CN112508941A - Three-dimensional ultrasonic scanning integrity detection method and device - Google Patents
Three-dimensional ultrasonic scanning integrity detection method and device Download PDFInfo
- Publication number
- CN112508941A CN112508941A CN202011556439.4A CN202011556439A CN112508941A CN 112508941 A CN112508941 A CN 112508941A CN 202011556439 A CN202011556439 A CN 202011556439A CN 112508941 A CN112508941 A CN 112508941A
- Authority
- CN
- China
- Prior art keywords
- integrity
- section
- dimensional ultrasonic
- scanning
- cross
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000002604 ultrasonography Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 239000000523 sample Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 210000000481 breast Anatomy 0.000 description 13
- 210000004907 gland Anatomy 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 208000030270 breast disease Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 238000013519 translation Methods 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
- G06T7/0002—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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G06T2207/10132—Ultrasound image
- G06T2207/10136—3D ultrasound image
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30068—Mammography; Breast
Abstract
The embodiment of the invention provides a method and a device for detecting the integrity of three-dimensional ultrasonic scanning, wherein the method comprises the following steps: acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning; cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image; acquiring a preset integrity artificial intelligence model, inputting section screenshots of a cross section and a sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model; and integrating the integrity detection results of the sectional screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result. By the adoption of the method, whether the current scanning is complete or not can be judged more quickly and efficiently, missing scanning is reduced quickly and efficiently, and scanning experience of a patient is improved.
Description
Technical Field
The invention relates to the technical field of medical instruments, in particular to a method and a device for detecting the integrity of three-dimensional ultrasonic scanning.
Background
The automatic breast ultrasonic imaging system is a new three-dimensional ultrasonic imaging technology, can realize the functions of whole breast scanning, three-dimensional reconstruction display of coronal plane images and the like, which are convenient to operate, and has good application prospect in diagnosis of breast diseases.
However, the breast three-dimensional ultrasonic imaging system changes the operation and scanning process familiar to the sonographer and the film reading diagnosis mode, requires training in the early stage and accumulation of a certain number of cases, and the result depends on a learning curve. Due to different doctors or different scanning and image reading technical levels, the condition of gland missing scanning can also occur by using the breast three-dimensional ultrasound, the condition can be reduced to a certain extent by image reading training of experienced doctors and image playback after scanning, but the method for replaying the scanned images after scanning is not efficient and has long time consumption, and the scanning experience of patients is reduced.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a method and a device for detecting the integrity of three-dimensional ultrasonic scanning.
The embodiment of the invention provides a three-dimensional ultrasonic scanning integrity detection method, which comprises the following steps:
acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning;
cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image;
acquiring a preset integrity artificial intelligence model, inputting the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model;
and integrating the integrity detection results of the section screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result.
In one embodiment, the method further comprises:
carrying out corresponding integrity judgment through section screenshots of the cross section and the sagittal plane, and obtaining scanning results of the cross section and the sagittal plane according to the integrity judgment;
and acquiring a threshold corresponding to the integrity artificial intelligence model, comparing the scanning result with the threshold, and detecting the integrity of the section screenshots of the cross section and the sagittal plane according to the comparison result.
In one embodiment, the method further comprises:
acquiring a three-dimensional ultrasonic image in historical data, and labeling the three-dimensional ultrasonic image;
performing data enhancement training on the three-dimensional ultrasonic image to obtain a corresponding DenseNet121 model;
and processing the DenseNet121 model by a preset parameter adjusting and optimizing method to obtain the integrity artificial intelligence model.
In one embodiment, the method further comprises:
the integrity artificial intelligence model comprises a transverse position model and a sagittal position model;
the detecting the integrity of the section screenshot through the integrity artificial intelligence model comprises the following steps:
and detecting the integrity of the screenshot of the cross section through the cross section model, and detecting the integrity of the screenshot of the sagittal section through the sagittal section model.
In one embodiment, the method further comprises:
preprocessing the section screenshot, wherein the preprocessing comprises the following steps: image cropping, image completion, pixel adjustment and pixel value normalization.
In one embodiment, the method further comprises:
and when the integrity detection result indicates that the incomplete screenshot does not exist in the section screenshot, controlling a scanning probe to scan the next position of the fixed position or ending the scanning.
In one embodiment, the method further comprises:
and when the integrity detection result is that an incomplete screenshot exists in the section screenshot, controlling a scanning probe to re-scan the corresponding part of the three-dimensional ultrasonic image in the fixed position.
The embodiment of the invention provides a three-dimensional ultrasonic scanning integrity detection device, which comprises:
the first acquisition module is used for acquiring a three-dimensional ultrasonic image of a fixed position obtained by scanning;
the cutting module is used for cutting the three-dimensional ultrasonic image to obtain section screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image;
the second acquisition module is used for acquiring a preset integrity artificial intelligence model, inputting the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model;
and the comprehensive module is used for synthesizing the integrity detection results of the section screenshots of the cross section and the sagittal plane and outputting the integrity detection result of the three-dimensional ultrasonic image according to the comprehensive result.
The embodiment of the invention provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the three-dimensional ultrasonic scanning integrity detection method.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the three-dimensional ultrasonic scanning integrity detection method described above.
The three-dimensional ultrasonic scanning integrity detection method and device provided by the embodiment of the invention are used for acquiring a three-dimensional ultrasonic image of a fixed position obtained by scanning; cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image; acquiring a preset integrity artificial intelligence model, inputting section screenshots at the edges of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model; and integrating the integrity detection results of the sectional screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result. Whether the current scanning is complete can be judged faster and more efficiently, missing scanning is reduced rapidly and efficiently, and scanning experience of a patient is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a three-dimensional ultrasonic scanning integrity detection method in an embodiment of the present invention;
FIG. 2 is a schematic diagram of scanning positions to be detected according to an embodiment of the present invention;
FIG. 3 is a flow chart of training of an integrity artificial intelligence model in an embodiment of the invention;
FIG. 4 is a flowchart of a three-dimensional ultrasonic scan integrity detection method according to another embodiment of the present invention;
FIG. 5 is a block diagram of a three-dimensional ultrasonic scanning integrity detection apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 three-dimensional ultrasonic scanning integrity detection method provided in an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a three-dimensional ultrasonic scanning integrity detection method, including:
and step S101, acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning.
Specifically, a three-dimensional ultrasonic image of the breast of the patient obtained through scanning by a related scanning instrument is acquired, wherein the three-dimensional ultrasonic image of the breast of the patient is a fixed-position three-dimensional ultrasonic image, and the fixed-position three-dimensional ultrasonic image refers to a three-dimensional ultrasonic image obtained through scanning in a single direction.
And S102, cutting the three-dimensional ultrasonic image to obtain a section screenshot of a cross section and a sagittal plane in the three-dimensional ultrasonic image.
Specifically, after a three-dimensional breast ultrasound image of a patient is acquired, image segmentation is performed on the three-dimensional breast ultrasound image according to an image processing device in a scanning workstation, a cut-plane screenshot in a specific direction after the segmentation is acquired, wherein the cut-plane screenshot generally refers to a screenshot on the edge of a cross-section and a sagittal plane, and when the image segmentation is performed, the three-dimensional breast ultrasound image can be segmented into a cross-section, a sagittal plane and a coronal plane, and a cross-section image and a sagittal plane image in the specific direction of a fixed orientation are processed (generally, images required to be scanned and tested for completeness are different according to different scanning directions), wherein a specific testing process can be as shown in fig. 2, and for the images in fig. 2, the R-LAT sagittal plane right side, the R-AP sagittal plane left side, the R-MED sagittal plane left side and the L-MED sagittal plane right side can be shown in fig. 2, The left and right L-AP sagittal and left L-LAT sagittal regions generally do not require a scan integrity check because the images of these locations would normally contain glands. Therefore, the image orientations for which scan integrity detection is required include the upper and lower lateral positions of each orientation, the left side of the R-LAT sagittal position, the right side of the R-MED sagittal position, the left side of the L-MED sagittal position, and the right side of the L-LAT sagittal position.
Further, the section screenshot can include a single section and a continuous section, the single section is directly subjected to subsequent processing, and for the continuous section, after the subsequent processing is respectively performed, the integrity detection is performed by performing arithmetic mean or weighted mean operation on the processed data.
And S103, acquiring a preset integrity artificial intelligence model, inputting the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model.
Specifically, a preset integrity artificial intelligence model is obtained, wherein the integrity artificial intelligence model may include a transverse section model and a sagittal section model, a transverse section screenshot and a sagittal section screenshot are input into the corresponding integrity artificial intelligence model, and integrity detection is performed through the integrity artificial intelligence model, wherein the judgment on the integrity refers to whether a gland appears in the screenshot at the edge of the transverse section and the sagittal section, when no gland exists in the screenshot, the scanning result is incomplete, and when no gland exists in the screenshot, the scanning result is complete.
The integrity detection can be that corresponding integrity judgment is carried out through section screenshots of the cross section and the sagittal plane, the section screenshots of the cross section and the sagittal plane are input into an integrity artificial intelligence model, a model prediction value of the section screenshots is obtained, then a threshold value corresponding to the integrity artificial intelligence model is obtained, the model prediction value is compared with the threshold value, and the integrity of the section screenshots of the cross section and the sagittal plane is detected according to a comparison result.
In addition, when the completeness is judged, the judgment can be carried out firstly by the edge image, when the gland exists in the edge image, the scanning result in the direction is considered to be incomplete, a plurality of section screenshots can be obtained in the direction for detection, and when the gland does not exist in the edge image, the scanning result in the direction can be considered to be complete.
In addition, before detecting the integrity of the sectional screenshot, the sectional screenshot may be subjected to a preprocessing step, including but not limited to adjustment of pixel pitch consistency of the cross-sectional or sagittal image, cropping or completing the image, pixel adjustment, pixel value normalization, and the like.
And step S104, integrating the integrity detection results of the section screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result.
Specifically, the completeness detection results of the section screenshots of the cross section and the sagittal plane are integrated, and the specific comprehensive result can be that when the section screenshots in all directions of the scanning direction are complete, the complete detection result of the breast three-dimensional ultrasound scanning direction image is output, and when the section screenshots in all directions are incomplete, the incomplete detection result of the three-dimensional ultrasound scanning direction image is output.
In addition, when the integrity detection result is that the incomplete screenshot does not exist in the section screenshot, the scanning probe is controlled to scan the next position of the fixed position, or the scanning is finished when the next position does not exist.
In addition, when the integrity detection result is that an incomplete screenshot exists in the section screenshot, the scanning probe is controlled to scan or add and scan the corresponding part of the three-dimensional ultrasonic image in the fixed direction.
The three-dimensional ultrasonic scanning integrity detection method provided by the embodiment of the invention comprises the steps of obtaining a three-dimensional ultrasonic image of a fixed position obtained by scanning; cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image; acquiring a preset integrity artificial intelligence model, inputting section screenshots of a cross section and a sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model; and integrating the integrity detection results of the sectional screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result. Whether the current scanning is complete can be judged faster and more efficiently, missing scanning is reduced rapidly and efficiently, and scanning experience of a patient is improved.
On the basis of the above embodiment, the three-dimensional ultrasonic scanning integrity detection method further includes:
acquiring a three-dimensional ultrasonic image in historical data, and labeling the three-dimensional ultrasonic image;
performing data enhancement training on the three-dimensional ultrasonic image to obtain a corresponding DenseNet121 model;
and processing the DenseNet121 model by a preset parameter adjusting and optimizing method to obtain the integrity artificial intelligence model.
In the embodiment of the present invention, a model training flowchart can be shown in fig. 3, and the steps in fig. 3 respectively obtain a transverse position model and a sagittal position model, wherein the training step of the preset integrity artificial intelligence model includes obtaining labeled training data (historical data, images of the upper side and the lower side of the transverse position of the breast three-dimensional ultrasound, and images of the left side and the right side of the sagittal position) to train the obtained DenseNet121 model, which includes but is not limited to the currently used model, and any deep learning classification model can be used. The training method includes but is not limited to image preprocessing, data enhancement, model training, parameter tuning optimization, loss function optimization and modification, transfer learning, domain self-adaptation and other methods. Further, the data enhancement step includes, but is not limited to, applying translation, rotation, flipping, random brightness, random contrast, blurring, contrast-limited adaptive histogram equalization (CLAHE), and the like to the image.
The embodiment of the invention obtains the integrity artificial intelligence model by training the historical data, and is used for detecting the integrity of the screenshot of the subsequent section.
In another embodiment, the three-dimensional ultrasonic scanning integrity detection method may be as shown in fig. 4, and includes:
the method comprises the steps of obtaining a breast three-dimensional ultrasonic image scanned by a doctor or a technician, obtaining a screenshot of the breast three-dimensional ultrasonic image in a specific direction according to a scanning direction, performing horizontal position image preprocessing (sagittal position image preprocessing), horizontal position model prediction (sagittal position model prediction), horizontal position output result postprocessing (sagittal position output result postprocessing), comprehensively prompting prediction results in two directions, finishing scanning when the scanning is complete, and rescanning or scanning when the scanning is incomplete.
Fig. 5 is a three-dimensional ultrasonic scanning integrity detection apparatus provided in an embodiment of the present invention, including: a first acquisition module 201, a second acquisition module 202, a calculation module 203, a detection module 204, and a compensation module 205, wherein:
the first acquiring module 201 is configured to acquire a three-dimensional ultrasonic image of a fixed position obtained by scanning.
The cutting module 202 is configured to cut the three-dimensional ultrasound image, and obtain a sectional screenshot of a cross section and a sagittal plane in the three-dimensional ultrasound image.
And the second obtaining module 203 is configured to obtain a preset integrity artificial intelligence model, input the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detect the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model.
And the integration module 204 is used for integrating the integrity detection results of the section screenshots of the cross section and the sagittal plane and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integration result.
In one embodiment, the apparatus may further comprise:
and the judging module is used for carrying out corresponding integrity judgment through the section screenshots of the cross section and the sagittal plane and obtaining the scanning results of the cross section and the sagittal plane according to the integrity judgment.
And the comparison module is used for acquiring a threshold corresponding to the integrity artificial intelligence model, comparing the scanning result with the threshold, and detecting the integrity of the section screenshots of the cross section and the sagittal plane according to the comparison result.
In one embodiment, the apparatus may further comprise:
and the third acquisition module is used for acquiring the three-dimensional ultrasonic image in the historical data and labeling the three-dimensional ultrasonic image.
And the training module is used for performing data enhancement training on the three-dimensional ultrasonic image to obtain a corresponding DenseNet121 model.
And the model processing module is used for processing the DenseNet121 model through a preset parameter adjusting and optimizing method to obtain the integrity artificial intelligence model.
In one embodiment, the apparatus may further comprise:
a preprocessing module, configured to perform a preprocessing step on the section screenshot, where the preprocessing step includes: image cropping, image completion, pixel adjustment and pixel value normalization.
In one embodiment, the apparatus may further comprise:
and the first control module is used for controlling the scanning probe to scan the next position of the fixed position or finish scanning when the integrity detection result indicates that the incomplete screenshot does not exist in the section screenshot.
In one embodiment, the apparatus may further comprise:
and the second control module is used for controlling the scanning probe to re-scan the corresponding part of the three-dimensional ultrasonic image in the fixed position when the integrity detection result indicates that the incomplete screenshot exists in the section screenshot.
For specific definition of the three-dimensional ultrasonic scanning integrity detection apparatus, reference may be made to the above definition of the three-dimensional ultrasonic scanning integrity detection method, which is not described herein again. The modules in the three-dimensional ultrasonic scanning integrity detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)301, a memory (memory)302, a communication Interface (Communications Interface)303 and a communication bus 304, wherein the processor 301, the memory 302 and the communication Interface 303 complete communication with each other through the communication bus 304. The processor 301 may call logic instructions in the memory 302 to perform the following method: acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning; cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image; acquiring a preset integrity artificial intelligence model, inputting section screenshots of a cross section and a sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model; and integrating the integrity detection results of the sectional screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result.
Furthermore, the logic instructions in the memory 302 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning; cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image; acquiring a preset integrity artificial intelligence model, inputting section screenshots of a cross section and a sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model; and integrating the integrity detection results of the sectional screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A three-dimensional ultrasonic scanning integrity detection method is characterized by comprising the following steps:
acquiring a three-dimensional ultrasonic image of a fixed direction obtained by scanning;
cutting the three-dimensional ultrasonic image to obtain sectional screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image;
acquiring a preset integrity artificial intelligence model, inputting the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model;
and integrating the integrity detection results of the section screenshots of the cross section and the sagittal plane, and outputting the integrity detection result of the three-dimensional ultrasonic image according to the integrated result.
2. The method for detecting the integrity of the three-dimensional ultrasonic scanning according to claim 1, wherein the detecting the integrity of the sectional screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model comprises:
carrying out corresponding integrity judgment through section screenshots of the cross section and the sagittal plane, and obtaining scanning results of the cross section and the sagittal plane according to the integrity judgment;
and acquiring a threshold corresponding to the integrity artificial intelligence model, comparing the scanning result with the threshold, and detecting the integrity of the section screenshots of the cross section and the sagittal plane according to the comparison result.
3. The three-dimensional ultrasonic scanning integrity detection method of claim 1, wherein the integrity artificial intelligence model comprises:
acquiring a three-dimensional ultrasonic image in historical data, and labeling the three-dimensional ultrasonic image;
performing data enhancement training on the three-dimensional ultrasonic image to obtain a corresponding DenseNet121 model;
and processing the DenseNet121 model by a preset parameter adjusting and optimizing method to obtain the integrity artificial intelligence model.
4. The three-dimensional ultrasonic scanning integrity detection method of claim 1, wherein obtaining a preset integrity artificial intelligence model comprises:
the integrity artificial intelligence model comprises a transverse position model and a sagittal position model;
the detecting the integrity of the section screenshot through the integrity artificial intelligence model comprises the following steps:
and detecting the integrity of the screenshot of the cross section through the cross section model, and detecting the integrity of the screenshot of the sagittal section through the sagittal section model.
5. The method for detecting the integrity of three-dimensional ultrasonic scanning according to claim 1, wherein before the detecting the integrity of the sectional screenshots of the transverse section and the sagittal plane by the integrity artificial intelligence model, the method further comprises:
preprocessing the section screenshot, wherein the preprocessing comprises the following steps: image cropping, image completion, pixel adjustment and pixel value normalization.
6. The three-dimensional ultrasonic scanning integrity detection method of claim 1, further comprising:
and when the integrity detection result indicates that the incomplete screenshot does not exist in the section screenshot, controlling a scanning probe to scan the next position of the fixed position or ending the scanning.
7. The three-dimensional ultrasonic scanning integrity detection method of claim 1, further comprising:
and when the integrity detection result is that an incomplete screenshot exists in the section screenshot, controlling a scanning probe to re-scan the corresponding part of the three-dimensional ultrasonic image in the fixed position.
8. A three-dimensional ultrasonic scanning integrity detection apparatus, the apparatus comprising:
the first acquisition module is used for acquiring a three-dimensional ultrasonic image of a fixed position obtained by scanning;
the cutting module is used for cutting the three-dimensional ultrasonic image to obtain section screenshots of a cross section and a sagittal plane in the three-dimensional ultrasonic image;
the second acquisition module is used for acquiring a preset integrity artificial intelligence model, inputting the section screenshots of the cross section and the sagittal plane into the integrity artificial intelligence model, and detecting the integrity of the section screenshots of the cross section and the sagittal plane through the integrity artificial intelligence model;
and the comprehensive module is used for synthesizing the integrity detection results of the section screenshots of the cross section and the sagittal plane and outputting the integrity detection result of the three-dimensional ultrasonic image according to the comprehensive result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the three-dimensional ultrasound scanning integrity detection method according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the three-dimensional ultrasound scan integrity detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011556439.4A CN112508941A (en) | 2020-12-25 | 2020-12-25 | Three-dimensional ultrasonic scanning integrity detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011556439.4A CN112508941A (en) | 2020-12-25 | 2020-12-25 | Three-dimensional ultrasonic scanning integrity detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112508941A true CN112508941A (en) | 2021-03-16 |
Family
ID=74921969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011556439.4A Pending CN112508941A (en) | 2020-12-25 | 2020-12-25 | Three-dimensional ultrasonic scanning integrity detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112508941A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113284145A (en) * | 2021-07-22 | 2021-08-20 | 杭州太美星程医药科技有限公司 | Image processing method and device, computer readable storage medium and electronic device |
| CN114376615A (en) * | 2022-03-04 | 2022-04-22 | 厦门大学附属中山医院 | Mammary gland ultrasonic screening system and method based on artificial intelligence |
| CN114565582A (en) * | 2022-03-01 | 2022-05-31 | 佛山读图科技有限公司 | Medical image classification and lesion area positioning method, system and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559295A (en) * | 2018-06-04 | 2019-04-02 | 新影智能科技(昆山)有限公司 | Image analysis system, method, computer readable storage medium and electric terminal |
| CN110338841A (en) * | 2015-02-16 | 2019-10-18 | 深圳迈瑞生物医疗电子股份有限公司 | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data |
| CN110399913A (en) * | 2019-07-12 | 2019-11-01 | 杭州依图医疗技术有限公司 | The classification method and device at position are shot in a kind of medical image |
| CN110533637A (en) * | 2019-08-02 | 2019-12-03 | 杭州依图医疗技术有限公司 | A kind of method and device of test object |
| CN111210444A (en) * | 2020-01-03 | 2020-05-29 | 中国科学技术大学 | Method, apparatus and medium for segmenting multi-modal magnetic resonance image |
| CN111242920A (en) * | 2020-01-10 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Biological tissue image detection method, device, equipment and medium |
| CN111340780A (en) * | 2020-02-26 | 2020-06-26 | 汕头市超声仪器研究所有限公司 | Focus detection method based on three-dimensional ultrasonic image |
| WO2020133510A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging method and device |
| CN111768379A (en) * | 2020-06-29 | 2020-10-13 | 深圳度影医疗科技有限公司 | Standard section detection method of three-dimensional uterine ultrasound image |
| CN111915698A (en) * | 2020-08-21 | 2020-11-10 | 南方科技大学 | Vascular infiltration detection method and device, computer equipment and storage medium |
| CN112070119A (en) * | 2020-08-11 | 2020-12-11 | 长沙大端信息科技有限公司 | Ultrasonic tangent plane image quality control method and device and computer equipment |
-
2020
- 2020-12-25 CN CN202011556439.4A patent/CN112508941A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110338841A (en) * | 2015-02-16 | 2019-10-18 | 深圳迈瑞生物医疗电子股份有限公司 | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data |
| CN109559295A (en) * | 2018-06-04 | 2019-04-02 | 新影智能科技(昆山)有限公司 | Image analysis system, method, computer readable storage medium and electric terminal |
| WO2020133510A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging method and device |
| CN110399913A (en) * | 2019-07-12 | 2019-11-01 | 杭州依图医疗技术有限公司 | The classification method and device at position are shot in a kind of medical image |
| CN110533637A (en) * | 2019-08-02 | 2019-12-03 | 杭州依图医疗技术有限公司 | A kind of method and device of test object |
| CN111210444A (en) * | 2020-01-03 | 2020-05-29 | 中国科学技术大学 | Method, apparatus and medium for segmenting multi-modal magnetic resonance image |
| CN111242920A (en) * | 2020-01-10 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Biological tissue image detection method, device, equipment and medium |
| CN111340780A (en) * | 2020-02-26 | 2020-06-26 | 汕头市超声仪器研究所有限公司 | Focus detection method based on three-dimensional ultrasonic image |
| CN111768379A (en) * | 2020-06-29 | 2020-10-13 | 深圳度影医疗科技有限公司 | Standard section detection method of three-dimensional uterine ultrasound image |
| CN112070119A (en) * | 2020-08-11 | 2020-12-11 | 长沙大端信息科技有限公司 | Ultrasonic tangent plane image quality control method and device and computer equipment |
| CN111915698A (en) * | 2020-08-21 | 2020-11-10 | 南方科技大学 | Vascular infiltration detection method and device, computer equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113284145A (en) * | 2021-07-22 | 2021-08-20 | 杭州太美星程医药科技有限公司 | Image processing method and device, computer readable storage medium and electronic device |
| CN113284145B (en) * | 2021-07-22 | 2021-11-30 | 杭州太美星程医药科技有限公司 | Image processing method and device, computer readable storage medium and electronic device |
| CN114565582A (en) * | 2022-03-01 | 2022-05-31 | 佛山读图科技有限公司 | Medical image classification and lesion area positioning method, system and storage medium |
| CN114565582B (en) * | 2022-03-01 | 2023-03-10 | 佛山读图科技有限公司 | Medical image classification and lesion area positioning method, system and storage medium |
| CN114376615A (en) * | 2022-03-04 | 2022-04-22 | 厦门大学附属中山医院 | Mammary gland ultrasonic screening system and method based on artificial intelligence |
| CN114376615B (en) * | 2022-03-04 | 2023-09-15 | 厦门大学附属中山医院 | Mammary gland ultrasonic screening system and screening method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741346B (en) | Region-of-interest extraction method, device, equipment and storage medium | |
| CN110458883B (en) | Medical image processing system, method, device and equipment | |
| CN110232383B (en) | Focus image recognition method and focus image recognition system based on deep learning model | |
| CN112508941A (en) | Three-dimensional ultrasonic scanning integrity detection method and device | |
| CN110110723B (en) | Method and device for automatically extracting target area in image | |
| CN111899244B (en) | Image segmentation method, network model training method, device and electronic equipment | |
| CN109919254B (en) | Breast density classification method, system, readable storage medium and computer device | |
| JP2023540910A (en) | Connected Machine Learning Model with Collaborative Training for Lesion Detection | |
| CN111166362B (en) | Medical image display method and device, storage medium and electronic equipment | |
| CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
| CN109087310B (en) | Meibomian gland texture region segmentation method and system, storage medium and intelligent terminal | |
| CN114757950B (en) | Ultrasonic image processing method, device and computer readable storage medium | |
| CN112132854B (en) | Image segmentation method and device and electronic equipment | |
| CN110956632A (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
| CN114332132A (en) | Image segmentation method and device and computer equipment | |
| CN111915626A (en) | Automatic segmentation method and device for ventricle area of heart ultrasonic image and storage medium | |
| CN113537408A (en) | Ultrasonic image processing method, device and equipment and storage medium | |
| CN115861250B (en) | Semi-supervised medical image organ segmentation method and system for self-adaptive data set | |
| CN109829921B (en) | Method and system for processing CT image of head, equipment and storage medium | |
| CN114399501B (en) | Deep learning convolutional neural network-based method for automatically segmenting prostate whole gland | |
| CN111325758A (en) | Lung image segmentation method and device and training method of image segmentation model | |
| CN112233126B (en) | Windowing method and device for medical image | |
| CN113920100A (en) | Knowledge distillation-based weak supervision bone scanning image hot spot segmentation method and system | |
| US20220409181A1 (en) | Method and system for identifying a tendon in ultrasound imaging data and verifying such identity in live deployment | |
| CN116523857B (en) | Hearing state prediction device and method based on diffusion tensor image |
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: 20210316 |