[0029] According to the InstanceNumber value of the medical image data, the medical image data is sorted in ascending order of the InstanceNumber value, and the position sequence data is obtained according to the relative position data of the medical image data.

[0030] Further preferably, the calculating the relative position data of the medical image data specifically includes:

[0031] Splitting the ImagePatientOrientation value of the medical image data into a first three-dimensional vector and a second three-dimensional vector;

[0032] Perform a cross product process on the first three-dimensional vector and the second three-dimensional vector to obtain a third three-dimensional vector;

[0033] The third three-dimensional vector is subjected to a dot product process with the three-dimensional vector represented by the ImagePatientPosition value to obtain the relative position data.

[0034] Preferably, the performing transformation processing on the second multi-volume sequence image data according to the position sequence data to obtain frequency domain image data specifically includes:

[0035] Performing discrete Fourier transform processing on the position sequence data to obtain a frequency domain sequence;

[0036] The frequency domain image data is obtained according to the frequency domain sequence and the second multi-volume sequence image data; wherein,

[0037] The frequency domain sequence is expressed as (f i ,v i )i=0,1,....,m,

[0038] Among them, f represents frequency, v represents amplitude, and m represents the sequence length of position sequence data.

[0039] The multi-volume sequence image data processing method according to claim 1 is characterized in that the amplitude zeroing processing is performed on the frequency domain image data according to the frequency domain sequence to obtain the amplitude zeroing frequency domain image data specifically:

[0040] Performing judgment processing on each amplitude value in the frequency domain sequence according to a first amplitude threshold;

[0041] The amplitude values ​​whose amplitude values ​​are less than the first amplitude threshold are set to 0, so as to obtain the amplitude-zeroed frequency domain image data.

[0042] Preferably, the step number calculation process is performed on the amplitude-zeroed frequency domain image data according to the number of cycles to obtain the step number of the amplitude-zeroed frequency domain image data, specifically comprising:

[0043] Determine the value of the number of cycles:

[0044] When the number of cycles = 1, determine the first one that satisfies the amplitude value v k The number of items k that are 0 determines the number of steps to be k;

[0045] When the number of cycles is > 1, find the first frequency value f that satisfies the amplitude value of 0 according to the span of n×number of cycles. k , determine the number of steps to be f k ; If no amplitude value of 0 is found, the number of steps is assigned to None.

[0046] Preferably, the classifying the multi-volume sequence image data or the second multi-volume sequence image data into a second number of first volume sequence image data according to the number of cycles and the number of steps is specifically:

[0047] Determine according to the number of cycles and the number of steps:

[0048] When the number of cycles = 1 and the number of steps is not None, determining the second number = the first number / the number of steps, taking the second number as the extraction interval, extracting the number of medical image data of the steps from the multi-volume sequence image data to generate the second number of first volume sequence image data respectively;

[0049] When the number of cycles=1 and the number of steps is None, the second number=1 is determined, and the multi-volume sequence image data is a first volume sequence image data;

[0050] When the number of cycles>1 and the number of steps is None, determining that the second number=the number of cycles, dividing the second multi-volume sequence image data into a sequence arranged in ascending order according to the InstanceNumber value, to obtain the second number of first volume sequence image data;

[0051] When the number of cycles>1 and the number of steps is not None, determine the second number=the first number / the number of steps×the number of cycles, and divide the frequency domain image data into the number of cycles subsequences according to the position sequence data, and use the first number / the number of steps as the extraction interval, extract the number of steps medical image data from each subsequence to generate the second number / the number of cycles first volume sequence image data, and obtain the second number of first volume sequence image data from the number of cycles and the second number / the number of cycles first volume sequence image data.

[0052] A second aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multi-volume sequence image data processing method as described in any one of claims 1 to 8 when executing the computer program.

[0053] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for processing multi-volume sequence image data as described in any one of claims 1 to 8 is implemented.

[0054] The present invention provides a multi-volume sequence image data processing method, which quantifies the overall periodicity and step characteristics of the entire multi-volume sequence based on the frequency domain characteristics of the spatial position of the multi-volume sequence image, and splits the multi-volume sequence into multi-volume sequence sub-sequences based on the quantization. The method has accurate splitting and high robustness. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of a method for processing multi-volume sequence image data according to the present invention;

[0056] Figure 2 A flowchart of a method for calculating position sequence data of multi-volume sequence image data according to the present invention;

[0057] Figure 3 is a flow chart of a method for calculating relative position data of medical image data according to the present invention;

[0058] Figure 4 is a flow chart of a method for calculating frequency domain image data and parameters according to the present invention;

[0059] Figure 5 is a schematic diagram of the relationship between InstanceNumber and Location of a DualEcho image according to the present invention;

[0060] Figure 6a is a schematic diagram of the relationship between InstanceNumber and Location of a CTP image according to the present invention;

[0061] Figure 6b In order to view the Figure 6a Schematic diagram of the relationship between CTP frequency domain data;

[0062] Figure 7 is a schematic diagram of a computer device according to the present invention. DETAILED DESCRIPTION

[0063] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0064] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0065] The first and second in the following text are only for distinction and have no other meanings.

[0066] The embodiments of the present invention are described below in conjunction with the accompanying drawings.

[0067] A first aspect of the present invention provides a method for processing multi-volume sequence image data, which is described in detail below. Figure 1 This is a flow chart of a method for processing multi-volume sequence image data according to the present invention. As shown in the figure, the method comprises the following steps:

[0068] Step 110 : acquiring multi-volume sequence image data to be processed, where the multi-volume sequence image data includes a first number of medical image data.

[0069] The medical imaging image data is medical digital imaging or communication image data.

[0070] Specifically, after receiving an external processing instruction, the multi-volume sequence image data processing method provided by the present invention is started. In the present invention, the first number is recorded as m. In this step, the multi-volume sequence image data to be processed is obtained according to the processing instruction, and the multi-volume sequence image data includes m medical image data that are medical digital imaging or communication image data. In the present invention, these medical image data that are medical digital imaging or communication image data are collectively referred to as medical image data.

[0071] The multi-volume sequence image data to be processed acquired by the present invention is received from the outside, and each medical image data included therein is formed by scanning by a medical imaging device, and different multiple labels are automatically added according to established standards and rules during the scanning process.

[0072] The purpose of the present invention is to separate a plurality of sub-sequence image data from the multi-volume sequence image data to be processed, that is, the second number of first volume sequence image data finally obtained by the present invention.

[0073] Step 120 : performing a first classification process on the multi-volume sequence image data to obtain second multi-volume sequence image data to be classified.

[0074] Specifically, in the embodiment of the present invention, each medical image data includes an ImagePatientOrientation tag, an ImagePatientPosition tag, and an InstanceNumber tag. The value of the ImagePatientOrientation tag is a tuple of length 6, indicating the direction of the image plane: it indicates the direction cosine of the first row and the first column of the image relative to the patient. The direction of the coordinate axis is determined according to the direction of the patient (LPS system: the x-axis points to the left hand side of the patient, the y-axis points to the back of the patient, and the z-axis points to the head of the patient.

[0075] The value of the ImagePatientPosition tag is a tuple of length 3, representing the position of the first pixel in the pixel matrix of the current image. And the value of the InstanceNumber tag is the unique number of the image in the entire sequence, which is an integer starting from 1.

[0076] In the embodiment of the present invention, the first classification process is a marking process, according to

[0077] The ImagePatientOrientation tag, ImagePatientPosition tag and InstanceNumber tag are used to mark each medical image data in the multi-volume sequence image data. The purpose is to classify each medical image data into usable image data and unusable image data after marking each medical image. What is actually accomplished is to classify each medical image data in the multi-volume sequence image data as usable or unusable.

[0078] The marking method provided by the optional scheme of the embodiment of the present invention is as follows: traverse each medical image data in the multi-volume sequence image data; add an availability tag to each of the medical image data, such as adding AvailabilityTag, and judge the ImagePatientOrientation tag, ImagePatientPosition tag and InstanceNumber tag of each medical image data, and assign the availability tag of the ImagePatientOrientation tag, ImagePatientPosition tag and / or InstanceNumber tag to enable, that is, AvailabilityTag=enable, indicating that the medical image data is available; if one of the ImagePatientOrientation tag, ImagePatientPosition tag and InstanceNumber tag of the medical image data is unavailable, then we assign the availability tag of the medical image data to disable, that is, AvailabilityTag=disable, indicating that the medical image data is unavailable.

[0079] After a complete traversal of the multi-volume sequence image data is completed, the medical image data with the availability tag AvailabilityTag added thereto constitutes the second multi-volume sequence image data. In other words, the second multi-volume sequence image data is formed by adding the availability tag AvailabilityTag to each medical image data of the multi-volume sequence image data.

[0080] It should be noted that the availability tag AvailabilityTag is added to each medical imaging image data of the multi-volume sequence image data. Therefore, the multi-volume sequence image data after the availability tag AvailabilityTag is added can be considered as the second multi-volume sequence image data.

[0081] Step 130 : Perform position calculation processing on the second multi-volume sequence image data to obtain position sequence data.

[0082] Specifically, this step includes two sub-steps, step 1301 and step 1302, and aims to obtain the position sequence data of the second multi-volume sequence image data through calculation. In the embodiment of the present invention, the position sequence data is represented by LocationSeries. Figure 2 This is a flow chart of a method for calculating position sequence data of multi-volume sequence image data according to the present invention. As shown in the figure, the method specifically includes:

[0083] Step 1301: Calculate the relative position data Location of the medical image data. Specifically, for each medical image data with an availability tag value of enable in the second multi-volume sequence image data, calculate the relative position data Location of the medical image data.

[0084] Step 1302, the position sequence data of the second multi-volume sequence image data is calculated. Specifically, after calculating the first position data, the medical image data is sorted in ascending order according to the InstanceNumber value of the medical image data, and the position sequence data LocationSeries is obtained according to the relative position data Location of the medical image data. Specifically, sorting in ascending order according to the InstanceNumber value is to rearrange the position sequence of each medical image data of the second volume sequence image data. Since each medical image data has a corresponding relative position data Location, as the sequence of the medical image data is rearranged, the relative position data Location of the medical image data is rearranged to form the position sequence data LocationSeries.

[0085] In an optional solution of the embodiment of the present invention, the relative position data Location of the medical image data in step 1301 is calculated by using the following method: Figure 3 The following will combine Figure 3 This method is explained in detail.

[0086] Figure 3 This is a flow chart of the method for calculating relative position data of medical image data according to the present invention. As shown in the figure, the method for calculating relative position data of medical image data includes steps 13011 to 13013:

[0087] Step 13011, split the ImagePatientOrientation tag of the medical image data into a first three-dimensional vector and a second three-dimensional vector. Specifically, the value of the ImagePatientOrientation tag of the medical image data in the embodiment of the present invention is a tuple with a length of 6. In this step, the tuple with a length of 6 needs to be split into two three-dimensional vectors, namely, the first three-dimensional vector and the second three-dimensional vector.

[0088] Step 13012, cross-product the first three-dimensional vector and the second three-dimensional vector to obtain a first three-dimensional vector. Specifically, the first three-dimensional vector and the second three-dimensional vector are the two three-dimensional vectors obtained by splitting in step 13011. Cross-product the two vectors to obtain a third three-dimensional vector.

[0089] Step 13013, dot product processing is performed on the third three-dimensional vector and the three-dimensional vector represented by the ImagePatientPosition tag to obtain relative position data. Specifically, the value of the ImagePatientPosition tag in the present invention is a tuple with a length of 3, and the relative position data of the medical image data is obtained by dot product of the third three-dimensional vector and the value of the ImagePatientPosition tag.

[0090] Each medical image data of the second multi-volume sequence image data obtained after processing in this step includes its relative position data, and the position sequence data of the second multi-volume sequence image data is obtained after being sorted in ascending order according to the InstanceNumber value of each medical image data.

[0091] Step 140 , transforming and calculating the second multi-volume sequence image data according to the position sequence data to obtain the number of cycles, the number of steps and frequency domain image data.

[0092] Specifically, the location sequence data LocationSeries obtained by step 130 is a finite discrete sequence, and a frequency domain sequence can be obtained by performing discrete Fourier transform on the finite discrete sequence data. The purpose of the present invention is to classify or split multi-volume sequence image data by using the characteristics of the frequency domain sequence. The image in the frequency domain has the following characteristics:

[0093] First, for a uniform linearly changing original sequence, starting from a frequency of 1, v n =v1 / n and so on.

[0094] Second, if the original sequence is periodic with a period of n, then the amplitude is non-zero only at frequencies that are multiples of n, v kn ≠0, k∈N.

[0095] Third, if the original sequence presents continuous identical values, we call it a step. In the periodic image, if the total number of steps is n, then the amplitude at frequency = n is exactly 0.

[0096] The purpose of this step is to obtain the number of cycles, the number of steps and the frequency domain image data of the second multi-volume sequence image data by calculation and transformation. Figure 4 The method shown is used for calculation, and the following is combined Figure 4 The calculation method of frequency domain image data and parameters obtained in this step is introduced in detail. Figure 4 This is a flow chart of a method for calculating frequency domain image data and parameters according to the present invention. As shown in the figure, the method comprises the following steps:

[0097] Step 1401 : transform the second multi-volume sequence image data according to the position sequence data to obtain a frequency domain sequence and frequency domain image data.

[0098] Specifically, in an optional solution of the embodiment of the present invention, the frequency domain sequence can be obtained by directly performing discrete Fourier transform processing on the location sequence data LocationSeries corresponding to the second multi-volume sequence image data. After the frequency domain sequence is obtained, it is corresponded to each medical image data of the second multi-volume sequence image data, so that the second multi-volume sequence image data with a frequency domain sequence is formed, which is recorded as frequency domain image data. In the embodiment of the present invention, the frequency domain sequence is expressed as:

[0099] (f i ,v i ) i = 0,1, ....,m, (Formula 1)

[0100] Among them, f represents frequency, v represents amplitude, m represents the sequence length of position sequence data, and i is an integer in the range of [0, m).

[0101] Step 1402 , performing amplitude zeroing processing on the frequency domain image data according to the frequency domain sequence to obtain amplitude zeroing frequency domain image data.

[0102] Specifically, in an optional solution of the embodiment of the present invention, each amplitude value v in the frequency domain sequence is judged and processed according to the first amplitude threshold, and the amplitude value v whose amplitude value v is smaller than the first amplitude threshold is selected as j Set to 0, that is, v j =0, and the amplitude-zeroed frequency domain image data is obtained. In the embodiment of the present invention, the first amplitude threshold can be considered according to the actual situation of the frequency domain image data and set to a reasonable value. In the preferred embodiment of the present invention, 5% of v1 is used as the first amplitude threshold. After this step, the amplitude values ​​of some items in the frequency domain sequence corresponding to the frequency domain image data are set to 0, and the processed frequency domain image data is recorded as the amplitude-zeroed frequency domain image data.

[0103] Step 1403, calculating the number of cycles according to the amplitude zeroed frequency domain image data.

[0104] Specifically, in the embodiment of the present invention, the period number refers to the number of periods, which is recorded as period. The calculation of the period number is specifically as follows: judging according to the frequency domain sequence corresponding to the amplitude zeroing frequency domain image data, finding all the frequencies f in the frequency domain sequence ln =1 when the amplitude value v ln , according to v ln Make a judgment:

[0105] If v ln >1, indicating that the frequency domain sequence is a non-periodic sequence, confirming that the period number period = 1.

[0106] If only v ln If it is not 0, then period = n. In which, ln, l∈N.

[0107] Step 1404 , performing step number calculation processing on the amplitude zeroing frequency domain image data according to the number of cycles to obtain the number of steps.

[0108] Specifically, the number of steps is recorded as foot_step, and the present invention uses the following method to calculate the number of steps foot_step in the embodiment. The value of the period number period is determined:

[0109] When the period number period=1, determine the first one that satisfies the amplitude value v k =0, the number of steps is determined to be k, that is, foot_step=k.

[0110] When the period number period>1, find the first one that satisfies the amplitude value v according to the span of n×period. k =Frequency value f k , determine the number of steps to be f k , that is, foot_step = f k ; If the amplitude value v is not found k =0, the number of steps is assigned to None, that is, foot_step = None.

[0111] After the processing in step 140 , frequency domain image data having a frequency domain sequence, as well as the number of periods period and the number of steps foot_step of the frequency domain image data are obtained.

[0112] Step 150 : classifying the multi-volume sequence image data or the frequency domain image data into a second number of first volume sequence image data according to the number of cycles and the number of steps.

[0113] Specifically, in the embodiment of the present invention, the period number period and the step number foot_step of the frequency domain image data are judged, and the multi-volume sequence image data is split into the second number Nvolume The first volume sequence image data includes the following situations:

[0114] Case 1: When period = 1, and foot_step ≠ None, determine N volume = m / foot_step, in N volume To extract the interval, extract foot_step medical image data from the multi-volume sequence image data to generate N volume Specifically, the original multi-volume sequence image data with this feature is a frame of medical image data having multiple first volume sequence image data at the same position, and the original multi-volume sequence image data is obtained by extracting N first volume sequence image data from the multi-volume sequence image data. volume To extract the medical image data in turn, N volume The first volume sequence image data is described in detail with an example, for example, taking a DualEcho image as an example, Figure 5 Schematic diagram of the relationship between InstanceNumber and Location of a DualEcho according to the present invention, as shown in Figure 5 As shown in the figure, the DualEcho image is a multi-volume sequence image data with a length of 176. At the same position in space, there are two medical image data with different Echo parameters. The relationship between InstanceNumber and Location presents fine steps. By calculating the frequency, foot_step = 88, so N volume =2. Extract the 1st, 3rd, 5th ... 175th from the DualEcho multi-volume sequence image data and merge them into one volume as a first multi-volume sequence image data, and extract the 2nd, 4th, 6th ... 176th volumes and merge them into a second volume as another first multi-volume sequence image data. That is to say, the DualEcho multi-volume sequence image data is split into two first multi-volume sequence image data by the method provided by the present invention.

[0115] Case 2: When period = 1 and foot_step = None, determine N volume =1, the multi-volume sequence image data is a first volume sequence image data. That is, in this case, the original multi-volume sequence image data to be processed only includes a first volume sequence image data, and it is not necessary to split it.

[0116] Case 3: When period>1, and foot_step=None, determine N volume=period, divide the second multi-volume sequence image data into a sequence arranged in ascending order according to the InstanceNumber value, and obtain N volume Includes m / N volume Specifically, taking a CTP image as an example, Figure 6a A schematic diagram of the relationship between InstanceNumber and Location of CTP according to the present invention, Figure 6b In order to view the Figure 6a Schematic diagram of CTP frequency domain data relationship, such as Figure 6a As shown, from the relationship between InstanceNumber and Location of CTP, it can be seen that the scanning position of each medical image data in the CTP multi-volume sequence image data is repeated, such as Figure 6b As shown, looking at the same CTP image in the frequency domain, there is a value at position 20, which means that the frequency domain is 20 times the frequency, that is, the number of periods period = 20. Therefore, according to the rule N volume =period=20, the CTP multi-volume sequence image data can be divided into 20 first multi-volume sequence image data. volume The entire CTP multi-volume sequence image data is split into 20 sub-sequences according to the sequence sorted in ascending order by InstanceNumber. Each sub-sequence is a volume, that is, each sub-sequence is a first multi-volume sequence image data. Figure 6a As shown. The CTP multi-volume sequence image data includes 4400 medical image data, and it can be determined that each volume contains 4400 / 20 medical image data. The first volume is obtained by sequentially forming a sequence of the 1st, 2nd, 3rd...220th medical image data, and the second volume is obtained by sequentially forming a sequence of the 221st, 222nd...440th medical image data, and so on, and finally the CTP multi-volume sequence image data is split into 20 first multi-volume sequence image data.

[0117] Case 4: When period>1 and foot_step≠None, determine N volume=m / foot_step×period, the second multi-volume sequence image data is divided into a sequence arranged in ascending order according to the InstanceNumber value to obtain period first subsequences, and m / foot_step is used as the extraction interval, foot_step medical imaging image data is extracted from each first subsequence of the obtained period first subsequences to generate m / foot_step first volume sequence image data in sequence, and m / foot_step×period first volume sequence image data are obtained from the m / foot_step first volume sequence image data extracted from each subsequence of the period first subsequences. Here, the method of splitting each first subsequence into m / foot_step first volume sequence image data is consistent with the splitting method in case 1 in step 150, and will not be repeated here.

[0118] The above is a multi-volume sequence image data processing method provided by the first aspect of the present invention. The method quantifies the overall periodicity and step characteristics of the entire multi-volume sequence based on the frequency domain characteristics of the spatial position of the multi-volume sequence image, and splits the multi-volume sequence into multi-volume sequence sub-sequences based on the quantization. The method has accurate splitting and high robustness.

[0119] Each step in the above-mentioned multi-volume sequence image data processing method of the present invention can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned steps can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above steps.

[0120] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0121] The computer device 7 includes a memory 71, a processor 72, and a network interface 73 that are interconnected and communicate with each other through a system bus. It should be noted that the figure only shows a computer device 7 with components connected to the memory 71, the processor 72, and the network interface 73, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital processing

[0122] Devices (Digital Signal Processor, DSP), embedded devices, etc.

[0123] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0124] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D interface display memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 71 can also be an external storage device of the computer device 7, such as a plug-in hard disk equipped on the computer device 7, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 71 can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the computer device 7, such as the program code for controlling electronic files, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.

[0125] The processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 72 is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code for controlling the electronic file.

[0126] The network interface 73 may include a wireless network interface or a wired network interface, and the network interface 73 is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0127] The present application also provides another implementation, namely, providing a computer-readable storage medium, which stores an interface display program. The interface display program can be executed by at least one processor to enable the at least one processor to perform the steps of the electronic file control method as described above.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0129] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

[0130] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for processing multi-volume sequence image data, characterized in that: The method comprises: Acquire multi-volume sequence image data to be processed, wherein the multi-volume sequence image data includes a first number of medical image data; wherein the medical image data is medical digital imaging or communication image data; performing a first classification process on the multi-volume sequence image data to obtain second multi-volume sequence image data to be classified; performing position calculation processing on the second multi-volume sequence image data to obtain position sequence data; transforming the second multi-volume sequence image data according to the position sequence data to obtain a frequency domain sequence and frequency domain image data; Performing amplitude zeroing processing on the frequency domain image data according to the frequency domain sequence to obtain amplitude zeroing frequency domain image data; Calculating the number of cycles according to the amplitude-zeroed frequency domain image data; According to the number of cycles, a step number calculation process is performed on the amplitude-zeroed frequency domain image data to obtain the step number of the amplitude-zeroed frequency domain image data; The multi-volume sequence image data or the second multi-volume sequence image data is classified into a second number of first volume sequence image data according to the number of cycles and the number of steps.

2. The method for processing multi-volume sequence image data according to claim 1, characterized in that: The first classification process includes: Traversing each medical image data in the multi-volume sequence image data; wherein the medical image data includes an ImagePatientOrientation tag, ImagePatientPosition tag and InstanceNumber tag; Adding an availability tag to each of the medical image data, and assigning a value of disable or enable to the availability tag according to the ImagePatientOrientation tag, the ImagePatientPosition tag and / or the InstanceNumber tag of each of the medical image data; The second multi-volume sequence image data is obtained according to the medical image data to which the availability label is added.

3. The method for processing multi-volume sequence image data according to claim 2, characterized in that: The position calculation process is performed on the second multi-volume sequence image data to obtain the position sequence data, specifically: For each medical image data whose availability tag value is enable in the second multi-volume sequence image data, calculating relative position data of the medical image data; According to the InstanceNumber value of the medical image data, the medical image data is sorted in ascending order of the InstanceNumber value, and the position sequence data is obtained according to the relative position data of the medical image data.

4. The method for processing multi-volume sequence image data according to claim 3, characterized in that: The calculating of the relative position data of the medical image data specifically includes: Splitting the ImagePatientOrientation value of the medical image data into a first three-dimensional vector and a second three-dimensional vector; Perform a cross product process on the first three-dimensional vector and the second three-dimensional vector to obtain a third three-dimensional vector; The third three-dimensional vector is subjected to a dot product process with the three-dimensional vector represented by the ImagePatientPosition value to obtain the relative position data.

5. The method for processing multi-volume sequence image data according to claim 1, characterized in that: The transforming the second multi-volume sequence image data according to the position sequence data to obtain the frequency domain image data specifically includes: Performing discrete Fourier transform processing on the position sequence data to obtain a frequency domain sequence; The frequency domain image data is obtained according to the frequency domain sequence and the second multi-volume sequence image data; wherein, The frequency domain sequence is expressed as (f i ,v i )i=0,1,....,m, Among them, f represents frequency, v represents amplitude, and m represents the sequence length of position sequence data.

6. The method for processing multi-volume sequence image data according to claim 1, characterized in that: The amplitude zeroing processing is performed on the frequency domain image data according to the frequency domain sequence to obtain the amplitude zeroing frequency domain image data, specifically: Performing judgment processing on each amplitude value in the frequency domain sequence according to a first amplitude threshold; The amplitude values ​​whose amplitude values ​​are less than the first amplitude threshold are set to 0, so as to obtain the amplitude-zeroed frequency domain image data.

7. The method for processing multi-volume sequence image data according to claim 1, characterized in that: The step number calculation process of the amplitude-zeroed frequency domain image data according to the number of cycles to obtain the step number of the amplitude-zeroed frequency domain image data specifically includes: Determine the value of the number of cycles: When the number of cycles = 1, determine the first one that satisfies the amplitude value v k The number of items k that are 0 determines the number of steps to be k; When the number of cycles is > 1, find the first frequency value f that satisfies the amplitude value of 0 according to the span of n×number of cycles. k , determine the number of steps to be f k ; If no amplitude value of 0 is found, the number of steps is assigned to None.

8. The method for processing multi-volume sequence image data according to claim 1, characterized in that: The classifying the multi-volume sequence image data or the second multi-volume sequence image data into a second number of first volume sequence image data according to the number of cycles and the number of steps is specifically: Determine according to the number of cycles and the number of steps: When the number of cycles = 1 and the number of steps is not None, determining the second number = the first number / the number of steps, taking the second number as the extraction interval, extracting the number of medical image data of the steps from the multi-volume sequence image data to generate the second number of first volume sequence image data respectively; When the number of cycles=1 and the number of steps is None, the second number=1 is determined, and the multi-volume sequence image data is a first volume sequence image data; When the number of cycles>1 and the number of steps is None, determining that the second number=the number of cycles, dividing the second multi-volume sequence image data into a sequence arranged in ascending order according to the InstanceNumber value, to obtain the second number of first volume sequence image data; When the number of cycles>1 and the number of steps is not None, determine the second number=the first number / the number of steps×the number of cycles, and divide the frequency domain image data into the number of cycles subsequences according to the position sequence data, and use the first number / the number of steps as the extraction interval, extract the number of steps medical image data from each subsequence to generate the second number / the number of cycles first volume sequence image data, and obtain the second number of first volume sequence image data from the number of cycles and the second number / the number of cycles first volume sequence image data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for processing multi-volume sequence image data according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for processing multi-volume sequence image data according to any one of claims 1 to 8 is implemented.

Images