CN110298832B - Infarct range area detection method, device, storage medium and equipment - Google Patents
Infarct range area detection method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN110298832B CN110298832B CN201910553962.2A CN201910553962A CN110298832B CN 110298832 B CN110298832 B CN 110298832B CN 201910553962 A CN201910553962 A CN 201910553962A CN 110298832 B CN110298832 B CN 110298832B
- Authority
- CN
- China
- Prior art keywords
- infarct
- candidate
- weighted imaging
- region
- diffusion weighted
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Abstract
The application discloses an infarct kitchen region detection method, device, storage medium and equipment, and the infarct kitchen region detection method comprises the following steps: obtaining a brain parenchymal tissue portion in the magnetic resonance image; obtaining an infarct focus candidate region from the brain parenchymal tissue portion according to a set surface diffusion coefficient threshold; obtaining an infarct focus confirmation area in which the ratio of the diffusion weighted imaging signal to the surface diffusion coefficient is higher than a set value in the brain parenchymal tissue part; determining a candidate communication region which is communicated with the infarct focus confirmation region in the infarct focus candidate region; and determining the target infarct focus area according to the diffusion weighted imaging signal value in the candidate communication area. The method and the device can detect the infarct focus in acute and hyperacute phases, are high in calculation speed, and can distinguish the tumor and the infarct focus areas which are also high in DWI value and low in ADC value.
Description
Technical Field
The present disclosure relates to the field of medical devices, and in particular, to a method, an apparatus, a storage medium, and a device for detecting an infarct focus area.
Background
In magnetic resonance imaging, diffusion-weighted imaging (DWI) and surface diffusion coefficient (apparent diffusion coefficients, ADC) imaging are imaging methods that can reflect the diffusion specificity of water molecules. In the acute phase of cerebral infarction, due to arterial occlusion, blood diffusion movement is weakened, DWI presents a significantly high signal, while ADC images present a significantly low signal; while the DWI high signal intensity gradually decreases with the progression of the disease, the ADC plot shows a gradual return of significantly lower signal intensity. It can be seen that DWI and ADC have high application value in diagnosing acute cerebral infarction.
In the related art, an infarct focus is usually detected through an ADC threshold value, and then the erroneous judgment is corrected by using a high DWI. However, due to the characteristics of human brain, the DWI and the ADC are not uniformly distributed, and the accuracy of a detection result is difficult to ensure by adopting a method for detecting by a hard threshold value; moreover, this detection method cannot exclude certain non-ischemic lesions, such as tumors, but with high DWI and low ADC.
Disclosure of Invention
In order to overcome the problems in the related art, the present specification provides a method, an apparatus, a storage medium, and a device for detecting an infarct focus area.
Specifically, the application is realized by the following technical scheme:
in a first aspect, there is provided a method of detecting an infarct focus area, the method comprising:
obtaining a brain parenchymal tissue portion in the magnetic resonance image;
obtaining an infarct focus candidate region from the brain parenchymal tissue portion according to a set surface diffusion coefficient threshold;
obtaining an infarct focus confirmation area in which the ratio of the diffusion weighted imaging signal to the surface diffusion coefficient is higher than a set value in the brain parenchymal tissue part;
determining a candidate communication region which is communicated with the infarct focus confirmation region in the infarct focus candidate region;
and determining the target infarct focus area according to the diffusion weighted imaging signal value in the candidate communication area.
Optionally, obtaining a brain parenchymal tissue portion in the magnetic resonance image comprises:
obtaining a first threshold value of diffusion weighted imaging signals in a magnetic resonance image;
a region in the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
Optionally, determining a candidate communication region, which is in communication with the infarct focus confirmation region, among the infarct focus candidate regions includes:
performing binarization treatment on the candidate infarct range area to obtain a connected domain in the candidate infarct range area;
performing binarization treatment on the infarct focus confirmation area to obtain a connected domain in the infarct focus confirmation area;
and determining a candidate connected region which has an intersection with the connected region of the infarct focus candidate region in the connected region of the infarct focus candidate region.
Optionally, determining the target infarct focus region according to the diffusion weighted imaging signal values in the candidate connected region includes:
determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion;
determining an average value of diffusion weighted imaging signals of the candidate connected regions and an average value of diffusion weighted imaging signals of neighborhood tissues of the candidate connected regions;
and determining the area, of the candidate communication areas, in which the average value of the diffusion weighted imaging signals and the average signal value or the global threshold value of diffusion weighted imaging of the regional tissue meet a set proportion relation, as a target infarct focus area.
Optionally, determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion comprises:
obtaining a second threshold value of diffusion weighted imaging signals of the brain parenchymal tissue part in the magnetic resonance image, wherein the second threshold value is obtained by carrying out maximum inter-class variance processing on the magnetic resonance image;
obtaining a low threshold and a high threshold of a diffusion weighted imaging signal respectively by carrying out twice maximum inter-class variance processing on the brain parenchymal tissue part;
and determining the global threshold according to the numerical relation between the second threshold and the low threshold and the high threshold.
In a second aspect, there is provided an infarct size detection device, the device comprising:
a first obtaining unit for obtaining a brain parenchymal tissue part in the magnetic resonance image;
a second obtaining unit for obtaining an infarct focus candidate region from the brain parenchymal tissue section according to a set surface diffusion coefficient threshold value;
a third obtaining unit for obtaining an infarct focus confirmation area in which a ratio of the diffusion weighted imaging signal to a surface diffusion coefficient is higher than a set value in the brain parenchymal tissue portion;
a first determination unit configured to determine a candidate communication area, among the infarct focus candidate areas, that communicates with the infarct focus confirmation area;
and a second determining unit, configured to determine a target infarct focus area according to the diffusion weighted imaging signal values in the candidate communication area.
Optionally, the first obtaining unit is specifically configured to:
obtaining a first threshold value of diffusion weighted imaging signals in a magnetic resonance image;
a region in the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
Optionally, the first determining unit is specifically configured to:
performing binarization treatment on the candidate infarct range area to obtain a connected domain in the candidate infarct range area;
performing binarization treatment on the infarct focus confirmation area to obtain a connected domain in the infarct focus confirmation area;
and determining a candidate connected region which has an intersection with the connected region of the infarct focus candidate region in the connected region of the infarct focus candidate region.
Optionally, the second determining unit is specifically configured to:
determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion;
determining an average value of diffusion weighted imaging signals of the candidate connected domain and an average value of diffusion weighted imaging signals of a neighborhood tissue of the candidate connected domain;
and determining the communication area, of the candidate communication areas, in which the average value of diffusion weighted imaging signals and the average signal value or the global threshold value of diffusion weighted imaging of the regional tissue meet a set proportion relation, as a target infarct focus area.
Optionally, the second determining unit, when used for determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue part, is specifically configured to:
obtaining a second threshold value of diffusion weighted imaging signals of the brain parenchymal tissue part in the magnetic resonance image, wherein the second threshold value is obtained by carrying out maximum inter-class variance processing on the magnetic resonance image;
obtaining a low threshold and a high threshold of a diffusion weighted imaging signal respectively by carrying out twice maximum inter-class variance processing on the brain parenchymal tissue part;
and determining the global threshold according to the numerical relation between the second threshold and the low threshold and the high threshold.
In a third aspect, there is provided an image detection apparatus comprising: an internal bus, and a memory, a processor and an external interface connected through the internal bus; wherein, the liquid crystal display device comprises a liquid crystal display device,
the external interface is used for acquiring a magnetic resonance image;
the memory is used for storing machine-readable instructions corresponding to the detection logic of the infarct focus area;
the processor is configured to read the machine-readable instructions on the memory and perform the infarct focus area detection method as described above.
A fourth method provides a computer-readable storage medium having stored thereon a program that is executed by a processor to perform the infarct size detection method as described above.
In the embodiment of the present disclosure, by screening candidate areas of infarct with the combination of the ratio of DWI to ADC and the ADC threshold, and further determining the areas of infarct according to the DWI value, detection of infarct in acute and hyperacute phases can be performed, and the areas of infarct and tumor can be distinguished from those of infarct with high DWI value and low ADC value at a high calculation speed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and together with the description, serve to explain the principles of the specification.
Fig. 1 is a flowchart illustrating a method for detecting an infarct focus area according to an exemplary embodiment of the present application;
FIG. 2 is an image of brain parenchyma tissue as shown in an exemplary embodiment of the present application;
FIG. 3 is a binarized infarct focus candidate region image, as shown in an exemplary embodiment of the present application;
FIG. 4 is a view showing a binary infarct focus determination area image according to an exemplary embodiment of the present application;
fig. 5 is an image of an infarct focus candidate region communicating with an infarct focus determination region, according to an exemplary embodiment of the present application;
FIG. 6 is a flowchart illustrating a method of determining a target infarct zone according to an exemplary embodiment of the present application;
fig. 7 is a schematic view of an infarct focus area detection apparatus according to an exemplary embodiment of the present application;
fig. 8 is a schematic structural view of an image detection apparatus according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present description as detailed in the accompanying claims.
In order to solve the problems that in the related art, the accuracy is difficult to guarantee and the focus with high DWI and low ADC cannot be eliminated by combining the ADC threshold value and the DWI value, the application provides an infarct focus area detection method, an infarct focus area detection device, an image processing device and a computer readable storage medium.
Referring to fig. 1, a flowchart of a method for detecting an infarct focus area according to an exemplary embodiment of the present application may include the steps of:
in step 101, a brain parenchymal tissue portion in a magnetic resonance image is obtained.
Since the infarct focus is within the brain parenchyma, it is necessary to filter the background from the magnetic resonance image and extract the brain parenchyma.
In one example, the brain parenchymal tissue portion in the magnetic resonance image may be obtained by:
firstly, a first threshold value of a diffusion weighted imaging DWI signal in a magnetic resonance image is obtained;
next, a region of the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
It will be appreciated by those skilled in the art that the method of obtaining a brain parenchymal tissue portion is not limited to that described above, and that other methods of extracting brain parenchymal tissue portions may be used.
The first threshold for the DWI signal may be obtained by a maximum inter-class variance method, or may be obtained by other methods.
The obtained partial image of the brain parenchyma tissue is shown in fig. 2, for example.
In step 102, a candidate region of infarct focus is obtained from the brain parenchymal tissue portion according to a set surface diffusion coefficient threshold.
In this step, the set ADC threshold is first obtained. The ADC threshold, namely the ADC hard threshold described in the related art, is used for screening the area which is possibly infarcted in the brain parenchymal tissue part. For example, the ADC threshold may be set to any value in the interval 620-635. It will be appreciated by those skilled in the art that the above range settings are merely examples, and the present embodiment does not limit the specific range of ADC threshold values.
Based on the obtained ADC threshold value, a region in the brain parenchymal tissue portion where the detected ADC value is smaller than the threshold value is determined as an infarct focus candidate region.
The infarct focus candidate region may be represented by a binarized image, as shown in fig. 3. Wherein, a pixel value of 1 indicates a suspected infarct focus tissue, and a pixel value of 0 indicates a non-infarct focus. All regions formed by suspected infarct focus tissues are candidate infarct focus regions.
In step 103, an infarct focus confirmation area is obtained in which the ratio of the diffusion weighted imaging signal to the surface diffusion coefficient is higher than a set value in the brain parenchymal tissue portion.
In this step, DWI signal values of respective pixels in a brain parenchymal tissue portion and ADC values are first obtained, and a ratio p of the DWI signal values to the ADC values is calculated.
Next, a set value for screening the high ratio region is obtained, and the set value may be set to, for example, 0.25 to 0.3, and the set value may be any value within the range. It will be appreciated by those skilled in the art that the above range settings are merely examples, and the present embodiment does not limit the specific range of the set values.
Finally, a region where the ratio p is higher than the set value is determined as an infarct size confirmation region. That is, in the infarct focus confirmation region, the ratio of DWI signals to ADC of all pixels is higher than the above-described set value. This infarct focus identification area may also be referred to as a high ratio area.
The infarct focus determination area may be represented by a binarized image, as shown in fig. 4. Wherein, a pixel value of 1 indicates a tissue with a ratio p higher than a set value, and 0 indicates a tissue with a ratio p lower than or equal to the set value. All tissues with a ratio p above the set value form a high ratio region, i.e. an infarct focus confirmation region.
In step 104, a candidate communication region that communicates with the infarct focus confirmation region among the infarct focus candidate regions is determined.
Communicates with the infarct focus identification zone, i.e. has an intersection with the infarct focus identification zone. Since the infarct size confirmation region is a region where the ratio p of DWI to ADC is high, that is, in this step, a candidate communication region where the ratio p of DWI to ADC is high is determined among the infarct size candidate regions.
Since the suspected infarct focus tissue may be discontinuously distributed in the infarct focus candidate region, there may be a plurality of subregions; as well as the infarct focus identification zone, there may be multiple sub-zones as the high ratio tissue may be non-continuously distributed. In this step, a plurality of subregions of the infarct focus candidate region are selected, and subregions having intersections with the infarct focus confirmation region (high-ratio region) are selected as candidate communication regions.
Reserving the determined candidate communication areas for subsequent processing; for tissue in other areas, the possibility of infarcted tissue is precluded because of its low DWI to ADC ratio p.
In one example, candidate communication areas that communicate with the infarct focus confirmation area are determined by the following method:
and carrying out binarization treatment on the infarct focus candidate region to obtain a connected domain in the infarct focus candidate region, and carrying out reference numerals on the obtained connected domain, wherein the reference is shown in fig. 3.
And (4) performing binarization treatment on the infarct focus identification area to obtain a connected domain in the infarct focus identification area, as shown in fig. 4.
And determining a candidate connected region which has an intersection with the connected region of the infarct focus candidate region in the connected region of the infarct focus candidate region. As shown in fig. 5, a connected domain having an intersection with the infarct focus confirmation region, that is, representing that it is connected to the infarct focus confirmation region, is shown, and the connected domain is determined as a candidate connected region.
Wherein, the connected domain can be regarded as a binarized display result of a continuous subarea in an infarct focus waiting area or an infarct focus confirming area.
In step 105, a target infarct zone is determined from diffusion weighted imaging signal values in the candidate connected regions.
For the candidate areas of infarct focus (candidate connected areas) that remain in step 104, the final target infarct focus area is determined from the diffusion weighted imaging signal values in that area.
Referring to fig. 6, a flowchart of a method for determining a target infarct size according to an exemplary embodiment of the present application may include the steps of:
in step 601, a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion is determined.
In this step, the global threshold T of the DWI signal global Refers to the gray average value M of normal brain parenchyma global . Since the region of normal brain parenchyma cannot be determined before the lesion is not determined, a global threshold T for estimating DWI signals is proposed in the disclosure global The method of (1):
first, a second threshold T of diffusion weighted imaging signals of the brain parenchymal tissue part is obtained from the magnetic resonance image air Second threshold T air Obtained by performing a maximum inter-class variance processing on the magnetic resonance image.
It should be noted that, in the case where the first threshold value described above is also obtained by using the maximum inter-class variance method, the second threshold value may be equal to the first threshold value.
Next, by performing maximum inter-class variance processing on the brain parenchymal tissue portion twice, low threshold T of DWI signal is obtained respectively low And a high threshold T high 。
Finally, according to the second threshold T air And a low threshold T low And a high threshold T high Determining a global threshold T global 。
For example, the global threshold T may be determined according to the following numerical relationship global : determining that the global threshold is a 2-fold second threshold if the 2-fold second threshold is between the low threshold and the high threshold; otherwise, the global threshold is determined as the one of the low threshold and the high threshold that is closer to a second threshold that is 2 times the distance.
I.e. if T low <2T air <T high Will 2*T air As T global ；
Otherwise, take T low And T is high Among them, distance 2*T air The closer one, T global 。
In step 602, an average of diffusion weighted imaging signals of the candidate connected regions and an average of diffusion weighted imaging signals of a neighborhood tissue of the candidate connected regions are determined.
In this step, determining the average value of the DWI signals of the candidate connected regions means determining the average value of the DWI signals of each connected region (sub-region) in the candidate connected regions, that is, the gray average value M of each connected region core The method comprises the steps of carrying out a first treatment on the surface of the Determining the average value of DWI signals of the neighborhood tissue of the candidate connected region refers to determining the average value of DWI signals of the domain tissue of each connected region (sub-region), namely the gray average value M of the neighborhood tissue of each connected region local 。
In step 603, a region in which the average value of the diffusion weighted imaging signals and the average signal value or the global threshold of the diffusion weighted imaging of the field tissue satisfy a set proportional relationship is determined as a target infarct focus region.
According to the ratio of the gray average value of each connected domain to the gray average value of the domain tissue, or the ratio of the gray average value of each connected domain to the gray average value of the normal brain parenchyma, the target infarct area can be determined.
In this step, the infarct focus area is determined not only according to the level of the DWI signal value in the candidate connected area, but also according to the relationship with the neighborhood tissue DWI signal or according to the relationship with the global threshold.
For example, M in the candidate communication area core ≧0.9×M globa l, or M core ≧1.2×M local Is determined as a target infarct range region; the other parts are filtered out, and finally only the region determined as the infarct focus remains in the magnetic resonance image.
It will be appreciated by those skilled in the art that the numerical values in the above proportional relationships are merely examples, and the present disclosure is not limited to the specific numerical values in the proportional relationships.
In this embodiment, by screening candidate areas of infarct with the combination of the ratio of DWI to ADC and the ADC threshold, and further determining the areas of infarct according to the DWI value, detection of infarct in acute and hyperacute phases can be performed, and the areas of infarct and tumor can be distinguished from those of infarct with high DWI value and low ADC value as well.
The execution order of the steps in the flowcharts shown in fig. 1 and 6 is not limited to the order in the flowcharts. Furthermore, the descriptions of the individual steps may be implemented in the form of software, hardware, or a combination thereof, for example, those skilled in the art may implement them in the form of software code, or may be computer-executable instructions capable of implementing the logic functions corresponding to the steps. When implemented in software, the executable instructions may be stored in memory and executed by a processor in the system.
Corresponding to the foregoing embodiments of the infarct size detection method, embodiments of the infarct size detection apparatus, image detection device, and computer-readable storage medium are also provided.
Referring to fig. 7, a block diagram of an embodiment of an infarct size detection device according to the present application may include: a first obtaining unit 710, a second obtaining unit 720, a third obtaining unit 730, a first determining unit 740, and a second determining unit 750.
Wherein the first obtaining unit 710 is configured to obtain a brain parenchymal tissue part in the magnetic resonance image;
a second obtaining unit 720 for obtaining an infarct focus candidate region from the brain parenchyma tissue section according to a set surface diffusion coefficient threshold value;
a third obtaining unit 730 for obtaining an infarct focus confirmation area in which a ratio of the diffusion weighted imaging signal to the surface diffusion coefficient is higher than a set value in the brain parenchymal tissue portion;
a first determining unit 740 for determining a candidate communication area, which is in communication with the infarct focus confirmation area, among the infarct focus candidate areas;
a second determining unit 750, configured to determine a target infarct focus area according to diffusion weighted imaging signal values in the candidate communication areas.
In an alternative embodiment, the first obtaining unit 710 is specifically configured to:
obtaining a first threshold value of diffusion weighted imaging signals in a magnetic resonance image;
a region in the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
In an alternative embodiment, the first determining unit 740 is specifically configured to:
performing binarization treatment on the candidate infarct range area to obtain a connected domain in the candidate infarct range area;
performing binarization treatment on the infarct focus confirmation area to obtain a connected domain in the infarct focus confirmation area;
and determining a candidate connected region which has an intersection with the connected region of the infarct focus candidate region in the connected region of the infarct focus candidate region.
In an alternative embodiment, the second determining unit 750 is specifically configured to:
determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion;
determining an average value of diffusion weighted imaging signals of the candidate connected domain and an average value of diffusion weighted imaging signals of a neighborhood tissue of the candidate connected domain;
and determining the communication area, of the candidate communication areas, in which the average value of diffusion weighted imaging signals and the average signal value or the global threshold value of diffusion weighted imaging of the regional tissue meet a set proportion relation, as a target infarct focus area.
In an alternative embodiment, the second determining unit 750, when used for determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue part, is specifically used for:
obtaining a second threshold value of diffusion weighted imaging signals of the brain parenchymal tissue part in the magnetic resonance image, wherein the second threshold value is obtained by carrying out maximum inter-class variance processing on the magnetic resonance image;
obtaining a low threshold and a high threshold of a diffusion weighted imaging signal respectively by carrying out twice maximum inter-class variance processing on the brain parenchymal tissue part;
and determining the global threshold according to the numerical relation between the second threshold and the low threshold and the high threshold.
Referring to fig. 8, a schematic diagram of an embodiment of an image detection apparatus of the present application may include: a memory 820, a processor 830, and an external interface 840 connected through an internal bus 810.
Wherein the external interface 840 is configured to acquire a magnetic resonance image;
a memory 820 for storing machine-readable instructions corresponding to the infarct focus area detection logic;
a processor 830 for reading the machine readable instructions on the memory 820 and performing the infarct zone detection method as described above.
The present application also proposes a computer-readable storage medium having stored thereon a program that is executed by a processor to perform the infarct focus area detection method as described above.
In embodiments of the present application, the computer-readable storage medium may take many forms, for example, in different examples, the machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof. In particular, the computer readable medium may also be paper or other suitable medium capable of printing a program. Using these media, the programs may be electronically captured (e.g., optically scanned), compiled, interpreted, and otherwise processed in a suitable manner, and then stored in a computer medium.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A method for detecting an infarct size, comprising:
obtaining a brain parenchymal tissue portion in the magnetic resonance image;
obtaining an infarct focus candidate region from the brain parenchymal tissue portion according to a set surface diffusion coefficient threshold;
obtaining an infarct focus confirmation area in which the ratio of the diffusion weighted imaging signal to the surface diffusion coefficient is higher than a set value in the brain parenchymal tissue part;
determining a candidate communication region which is communicated with the infarct focus confirmation region in the infarct focus candidate region;
determining a target infarct focus region according to the diffusion weighted imaging signal values in the candidate connected regions, comprising: determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion; determining an average value of diffusion weighted imaging signals of the candidate connected regions and an average value of diffusion weighted imaging signals of neighborhood tissues of the candidate connected regions; and determining the area, of the candidate communication areas, in which the average value of the diffusion weighted imaging signals and the average signal value or the global threshold value of diffusion weighted imaging of the regional tissue meet a set proportion relation, as a target infarct focus area.
2. The method of claim 1, wherein obtaining a brain parenchymal tissue portion in a magnetic resonance image comprises:
obtaining a first threshold value of diffusion weighted imaging signals in a magnetic resonance image;
a region in the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
3. The method according to claim 1, wherein determining a candidate communication region, among the infarct focus candidate regions, that communicates with the infarct focus confirmation region, comprises:
performing binarization treatment on the candidate infarct range area to obtain a connected domain in the candidate infarct range area;
performing binarization treatment on the infarct focus confirmation area to obtain a connected domain in the infarct focus confirmation area;
and determining a candidate connected region which has an intersection with the connected region of the infarct focus candidate region in the connected region of the infarct focus candidate region.
4. The method of claim 1, wherein determining a global threshold for diffusion weighted imaging signals in the brain parenchymal tissue portion comprises:
obtaining a second threshold value of diffusion weighted imaging signals of the brain parenchymal tissue part in the magnetic resonance image, wherein the second threshold value is obtained by carrying out maximum inter-class variance processing on the magnetic resonance image;
obtaining a low threshold and a high threshold of a diffusion weighted imaging signal respectively by carrying out twice maximum inter-class variance processing on the brain parenchymal tissue part;
and determining the global threshold according to the numerical relation between the second threshold and the low threshold and the high threshold.
5. An infarct size detection device, comprising:
a first obtaining unit for obtaining a brain parenchymal tissue part in the magnetic resonance image;
a second obtaining unit for obtaining an infarct focus candidate region from the brain parenchymal tissue section according to a set surface diffusion coefficient threshold value;
a third obtaining unit for obtaining an infarct focus confirmation area in which a ratio of the diffusion weighted imaging signal to a surface diffusion coefficient is higher than a set value in the brain parenchymal tissue portion;
a first determination unit configured to determine a candidate communication area, among the infarct focus candidate areas, that communicates with the infarct focus confirmation area;
a second determining unit, configured to determine a target infarct focus area according to the diffusion weighted imaging signal values in the candidate communication area;
the second determining unit is specifically configured to:
determining a global threshold of diffusion weighted imaging signals in the brain parenchymal tissue portion;
determining an average value of diffusion weighted imaging signals of the candidate connected domain and an average value of diffusion weighted imaging signals of a neighborhood tissue of the candidate connected domain;
and determining the communication area, of the candidate communication areas, in which the average value of diffusion weighted imaging signals and the average signal value or the global threshold value of diffusion weighted imaging of the regional tissue meet a set proportion relation, as a target infarct focus area.
6. The apparatus according to claim 5, wherein the first obtaining unit is specifically configured to:
obtaining a first threshold value of diffusion weighted imaging signals in a magnetic resonance image;
a region in the magnetic resonance image where the diffusion weighted imaging signal is above a first threshold of the weighted imaging signal is determined as a brain parenchymal tissue portion.
7. An image detection apparatus, characterized by comprising: an internal bus, and a memory, a processor and an external interface connected through the internal bus; wherein, the liquid crystal display device comprises a liquid crystal display device,
the external interface is used for acquiring a magnetic resonance image;
the memory is used for storing machine-readable instructions corresponding to the detection logic of the infarct focus area;
the processor being configured to read the machine readable instructions on the memory and perform the method of any of claims 1-4.
8. A computer readable storage medium having a program stored thereon, characterized in that the program is executed by a processor for performing the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553962.2A CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553962.2A CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298832A CN110298832A (en) | 2019-10-01 |
| CN110298832B true CN110298832B (en) | 2023-05-02 |
Family
ID=68028791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910553962.2A Active CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298832B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127428A (en) * | 2019-12-24 | 2020-05-08 | 强联智创（北京）科技有限公司 | Method and system for extracting target region based on brain image data |
| CN115578554B (en) * | 2021-06-21 | 2024-02-02 | 数坤(上海)医疗科技有限公司 | Vascular focus identification method, device, electronic equipment and readable storage medium |
| CN115205294B (en) * | 2022-09-16 | 2022-11-22 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104510469A (en) * | 2013-09-26 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristic based on magnetic resonance diffusion-weighted image |
| CN104510470A (en) * | 2013-09-29 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristics based on diffusion-weighted magnetic resonance imaging |
| CN107301645A (en) * | 2017-06-20 | 2017-10-27 | 上海联影医疗科技有限公司 | A kind of data processing method and device |
| CN107427255A (en) * | 2015-03-12 | 2017-12-01 | 财团法人峨山社会福祉财团 | The method that the generation time point of infarct area is estimated based on brain image |
| CN108122221A (en) * | 2016-11-29 | 2018-06-05 | 中国科学院深圳先进技术研究院 | The dividing method and device of diffusion-weighted imaging image midbrain ischemic area |
-
2019
- 2019-06-25 CN CN201910553962.2A patent/CN110298832B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104510469A (en) * | 2013-09-26 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristic based on magnetic resonance diffusion-weighted image |
| CN104510470A (en) * | 2013-09-29 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristics based on diffusion-weighted magnetic resonance imaging |
| CN107427255A (en) * | 2015-03-12 | 2017-12-01 | 财团法人峨山社会福祉财团 | The method that the generation time point of infarct area is estimated based on brain image |
| CN108122221A (en) * | 2016-11-29 | 2018-06-05 | 中国科学院深圳先进技术研究院 | The dividing method and device of diffusion-weighted imaging image midbrain ischemic area |
| CN107301645A (en) * | 2017-06-20 | 2017-10-27 | 上海联影医疗科技有限公司 | A kind of data processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| Apparent diffusion coefficient threshold for delineation of ischemic core;Archana Purushotham et al;《International Journal of Stroke》;20150430;全文 * |
| DWI与ADC在早期脑梗死中的诊断价值;徐天同;《现代中西医结合杂志》;20121031;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298832A (en) | 2019-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298832B (en) | Infarct range area detection method, device, storage medium and equipment | |
| Kuijf et al. | Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform | |
| US11727574B2 (en) | Methods, apparatuses, and systems for creating 3-dimensional representations exhibiting geometric and surface characteristics of brain lesions | |
| US6366797B1 (en) | Method and system for brain volume analysis | |
| JP5200101B2 (en) | Detection of hemorrhagic stroke in CT image data | |
| Kim et al. | Automatic hippocampal segmentation in temporal lobe epilepsy: impact of developmental abnormalities | |
| EP2130497A1 (en) | Anatomical feature extraction from an ultrasound liver image | |
| Patel et al. | The value of MR textural analysis in prostate cancer | |
| Chesebro et al. | Automated detection of cerebral microbleeds on T2*-weighted MRI | |
| US20100322495A1 (en) | Medical imaging system | |
| WO2005002444A1 (en) | Method and apparatus for extracting third ventricle information | |
| JP2009034517A (en) | Abnormal tissue pattern detection apparatus, method and program | |
| WO2013086026A1 (en) | System and method of automatically detecting tissue abnormalities | |
| D’Souza et al. | Fiber-tract localized diffusion coefficients highlight patterns of white matter disruption induced by proximity to glioma | |
| Eloyan et al. | Health effects of lesion localization in multiple sclerosis: spatial registration and confounding adjustment | |
| Avadiappan et al. | A fully automated method for segmenting arteries and quantifying vessel radii on magnetic resonance angiography images of varying projection thickness | |
| KR102258902B1 (en) | Method and system for predicting isocitrate dehydrogenase (idh) mutation using recurrent neural network | |
| KR101590483B1 (en) | Method for processing image segmentation using Morphological operation | |
| Weizman et al. | Automatic segmentation and components classification of optic pathway gliomas in MRI | |
| Yokoyama et al. | Development of an automated method for the detection of chronic lacunar infarct regions in brain MR images | |
| Forkert et al. | Automatic brain segmentation in time-of-flight MRA images | |
| Jodas et al. | Lumen segmentation in magnetic resonance images of the carotid artery | |
| CN110859622B (en) | Imaging method, imaging device and nuclear magnetic system | |
| JP2019195426A (en) | Medical image processing apparatus, method, and program | |
| US20200013171A1 (en) | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |