WO2022134049A1 - 胎儿颅骨的超声成像方法和超声成像系统 - Google Patents

胎儿颅骨的超声成像方法和超声成像系统 Download PDF

Info

Publication number
WO2022134049A1
WO2022134049A1 PCT/CN2020/139558 CN2020139558W WO2022134049A1 WO 2022134049 A1 WO2022134049 A1 WO 2022134049A1 CN 2020139558 W CN2020139558 W CN 2020139558W WO 2022134049 A1 WO2022134049 A1 WO 2022134049A1
Authority
WO
WIPO (PCT)
Prior art keywords
region
skull
dimensional
ultrasound data
processor
Prior art date
Application number
PCT/CN2020/139558
Other languages
English (en)
French (fr)
Inventor
张明
邹耀贤
林穆清
贺豪杰
Original Assignee
深圳迈瑞生物医疗电子股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳迈瑞生物医疗电子股份有限公司 filed Critical 深圳迈瑞生物医疗电子股份有限公司
Priority to PCT/CN2020/139558 priority Critical patent/WO2022134049A1/zh
Priority to CN202080107457.6A priority patent/CN116568223A/zh
Publication of WO2022134049A1 publication Critical patent/WO2022134049A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings

Definitions

  • the present application relates to the technical field of ultrasound imaging, and more particularly, to an ultrasound imaging method and an ultrasound imaging system of a fetal skull.
  • fetal skull development is usually measured by ultrasound imaging of the fetal skull. Whether the bone structure of the fetal skull can be accurately imaged is of great significance to the choice of the mode of delivery of pregnant women and the treatment of clinical abnormalities.
  • the shape of the fetal skull is relatively complex, with thin bones and obvious curvature changes, making the overall imaging difficult.
  • Conventional two-dimensional ultrasound cannot fully display the overall structure of the fetal fontanelle and cranial suture, and the demarcation line between the cranial sutures is often difficult. Therefore, the diagnostic results of two-dimensional ultrasound are relatively rough, and the diagnostic conclusions are not accurate enough.
  • Three-dimensional ultrasound can visually display the shape of the fetus's skull, and can visually express the anatomical connection between the skulls, making the structure of the cranial suture and fontanelle at the top of the fetus clear and easy to identify, making up for the lack of spatial expression of two-dimensional ultrasound.
  • 3D ultrasound top imaging is more difficult than frontal and lateral imaging, and often requires a slight rotation when imaging from the side or back to observe structures of interest such as the sagittal suture.
  • the overall operation process of 3D ultrasonography is as follows: clinicians first frame an appropriate region of interest for 3D imaging, then manually rotate the collected 3D data to observe the sagittal suture and fontanelle, and finally set an appropriate rendering mode to display the skull.
  • the bony structure is complex and time-consuming.
  • a first aspect of the embodiments of the present application provides an ultrasonic imaging method of a fetal skull, the method comprising:
  • the processor controls the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested, and receives the echoes of the ultrasonic waves to obtain the echo signals of the ultrasonic waves;
  • the processor obtains three-dimensional ultrasound data of the cranial brain of the fetus to be tested based on the echo signal of the ultrasound;
  • the processor determines a target orientation based on the three-dimensional ultrasound data, the target orientation being an orientation in which the skull region in the three-dimensional ultrasound data is at a rendering angle;
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation
  • the processor determines a skull region in the three-dimensional ultrasound data
  • the processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image.
  • a second aspect of the embodiments of the present application provides an ultrasonic imaging method of a fetal skull, the method comprising:
  • the processor obtains three-dimensional ultrasound data of the cranial brain of the fetus to be tested;
  • the processor determines a target orientation based on the three-dimensional ultrasound data
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation
  • the processor determines a skull region in the three-dimensional ultrasound data
  • the processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image.
  • a third aspect of the embodiments of the present application provides an ultrasonic imaging method of a fetal skull, the method comprising:
  • the rendered image is displayed.
  • a fourth aspect of the embodiments of the present application provides an ultrasound imaging system, where the ultrasound imaging system includes:
  • a transmitting circuit used to excite the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested;
  • a receiving circuit for controlling the ultrasonic probe to receive the echo of the ultrasonic wave to obtain the echo signal of the ultrasonic wave
  • a processor configured to execute the steps of the ultrasound imaging method of the fetal skull according to the first aspect of the embodiments of the present invention
  • a display for displaying the rendered image obtained by the processor is a display for displaying the rendered image obtained by the processor.
  • a fifth aspect of the embodiments of the present application provides an ultrasound imaging system, where the ultrasound imaging system includes:
  • a transmitting circuit used to excite the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested;
  • a receiving circuit configured to control the ultrasonic probe to receive the echo of the ultrasonic wave to obtain an ultrasonic echo signal
  • a processor configured to execute the steps of the ultrasound imaging method for a fetal skull according to the second aspect of the embodiments of the present invention
  • a display for displaying the rendered image obtained by the processor is a display for displaying the rendered image obtained by the processor.
  • a sixth aspect of the embodiments of the present application provides an ultrasound imaging system, where the ultrasound imaging system includes:
  • a transmitting circuit used to excite the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested;
  • a receiving circuit for controlling the ultrasonic probe to receive the echo of the ultrasonic wave to obtain the echo signal of the ultrasonic wave
  • a processor configured to execute the steps of the ultrasound imaging method for a fetal skull according to the third aspect of the embodiments of the present invention
  • a display for displaying the rendered image obtained by the processor is a display for displaying the rendered image obtained by the processor.
  • the ultrasonic imaging method and ultrasonic imaging system of the fetal skull can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the user, and improve the efficiency and accuracy of the fetal skull ultrasonic examination.
  • FIG. 1 shows a schematic block diagram of an ultrasound imaging system according to an embodiment of the present application
  • FIG. 2 shows a schematic flowchart of a method for ultrasound imaging of a fetal skull according to an embodiment of the present invention
  • FIG. 3 shows a comparison diagram of a feature structure diagram of a fetal skull and a rendered image according to an embodiment of the present invention
  • FIG. 4 shows a schematic diagram of determining a region of interest based on CMPR according to an embodiment of the present invention
  • FIG. 5 shows a schematic flow chart of a method for ultrasound imaging of a fetal skull according to another embodiment of the present invention
  • FIG. 6 shows a schematic flowchart of a method for ultrasound imaging of a fetal skull according to yet another embodiment of the present invention.
  • FIG. 1 shows a schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of the present application.
  • the ultrasound imaging system 100 includes an ultrasound probe 110 , a transmitting circuit 112 , a receiving circuit 114 , a processor 116 and a display 118 . Further, the ultrasound imaging system may further include a transmit/receive selection switch 120 and a beam forming module 122 , and the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120 .
  • the ultrasonic probe 110 includes a plurality of transducer array elements, and the plurality of transducer array elements can be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form an area array, and a plurality of transducer array elements can also form a convex array. .
  • the transducer array element is used to transmit ultrasonic waves according to the excitation electrical signal, or convert the received ultrasonic waves into electrical signals, so each transducer array element can be used to realize the mutual conversion of electrical pulse signals and ultrasonic waves, so as to realize the transmission to the measured object.
  • the tissue in the target area transmits ultrasonic waves, and can also be used to receive ultrasonic echoes reflected by the tissue.
  • transducer array elements are used to transmit ultrasonic waves and which transducer array elements are used to receive ultrasonic waves can be controlled through the transmitting sequence and receiving sequence, or the transducer array elements can be controlled to divide time slots for transmitting ultrasonic waves Or receive echoes of ultrasonic waves.
  • the transducer array elements participating in ultrasonic emission can be excited by electrical signals at the same time, so as to emit ultrasonic waves at the same time; Ultrasound at certain time intervals.
  • the transmit circuit 112 transmits the delayed-focused transmit pulses to the ultrasound probe 110 through the transmit/receive selection switch 120 .
  • the ultrasonic probe 110 is stimulated by the transmission pulse to transmit an ultrasonic beam to the tissue in the target area of the object to be measured, and after a certain delay, receives the ultrasonic echo with tissue information reflected from the tissue in the target area, and sends the ultrasonic wave back to the target area.
  • the waves are reconverted into electrical signals.
  • the receiving circuit 114 receives the electrical signals converted and generated by the ultrasonic probe 110, obtains ultrasonic echo signals, and sends these ultrasonic echo signals to the beamforming module 122, and the beamforming module 122 performs focus delay, weighting and channeling on the ultrasonic echo data Summation, etc., are then sent to processor 116.
  • the processor 116 performs signal detection, signal enhancement, data conversion, logarithmic compression, etc. on the ultrasonic echo signal to form an ultrasonic image.
  • the ultrasound images obtained by the processor 116 may be displayed on the display 118 or stored in the memory 124 .
  • the processor 116 may be implemented as software, hardware, firmware, or any combination thereof, and may use single or multiple application specific integrated circuits (ASICs), single or multiple general-purpose integrated circuits, single or multiple microprocessors, single or multiple programmable logic devices, or any combination of the foregoing circuits and/or devices, or other suitable circuits or devices. Also, the processor 116 may control other components in the ultrasound imaging system 100 to perform corresponding steps of the methods in the various embodiments in this specification.
  • ASICs application specific integrated circuits
  • the processor 116 may control other components in the ultrasound imaging system 100 to perform corresponding steps of the methods in the various embodiments in this specification.
  • the display 118 is connected to the processor 116, and the display 118 may be a touch display screen, a liquid crystal display screen, etc.; or, the display 118 may be an independent display such as a liquid crystal display, a television, etc., which is independent of the ultrasound imaging system 100; or, the display 118 may be It is the display screen of electronic devices such as smartphones, tablets, etc.
  • the number of displays 118 may be one or more.
  • the display 118 may include a main screen and a touch screen, where the main screen is mainly used for displaying ultrasound images, and the touch screen is mainly used for human-computer interaction.
  • Display 118 may display ultrasound images obtained by processor 116 .
  • the display 118 can also provide a graphical interface for the user to perform human-computer interaction while displaying the ultrasound image, set one or more controlled objects on the graphical interface, and provide the user with a human-computer interaction device to input operating instructions to control these objects.
  • the controlled object so as to perform the corresponding control operation.
  • an icon is displayed on the graphical interface, and the icon can be operated by using a human-computer interaction device to perform a specific function, such as drawing a region of interest frame on the ultrasound image.
  • the ultrasound imaging system 100 may also include other human-computer interaction devices other than the display 118, which are connected to the processor 116.
  • the processor 116 may be connected to the human-computer interaction device through an external input/output port.
  • the output port can be a wireless communication module, a wired communication module, or a combination of the two.
  • External input/output ports may also be implemented based on USB, bus protocols such as CAN, and/or wired network protocols, and the like.
  • the human-computer interaction device may include an input device for detecting the user's input information, for example, the input information may be a control instruction for the ultrasonic transmission/reception sequence, or a point, line or frame drawn on the ultrasonic image. Manipulate input instructions, or may also include other instruction types.
  • Input devices may include one or a combination of keyboards, mice, scroll wheels, trackballs, mobile input devices (eg, mobile devices with touch display screens, cell phones, etc.), multifunction knobs, and the like.
  • the human-computer interaction apparatus may also include an output device such as a printer.
  • the ultrasound imaging system 100 may also include a memory 124 for storing instructions executed by the processor, storing received ultrasound echoes, storing ultrasound images, and the like.
  • the memory may be a flash memory card, solid state memory, hard disk, or the like. It may be volatile memory and/or non-volatile memory, removable memory and/or non-removable memory, and the like.
  • the components included in the ultrasound imaging system 100 shown in FIG. 1 are only illustrative, and may include more or less components. This application is not limited to this.
  • FIG. 2 is a schematic flowchart of a method 200 for ultrasound imaging of a fetal skull according to an embodiment of the present application.
  • the ultrasound imaging method 200 of the fetal skull includes the following steps:
  • step S210 the processor controls the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested, and receives the echoes of the ultrasonic waves, so as to obtain the echo signals of the ultrasonic waves;
  • step S220 the processor obtains three-dimensional ultrasound data of the cranial brain of the fetus to be tested based on the echo signal of the ultrasound;
  • step S230 the processor determines a target orientation based on the three-dimensional ultrasound data, where the target orientation is an orientation that causes the skull region in the three-dimensional ultrasound data to be under the rendering angle;
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation
  • step S250 the processor determines the skull region in the three-dimensional ultrasound data
  • step S260 the processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image.
  • the ultrasound imaging method 200 of the fetal skull can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the user, and improve the efficiency and accuracy of the fetal skull examination.
  • an ultrasound scan may be performed based on the ultrasound imaging system 100 shown in FIG. 1 .
  • the user moves the ultrasound probe 110 to select an appropriate position and angle to perform a three-dimensional ultrasound scan on the cranial brain of the fetus to be tested.
  • the transmitting circuit 112 sends a group of delayed-focusing transmitting pulses to the ultrasound probe 110 to excite the ultrasound probe 110 to transmit ultrasound waves to the cranial brain of the fetus to be tested along the two-dimensional scanning plane.
  • the receiving circuit 114 controls the ultrasonic probe 110 to receive the ultrasonic echoes reflected from the cranial brain of the fetus to be tested, and convert them into electrical signals.
  • the processing of delay and weighted summation realizes beamforming, and is then sent to the processor 116 for subsequent signal processing.
  • step S220 the processor of the ultrasound imaging system obtains three-dimensional ultrasound data of the cranial brain of the fetus to be tested based on the received echo signals of the ultrasound.
  • the processor 116 can integrate the three-dimensional spatial relationship of the ultrasound echo signals obtained by scanning the ultrasound probe 110 in a series of scanning planes, so as to realize the scanning of the fetal skull in the three-dimensional space and the three-dimensional ultrasound. Reconstruction of data.
  • image post-processing steps such as denoising, smoothing, and enhancement, the 3D ultrasound data of the fetal brain is obtained.
  • step S230 the processor determines a target orientation based on the three-dimensional ultrasound data, where the target orientation is an orientation in which the skull region in the three-dimensional ultrasound data is under the rendering angle.
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation determined in step S230, that is, the processor automatically corrects the three-dimensional ultrasound data.
  • Rotating the 3D ultrasound data to the target orientation can rotate the skull region in the 3D ultrasound data to the rendering angle, so that the final rendered image containing the skull region can be obtained without the need for the user to manually rotate, improving the efficiency and accuracy of fetal skull ultrasound examination sex.
  • the target orientation may be an orientation that places the region of interest features of the skull in the three-dimensional ultrasound data at the rendering angle.
  • Features of interest may include cranial sutures, fontanelles, and other features that require careful inspection by the user.
  • the feature structure of interest can also be other feature structures of the fetal skull that need to be observed. Since different feature structures of interest may be located in different positions of the fetal skull, the target positions may include multiple, such as the front, side, and top of the fetal skull, and different target positions may correspond to different feature structures of interest.
  • a plurality of candidate target orientations may be preset for the user to select, the processor determines the target orientation according to the received selection instruction, and performs automatic ultrasound imaging on the skull of the fetus to be tested under the target orientation, so that the user can observe the target orientation.
  • the feature structure of interest corresponding to the target orientation may be preset for the user to select.
  • determining the target orientation may include: detecting the region of the target feature structure in the three-dimensional ultrasound data, and determining the angle that the three-dimensional ultrasound data needs to rotate according to the location of the detected target feature structure region, or according to The relative positional relationship between the regions of at least two target features determines the angle by which the three-dimensional ultrasound data needs to be rotated.
  • the target feature structure includes at least one of the following: midline of the brain, thalamus, corpus callosum, eyeball, brain stem, cerebellum, fontanelle, cranial suture and skull, and the target feature structure can also be other landmark features of the fetal skull or skull.
  • the traditional target detection method or the machine learning method can be used to detect the target feature structure in the three-dimensional ultrasound data.
  • the target feature structure can be detected in multiple two-dimensional slices of the three-dimensional ultrasound data, and the detection results of the target feature structure on the multiple two-dimensional slices can be integrated to obtain the target feature structure in the three-dimensional ultrasound data.
  • the three-dimensional detection result of the target can also be directly performed on the three-dimensional ultrasonic data to obtain the three-dimensional detection result of the target feature structure.
  • the traditional object detection method may include three steps of region selection, feature extraction and classification.
  • region selection refers to the selection of candidate target regions based on a method such as a sliding window
  • feature extraction refers to feature extraction on candidate target regions, and the extracted features such as SIFT (Scale Invariant Feature Transform), HOG (Orientation) Gradient histogram) and other features.
  • Classification refers to using a classifier to classify candidate target areas to determine whether the current candidate target area includes the target feature structure.
  • the classifier can use KNN (K-nearest neighbor algorithm), SVM (support vector machine), random forest and other types of classification device.
  • Traditional object detection methods can also include pixel clustering, edge segmentation, graph cutting or threshold-based image segmentation algorithms.
  • Detecting target feature structures in 3D ultrasound data based on machine learning methods requires pre-constructing a 3D ultrasound database for each target feature structure, in which each 3D ultrasound data marks the position corresponding to the target feature structure, and then learns a target feature structure based on the 3D ultrasound database.
  • Machine learning methods can include the following methods, which can be implemented individually or combined with each other.
  • the first optional machine learning method is a sliding window-based method. Specifically, feature extraction is first performed on the area within the sliding window.
  • the extracted features can be traditional PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), Harr features, textures and other features, or a deep neural network can be used to extract features. Perform feature extraction. Then, use the trained classifier for classification to determine whether the target feature structure is included in the current window.
  • the second optional machine learning method is the deep learning method based on the bounding box (Bounding-Box).
  • the network is first constructed by stacking convolutional layers and fully connected layers. Based on the constructed 3D ultrasound database, feature learning and parameter regression are performed through the network, and the training samples in the 3D ultrasound database are sent to the pre-built network. , optimize the loss function of the network for training until the network reaches convergence, during the training process the network can learn how to identify the location of the target feature structure from the 3D ultrasound data.
  • the specific process of training the machine learning model can be to directly train the 3D ultrasound data, or it can decompose the 3D ultrasound data into multiple 2D slices, train the multiple 2D slices separately, and then splicing the training results of the 3D ultrasound data. .
  • the bounding box of the corresponding target feature structure can be directly regressed through the network, and the category of the target feature structure contained in the bounding box can be obtained at the same time.
  • the network structure includes but is not limited to R-CNN, Fast R-CNN, Faster-RCNN, SSD, YOLO, etc.
  • the third optional machine learning method is an end-to-end semantic segmentation network method based on deep learning, which is similar in structure to the above-mentioned bounding box-based deep learning method.
  • the connection layer is removed, and an upsampling or deconvolution layer is added to make the input and output the same size, so as to directly obtain the target feature structure and its corresponding category in the 3D ultrasound data input to the network.
  • the network structure of the semantic segmentation network includes, but is not limited to, FCN, U-Net, Mask R-CNN, and the like.
  • the angle that the three-dimensional ultrasound data of the fetal skull needs to be rotated can be indirectly calculated according to the target feature structure.
  • the angle by which the three-dimensional ultrasound data needs to be rotated may be determined according to the position of the region of at least one target feature structure.
  • the rotation angle required to rotate the three-dimensional ultrasound data to the target orientation can be indirectly determined by calculating the rotation angle required to rotate the target feature from the current position to the target position.
  • the angle by which the three-dimensional ultrasound data needs to be rotated may be determined according to the relative positional relationship between the regions of at least two target feature structures.
  • the angle by which the three-dimensional ultrasound data needs to be rotated can be determined based on the symmetry between the target structures.
  • the three-dimensional ultrasound data acquired in step S220 is rotated to the target orientation based on the angle by which the three-dimensional ultrasound data needs to be rotated determined according to the target feature structure. Since the ultrasound data is three-dimensional ultrasound data, the three dimensions correspond to a rotation angle during rotation, and the rotated three-dimensional ultrasound data can be obtained by rotating the corresponding angles along the three dimensions respectively.
  • the trained machine learning model can be used to directly regress the angle that the 3D ultrasound data needs to be rotated.
  • the angle of rotation rotates the three-dimensional ultrasound data to the target orientation.
  • a three-dimensional ultrasound database of the fetal skull needs to be pre-built for training the machine learning model.
  • the 3D ultrasound database of the fetal brain contains the calibration results corresponding to the 3D ultrasound data of at least one fetal brain.
  • the calibration result is the angle at which the 3D ultrasound data needs to be rotated.
  • the trained machine learning model can directly return the rotation angle. .
  • the machine learning model can use a deep learning network, and the deep learning network structure includes but is not limited to VGG, ResNet, DenseNet, DPN, etc.
  • the three-dimensional ultrasound data obtained in step S220 is rotated to the target orientation.
  • the angle output by the machine learning model can also be the rotation angle corresponding to the three dimensions, and the rotated three-dimensional ultrasound data can be obtained by rotating the corresponding angle along the three dimensions respectively.
  • the processor determines the skull region in the three-dimensional ultrasound data of the fetal skull, thereby determining the final imaging display range of the three-dimensional ultrasound data. Rendering and imaging for the skull can improve the accuracy of the ultrasound imaging of the fetal skull and avoid Other tissue areas affect how the skull area is rendered.
  • the processor may determine the skull region in the three-dimensional ultrasound data before rotation, and rotate the skull region to obtain the rotated skull region; and may also determine the skull region in the rotated three-dimensional ultrasound data.
  • the methods for determining the skull region include the following:
  • a first optional method for determining the skull region includes: segmenting the border of the skull region in the three-dimensional ultrasound data, and using the region formed by the border of the skull region as the skull region.
  • a traditional target detection method or a machine learning method similar to that in step S230 may be used to automatically segment the skull region from the three-dimensional ultrasound data, and the segmentation result of the skull region may be used as the determined skull region.
  • a second optional method for determining the skull region includes detecting a region of interest containing the skull region in the three-dimensional ultrasound data, and determining the skull region in the region of interest.
  • the method automatically detects the position and size of the skull region to set the appropriate skull region.
  • a traditional target detection method or a machine learning method similar to that in step S230 can be used to identify the position of the skull region, and based on the identification result, the size of the skull region is further calculated.
  • an appropriate bounding box such as the largest circumscribed trapezoid box, is set as the region of interest, and the skull region is determined in the region of interest.
  • a third optional method for determining the skull region includes determining the skull region by setting CMPR (Curve Multiple Plane Rendering) reference lines. Specifically, a target two-dimensional slice containing the skull region is extracted from the three-dimensional ultrasound data; a CMPR reference line is drawn along the skull region on the target two-dimensional slice, and a two-dimensional region of interest in the target two-dimensional slice is determined according to the CMPR reference line ; Select a 3D region perpendicular to the 2D region of interest in the direction perpendicular to the target 2D slice; determine the skull region in the selected 3D region.
  • the CMPR reference line refers to a curve drawn along the skull area from the target 2D section of the 3D ultrasound data.
  • CMPR imaging needs to follow the CMPR
  • the orientation of the reference line straightens the 3D ultrasound data for this thickness.
  • FIG. 3 the left side of FIG. 3 shows a CMPR reference line, and the right side is a rendered image obtained based on the CMPR reference line.
  • extracting the target two-dimensional slice including the skull region in the three-dimensional ultrasound data includes: randomly intercepting at least one two-dimensional slice in the three-dimensional ultrasound data, or intercepting at least one two-dimensional slice along a preset direction; In the slice, a two-dimensional slice including the skull region is determined as a target two-dimensional slice.
  • the processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image. Due to the occlusion of the superficial and middle tissue structures, direct imaging of 3D ultrasound data may not be able to visually observe the skull bone structure of the fetus, while rendering for the skull region can more clearly present the skull bone structure, which is convenient for users to observe the skull bone structure. developmental examination.
  • the rendering of the skull region may be to render only the skull region, for example, three-dimensional ultrasound data other than the skull region may be removed, and the reserved skull region may be rendered.
  • the rendering of the skull region may be to render the region including the skull region, and during the rendering process, the skull region and other regions may be distinguished by setting the rendering mode, so as to highlight the bony structure of the skull.
  • the method for rendering the skull region mainly includes a volume rendering method and a surface rendering method.
  • the volume rendering method is mainly a ray tracing algorithm.
  • the algorithm emits multiple rays that pass through the 3D ultrasound data based on the line of sight. Each ray progresses by a fixed step size. The color and opacity of each sampling point, then accumulate the color and opacity on each ray path, and finally map the accumulated color value to each pixel of the 2D image to get VR (Volume Rendering) rendering picture.
  • the 3D rendering mode used for volume rendering includes any of the following:
  • Maximum echo mode which mainly displays the maximum value information inside the object
  • Min mode which mainly displays the minimum value information inside the object
  • X-ray mode (X-Ray mode), which mainly displays the internal structure information of the object;
  • Light and shadow imaging mode (Volume Rendering with Global Illumination mode), which displays surface information of objects based on the global illumination model, and can simulate real skin texture and shadow effects;
  • f. Contour mode (Silhouette mode), this mode displays the inner and outer contour information of the object through the translucent effect.
  • the above three-dimensional rendering modes can also be combined with each other.
  • the main methods of surface rendering are divided into two methods: “based on fault contours (Delaunay)” and “extracting isosurfaces from voxels (MarchingCube)”.
  • MarchingCube by extracting the equivalent value of tissues or organs in 3D ultrasound data Face (ie, surface outline) information - the normal vector and vertex coordinates of the triangular facet, establish a triangular mesh model, and then combine the lighting model (including ambient light, scattered light, highlight, etc., different light source parameters) for stereo rendering, among which The lighting model includes ambient light, scattered light, highlight, etc. Different light source parameters (type, direction, position, angle) will affect the effect of the lighting model to different degrees, and the rendered image can be obtained.
  • the processor may further control the display to display the identifiers representing the feature structures corresponding to different regions in the rendered image, so as to facilitate the user's reference.
  • the identifiers displayed by the processor can be the names of the characteristic structures corresponding to different regions, such as parietal bone, bregma, posterior bregma, etc.; the identifiers displayed by the processor can also be symbols or graphics that can represent different characteristic structures.
  • the processor may generate identifiers of feature structures corresponding to different regions in the rendered image according to the corresponding relationship between the feature structure map of the fetal skull and the rendered image.
  • the left side shows the characteristic structure of the fetal skull
  • the right side shows the rendered image.
  • the characteristic structure diagram of the fetal skull shows the identification of the characteristic structure corresponding to each region
  • the processor can generate the identification corresponding to the same characteristic structure at the corresponding position in the rendered image according to the identification in the characteristic structure diagram of the fetal skull.
  • the processor may not divide the specific area of each feature in the rendered image.
  • the processor may first determine regions of different feature structures in the rendered image, and generate an identifier of a feature structure corresponding to each feature structure region according to the regions of different feature structures.
  • determining regions corresponding to different feature structures in the rendered image includes: extracting image features of the rendered image; and classifying the image features to divide regions corresponding to different feature structures in the rendered image.
  • a traditional target detection method or a machine learning method similar to that in step S230 may be used to perform feature extraction and feature classification, so as to determine regions corresponding to different feature structures in the rendered image.
  • the processor may control the display to display the regions corresponding to different feature structures in a differentiated manner.
  • this embodiment can be implemented independently, that is, the processor only controls the display to display regions corresponding to different feature structures in a differentiated manner, so that the user can distinguish different regions without displaying the signs corresponding to different feature structures; this embodiment also It can be combined with the above-mentioned embodiments, that is, while controlling the display to display regions corresponding to different feature structures in a differentiated manner, the processor can also control the display to display identifiers representing feature structures corresponding to different regions in the rendered image.
  • displaying regions corresponding to different feature structures in a differentiated manner includes: displaying regions corresponding to different feature structures in different forms in the rendered image.
  • the processor may control the display to display regions corresponding to different features in different colors, transparency, brightness, and the like.
  • the processor may also control the display to display the boundaries of different regions in different forms, so as to distinguish regions corresponding to different feature structures.
  • the display when the processor receives a selection instruction for regions corresponding to different feature structures in the rendered image, the display is controlled to highlight the region selected by the selection instruction in the rendered image.
  • the form of highlighting includes but is not limited to highlighting, blinking, magnifying and the like.
  • the selection instruction for the regions corresponding to different feature structures in the rendered image may be received based on the identifiers corresponding to the above-mentioned different feature structures, that is, when it is detected that the user selects the identifier of a certain feature structure, the region corresponding to the identifier is highlighted;
  • the selection instruction may also be received based on the rendered image itself, that is, when it is detected that the user has selected a certain position of the rendered image, the region to which the position belongs is highlighted.
  • the selection instruction may also be received based on a controlled object other than the rendered image that has a mapping relationship with different regions of the rendered image.
  • the ultrasound imaging method 200 of the fetal skull can realize the automatic imaging of the fetal skull, greatly reduce the manual operation of the doctor, and improve the efficiency and accuracy of the ultrasound examination of the fetal skull.
  • Embodiments of the present application further provide an ultrasonic imaging system for implementing the above-mentioned ultrasonic imaging method 200 of a fetal skull.
  • the ultrasonic imaging system includes an ultrasonic probe, a transmitting circuit, a receiving circuit, a processor and a display.
  • the transmitting circuit is used to excite the ultrasonic probe to transmit ultrasonic waves to the skull of the fetus to be tested; the receiving circuit is used to control the ultrasonic probe to receive ultrasonic echoes to obtain ultrasonic echo signals; the processor is used to perform the above ultrasonic imaging of the fetal skull
  • the steps of method 200 specifically include: the processor controls the ultrasonic probe to transmit ultrasonic waves to the cranial brain of the fetus to be tested, and receives the echoes of the ultrasonic waves to obtain the echo signals of the ultrasonic waves; the processor is based on the ultrasonic waves
  • the three-dimensional ultrasound data of the skull of the fetus to be tested is obtained from the echo signal of the fetus; the processor determines a target orientation based on the three-dimensional ultrasound data, and the target orientation is to make the skull region in the three-dimensional ultrasound data at a rendering angle
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation
  • the ultrasound imaging system may be implemented as an ultrasound imaging system 100 as shown in FIG. 1 .
  • the ultrasound imaging system 100 may include an ultrasound probe 110 , a transmitting circuit 112 , a receiving circuit 114 , a processor 116 and a display 118 , which may
  • the ultrasound imaging system 100 may further include a transmit/receive selection switch 120 and a beam forming module 122, and the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • a transmit/receive selection switch 120 and a beam forming module 122
  • the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • the ultrasound imaging system of the embodiment of the present application can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the doctor, and improve the efficiency and accuracy of the fetal skull ultrasound examination.
  • FIG. 5 is a schematic flowchart of a method 500 for ultrasound imaging of a fetal skull according to an embodiment of the present application.
  • the ultrasound imaging method 500 of the fetal skull includes the following steps:
  • step S510 the processor obtains three-dimensional ultrasound data of the cranial brain of the fetus to be tested;
  • step S520 the processor determines a target orientation based on the three-dimensional ultrasound data
  • the processor rotates the three-dimensional ultrasound data to the target orientation based on the target orientation
  • step S540 the processor determines the skull region in the three-dimensional ultrasound data
  • step S550 the processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image.
  • the main difference between the ultrasonic imaging method 500 of the fetal skull in this embodiment and the ultrasonic imaging method 200 above is that the ultrasonic imaging method 500 of the fetal skull in this embodiment does not restrict the processor to obtain three-dimensional ultrasonic data of the skull of the fetus to be tested specific way.
  • the processor may perform three-dimensional ultrasound scanning in real time by using the method described in the ultrasound imaging method 200 of the fetal skull to obtain the three-dimensional ultrasound data of the fetal skull to be tested; Three-dimensional ultrasound data of fetal brain, etc.
  • the ultrasonic imaging method 500 of the fetal skull according to the embodiment of the present application is substantially similar to the ultrasonic imaging method 200 of the fetal skull described with reference to FIG. 2 , and for brevity, the same details are not repeated here.
  • Embodiments of the present application further provide an ultrasonic imaging system for implementing the above-mentioned ultrasonic imaging method 500 of a fetal skull.
  • the ultrasonic imaging system includes an ultrasonic probe, a transmitting circuit, a receiving circuit, a processor and a display.
  • the transmitting circuit is used to excite the ultrasonic probe to transmit ultrasonic waves to the skull of the fetus to be tested; the receiving circuit is used to control the ultrasonic probe to receive ultrasonic echoes to obtain ultrasonic echo signals; the processor is used to perform the above ultrasonic imaging of the fetal skull
  • the steps of method 500 specifically include: the processor obtains three-dimensional ultrasound data of the brain of the fetus to be tested; the processor determines the target orientation based on the three-dimensional ultrasound data; the processor rotates the three-dimensional ultrasound data to the target orientation; The processor renders the skull region in the rotated three-dimensional ultrasound data to obtain a rendered image, and controls the display to display the rendered image; the display is used to display the rendered image obtained by the processor.
  • the ultrasound imaging system may be implemented as an ultrasound imaging system 100 as shown in FIG. 1 .
  • the ultrasound imaging system 100 may include an ultrasound probe 110 , a transmitting circuit 112 , a receiving circuit 114 , a processor 116 and a display 118 , which may
  • the ultrasound imaging system 100 may further include a transmit/receive selection switch 120 and a beam forming module 122, and the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • a transmit/receive selection switch 120 and a beam forming module 122
  • the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • the ultrasound imaging method 500 of the fetal skull and the ultrasound imaging system of the embodiment of the present application can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the doctor, and improve the efficiency and accuracy of the ultrasound examination of the fetal skull.
  • FIG. 6 is a schematic flowchart of a method 600 for ultrasound imaging of a fetal skull according to an embodiment of the present application.
  • an ultrasonic imaging method 600 includes the following steps:
  • step S610 obtain three-dimensional ultrasound data of the cranial brain of the fetus to be tested
  • step S620 determining the skull region in the three-dimensional ultrasound data based on the skull image features of the fetus
  • step S630 rendering the skull region to obtain a rendered image
  • step S640 the rendered image is displayed.
  • the ultrasound imaging method 600 does not rotate the three-dimensional ultrasound data. In some cases, rendering of the skull can be achieved without the need to rotate the 3D ultrasound data.
  • the orientation of the three-dimensional ultrasound data can be adjusted by the user by adjusting the probe angle during the ultrasound scan, or the user can manually rotate the three-dimensional ultrasound data after acquiring the three-dimensional ultrasound data.
  • determining the skull region in the three-dimensional ultrasound data includes: segmenting the border of the skull region in the three-dimensional ultrasound data, and using the region formed by the border of the skull region as the skull region; The region of interest of the skull region, in which the region of the skull is identified.
  • step S250 of the method 200 for ultrasound imaging of the fetal skull For the specific details of this method, reference may be made to the relevant description in step S250 of the method 200 for ultrasound imaging of the fetal skull.
  • determining the skull region in the three-dimensional ultrasound data includes: extracting a target two-dimensional section including the skull region in the three-dimensional ultrasound data; drawing a curved multi-plane rendering reference line along the skull region on the target two-dimensional section, And determine the 2D region of interest in the target 2D section according to the curve multi-plane rendering reference line; select the 3D region perpendicular to the 2D region of interest in the direction perpendicular to the target 2D section; determine the skull in the selected 3D region area.
  • step S250 of the method 200 for ultrasound imaging of the fetal skull For the specific details of this method, reference may be made to the relevant description in step S250 of the method 200 for ultrasound imaging of the fetal skull.
  • identifiers representing feature structures corresponding to different regions in the rendered image may also be displayed.
  • the displayed logos can be the names of the feature structures corresponding to different regions, and the displayed logos can also be symbols or graphics that can represent different feature structures.
  • the identifiers of the feature structures corresponding to different regions in the rendered image may be generated according to the corresponding relationship between the feature structure map of the fetal skull and the rendered image.
  • the feature structure diagram shows the identification of the region corresponding to each feature structure, and the identification corresponding to the same feature structure can be generated at the corresponding position in the rendered image according to the identification in the feature structure diagram of the fetal skull.
  • regions of different feature structures in the rendered image may be determined, and a feature structure identifier corresponding to each feature structure region may be generated according to the regions of different feature structures.
  • the image features of the rendered image can be extracted and classified, so as to divide regions corresponding to different feature structures in the rendered image.
  • traditional object detection methods or machine learning methods can be used to perform feature extraction and feature classification to determine regions corresponding to different feature structures in the rendered image.
  • the regions corresponding to different feature structures in the rendered image can be displayed in a differentiated manner. For example, regions corresponding to different feature structures can be displayed with different colors, transparency, brightness, and the like. Alternatively, the boundaries of different regions can also be displayed in different forms to distinguish regions corresponding to different feature structures.
  • the region selected by the selection instruction may be highlighted.
  • the form of highlighting includes but is not limited to highlighting, blinking, magnifying and the like.
  • the selection instruction for the regions corresponding to different feature structures in the rendered image may be received based on the identifiers corresponding to the above-mentioned different feature structures, that is, when it is detected that the user selects the identifier of a certain feature structure, the region corresponding to the identifier is highlighted;
  • the selection instruction may also be received based on the rendered image itself, that is, when it is detected that the user has selected a certain position of the rendered image, the region to which the position belongs is highlighted.
  • the selection instruction may also be received based on a controlled object other than the rendered image that has a mapping relationship with different regions of the rendered image.
  • the ultrasonic imaging method 600 of the embodiment of the present application can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the doctor, and improve the efficiency and accuracy of the fetal skull ultrasonic examination.
  • Embodiments of the present application further provide an ultrasonic imaging system, which is used to implement the above-mentioned ultrasonic imaging method 600 .
  • the ultrasonic imaging system includes an ultrasonic probe, a transmitting circuit, a receiving circuit, a processor and a display.
  • the transmitting circuit is used to excite the ultrasonic probe to transmit ultrasonic waves to the brain of the fetus to be tested;
  • the receiving circuit is used to control the ultrasonic probe to receive ultrasonic echoes to obtain ultrasonic echo signals;
  • the processor is used to execute the above ultrasonic imaging method 600
  • the steps specifically include: acquiring three-dimensional ultrasound data of the skull of the fetus to be tested; determining a skull region in the three-dimensional ultrasound data based on the features of the skull image of the fetus; rendering the skull region to obtain a rendered image; in step S640 to display the rendered image.
  • the ultrasound imaging system may be implemented as an ultrasound imaging system 100 as shown in FIG. 1 .
  • the ultrasound imaging system 100 may include an ultrasound probe 110 , a transmitting circuit 112 , a receiving circuit 114 , a processor 116 and a display 118 , which may
  • the ultrasound imaging system 100 may further include a transmit/receive selection switch 120 and a beam forming module 122, and the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • a transmit/receive selection switch 120 and a beam forming module 122
  • the transmit circuit 112 and the reception circuit 114 may be connected to the ultrasound probe 110 through the transmit/receive selection switch 120.
  • a computer storage medium is also provided, where program instructions are stored on the computer storage medium, and the program instructions are used to execute the fetus of the embodiments of the present application when the program instructions are executed by a computer or a processor.
  • program instructions are stored on the computer storage medium, and the program instructions are used to execute the fetus of the embodiments of the present application when the program instructions are executed by a computer or a processor.
  • the storage medium may include, for example, a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, read only memory (ROM), erasable programmable read only memory (EPROM), portable compact disk read only memory (CD-ROM), USB memory, or any combination of the above storage media.
  • the computer-readable storage medium can be any combination of one or more computer-readable storage media.
  • a computer program is also provided, and the computer program can be stored in the cloud or on a local storage medium.
  • the computer program is run by a computer or a processor, it is used to execute the corresponding steps of the ultrasound imaging method of the fetal skull according to the embodiment of the present application.
  • the ultrasonic imaging method and ultrasonic imaging system of the fetal skull can realize automatic imaging of the fetal skull, greatly reduce the manual operation of the doctor, and improve the efficiency and accuracy of the fetal skull ultrasonic examination.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or May be integrated into another device, or some features may be omitted, or not implemented.
  • Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application.
  • DSP digital signal processor
  • the present application can also be implemented as a program of apparatus (eg, computer programs and computer program products) for performing part or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.

Abstract

一种胎儿颅骨的超声成像方法和超声成像系统，该方法包括：处理器（116）控制超声探头向待测胎儿的颅脑发射超声波，并接收超声波的回波，以获得超声波的回波信号（S210）；处理器（116）基于超声波的回波信号获得待测胎儿的颅脑的三维超声数据（S220）；处理器（116）基于三维超声数据确定目标方位，目标方位为使三维超声数据中的颅骨区域处于渲染角度下的方位（S230）；处理器（116）基于目标方位将三维超声数据旋转到目标方位（S240）；处理器（116）确定三维超声数据中的颅骨区域（S250）；处理器（116）对旋转后的三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器（118）显示渲染图像（S260），能够实现对胎儿颅骨的自动成像，提高胎儿颅骨超声检查的效率与准确率。

Description

胎儿颅骨的超声成像方法和超声成像系统
说明书
技术领域
本申请涉及超声成像技术领域，更具体地涉及一种胎儿颅骨的超声成像方法和超声成像系统。
背景技术
临床中通常通过对胎儿颅骨进行超声成像来衡量胎儿颅骨的发育情况。能否对胎儿颅骨的骨性结构准确显像对孕妇分娩方式的选择以及临床中异常情况的处理有着重要的意义。然而，胎儿颅骨的形态较为复杂，骨质薄，弧度变化明显，整体显像难度大，常规的二维超声难以完全显示胎儿囟门、颅缝的总体结构，颅缝间的分界线也常常比较难辨别，导致二维超声的诊断结果相对粗糙，诊断结论也不够精准。
三维超声能够直观的显示胎儿的颅骨形态，可以形象的表达颅骨之间的解剖连接关系，使胎儿顶部颅缝和囟门结构清晰易辨，弥补了二维超声在空间表达上的不足。然而，三维超声顶部成像较正面成像及侧面成像难度大，常常需要从侧面或后面成像时稍作旋转来观察矢状缝等感兴趣的结构。三维超声检查总体的操作流程为：临床医生先框定合适的感兴趣区域进行三维成像，然后再手动旋转采集到的三维数据来观察到矢状缝与囟门，最后设定合适的渲染模式来显示颅骨的骨性结构，过程复杂且耗时。
发明内容
在发明内容部分中引入了一系列简化形式的概念，这将在具体实施方式部分中进一步详细说明。本发明的发明内容部分并不意味着要试图限定出所要求保护的技术方案的关键特征和必要技术特征，更不意味着试图确定所要求保护的技术方案的保护范围。
本申请实施例第一方面提供一种胎儿颅骨的超声成像方法，所述方法包括：
处理器控制超声探头向待测胎儿的颅脑发射超声波，并接收所述超声波 的回波，以获得所述超声波的回波信号；
所述处理器基于所述超声波的回波信号获得所述待测胎儿的颅脑的三维超声数据；
所述处理器基于所述三维超声数据确定目标方位，所述目标方位为使所述三维超声数据中的颅骨区域处于渲染角度下的方位；
所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
所述处理器确定所述三维超声数据中的颅骨区域；
所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
本申请实施例第二方面提供一种胎儿颅骨的超声成像方法，所述方法包括：
处理器获得待测胎儿的颅脑的三维超声数据；
所述处理器基于所述三维超声数据确定目标方位；
所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
所述处理器确定所述三维超声数据中的颅骨区域；
所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
本申请实施例第三方面提供一种胎儿颅骨的超声成像方法，所述方法包括：
获取待测胎儿的颅脑的三维超声数据；
基于胎儿的颅骨图像特征在所述三维超声数据中确定颅骨区域；
对所述颅骨区域进行渲染，以得到渲染图像；
显示所述渲染图像。
本申请实施例第四方面提供一种超声成像系统，所述超声成像系统包括：
超声探头；
发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
接收电路，用于控制所述超声探头接收所述超声波的回波，以获得所述超声波的回波信号；
处理器，用于执行本发明实施例第一方面所述的胎儿颅骨的超声成像方法的步骤；
显示器，用于显示所述处理器得到的渲染图像。
本申请实施例第五方面提供一种超声成像系统，所述超声成像系统包括：
超声探头；
发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
接收电路，用于控制所述超声探头接收所述超声波的回波，以获得超声回波信号；
处理器，用于执行本发明实施例第二方面所述的胎儿颅骨的超声成像方法的步骤；
显示器，用于显示所述处理器得到的渲染图像。
本申请实施例第六方面提供一种超声成像系统，所述超声成像系统包括：
超声探头；
发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
接收电路，用于控制所述超声探头接收所述超声波的回波，以获得所述超声波的回波信号；
处理器，用于执行本发明实施例第三方面所述的胎儿颅骨的超声成像方法的步骤；
显示器，用于显示所述处理器得到的渲染图像。
根据本申请实施例的胎儿颅骨的超声成像方法和超声成像系统能够实现对胎儿颅骨的自动成像，大幅减少用户的手动操作，提高胎儿颅骨超声检查的效率与准确率。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
在附图中：
图1示出根据本申请实施例的超声成像系统的示意性框图；
图2示出根据本发明一实施例的胎儿颅骨的超声成像方法的示意性流程图；
图3示出根据本发明一实施例的胎儿颅骨的特征结构图与渲染图像的对照图；
图4示出根据本发明一实施例的基于CMPR确定感兴趣区域的示意图；
图5示出根据本发明另一实施例的胎儿颅骨的超声成像方法的示意性流程图；
图6示出根据本发明又一实施例的胎儿颅骨的超声成像方法的示意性流程图。
具体实施方式
为了使得本申请的目的、技术方案和优点更为明显，下面将参照附图详细描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。基于本申请中描述的本申请实施例，本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本申请的保护范围之内。
在下文的描述中，给出了大量具体的细节以便提供对本申请更为彻底的理解。然而，对于本领域技术人员而言显而易见的是，本申请可以无需一个或多个这些细节而得以实施。在其他的例子中，为了避免与本申请发生混淆，对于本领域公知的一些技术特征未进行描述。
应当理解的是，本申请能够以不同形式实施，而不应当解释为局限于这里提出的实施例。相反地，提供这些实施例将使公开彻底和完全，并且将本申请的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本申请的限制。在此使用时，单数形式的“一”、“一个”和“所述/该”也意图包括复数形式，除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”，当在该说明书中使用时，确定所述特征、整数、步骤、操作、元件和/或部件的存在，但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时，术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本申请，将在下列的描述中提出详细的结构，以便阐释本申请提出的技术方案。本申请的可选实施例详细描述如下，然而除了这些详细描述外，本申请还可以具有其他实施方式。
下面，首先参考图1描述根据本申请一个实施例的超声成像系统，图1 示出了根据本申请实施例的超声成像系统100的示意性结构框图。
如图1所示，超声成像系统100包括超声探头110、发射电路112、接收电路114、处理器116和显示器118。进一步地，超声成像系统还可以包括发射/接收选择开关120和波束合成模块122，发射电路112和接收电路114可以通过发射/接收选择开关120与超声探头110连接。
超声探头110包括多个换能器阵元，多个换能器阵元可以排列成一排构成线阵，或排布成二维矩阵构成面阵，多个换能器阵元也可以构成凸阵列。换能器阵元用于根据激励电信号发射超声波，或将接收的超声波转换为电信号，因此每个换能器阵元可用于实现电脉冲信号和超声波的相互转换，从而实现向被测对象的目标区域的组织发射超声波、也可用于接收经组织反射回的超声波回波。在进行超声检测时，可通过发射序列和接收序列控制哪些换能器阵元用于发射超声波，哪些换能器阵元用于接收超声波，或者控制换能器阵元分时隙用于发射超声波或接收超声波的回波。参与超声波发射的换能器阵元可以同时被电信号激励，从而同时发射超声波；或者，参与超声波束发射的换能器阵元也可以被具有一定时间间隔的若干电信号激励，从而持续发射具有一定时间间隔的超声波。
在超声成像过程中，发射电路112将经过延迟聚焦的发射脉冲通过发射/接收选择开关120发送到超声探头110。超声探头110受发射脉冲的激励而向被测对象的目标区域的组织发射超声波束，经一定延时后接收从目标区域的组织反射回来的带有组织信息的超声回波，并将此超声回波重新转换为电信号。接收电路114接收超声探头110转换生成的电信号，获得超声回波信号，并将这些超声回波信号送入波束合成模块122，波束合成模块122对超声回波数据进行聚焦延时、加权和通道求和等处理，然后送入处理器116。处理器116对超声回波信号进行信号检测、信号增强、数据转换、对数压缩等处理形成超声图像。处理器116得到的超声图像可以在显示器118上显示，也可以存储于存储器124中。
可选地，处理器116可以实现为软件、硬件、固件或其任意组合，并且可以使用单个或多个专用集成电路(Application Specific Integrated Circuit，ASIC)、单个或多个通用集成电路、单个或多个微处理器、单个或多个可编程逻辑器件、或者前述电路和/或器件的任意组合、或者其他适合的电路或器件。并且，处理器116可以控制所述超声成像系统100中的其它组件以执行 本说明书中的各个实施例中的方法的相应步骤。
显示器118与处理器116连接，显示器118可以为触摸显示屏、液晶显示屏等；或者，显示器118可以为独立于超声成像系统100之外的液晶显示器、电视机等独立显示器；或者，显示器118可以是智能手机、平板电脑等电子设备的显示屏，等等。其中，显示器118的数量可以为一个或多个。例如，显示器118可以包括主屏和触摸屏，主屏主要用于显示超声图像，触摸屏主要用于人机交互。
显示器118可以显示处理器116得到的超声图像。此外，显示器118在显示超声图像的同时还可以提供给用户进行人机交互的图形界面，在图形界面上设置一个或多个被控对象，提供给用户利用人机交互装置输入操作指令来控制这些被控对象，从而执行相应的控制操作。例如，在图形界面上显示图标，利用人机交互装置可以对该图标进行操作，用来执行特定的功能，例如在超声图像上绘制出感兴趣区域框等。
可选地，超声成像系统100还可以包括显示器118之外的其他人机交互装置，其与处理器116连接，例如，处理器116可以通过外部输入/输出端口与人机交互装置连接，外部输入/输出端口可以是无线通信模块，也可以是有线通信模块，或者两者的组合。外部输入/输出端口也可基于USB、如CAN等总线协议、和/或有线网络协议等来实现。
其中，人机交互装置可以包括输入设备，用于检测用户的输入信息，该输入信息例如可以是对超声波发射/接收时序的控制指令，可以是在超声图像上绘制出点、线或框等的操作输入指令，或者还可以包括其他指令类型。输入设备可以包括键盘、鼠标、滚轮、轨迹球、移动式输入设备(例如带触摸显示屏的移动设备、手机等等)、多功能旋钮等等其中之一或者多个的结合。人机交互装置还可以包括诸如打印机之类的输出设备。
超声成像系统100还可以包括存储器124，用于存储处理器执行的指令、存储接收到的超声回波、存储超声图像，等等。存储器可以为闪存卡、固态存储器、硬盘等。其可以为易失性存储器和/或非易失性存储器，为可移除存储器和/或不可移除存储器等。
应理解，图1所示的超声成像系统100所包括的部件只是示意性的，其可以包括更多或更少的部件。本申请对此不限定。
下面，将参考图2描述根据本申请实施例的胎儿颅骨的超声成像方法。图2是本申请实施例的胎儿颅骨的超声成像方法200的一个示意性流程图。
如图2所示，本申请一个实施例的胎儿颅骨的超声成像方法200包括如下步骤：
在步骤S210，处理器控制超声探头向待测胎儿的颅脑发射超声波，并接收所述超声波的回波，以获得所述超声波的回波信号；
在步骤S220，所述处理器基于所述超声波的回波信号获得所述待测胎儿的颅脑的三维超声数据；
在步骤S230，所述处理器基于所述三维超声数据确定目标方位，所述目标方位为使所述三维超声数据中的颅骨区域处于渲染角度下的方位；
在步骤S240，所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
在步骤S250，所述处理器确定所述三维超声数据中的颅骨区域；
在步骤S260，所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
本申请实施例的胎儿颅骨的超声成像方法200能够实现对胎儿颅骨的自动成像，大幅减少用户的手动操作，提高胎儿颅骨检查的效率与准确率。
示例性地，在步骤S210中，可以基于图1所示的超声成像系统100进行超声扫描。用户移动超声探头110选择合适的位置和角度对待测胎儿的颅脑进行三维超声扫描，三维超声扫描可以是针对胎儿颅脑的矢状面、冠状面或者横截面。在扫描过程中，发射电路112将一组经过延迟聚焦的发射脉冲发送到超声探头110，以激励超声探头110沿二维扫描平面向待测胎儿的颅脑发射超声波。接收电路114控制超声探头110接收到待测胎儿的颅脑反射回的超声回波后，将其转化为电信号，由波束合成模块112对多次发射和接收得到的超声回波信号进行相应的延时与加权求和的处理，实现波束合成，再送入处理器116进行后续的信号处理。
在步骤S220中，超声成像系统的处理器基于接收到的超声波的回波信号获得待测胎儿的颅脑的三维超声数据。示例性地，继续参照图1，处理器116可以对超声探头110在一系列扫描平面内扫描得到的超声回波信号的三维空间关系进行整合，从而实现胎儿颅脑在三维空间的扫描以及三维超声数据的重建。最后，经过去噪、平滑、增强等部分或全部图像后处理步骤后，获得 胎儿颅脑的三维超声数据。
在步骤S230中，处理器基于三维超声数据确定目标方位，目标方位为使三维超声数据中的颅骨区域处于渲染角度下的方位。确定目标方位后，在步骤S240，处理器基于步骤S230中确定的目标方位将三维超声数据旋转到该目标方位，即由处理器实现对三维超声数据的自动摆正。将三维超声数据旋转到目标方位可以将三维超声数据中的颅骨区域旋转到渲染角度下，以便于最终得到包含颅骨区域的渲染图像，而无需用户手动进行旋转，提高胎儿颅骨超声检查的效率和准确性。
其中，目标方位可以是使三维超声数据中的颅骨的感兴趣特征结构的区域处于渲染角度下的方位。感兴趣特征结构可以包括颅缝、囟门等需要用户仔细检查的特征结构。当然，感兴趣特征结构也可以是胎儿颅骨的其他需要观察的特征结构。由于不同感兴趣特征结构可能位于胎儿颅骨的不同方位，目标方位可以包括多个，例如胎儿颅脑的正面、侧面，头顶等，不同的目标方位可以对应不同的感兴趣特征结构。示例性地，可以预先设定多个备选目标方位供用户选择，处理器根据接收到的选择指令确定目标方位，在该目标方位下对待测胎儿的颅骨进行自动超声成像，以便于用户观察该目标方位对应的感兴趣特征结构。
作为一种可选的实现方式，确定目标方位可以包括：在三维超声数据中检测目标特征结构的区域，根据检测到的目标特征结构的区域所在的位置确定三维超声数据需要旋转的角度，或者根据至少两个目标特征结构的区域之间的相对位置关系确定三维超声数据需要旋转的角度。目标特征结构包括以下至少之一：脑中线，丘脑，胼胝体、眼球、脑干、小脑、囟门、颅缝和颅骨，目标特征结构也可以是胎儿颅脑或颅骨的其他标志性特征结构。
其中，可以采用传统的目标检测方法或者机器学习方法在三维超声数据中检测目标特征结构。在检测目标特征结构时，既可以在三维超声数据的多个二维切面中检测目标特征结构，并综合多个二维切面上目标特征结构的检测结果，以得到目标特征结构在三维超声数据中的三维检测结果；也可以直接对三维超声数据进行三维检测，以得到目标特征结构的三维检测结果。
示例性地，传统的目标检测方法可以包括区域选择、特征提取和分类三个步骤。具体地，区域选择是指基于例如滑动窗口的方法，框选出候选目标区域；特征提取是指对候选目标区域进行特征提取，所提取的特征例如SIFT (尺度不变特征变换)、HOG(方向梯度直方图)等特征。分类是指利用分类器对候选目标区域进行分类，以确定当前候选目标区域是否包括目标特征结构，分类器可以采用KNN(K-近邻算法)、SVM(支持向量机)、随机森林等类型的分类器。传统的目标检测方法还可以包括像素聚类法、边缘分割、图切割或基于阈值的图像分割算法等。
基于机器学习方法在三维超声数据中检测目标特征结构需要预先构建针对每个目标特征结构的三维超声数据库，其中每一个三维超声数据均标记了目标特征结构对应的位置，之后基于三维超声数据库学习一个最优映射函数，用于从三维超声数据映射到目标特征结构。机器学习方法可以包括以下几种方法，以下几种方法可以单独实现，也可以相互结合。
其中，第一种可选的机器学习方法为基于滑动窗口的方法。具体地，首先对滑窗内的区域进行特征提取，所提取的特征可以是传统的PCA(主成分分析)、LDA(线性判别分析)、Harr特征、纹理等特征，也可以采用深度神经网络来进行特征提取。然后，利用训练好的分类器进行分类，确定当前窗口内是否包括目标特征结构。
第二种可选的机器学习方法为基于边界框(Bounding-Box)的深度学习方法。其中，首先通过堆叠卷积层和全连接层来构建网络，基于构建好的三维超声数据库通过网络进行特征的学习和参数的回归，将三维超声数据库中的训练样本送入提前构建好的网络中，优化网络的损失函数以进行训练，直到网络达到收敛，在训练过程中网络能够学习到如何从三维超声数据中识别到目标特征结构所在的位置。训练机器学习模型的具体过程可以是直接对三维超声数据进行训练，也可以是将三维超声数据分解为多个二维切面，分别对多个二维切面进行训练再拼接成三维超声数据的训练结果。
训练好网络后，对于输入到网络中的三位超声数据，可以通过该网络直接回归出对应的目标特征结构的边界框，同时获取边界框内包含的目标特征结构的类别。网络结构包括但不限于R-CNN、Fast R-CNN、Faster-RCNN、SSD、YOLO等。
第三种可选的机器学习方法为基于深度学习的端到端的语义分割网络方法，该类方法与上述基于边界框的深度学习方法结构类似，不同之处在于，语义分割网络将网络最后的全连接层去除，加入上采样或者反卷积层来使得输入与输出的尺寸相同，从而直接得到输入网络的三维超声数据中目标特征 结构及其相应类别。示例性地，语义分割网络的网络结构包括但不限于FCN、U-Net、Mask R-CNN等。
在检测到三维超声数据中的目标特征结构之后，可以根据目标特征结构来间接计算胎儿颅脑的三维超声数据需要旋转的角度。其中，可以根据至少一个目标特征结构的区域所在的位置确定三维超声数据需要旋转的角度。例如，可以通过计算将目标特征结构从当前位置旋转到目标位置所需的旋转角度来间接确定三维超声数据旋转到目标方位所需的旋转角度。或者，可以根据至少两个目标特征结构的区域之间的相对位置关系确定三维超声数据需要旋转的角度。例如，可以根据目标结构之间的对称性来确定三维超声数据需要旋转的角度。
之后，基于根据目标特征结构确定的三维超声数据需要旋转的角度，将步骤S220获取到的三维超声数据旋转到目标方位。由于该超声数据为是三维超声数据，旋转时三个维度都对应着一个旋转角度，沿着三个维度分别旋转对应的角度，即可得到旋转后的三维超声数据。
作为将三维超声数据旋转到目标方位的另外一种可选的实现方式，可以直接采用训练好的机器学习模型回归出三维超声数据需要旋转的角度，并根据基于机器学习模型得到的三维超声数据需要旋转的角度将所述三维超声数据旋转到所述目标方位。
当采用机器学习模型确定三维超声数据需要旋转的角度时，需要预先构建胎儿颅脑的三维超声数据库，用于训练机器学习模型。胎儿颅脑的三维超声数据库中包含对至少一个胎儿颅脑的三维超声数据对应的标定结果，该标定结果即为三维超声数据需要旋转的角度，通过训练好的机器学习模型可以直接回归出旋转角度。该机器学习模型可以采用深度学习网络，深度学习网络结构包括但不限于VGG、ResNet、DenseNet、DPN等。
之后，基于机器学习模型输出的三维超声数据需要旋转的角度，将步骤S220获取到的三维超声数据旋转到目标方位。类似地，机器学习模型输出的角度也可以是三个维度对应的旋转角度，沿着三个维度分别旋转对应的角度，即可得到旋转后的三维超声数据。
之后，在步骤S250，处理器在胎儿颅脑的三维超声数据中确定颅骨区域，从而确定三维超声数据的最终的成像显示范围，针对颅骨进行渲染成像可以提高胎儿颅骨的超声成像的准确度，避免其他组织区域影响对颅骨区域的渲染效果。具体地，处理器可以在旋转前的三维超声数据中确定颅骨区域，并 对颅骨区域进行旋转，以得到旋转后的颅骨区域；也可以在旋转后的三维超声数据中确定颅骨区域。
示例性地，根据颅骨区域的形态以及形成方式的不同，确定颅骨区域的方法包含以下几种：
确定颅骨区域的第一种可选的方法包括：在三维超声数据中分割出颅骨区域的边界，将颅骨区域的边界形成的区域作为颅骨区域。具体地，可以采用与步骤S230中类似的传统目标检测方法或机器学习方法来从三维超声数据中自动分割出颅骨区域，将该颅骨区域的分割结果作为所确定的颅骨区域。
确定颅骨区域的第二种可选的方法包括：在三维超声数据中检测出包含颅骨区域的感兴趣区域，在感兴趣区域中确定颅骨区域。该方法自动检测出颅骨区域的位置与大小，以设定合适的颅骨区域。具体地，首先可以采用与步骤S230中类似的传统目标检测方法或机器学习方法来识别出颅骨区域的位置，并基于识别结果进一步计算颅骨区域的大小。最后，根据颅骨区域的位置与大小来设置合适的边界框，例如最大外接梯形框，以作为感兴趣区域，并在感兴趣区域中确定颅骨区域。
确定颅骨区域的第三种可选的方法包括：通过设置CMPR(Curve Multiple Plane Rendering，曲线多平面渲染)参考线来确定颅骨区域。具体地，在三维超声数据中提取包含颅骨区域的目标二维切面；在目标二维切面上沿着颅骨区域绘制CMPR参考线，并根据CMPR参考线确定目标二维切面中的二维感兴趣区域；在垂直于目标二维切面的方向选择垂直于二维感兴趣区域的三维区域；在选择的三维区域中确定颅骨区域。其中，CMPR参考线是指从三维超声数据的目标二维切面中沿着颅骨区域绘制的一条曲线，垂直于目标二维切面的方向选择合适的厚度可进行CMPR成像，CMPR成像时需沿着CMPR参考线的方向对这一厚度的三维超声数据进行拉直。参照图3，图3左侧示出了CMPR参考线，右侧为基于CMPR参考线得到的渲染图像。
示例性地，在三维超声数据中提取包含颅骨区域的目标二维切面包括：在三维超声数据中随机截取至少一个二维切面，或沿预设方向截取至少一个二维切面；在至少一个二维切面中确定包含所述颅骨区域的二维切面，以作为目标二维切面。
在步骤S260中，处理器对旋转后的三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示该渲染图像。由于表层以及中层组织结构的遮挡，直接对三维超声数据进行成像可能无法直观地观察到胎儿的颅骨 骨性结构，而针对颅骨区域进行渲染可以更清晰地呈现颅骨的骨性结构，便于用户对颅骨的发育情况进行检查。其中，对颅骨区域进行渲染可以是仅对颅骨区域进行渲染，例如可以去除颅骨区域以外的三维超声数据，对保留的颅骨区域进行渲染。或者，对颅骨区域进行渲染可以是对包含颅骨区域的区域进行渲染，并在渲染过程中通过渲染方式的设定对颅骨区域和其他区域进行区分，以凸显出颅骨的骨性结构。
示例性地，对颅骨区域进行渲染的方法主要包括体绘制的方法和面绘制的方法。
体绘制的方法主要为光线追踪算法，该算法基于视线方向发射多根穿过三维超声数据的光线，每一根光线按固定步长进行递进，对光线路径上的三维超声数据进行采样，计算每个采样点的颜色与不透明度，再对每一根光线路径上的颜色和不透明度进行累积，最后将累积颜色值映射到2D图像的每个像素上，即可得到VR(Volume Rendering)渲染图。其中，体绘制所采用的三维渲染模式包括以下任意一种：
a、表面成像模式(Surface模式)，该模式主要显示物体表面信息；
b、最大回声模式(Max模式)，该模式主要显示物体内部最大值信息；
c、最小回声模式(Min模式)，该模式主要显示物体内部最小值信息；
d、X光模式(X-Ray模式)，该模式主要显示物体内部结构信息；
e、光影成像模式(Volume Rendering with Global Illumination模式)，该模式基于全局光照模型显示物体表面信息，能够模拟真实皮肤质感以及阴影效果；
f、轮廓模式(Silhouette模式)，该模式通过半透明效果显示物体内外轮廓信息。
可选地，以上几种三维渲染模式也可以相互结合。
面绘制的主要方法分为“基于断层轮廓线(Delaunay)”以及“体素中抽取等值面(MarchingCube)”两类方法，以MarchingCube为例，通过提取三维超声数据中组织或器官的等值面(即表面轮廓)信息——三角面片的法向量以及顶点坐标，建立三角形网格模型，然后再结合光照模型(包括环境光、散射光、高光等，不同光源参数)进行立体渲染，其中光照模型包括环境光、散射光、高光等，不同光源参数(类型、方向、位置、角度)会在不同程度上影响光照模型的效果，即可得到渲染图像。
进一步地，在得到渲染图像之后，处理器还可以控制显示器显示表征渲染图像中不同区域对应的特征结构的标识，以便于用户参考。处理器显示的 标识可以是不同区域对应的特征结构的名称，例如顶骨、前囟、后囟等；处理器显示的标识也可以是能够表征不同特征结构的符号或图形。
在一个实施例中，处理器可以根据胎儿颅骨的特征结构图与渲染图像的对应关系生成渲染图像中不同区域对应的特征结构的标识。参照图4，其中左侧显示的是胎儿颅骨的特征结构图，右侧显示的是渲染图像。胎儿颅骨的特征结构图中显示有对每个区域对应的特征结构的标识，处理器可以根据胎儿颅骨的特征结构图中的标识，在渲染图像中相应的位置生成对应同一特征结构的标识。在该实施例中，处理器可以不划分渲染图像中每个特征结构的具体区域。
在另一个实施例中，处理器可以首先确定渲染图像中不同特征结构的区域，根据不同特征结构的区域生成每个特征结构的区域对应的特征结构的标识。
示例性地，确定渲染图像中不同特征结构对应的区域包括：提取渲染图像的图像特征；对图像特征进行分类，以在渲染图像中划分出不同特征结构对应的区域。具体地，可以采用类似步骤S230中的传统目标检测方法或机器学习方法进行特征提取和特征分类，以确定渲染图像中不同特征结构对应的区域。
在一些实施例中，处理器在确定渲染图像中不同特征结构对应的区域后，可以控制显示器将不同特征结构对应的区域进行区别化显示。可选地，该实施例可以单独实现，即处理器仅控制显示器将不同特征结构对应的区域进行区别化显示，以便于用户区分不同区域，而无需显示不同特征结构对应的标识；该实施例也可以与上文所述的实施例结合，即处理器在控制显示器将不同特征结构对应的区域进行区别化显示的同时，还可以控制显示器显示表征渲染图像中不同区域对应的特征结构的标识。
示例性地，将不同特征结构对应的区域进行区别化显示，包括：在渲染图像中将不同特征结构对应的区域显示为不同的形式。例如，处理器可以控制显示器将不同特征结构对应区域显示为不同的颜色、透明度、亮度等。处理器也可以控制显示器将不同区域的边界显示为不同的形式，以对不同特征结构对应的区域进行区分。
在一些实施例中，当处理器接收到对渲染图像中不同特征结构对应的区域的选择指令时，控制显示器将该选择指令所选择的区域在渲染图像中突出显示。突出显示的形式包括但不限于高亮显示、闪烁显示、放大显示等。其中，对渲染图像中不同特征结构对应的区域的选择指令可以基于上述不同特 征结构对应的标识接收到的，即检测到用户选择某一特征结构的标识时，将该标识对应的区域突出显示；选择指令也可以是基于渲染图像本身所接收到的，即检测到用户选择了渲染图像的某一位置时，将该位置所属的区域突出显示。或者，选择指令也可以是基于渲染图像以外的其他与渲染图像的不同区域具有映射关系的被控对象所接收到的。
综上所述，本申请实施例的胎儿颅骨的超声成像方法200能够实现对胎儿颅骨的自动成像，大幅减少医生的手动操作，提高胎儿颅骨超声检查的效率与准确率。
本申请实施例还提供一种超声成像系统，用于实现上述的胎儿颅骨的超声成像方法200。该超声成像系统包括超声探头、发射电路、接收电路、处理器和显示器。其中，发射电路用于激励超声探头向待测胎儿的颅脑发射超声波；接收电路用于控制超声探头接收超声波的回波，以获得超声回波信号；处理器用于执行如上的胎儿颅骨的超声成像方法200的步骤，具体包括：处理器控制超声探头向待测胎儿的颅脑发射超声波，并接收所述超声波的回波，以获得所述超声波的回波信号；所述处理器基于所述超声波的回波信号获得所述待测胎儿的颅脑的三维超声数据；所述处理器基于所述三维超声数据确定目标方位，所述目标方位为使所述三维超声数据中的颅骨区域处于渲染角度下的方位；所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；所述处理器确定所述三维超声数据中的颅骨区域；所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
现在重新参照图1，该超声成像系统可以实现为如图1所示的超声成像系统100，超声成像系统100可以包括超声探头110、发射电路112、接收电路114、处理器116以及显示器118，可选地，超声成像系统100还可以包括发射/接收选择开关120和波束合成模块122，发射电路112和接收电路114可以通过发射/接收选择开关120与超声探头110连接，各个部件的相关描述可以参照上文的相关描述，在此不做赘述。
以上仅描述了超声成像系统各部件的主要功能，更多细节参见对胎儿颅骨的超声成像方法200进行的相关描述。本申请实施例的超声成像系统能够实现对胎儿颅骨的自动成像，大幅减少医生的手动操作，提高胎儿颅骨超声检查的效率与准确率。
下面，将参考图5描述根据本申请另一实施例的胎儿颅骨的超声成像方法。图5是本申请实施例的胎儿颅骨的超声成像方法500的一个示意性流程图。
如图5所示，胎儿颅骨的超声成像方法500包括如下步骤：
在步骤S510，处理器获得待测胎儿的颅脑的三维超声数据；
在步骤S520，所述处理器基于所述三维超声数据确定目标方位；
在步骤S530，所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
在步骤S540，所述处理器确定所述三维超声数据中的颅骨区域；
在步骤S550，所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
本实施例的胎儿颅骨的超声成像方法500与上文中的超声成像方法200的主要区别在于：本实施例的胎儿颅骨的超声成像方法500不限制处理器获得待测胎儿的颅脑的三维超声数据的具体方式。例如，处理器可以采用如胎儿颅骨的超声成像方法200中所述的方法实时进行三维超声扫描以获取待测胎儿颅脑的三维超声数据；或者，处理器也可以从存储器中提取预先采集的待测胎儿颅脑的三维超声数据等。除此之外，根据本申请实施例的胎儿颅骨的超声成像方法500中与参考图2描述的胎儿颅骨的超声成像方法200大体上类似，为了简洁，此处不再赘述相同的细节内容。
本申请实施例还提供一种超声成像系统，用于实现上述的胎儿颅骨的超声成像方法500。该超声成像系统包括超声探头、发射电路、接收电路、处理器和显示器。其中，发射电路用于激励超声探头向待测胎儿的颅脑发射超声波；接收电路用于控制超声探头接收超声波的回波，以获得超声回波信号；处理器用于执行如上的胎儿颅骨的超声成像方法500的步骤，具体包括：处理器获得待测胎儿的颅脑的三维超声数据；处理器基于三维超声数据确定目标方位；处理器将三维超声数据旋转到目标方位；处理器确定三维超声数据中的颅骨区域；处理器对旋转后的三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示渲染图像；显示器用于显示处理器得到的渲染图像。
现在重新参照图1，该超声成像系统可以实现为如图1所示的超声成像系统100，超声成像系统100可以包括超声探头110、发射电路112、接收电 路114、处理器116以及显示器118，可选地，超声成像系统100还可以包括发射/接收选择开关120和波束合成模块122，发射电路112和接收电路114可以通过发射/接收选择开关120与超声探头110连接，各个部件的相关描述可以参照上文的相关描述，在此不做赘述。
以上仅描述了超声成像系统各部件的主要功能，更多细节参见上文相关描述。本申请实施例的胎儿颅骨的超声成像方法500和超声成像系统能够实现对胎儿颅骨的自动成像，大幅减少医生的手动操作，提高胎儿颅骨超声检查的效率与准确率。
下面，将参考图6描述根据本申请另一实施例的超声成像方法。图6是本申请实施例的胎儿颅骨的超声成像方法600的一个示意性流程图。
如图6所示，本申请一个实施例的超声成像方法600包括如下步骤：
在步骤S610，获取待测胎儿的颅脑的三维超声数据；
在步骤S620，基于胎儿的颅骨图像特征在所述三维超声数据中确定颅骨区域；
在步骤S630，对所述颅骨区域进行渲染，以得到渲染图像；
在步骤S640，显示所述渲染图像。
根据本申请实施例的胎儿颅骨的超声成像方法600中与参考图2描述的胎儿颅骨的超声成像方法200和参考图5描述的胎儿颅骨的超声成像方法500的主要区别之处在于，胎儿颅骨的超声成像方法600不对三维超声数据进行旋转。在一些情况下，无需对三维超声数据进行旋转即可实现对颅骨的渲染成像。可选地，可以由用户在进行超声扫查的过程中通过调整探头角度实现对三维超声数据方位的调整，或者可以在获取三维超声数据后由用户手动旋转。
在一个实施例中，在三维超声数据中确定颅骨区域包括：在三维超声数据中分割出颅骨区域的边界，将颅骨区域的边界形成的区域作为颅骨区域；或者，在三维超声数据中检测出包含颅骨区域的感兴趣区域，在感兴趣区域中确定颅骨区域。该方式的具体细节可以参照胎儿颅骨的超声成像方法200的步骤S250中的相关描述。
在另一个实施例中，在三维超声数据中确定颅骨区域包括：在三维超声数据中提取包含颅骨区域的目标二维切面；在目标二维切面上沿着颅骨区域 绘制曲线多平面渲染参考线，并根据曲线多平面渲染参考线确定目标二维切面中的二维感兴趣区域；在垂直于目标二维切面的方向选择垂直于二维感兴趣区域的三维区域；在选择的三维区域中确定颅骨区域。该方式的具体细节可以参照胎儿颅骨的超声成像方法200的步骤S250中的相关描述。
在步骤S640中，还可以显示表征所述渲染图像中不同区域对应的特征结构的标识。显示的标识可以是不同区域对应的特征结构的名称，显示的标识也可以是能够表征不同特征结构的符号或图形。
示例性地，可以根据胎儿颅骨的特征结构图与渲染图像的对应关系生成渲染图像中不同区域对应的特征结构的标识。特征结构图中显示有对每个特征结构对应的区域进行的标识，可以根据胎儿颅骨的特征结构图中的标识，在渲染图像中相应的位置生成对应同一特征结构的标识。
或者，可以确定渲染图像中不同特征结构的区域，根据不同特征结构的区域生成每个特征结构的区域对应的特征结构的标识。例如，可以提取渲染图像的图像特征，并对图像特征进行分类，以在渲染图像中划分出不同特征结构对应的区域。具体地，可以采用传统目标检测方法或机器学习方法进行特征提取和特征分类，以确定渲染图像中不同特征结构对应的区域。
在确定渲染图像中不同特征结构对应的区域后，可以将不同特征结构对应的区域进行区别化显示。例如，可以将不同特征结构对应区域显示为不同的颜色、透明度、亮度等。或者，也可以将不同区域的边界显示为不同的形式，以对不同特征结构对应的区域进行区分。
在一些实施例中，当接收到对渲染图像中不同特征结构对应的区域的选择指令时，可以将该选择指令所选择的区域突出显示。突出显示的形式包括但不限于高亮显示、闪烁显示、放大显示等。其中，对渲染图像中不同特征结构对应的区域的选择指令可以基于上述不同特征结构对应的标识接收到的，即检测到用户选择某一特征结构的标识时，将该标识对应的区域突出显示；选择指令也可以是基于渲染图像本身所接收到的，即检测到用户选择了渲染图像的某一位置时，将该位置所属的区域突出显示。或者，选择指令也可以是基于渲染图像以外的其他与渲染图像的不同区域具有映射关系的被控对象所接收到的。
本申请实施例的超声成像方法600能够实现对胎儿颅骨的自动成像，大幅减少医生的手动操作，提高胎儿颅骨超声检查的效率与准确率。
本申请实施例还提供一种超声成像系统，用于实现上述的超声成像方法600。该超声成像系统包括超声探头、发射电路、接收电路、处理器和显示器。其中，发射电路用于激励超声探头向待测胎儿的颅脑发射超声波；接收电路用于控制超声探头接收超声波的回波，以获得超声回波信号；处理器用于执行如上的超声成像方法600的步骤，具体包括：获取待测胎儿的颅脑的三维超声数据；基于胎儿的颅骨图像特征在所述三维超声数据中确定颅骨区域；对所述颅骨区域进行渲染，以得到渲染图像；在步骤S640，显示所述渲染图像。
现在重新参照图1，该超声成像系统可以实现为如图1所示的超声成像系统100，超声成像系统100可以包括超声探头110、发射电路112、接收电路114、处理器116以及显示器118，可选地，超声成像系统100还可以包括发射/接收选择开关120和波束合成模块122，发射电路112和接收电路114可以通过发射/接收选择开关120与超声探头110连接，各个部件的相关描述可以参照上文的相关描述，在此不做赘述。
以上仅描述了超声成像系统100各部件的主要功能，更多细节参见上文的相关描述。
此外，根据本申请实施例，还提供了一种计算机存储介质，在所述计算机存储介质上存储了程序指令，在所述程序指令被计算机或处理器运行时用于执行本申请实施例的胎儿颅骨的超声成像方法200、胎儿颅骨的超声成像方法500或胎儿颅骨的超声成像方法600的相应步骤。所述存储介质例如可以包括智能电话的存储卡、平板电脑的存储部件、个人计算机的硬盘、只读存储器(ROM)、可擦除可编程只读存储器(EPROM)、便携式紧致盘只读存储器(CD-ROM)、USB存储器、或者上述存储介质的任意组合。所述计算机可读存储介质可以是一个或多个计算机可读存储介质的任意组合。
此外，根据本申请实施例，还提供了一种计算机程序，该计算机程序可以存储在云端或本地的存储介质上。在该计算机程序被计算机或处理器运行时用于执行本申请实施例的胎儿颅骨的超声成像方法的相应步骤。
基于上面的描述，根据本申请实施例的胎儿颅骨的超声成像方法和超声成像系统能够实现对胎儿颅骨的自动成像，大幅减少医生的手动操作，提高胎儿颅骨超声检查的效率与准确率。
尽管这里已经参考附图描述了示例实施例，应理解上述示例实施例仅仅 是示例性的，并且不意图将本申请的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改，而不偏离本申请的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本申请的范围之内。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个设备，或一些特征可以忽略，或不执行。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该本申请的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如相应的权利要求书所反映的那样，其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域的技术人员可以理解，除了特征之间相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组 合意味着处于本申请的范围之内并且形成不同的实施例。例如，在权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的一些模块的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
以上所述，仅为本申请的具体实施方式或对具体实施方式的说明，本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。本申请的保护范围应以权利要求的保护范围为准。

Claims (23)

  1. 一种胎儿颅骨的超声成像方法，其特征在于，所述方法包括：
    处理器控制超声探头向待测胎儿的颅脑发射超声波，并接收所述超声波的回波，以获得所述超声波的回波信号；
    所述处理器基于所述超声波的回波信号获得所述待测胎儿的颅脑的三维超声数据；
    所述处理器基于所述三维超声数据确定目标方位，所述目标方位为使所述三维超声数据中颅骨区域朝向渲染方向的方位；
    所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
    所述处理器确定所述三维超声数据中的颅骨区域；
    所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
  2. 根据权利要求1所述的方法，其特征在于，还包括：所述处理器控制所述显示器显示表征所述渲染图像中不同区域对应的特征结构的标识。
  3. 根据权利要求2所述的方法，其特征在于，还包括：
    所述处理器根据胎儿颅骨的特征结构图与所述渲染图像的对应关系生成所述渲染图像中不同区域对应的特征结构的标识；或者，
    所述处理器确定所述渲染图像中不同特征结构的区域，根据不同特征结构的区域生成每个特征结构的区域对应的特征结构的标识。
  4. 根据权利要求1所述的方法，其特征在于，还包括：所述处理器确定所述渲染图像中不同特征结构对应的区域，并控制所述显示器将所述不同特征结构对应的区域进行区别化显示。
  5. 根据权利要求4所述的方法，其特征在于，所述将所述不同特征结构对应的区域进行区别化显示，包括：在所述渲染图像中将不同特征结构对应的区域显示为不同的颜色。
  6. 根据权利要求3-5中任一项所述的方法，其特征在于，确定所述渲染图像中不同特征结构对应的区域包括：
    提取所述渲染图像的图像特征；
    对所述图像特征进行分类，以在所述渲染图像中划分出不同特征结构对应的区域。
  7. 根据权利要求4所述的方法，其特征在于，还包括：当所述处理器接收到对所述渲染图像中不同特征结构对应的区域的选择指令时，控制所述显示器将所述选择指令所选择的区域在所述渲染图像中突出显示。
  8. 根据权利要求1所述的方法，其特征在于，基于所述三维超声数据确定目标方位包括：
    在所述三维超声数据中检测目标特征结构的区域，所述目标特征结构包括以下至少之一：脑中线，丘脑，胼胝体、眼球、脑干、小脑、囟门、颅缝和颅骨；
    根据所述至少一个目标特征结构的区域所在的位置确定所述三维超声数据需要旋转的角度，或根据至少两个目标特征结构的区域之间的相对位置关系确定所述三维超声数据需要旋转的角度。
  9. 根据权利要求1所述的方法，其特征在于，基于所述三维超声数据确定目标方向包括：
    利用训练好的机器学习模型回归出所述三维超声数据需要旋转的角度。
  10. 根据权利要求1所述的方法，其特征在于，确定所述三维超声数据中的颅骨区域，包括：
    在所述三维超声数据中分割出颅骨区域的边界，将所述颅骨区域的边界形成的区域作为所述颅骨区域；或者，
    在所述三维超声数据中检测出包含颅骨区域的感兴趣区域，在所述感兴趣区域中确定所述颅骨区域。
  11. 根据权利要求1所述的方法，其特征在于，确定所述三维超声数据中的颅骨区域，包括：
    在所述三维超声数据中提取包含颅骨区域的目标二维切面；
    在所述目标二维切面上沿着所述颅骨区域绘制曲线多平面渲染参考线，并根据所述曲线多平面渲染参考线确定所述目标二维切面中的二维感兴趣区域；
    在垂直于所述目标二维切面的方向选择垂直于所述二维感兴趣区域的三维区域；
    在选择的所述三维区域中确定所述颅骨区域。
  12. 根据权利要求11所述的方法，其特征在于，所述在所述三维超声数据中提取包含颅骨区域的目标二维切面包括：
    在所述三维超声数据中随机截取至少一个二维切面或沿预设方向截取至少一个二维切面；
    在所述至少一个二维切面中确定包含所述颅骨区域的二维切面，以作为所述目标二维切面。
  13. 一种胎儿颅骨的超声成像方法，其特征在于，所述方法包括：
    处理器获得待测胎儿的颅脑的三维超声数据；
    所述处理器基于所述三维超声数据确定目标方位；
    所述处理器基于所述目标方位将所述三维超声数据旋转到所述目标方位；
    所述处理器确定所述三维超声数据中的颅骨区域；
    所述处理器对旋转后的所述三维超声数据中的颅骨区域进行渲染，以得到渲染图像，并控制显示器显示所述渲染图像。
  14. 一种超声成像方法，其特征在于，所述方法包括：
    获取待测胎儿的颅脑的三维超声数据；
    基于胎儿的颅骨图像特征在所述三维超声数据中确定颅骨区域；
    对所述颅骨区域进行渲染，以得到渲染图像；
    显示所述渲染图像。
  15. 根据权利要求14所述的方法，其特征在于，还包括：
    显示表征所述渲染图像中不同区域对应的特征结构的标识。
  16. 根据权利要求15所述的方法，其特征在于，还包括：
    根据胎儿颅骨的特征结构图与所述渲染图像的对应关系生成所述渲染图像中不同区域对应的特征结构的标识；或者，
    确定所述渲染图像中不同特征结构的区域，根据不同特征结构的区域生成每个特征结构的区域对应的特征结构的标识。
  17. 根据权利要求14所述的方法，其特征在于，还包括：
    确定所述渲染图像中不同特征结构对应的区域，并将所述不同特征结构对应的区域进行区别化显示。
  18. 根据权利要求17所述的方法，其特征在于，还包括：
    当接收到对所述渲染图像中不同特征结构对应的区域的选择指令时，将所述选择指令所选择的区域在所述渲染图像中突出显示。
  19. 根据权利要求14所述的方法，其特征在于，在所述三维超声数据中确定颅骨区域，包括：
    在所述三维超声数据中分割出颅骨区域的边界，将所述颅骨区域的边界形成的区域作为颅骨区域；或者，
    在所述三维超声数据中检测出包含颅骨区域的感兴趣区域，在所述感兴趣区域中确定所述颅骨区域。
  20. 根据权利要求14所述的方法，其特征在于，在所述三维超声数据中确定颅骨区域，包括：
    在所述三维超声数据中提取包含颅骨区域的目标二维切面；
    在所述目标二维切面上沿着所述颅骨区域绘制曲线多平面渲染参考线，并根据所述曲线多平面渲染参考线确定所述目标二维切面中的二维感兴趣区域；
    在垂直于所述目标二维切面的方向选择垂直于所述二维感兴趣区域的三维区域；
    在选择的所述三维区域中确定所述颅骨区域。
  21. 一种超声成像系统，其特征在于，包括：
    超声探头；
    发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
    接收电路，用于控制所述超声探头接收所述超声波的回波，以获得所述超声波的回波信号；
    处理器，用于执行权利要求1-12中任一项所述的胎儿颅骨的超声成像方法的步骤；
    显示器，用于显示所述处理器得到的渲染图像。
  22. 一种超声成像系统，其特征在于，包括：
    超声探头；
    发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
    接收电路，用于控制所述超声探头接收所述超声波的回波，以获得所述超声波的回波信号；
    处理器，用于执行权利要求13所述的胎儿颅骨的超声成像方法的步骤；
    显示器，用于显示所述处理器得到的渲染图像。
  23. 一种超声成像系统，其特征在于，包括：
    超声探头；
    发射电路，用于激励所述超声探头向待测胎儿的颅脑发射超声波；
    接收电路，用于控制所述超声探头接收所述超声波的回波，以获得所述超声波的回波信号；
    处理器，用于执行权利要求14-20中任一项所述的胎儿颅骨的超声成像方法的步骤；
    显示器，用于显示所述处理器得到的渲染图像。
PCT/CN2020/139558 2020-12-25 2020-12-25 胎儿颅骨的超声成像方法和超声成像系统 WO2022134049A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/139558 WO2022134049A1 (zh) 2020-12-25 2020-12-25 胎儿颅骨的超声成像方法和超声成像系统
CN202080107457.6A CN116568223A (zh) 2020-12-25 2020-12-25 胎儿颅骨的超声成像方法和超声成像系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/139558 WO2022134049A1 (zh) 2020-12-25 2020-12-25 胎儿颅骨的超声成像方法和超声成像系统

Publications (1)

Publication Number Publication Date
WO2022134049A1 true WO2022134049A1 (zh) 2022-06-30

Family

ID=82157275

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/139558 WO2022134049A1 (zh) 2020-12-25 2020-12-25 胎儿颅骨的超声成像方法和超声成像系统

Country Status (2)

Country Link
CN (1) CN116568223A (zh)
WO (1) WO2022134049A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101057787A (zh) * 2006-04-20 2007-10-24 通用电气公司 基于患者特定信息自动获得超声象平面的系统和方法
CN104545919A (zh) * 2014-12-31 2015-04-29 中国科学院深圳先进技术研究院 一种超声穿颅聚焦的方法
US20170119354A1 (en) * 2014-05-09 2017-05-04 Koninklijke Philips N.V. Imaging systems and methods for positioning a 3d ultrasound volume in a desired orientation
EP3689248A1 (en) * 2019-01-30 2020-08-05 Samsung Medison Co., Ltd. Ultrasound imaging apparatus and method of generating ultrasound image
CN107106143B (zh) * 2015-05-07 2020-10-20 深圳迈瑞生物医疗电子股份有限公司 三维超声成像方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101057787A (zh) * 2006-04-20 2007-10-24 通用电气公司 基于患者特定信息自动获得超声象平面的系统和方法
US20170119354A1 (en) * 2014-05-09 2017-05-04 Koninklijke Philips N.V. Imaging systems and methods for positioning a 3d ultrasound volume in a desired orientation
CN104545919A (zh) * 2014-12-31 2015-04-29 中国科学院深圳先进技术研究院 一种超声穿颅聚焦的方法
CN107106143B (zh) * 2015-05-07 2020-10-20 深圳迈瑞生物医疗电子股份有限公司 三维超声成像方法和装置
EP3689248A1 (en) * 2019-01-30 2020-08-05 Samsung Medison Co., Ltd. Ultrasound imaging apparatus and method of generating ultrasound image

Also Published As

Publication number Publication date
CN116568223A (zh) 2023-08-08

Similar Documents

Publication Publication Date Title
JP6629094B2 (ja) 超音波診断装置、医用画像処理装置及び医用画像処理プログラム
JP2021531885A (ja) 誘導肝イメージングのための人工ニューラルネットワークを有する超音波システム
US10127654B2 (en) Medical image processing apparatus and method
JP2011224362A (ja) 超音波データにおいて関心領域を決定するための方法及びシステム
JP2021506470A (ja) 超音波システムのためのエコー窓のアーチファクト分類及び視覚的インジケータ
WO2018195946A1 (zh) 一种超声图像显示方法、设备及存储介质
US20210393240A1 (en) Ultrasonic imaging method and device
WO2018205274A1 (zh) 一种超声设备及其三维超声图像的显示变换方法、系统
US20230210501A1 (en) Ultrasound contrast imaging method and device and storage medium
JP2012008027A (ja) 病理診断支援装置、病理診断支援方法、病理診断支援のための制御プログラムおよび該制御プログラムを記録した記録媒体
JP5113548B2 (ja) 超音波画像処理装置
WO2022099705A1 (zh) 早孕期胎儿的超声成像方法和超声成像系统
WO2022134049A1 (zh) 胎儿颅骨的超声成像方法和超声成像系统
WO2022099704A1 (zh) 中晚孕期胎儿的超声成像方法和超声成像系统
CN113229850A (zh) 超声盆底成像方法和超声成像系统
CN114617581A (zh) 一种早孕期胎儿的超声成像方法和系统
WO2020133236A1 (zh) 一种脊柱的成像方法以及超声成像系统
CN111383323B (zh) 一种超声成像方法和系统以及超声图像处理方法和系统
WO2024093911A1 (zh) 一种超声成像方法及超声设备
CN111403007A (zh) 一种超声成像的优化方法、超声成像系统和计算机可读存储介质
CN116327237A (zh) 超声成像系统及方法、超声图像处理系统及方法
CN113974688B (zh) 超声成像方法和超声成像系统
CN115778435A (zh) 胎儿颜面部的超声成像方法和超声成像系统
CN114642451A (zh) 一种超声成像装置
CN115886876A (zh) 胎儿姿态的评估方法、超声成像方法及超声成像系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20966614

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202080107457.6

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20966614

Country of ref document: EP

Kind code of ref document: A1