CN113256705A - Processing method, display method and processing device of craniocerebral image - Google Patents
Processing method, display method and processing device of craniocerebral image Download PDFInfo
- Publication number
- CN113256705A CN113256705A CN202110309317.3A CN202110309317A CN113256705A CN 113256705 A CN113256705 A CN 113256705A CN 202110309317 A CN202110309317 A CN 202110309317A CN 113256705 A CN113256705 A CN 113256705A
- Authority
- CN
- China
- Prior art keywords
- midline
- craniocerebral
- relative
- offset
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 title claims abstract description 18
- 238000003672 processing method Methods 0.000 title abstract description 8
- 210000004556 brain Anatomy 0.000 claims abstract description 52
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 208000014644 Brain disease Diseases 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 208000004020 Brain Abscess Diseases 0.000 description 1
- 208000003174 Brain Neoplasms Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000029028 brain injury Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Abstract
The invention discloses a processing method, a display method and a processing device of a craniocerebral image. The processing method comprises the following steps: acquiring a first central line and a second central line of a plurality of frames of craniocerebral images; and judging whether the craniocerebral midline deviates or not according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline. According to the technical scheme, the first midline and the second midline can be displayed on the brain image, whether the brain midline deviates or not is judged according to the first midline and the second midline, and corresponding display is carried out, so that film reading by doctors is facilitated, and the diagnosis efficiency of the brain diseases is improved.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a processing method, a display method and a processing device of a craniocerebral image.
Background
Whether the craniocerebral midline is deviated or not is important diagnosis information, whether extrusion and occupation effects exist in the craniocerebral can be effectively reflected, and whether diseases such as brain injury, stroke, brain tumor, abscess and the like exist or not can be diagnosed by judging the craniocerebral midline deviation. Namely, the judgment of the deviation of the craniocerebral midline is beneficial to helping doctors to judge whether the brain is damaged.
Currently, the judgment of the craniocerebral midline offset is generally determined by a doctor manually measuring the midline offset distance. However, when the brain image is shot, the posture of the patient may not be standard, and the acquired brain image is not the brain image of the standard position, in this case, it is difficult for the doctor to determine the distance of the midline offset by the manual measurement, and even if the distance of the craniocerebral midline offset is measured by the manual measurement, the error is easy to occur, and the efficiency is low by the manual measurement. Thus, determining the craniocerebral midline offset using existing methods is less accurate and less efficient.
Because the conventional film reading software only can provide the functions of amplifying and viewing the craniocerebral image, but has single functions in information extraction (such as determining whether the craniocerebral midline deviates) and display in the craniocerebral image, how to provide more abundant craniocerebral information and a better presentation mode to help doctors to make diagnosis quickly becomes one of the problems to be solved in the field.
Disclosure of Invention
The invention provides a display method, a processing method and a device of a brain image, which can display an actual central line and a theoretical central line on the brain image and prompt whether the brain central line deviates or not, and are convenient for a doctor to read and diagnose.
The invention provides a method for processing a craniocerebral image, which comprises the following steps:
acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
and judging whether the craniocerebral midline deviates or not according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
Optionally, the method further includes:
determining a maximum offset layer based on the first and second centerlines;
and on the maximum offset layer, judging whether the craniocerebral midline is offset or not according to the offset position of the second midline relative to the first midline and/or the offset distance of the second midline relative to the first midline.
Optionally, the first midline and the second midline of the obtained multiple frames of craniocerebral images are obtained according to a pre-trained image recognition neural network model, and the image recognition neural network model is obtained by training a large number of craniocerebral images marked with the first midline and the second midline.
Optionally, the determining a maximum offset layer based on the first middle line and the second middle line includes:
and calculating the offset distance of the second midline of each frame of the brain image relative to the first midline, and taking the frame with the maximum offset distance as a maximum offset layer.
Optionally, the determining whether the craniocerebral midline deviates according to the position of the second midline deviating from the first midline includes:
and acquiring the maximum offset position relative to the first midline in the second midline, and judging that the craniocerebral midline is offset when the vertical projection of the maximum offset position on the first midline is positioned in a preset range of the first midline.
Optionally, the determining whether the craniocerebral midline deviates according to the distance that the second midline deviates from the first midline includes:
determining a first offset line segment of which the offset degree of a second midline relative to a first midline in the multi-frame brain images is greater than a first threshold value;
and when the length of the first deviation line segment is greater than a preset value, judging that the craniocerebral midline deviates.
Optionally, when the length of a first offset line segment of N continuous frames of the brain images is greater than a preset value, it is determined that the brain midline has offset, where N is a natural number greater than or equal to 3.
Optionally, the determining whether the craniocerebral midline deviates according to the distance that the second midline deviates from the first midline includes:
and when the deviation degree of a second central line of the continuous M frames of brain images relative to the first central line is greater than a second threshold value and the brain images comprise focuses, judging that the brain central line deviates, wherein M is a natural number greater than or equal to 2.
The invention also discloses a display method of the craniocerebral image, which comprises the following steps:
displaying a first midline and a second midline on the craniocerebral image;
when the craniocerebral midline is judged to be deviated, displaying a prompt of midline deviation;
the deviation of the craniocerebral midline is obtained by judging the position of the second midline deviated relative to the first midline and/or the distance of the second midline deviated relative to the first midline.
The invention also discloses a device for processing the craniocerebral image, which comprises:
the central line acquisition unit is used for acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
and the midline deviation determining unit is used for judging whether the craniocerebral midline deviates according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
According to the display method, the processing method and the device of the brain image, the first midline and the second midline in the brain image are automatically identified and displayed, whether the brain midline deviates or not is judged according to the first midline and the second midline, and a doctor is prompted when the brain midline deviates, so that the doctor can quickly know whether the brain midline deviates or not, and the accuracy and the efficiency of film reading are effectively improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of a method for processing a craniocerebral image according to an embodiment of the present invention;
FIG. 2 is a first midline schematic of a craniocerebral image of an embodiment of the present invention;
FIG. 3 is a second centerline view of a craniocerebral image of an embodiment of the present invention;
FIG. 4 is a schematic diagram of a first midline and a second midline of a craniocerebral image of an embodiment of the present invention;
FIG. 5 is a second centerline view of an anomaly in accordance with an embodiment of the present invention;
fig. 6 is a schematic flow chart of a method for displaying a brain image according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for processing a brain image according to an embodiment of the present invention. As shown in fig. 1, the method for processing a brain image includes:
s101, acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
s102, judging whether the craniocerebral midline deviates or not according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
And S1 is executed, and a first midline and a second midline of the multi-frame craniocerebral images are obtained. The brain image is a digital medical image such as an MR image and a CT image, and the CT image is taken as an example in this embodiment. The first midline can also be called a theoretical midline, that is, the first midline can approximately divide the cranium into symmetrical left and right brains, and the first midline is determined based on the upper and lower key points in the cranium image in the embodiment. Fig. 2 is a schematic diagram of a first centerline of a brain image according to an embodiment of the present invention, as shown in fig. 2, the first centerline 10 may be determined by two key points, such as the anteroposterior sinus 11 and the posterosuperior sagittal sinus 12, in this embodiment, the key points are obtained by a pre-trained first image recognition neural network model, in other embodiments, other key points may also be used, as long as anterior-posterior correspondence is satisfied and a connecting line can bisect the brain into key points of left and right brains, which can be used as key points for determining the first centerline 10. In the embodiment, the scheme that the connecting line of the upper key point and the lower key point is used as the first central line has a good left-right segmentation effect on the craniocerebral images of different types or on the craniocerebral images of non-standard positions.
Fig. 3 is a second midline schematic view of a craniocerebral image according to an embodiment of the invention. The second midline is also called as an actual midline and is drawn according to the actual condition of the cranium of the image reaction of the cranium of the patient. As shown in FIG. 3, due to the nature of the craniocerebral structure, the second midline 20 will appear as a slightly curved segment, even in a normal human. In this embodiment, the second centerline is obtained by a pre-trained second image recognition neural network model, which is obtained by training a large number of brain images identifying the actual centerline of the brain.
The first and second image recognition neural network models can be deep learning image recognition models constructed based on a Unet image network model, a Vnet image network model, an FCN image network model and the like. After training, the image recognition neural network model is required to be tested until the recognition result of the image recognition neural network model meets the preset requirement.
And S102, judging whether the craniocerebral midline deviates or not according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
In this embodiment, determining whether the craniocerebral midline deviates according to the position of the second midline deviating from the first midline includes: and acquiring the maximum offset position of the second midline relative to the first midline, and judging that the craniocerebral midline is offset when the vertical projection of the maximum offset position on the first midline is positioned in a preset range of the first midline. FIG. 4 is a schematic first midline and second midline of a craniocerebral image of an embodiment of the present invention. As shown in fig. 4, the maximum offset position a of the second central line 20 from the first central line 10 is a position of a farthest point from the first central line 10 among all points on the second central line 20, when a vertical projection point B of the maximum offset position a on the first central line 10 is located in a preset range of the first central line, in this embodiment, the preset range may be a middle range of the first central line, and when the projection point B is located in the middle range of the first central line, it is determined that the craniocerebral central line is offset. In this embodiment, the middle range of the first middle line may include 3/5 of the first middle line, and in other embodiments, 1/2 of the first middle line, 1/3 of the first middle line, and the like. In the present embodiment, the maximum offset position of the second central line with respect to the first central line is defined in a predetermined range of the first central line in the vertical projection of the first central line, such as the middle range, for the purpose of: generally speaking, when a craniocerebral midline is deviated, the vertical projection of the maximum deviation position of the second midline relative to the first midline on the first midline is located in the middle range of the first midline, and if the maximum deviation position is located at the two ends of the first midline, the probability is that the image recognition neural network model performs false recognition when recognizing the second midline, and therefore the false recognition can be ignored.
In this embodiment, determining whether the craniocerebral midline deviates according to the distance that the second midline deviates from the first midline includes:
determining a first offset line segment of which the offset degree of a second midline relative to a first midline in the multi-frame brain images is greater than a first threshold value;
and when the length of the first deviation line segment is greater than a preset value, judging that the craniocerebral midline deviates.
As described above, because of the structural characteristics of the cranium, even in normal persons, the second midline is a slightly curved line segment, and therefore it cannot be said that a point on the second midline does not overlap the first midline or the cranium midline is offset. In this embodiment, a second median line is considered to be offset from a first median line at a location only when a point on the second median line is more than a certain distance from the first median line. Therefore, in this embodiment, a portion of the second central line, which is shifted from the first central line by more than a first threshold value, is used as the first shift line segment, and the first threshold value may be any value of more than 6mm and less than 10 mm.
After the first deviation line segment on the second midline is determined by the method, the first deviation line segment is compared with a preset value to judge whether the craniocerebral midline deviates. In this embodiment, in order to reduce the calculation amount, the length of the perpendicular projection of the first offset line segment on the first centerline may be used as the length of the first offset line segment, and the length of the first offset line segment is compared with the length of the first centerline, and when the length of the first offset line segment is greater than a preset length (preset value), the craniocerebral centerline is considered to be offset. The preset length may be 1/6 of the first middle line length in this embodiment, in other embodiments, 1/7 or 1/5 of the first middle line length, or a fixed length, such as: 2cm, 3cm, etc. In this embodiment, the purpose of limiting the length of the first offset line segment to be greater than the preset value is that, as shown in fig. 5, when the length of the first offset line segment is short, it is highly probable that the image recognition neural network model performs misrecognition in recognizing the second central line, and therefore, the misrecognition can be ignored. In other embodiments, the length of the first offset line segment may be directly calculated and compared with a preset value.
In order to further improve the reliability and accuracy of the determination result, in this embodiment, it may be further determined whether the length of the first offset line segment of the N consecutive frames of the brain images is greater than a preset value, and only when the length of the first offset line segment of the N consecutive frames of the brain images is greater than the preset value, it is determined that the craniocerebral midline is offset, where N is a natural number greater than or equal to 3. In the embodiment, the length of the first offset line segment in the multi-frame brain image is judged, so that the problem of misjudgment caused by errors of the image recognition neural network model in a certain frame of image can be effectively solved.
In another embodiment, determining whether the craniocerebral midline is offset based on the distance that the second midline is offset from the first midline comprises:
and when the deviation degree of a second central line of the continuous M frames of brain images relative to the first central line is greater than a second threshold value and the brain images comprise focuses, judging that the brain central line deviates, wherein M is a natural number greater than or equal to 2.
In general, when the shift of the craniocerebral midline occurs, it may be caused by the focus contained in the craniocerebral image, and when the focus is detected in the craniocerebral image, the shift of the second midline relative to the first midline is likely to be the midline shift caused by the focus, in this case, compared with the foregoing embodiment, when determining whether the craniocerebral midline has a shift, the requirement for the shift degree of the second midline relative to the first midline may not be very high, and therefore, in this embodiment, the second threshold may be any value greater than 3mm and less than 5mm, and the number of the craniocerebral images in which the shift degree of the second midline relative to the first midline is greater than the second threshold may be less than that in the foregoing embodiment, as long as the requirement that the shift degree of the second midline relative to the first midline in at least two consecutive craniocerebral images is greater than the second threshold is satisfied in this embodiment.
In another embodiment, the method for processing a brain image further includes:
determining a maximum offset layer based on the first and second centerlines;
and on the maximum offset layer, judging whether the craniocerebral midline is offset or not according to the offset position of the second midline relative to the first midline and/or the offset distance of the second midline relative to the first midline.
Determining the maximum shift layer according to the first middle line and the second middle line may be: and calculating the offset distance of the second midline of each frame of the brain image relative to the first midline, and taking the frame with the maximum offset distance as a maximum offset layer. Or calculating the area between the first midline and the second midline of each frame of the brain image, and taking the frame with the maximum area as the maximum shift layer. With continued reference to fig. 4, the offset distance of the second central line 20 with respect to the first central line 10 may be the distance between the point a farthest from the first central line 10 among all points of the second central line 20 and the first central line 10 (line segment AB in fig. 4). The area between the first and second central lines 10 and 20 refers to a region surrounded by the first and second central lines 10 and 20 (white region in fig. 5). After the maximum deviation layer is determined, whether the craniocerebral midline deviation occurs or not is determined on the maximum deviation layer according to the position of the second midline deviated relative to the first midline and/or the distance of the second midline deviated relative to the first midline, and how to judge the craniocerebral midline deviation specifically, which has been described in detail above, is not repeated herein. By judging whether the craniocerebral midline deviates only on the maximum deviation layer, the computing resource of the device is saved to a certain extent, and the judgment efficiency is improved.
It should be noted that, in this embodiment, whether the craniocerebral midline deviates or not is determined, and whether the craniocerebral midline deviates or not may be determined simultaneously according to the position of the second midline deviating from the first midline and the distance of the second midline deviating from the first midline. That is, the foregoing various judgment conditions may be arbitrarily combined to determine whether the craniocerebral midline is deviated.
Based on the same inventive concept, the embodiment of the invention also discloses a display method of the craniocerebral image. Fig. 6 is a schematic flow chart of a method for displaying a brain image according to an embodiment of the present invention. As shown in fig. 6, the method includes:
s201, displaying a first midline and a second midline on a craniocerebral image;
s202, when the deviation of the craniocerebral midline is judged, the prompt of the midline deviation is displayed,
the deviation of the craniocerebral midline is obtained by judging the position of the second midline deviated relative to the first midline and/or the distance of the second midline deviated relative to the first midline.
S201 is performed, displaying a first midline and a second midline on the brain image. The craniocerebral image is a cross-sectional view of a craniocerebral image such as an MR image, a CT image and the like, and when the first middle line and the second middle line are displayed, the first middle line and the second middle line can be displayed on the cross section of each layer of the craniocerebral image, or the first middle line and the second middle line can be displayed only on the maximum offset layer or a specified plurality of layers.
And S202, when the craniocerebral midline is deviated, displaying a prompt of midline deviation. The prompt of midline deviation can display the line segment deviated on the second midline in a thickening, highlighting and other modes, and can also display the deviation of the craniocerebral midline in the craniocerebral image through text prompt.
Based on the same inventive concept, the invention also discloses a processing device of the craniocerebral image, which comprises:
the central line acquisition unit is used for acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
and the midline deviation determining unit is used for judging whether the craniocerebral midline deviates according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
Based on the same technical concept, the invention also discloses a computer device comprising at least one processor and at least one memory, wherein the memory stores a computer program, and when the program is executed by the processor, the processor can execute the processing method of the brain image.
Based on the same technical concept, the invention also discloses a computer readable storage medium, wherein when the instructions in the storage medium are executed by a processor in the device, the device can execute the method for processing the brain images.
It should be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for processing a craniocerebral image, comprising:
acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
and judging whether the craniocerebral midline deviates or not according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
2. The method of claim 1, further comprising:
determining a maximum offset layer based on the first and second centerlines;
and on the maximum offset layer, judging whether the craniocerebral midline is offset or not according to the offset position of the second midline relative to the first midline and/or the offset distance of the second midline relative to the first midline.
3. The method of claim 1,
the first midline and the second midline of the obtained multi-frame craniocerebral images are obtained according to a pre-trained image recognition neural network model, and the image recognition neural network model is obtained by training a large number of craniocerebral images marked with the first midline and the second midline.
4. The method of claim 2, wherein determining a maximum offset layer based on the first and second centerlines comprises:
and calculating the offset distance of the second midline of each frame of the brain image relative to the first midline, and taking the frame with the maximum offset distance as a maximum offset layer.
5. The method of claim 1, wherein determining whether the craniocerebral midline has shifted based on the position of the second midline relative to the first midline comprises:
and acquiring the maximum offset position of the second midline relative to the first midline, and judging that the craniocerebral midline is offset when the vertical projection of the maximum offset position on the first midline is positioned in a preset range of the first midline.
6. The method of claim 1, wherein determining whether the craniocerebral midline has shifted based on the distance that the second midline has shifted relative to the first midline comprises:
determining a first offset line segment of which the offset degree of a second midline relative to a first midline in the multi-frame brain images is greater than a first threshold value;
and when the length of the first deviation line segment is greater than a preset value, judging that the craniocerebral midline deviates.
7. The method of claim 6,
and when the length of a first offset line segment of the continuous N frames of the brain images is greater than a preset value, judging that the middle line of the brain deviates, wherein N is a natural number which is greater than or equal to 3.
8. The method of claim 1, wherein determining whether the craniocerebral midline has shifted based on the distance that the second midline has shifted relative to the first midline comprises:
and when the deviation degree of a second central line of the continuous M frames of brain images relative to the first central line is greater than a second threshold value and the brain images comprise focuses, judging that the brain central line deviates, wherein M is a natural number greater than or equal to 2.
9. A method for displaying a craniocerebral image, comprising:
displaying a first midline and a second midline on the craniocerebral image;
when the craniocerebral midline is judged to be deviated, displaying a prompt of midline deviation;
the deviation of the craniocerebral midline is obtained by judging the position of the second midline deviated relative to the first midline and/or the distance of the second midline deviated relative to the first midline.
10. A device for processing a craniocerebral image, comprising:
the central line acquisition unit is used for acquiring a first central line and a second central line of a plurality of frames of craniocerebral images;
and the midline deviation determining unit is used for judging whether the craniocerebral midline deviates according to the position of the second midline deviating relative to the first midline and/or the distance of the second midline deviating relative to the first midline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110309317.3A CN113256705A (en) | 2021-03-23 | 2021-03-23 | Processing method, display method and processing device of craniocerebral image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110309317.3A CN113256705A (en) | 2021-03-23 | 2021-03-23 | Processing method, display method and processing device of craniocerebral image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113256705A true CN113256705A (en) | 2021-08-13 |
Family
ID=77181137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110309317.3A Pending CN113256705A (en) | 2021-03-23 | 2021-03-23 | Processing method, display method and processing device of craniocerebral image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256705A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120184840A1 (en) * | 2009-04-07 | 2012-07-19 | Kayvan Najarian | Automated Measurement of Brain Injury Indices Using Brain CT Images, Injury Data, and Machine Learning |
| CN108962380A (en) * | 2017-05-27 | 2018-12-07 | 周仁海 | The device and method of interpretation brain phantom and the device of offer brain status information |
| US20190033415A1 (en) * | 2016-11-22 | 2019-01-31 | Hyperfine Research, Inc. | Systems and methods for automated detection in magnetic resonance images |
| CN110473172A (en) * | 2019-07-24 | 2019-11-19 | 上海联影智能医疗科技有限公司 | Medical image anatomical midline determines method, computer equipment and storage medium |
| CN110956636A (en) * | 2019-11-28 | 2020-04-03 | 北京推想科技有限公司 | Image processing method and device |
| CN111583212A (en) * | 2020-04-29 | 2020-08-25 | 上海杏脉信息科技有限公司 | Method and device for determining brain midline shift |
-
2021
- 2021-03-23 CN CN202110309317.3A patent/CN113256705A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120184840A1 (en) * | 2009-04-07 | 2012-07-19 | Kayvan Najarian | Automated Measurement of Brain Injury Indices Using Brain CT Images, Injury Data, and Machine Learning |
| US20190033415A1 (en) * | 2016-11-22 | 2019-01-31 | Hyperfine Research, Inc. | Systems and methods for automated detection in magnetic resonance images |
| CN108962380A (en) * | 2017-05-27 | 2018-12-07 | 周仁海 | The device and method of interpretation brain phantom and the device of offer brain status information |
| CN110473172A (en) * | 2019-07-24 | 2019-11-19 | 上海联影智能医疗科技有限公司 | Medical image anatomical midline determines method, computer equipment and storage medium |
| CN110956636A (en) * | 2019-11-28 | 2020-04-03 | 北京推想科技有限公司 | Image processing method and device |
| CN111583212A (en) * | 2020-04-29 | 2020-08-25 | 上海杏脉信息科技有限公司 | Method and device for determining brain midline shift |
Non-Patent Citations (1)
| Title |
|---|
| 林周璋编: "《超声诊断与鉴别诊断 A型示波法》", 30 October 1979 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7653227B2 (en) | Hierarchical modeling in medical abnormality detection | |
| CN110796613B (en) | Automatic identification method and device for image artifacts | |
| CN109924956B (en) | Method and device for measuring morphological parameters of intracranial aneurysm image | |
| US9123101B2 (en) | Automatic quantification of asymmetry | |
| CN111368586B (en) | Ultrasonic imaging method and system | |
| US20220354466A1 (en) | Automated Maternal and Prenatal Health Diagnostics from Ultrasound Blind Sweep Video Sequences | |
| KR20190105180A (en) | Apparatus for Lesion Diagnosis Based on Convolutional Neural Network and Method thereof | |
| CN110400299A (en) | A kind of method and device of lung's pleural effusion detection | |
| CN110782446A (en) | Method and device for determining volume of lung nodule | |
| US9117121B2 (en) | Detection of disease-related retinal nerve fiber layer thinning | |
| CN111738992B (en) | Method, device, electronic equipment and storage medium for extracting lung focus area | |
| US20210020304A1 (en) | Systems and methods for generating classifying and quantitative analysis reports of aneurysms from medical image data | |
| CN116312986A (en) | Three-dimensional medical image labeling method and device, electronic equipment and readable storage medium | |
| CN111583212B (en) | Method and device for determining brain midline shift | |
| US9436889B2 (en) | Image processing device, method, and program | |
| CN113298800A (en) | Processing method, device and equipment of CT angiography CTA source image | |
| CN113256705A (en) | Processing method, display method and processing device of craniocerebral image | |
| CN116452593B (en) | Method, device and system for constructing AI evaluation model of vascular cognitive disorder | |
| CN112419340A (en) | Generation method, application method and device of cerebrospinal fluid segmentation model | |
| CN111402218A (en) | Cerebral hemorrhage detection method and device | |
| EP4231311A1 (en) | Method and apparatus for providing information needed for dementia diagnosis | |
| CN111445443A (en) | Method and device for detecting early acute cerebral infarction | |
| CN113888663B (en) | Reconstruction model training method, anomaly detection method, device, equipment and medium | |
| CN115690556A (en) | Image recognition method and system based on multi-modal iconography characteristics | |
| CN114511556A (en) | Gastric mucosa bleeding risk early warning method and device and medical image processing equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |