Breast magnetic resonance rapid scanning imaging method and device and electronic equipment

Abstract

The invention provides a mammary gland magnetic resonance rapid scanning imaging method and device and electronic equipment, and relates to the technical field of medical imagines.The method comprises the steps that accelerated scanning is conducted on axial position T1WI, dispersion, enhanced T1WI 3 periods and sagittal position T1WI sequences based on an artificial intelligence compressed sensing model, and mammary gland scanning information of an examined person is obtained; inputting the mammary gland scanning information into a CS network topological structure model to obtain a mammary gland target image; and performing noise reduction processing on the mammary gland target image in a reading gradient direction, a layer selection gradient direction and a phase encoding direction to obtain a denoised mammary gland target image for assisting in assessing a mammary gland focus and positioning. According to the method, efficient and rapid mammary gland imaging is achieved, the examination time is remarkably shortened, and meanwhile the high-quality image resolution is kept.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and in particular to a breast magnetic resonance rapid scanning imaging method, device and electronic equipment. Background Art

[0002] In the clinical diagnosis of breast diseases, magnetic resonance imaging (MRI) technology has become a key tool for evaluating breast structural abnormalities and diagnosing breast cancer with its high soft tissue resolution, no radiation exposure, and multi-parameter imaging capabilities. However, the traditional breast MRI scanning process is time-consuming, especially core sequences such as high B-value diffusion-weighted imaging (DWI) and breast dynamic enhancement scanning (DCE), which significantly increase the overall examination time. This situation may not only lead to increased patient discomfort, but also affect the efficiency of clinical workflow, especially in medical environments with high patient loads.

[0003] Dynamic enhanced scanning (DCE) continuously acquires breast images after contrast agent injection to evaluate the vascularization and hemodynamic characteristics of breast tissue, and is an important means of distinguishing benign and malignant breast lesions. However, this process usually takes more than 8 minutes to capture sufficient phase information for subsequent analysis. High B-value diffusion-weighted imaging (DWI) evaluates changes in tissue microstructure by measuring the diffusion motion of water molecules and has a high sensitivity for the detection of breast cancer. In order to obtain high-quality DWI images, a scanning time of at least 3 minutes is usually required to fully suppress motion artifacts and optimize image contrast. Combining core sequences such as DCE and DWI, plus necessary positioning, calibration, and plain scan sequences, the total time for the entire breast MRI examination may be as long as 18-25 minutes. This not only prolongs the patient's examination experience, but may also cause image quality degradation or patient discomfort due to long-term stillness.

[0004] Therefore, a breast magnetic resonance rapid scanning imaging method, device and electronic equipment are proposed. Summary of the invention

[0005] The present specification provides a breast magnetic resonance rapid scanning imaging method, device and electronic equipment, which realizes efficient and rapid breast imaging, significantly shortens the examination time, and maintains high-quality image resolution.

[0006] This specification provides a breast magnetic resonance rapid scanning imaging method, comprising:

[0007] Based on the artificial intelligence compressed sensing model, the axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences are accelerated to obtain the breast scan information of the person being examined;

[0008] Inputting the breast scan information into the CS network topology model to obtain a breast target image;

[0009] The breast target image is subjected to noise reduction processing in the readout gradient direction, the layer selection gradient direction, and the phase encoding direction to obtain a noise-reduced breast target image for assisting in the assessment and positioning of breast lesions.

[0010] Optionally, imaging parameters for accelerated scanning are: repetition time of 5.3-3683 ms, echo time of 2.6-90 ms, layer thickness of 1-4 mm, deflection angle of 10-90 degrees, and bandwidth of 186.6-718.9 Hz / pixel.

[0011] Optionally, obtaining breast scan information corresponding to the sagittal T1WI includes:

[0012] The examinee faces downward with his back facing upward, and his chest is placed in a semi-enclosed breast coil, and the back of the examinee is covered with an abdominal soft coil, so as to obtain the breast image of the examinee;

[0013] Determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline;

[0014] The person being examined is accelerated scanned based on the sagittal positioning line to obtain breast scan information corresponding to the sagittal T1WI.

[0015] Optionally, determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline, includes:

[0016] Determine the line between the points where the breast skin is inflected based on the breast image, and use it as a baseline;

[0017] A perpendicular line is determined based on the baseline and is used as the sagittal positioning line.

[0018] Optionally, obtaining breast scan information corresponding to the enhanced T1WI stage 3 further includes:

[0019] After scanning a mask film, the contrast agent is directly injected, and the scanning start time after the injection of the contrast agent is determined according to the scanning duration of each phase to ensure that the 90th second is exactly located at the center of the K space, and the 90th second image is output as the breast scanning information corresponding to the enhanced T1WI 3 phase.

[0020] Optionally, inputting the breast scan information into a CS network topology model to obtain a breast target image includes:

[0021] The breast target image includes a breast amplitude image and a breast function image;

[0022] Merging the multi-channel complex information of the object to be scanned corresponding to the breast scanning information to obtain single-channel complex information;

[0023] The single-channel complex information is converted into a breast amplitude image and / or a breast function image.

[0024] This specification provides a breast magnetic resonance rapid scanning imaging device, comprising:

[0025] The acquisition module is used to perform accelerated scanning of axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences based on an artificial intelligence compressed sensing model to obtain breast scan information of the person being examined;

[0026] An input module, used for inputting the breast scan information into the CS network topology model to obtain a breast target image;

[0027] The denoising module is used to perform denoising processing on the breast target image in the readout gradient direction, the layer selection gradient direction and the phase encoding direction to obtain the denoised breast target image to assist in the assessment and positioning of breast lesions.

[0028] Optionally, imaging parameters for accelerated scanning are: repetition time of 5.3-3683 ms, echo time of 2.6-90 ms, layer thickness of 1-4 mm, deflection angle of 10-90 degrees, and bandwidth of 186.6-718.9 Hz / pixel.

[0029] Optionally, obtaining breast scan information corresponding to the sagittal T1WI includes:

[0030] The examinee faces downward with his back facing upward, and his chest is placed in a semi-enclosed breast coil, and the back of the examinee is covered with an abdominal soft coil, so as to obtain the breast image of the examinee;

[0031] Determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline;

[0032] The person being examined is accelerated scanned based on the sagittal positioning line to obtain breast scan information corresponding to the sagittal T1WI.

[0033] Optionally, determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline, includes:

[0034] Determine the line between the points where the breast skin is inflected based on the breast image, and use it as a baseline;

[0035] A perpendicular line is determined based on the baseline and is used as the sagittal positioning line.

[0036] Optionally, obtaining breast scan information corresponding to the enhanced T1WI stage 3 further includes:

[0037] After scanning a mask film, the contrast agent is directly injected, and the scanning start time after the contrast agent injection is determined according to the scanning duration of each phase to ensure that the 90th second is exactly located at the center of the K space, and the 90th second image is output as the breast scanning information corresponding to the enhanced T1WI 3 phase.

[0038] Optionally, the input module includes:

[0039] The breast target image includes a breast amplitude image and a breast function image;

[0040] Merging the multi-channel complex information of the object to be scanned corresponding to the breast scanning information to obtain single-channel complex information;

[0041] The single-channel complex information is converted into a breast amplitude image and / or a breast function image.

[0042] This specification also provides an electronic device, wherein the electronic device includes:

[0043] processor; and,

[0044] A memory storing computer executable instructions, which when executed cause the processor to perform any of the above methods.

[0045] The present specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0046] In the present invention, by optimizing accelerated scanning parameters, such as reasonable repetition time, echo time, layer thickness, deflection angle and bandwidth settings, the method achieves efficient and fast breast imaging, significantly shortens the inspection time, and maintains high-quality image resolution. By using the CS network topology model, complex breast scanning information can be converted into accurate breast target images, including breast amplitude images and functional images, providing doctors with auxiliary diagnostic information. In addition, the method pays special attention to noise reduction processing, and performs fine noise suppression in the readout gradient direction, layer selection gradient direction and phase encoding direction to ensure the clarity and accuracy of the image. It is particularly worth mentioning that in the enhanced T1WI scan, the method ensures that the 90th second image is exactly located in the center of the K space by accurately controlling the scanning time after the contrast agent injection, thereby capturing the breast information at the peak moment of the contrast agent, which is of great value for assisting the evaluation of breast lesions and their positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram of the principle of a breast magnetic resonance rapid scanning imaging method provided in an embodiment of this specification;

[0049] Figure 2 Demonstration diagram for drawing sagittal positioning line;

[0050] Figure 3 A schematic diagram of semi-enclosed detection using an existing breast coil;

[0051] Figure 4 This is a schematic diagram of full enclosure detection using a breast coil combined with an abdominal soft coil;

[0052] Figure 5 A schematic diagram of the structure of a breast magnetic resonance rapid scanning imaging device provided in an embodiment of this specification;

[0053] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0054] Figure 7 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification. DETAILED DESCRIPTION

[0055] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0056] The following is combined with Figure 1-7 The exemplary embodiments of the present invention are described more fully. However, the exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments can make the present invention more comprehensive and complete, and it is more convenient to fully convey the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0057] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0058] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0059] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0060] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0061] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0062] Figure 1 A schematic diagram of the principle of a breast magnetic resonance rapid scanning imaging method provided in an embodiment of this specification, the method may include:

[0063] S110: Based on the artificial intelligence compressed sensing model, the axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences are accelerated to obtain the breast scan information of the person being examined;

[0064] In the specific implementation of this specification, the artificial intelligence-compressed sensing model (AICS) applies artificial intelligence technology, especially deep learning and convolutional neural network (CNN), to the compressed sensing framework to improve the reconstruction quality and processing speed of images or signals. Compressed sensing itself is a signal processing technology that can accurately reconstruct signals by utilizing the sparsity of signals at much lower than traditional sampling rates.

[0065] In AICS, it is first assumed that the signal or image is sparse in a certain domain (such as frequency domain, time domain or space domain), that is, most elements are zero or close to zero, and only a few elements have significant values. Unlike traditional uniform sampling, AICS uses a random sampling strategy to collect discrete samples of signals or images. This sampling method can more effectively capture the sparse characteristics of the signal. Using deep learning algorithms, especially CNN, the collected samples are nonlinearly reconstructed to restore high-quality signals or images. This step is the key in AICS, which relies on a large amount of training data and advanced algorithms to optimize the reconstruction process.

[0066] Conventional breast scanning sequences can be divided into qualitative value sequences and positioning value sequences according to their application value. Qualitative value sequences, that is, sequences with high auxiliary diagnostic value but low positioning value, such as diffusion sequences and enhanced delayed scans. For patients with breast tumors that have been clinically qualitatively diagnosed, puncture will be performed routinely before surgery, so the qualitative value demand of MRI magnetic resonance examination is greatly reduced. Surgeons are more concerned about the size, morphology, relative position and spatial relationship of the tumor itself with surrounding tissues, that is, the positioning value. Therefore, for this part of patients, sequences with high diagnostic value can be abandoned, and sequences with high positioning value can be added, including sagittal T1 enhanced scanning and T1WI non-fat suppression sequence. In the original non-ultrafast simplified sequence, these two sequences were not added due to scanning time limitations and insufficient understanding of the importance of this sequence. Even because the diagnostic value of T1WI without fat suppression is not high enough, it will be abandoned in the conventional breast scanning sequence. However, the T1WI sequence without fat suppression can better reflect the relationship between the mass and fat, and the degree of mass infiltration observed by the naked eye is closer to the perspective of surgery.

[0067] It is worth noting that the scanning range of the sagittal T1WI sequence of the present application includes the unilateral breast and the ipsilateral axilla. Moreover, the conventional breast MRI scanning time is 18-25 minutes, while the breast MRI scanning time of the present application is 6-7 minutes.

[0068] Optionally, imaging parameters for accelerated scanning are: repetition time of 5.3-3683 ms, echo time of 2.6-90 ms, layer thickness of 1-4 mm, deflection angle of 10-90 degrees, and bandwidth of 186.6-718.9 Hz / pixel.

[0069] In the specific implementation of this specification, a 1.5T scanner (Philips Ambition 007, Philips Healthcare, the Netherlands) is used for accelerated scanning, and the imaging parameters of the accelerated scanning are shown in Table 1 below.

[0070] Table 1 Accelerated scanning scheme

[0071]

[0072] Optionally, obtaining breast scan information corresponding to the sagittal T1WI includes: The examinee faces downward with his back facing upward, and his chest is placed in a semi-enclosed breast coil, and the back of the examinee is covered with an abdominal soft coil, so as to obtain the breast image of the examinee;

[0073] Determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline;

[0074] The person being examined is accelerated scanned based on the sagittal positioning line to obtain breast scan information corresponding to the sagittal T1WI.

[0075] Optionally, determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline, includes:

[0076] Determine the line between the points where the breast skin is inflected based on the breast image, and use it as a baseline;

[0077] A perpendicular line is determined based on the baseline and is used as the sagittal positioning line.

[0078] In the specific implementation of this specification, Figure 2 As shown in the figure, the conventional sagittal positioning line is a positioning line that is perpendicular or horizontal to the human breast image (see white line), or a positioning line obtained by drawing a vertical line perpendicular to the chest (such as purple line and blue line). When performing prone breast scanning, due to differences in the size, shape, elasticity and whether the breast of adult women has undergone surgery, the traditional horizontal or vertical positioning method often cannot ensure the accuracy and consistency of the scan. Therefore, based on the breast image, the points where the breast skin is folded are determined. These points are usually located at the junction of the breast and the chest wall and are the landmarks of the breast base. Then, these points are connected to form a baseline (see orange line), which represents the outline of the breast base. Next, with this baseline as a reference, draw a vertical line perpendicular to the baseline (see green line). These vertical lines will be completely perpendicular to the base of the breast, thereby ensuring the perpendicularity of the scanning direction to the breast. Through this positioning method, standard scan images that meet the clinical quadrant segmentation conditions can be obtained. These images are not only highly accurate and consistent, but also can more accurately reflect the internal structure and pathological conditions of the breast. In addition, this method also fully considers the individual differences of different female breasts, ensuring the personalized and targeted scanning. Therefore, when performing prone breast scanning, it is recommended to use this positioning method with the line connecting the breast skin inflection points as the baseline to improve the accuracy and reliability of the scan.

[0079] Lymph node status plays a central role in the prognosis and treatment of breast cancer. In particular, the introduction of sentinel lymph node biopsy (SLNB) technology provides a more accurate and less complication-free axillary staging method for patients with clinically node-negative (cN0) breast cancer. Compared with traditional axillary lymph node dissection (ALND), SLNB significantly reduces the risk of complications such as lymphedema and limited arm movement, while maintaining the effectiveness of treatment. In addition, lymph node status assessment is crucial for guiding subsequent treatment. For example, patients with negative SLNB can avoid unnecessary ALND. In the context of the increasing popularity of breast-conserving surgery, lymph node evaluation is particularly important because it not only affects the safety of surgery, but also affects radiotherapy decisions, such as the necessity of regional lymph node irradiation (RNI). Especially for patients with ipsilateral breast recurrence after breast-conserving surgery, re-SLNB has been proven to be a feasible and safe axillary assessment method, which helps to adjust the treatment plan. The latest version of BIRADS (6th edition) further refines the requirements for lymph node evaluation during breast-conserving surgery, including the inclusion of lymph nodes in the supraclavicular and axillary areas in the analysis. This reflects the importance of lymph node evaluation in the personalized treatment of breast cancer, aiming to improve the accuracy of treatment, reduce complications, and ultimately improve the quality of life of patients.

[0080] like Figure 3 As shown, the existing breast coil is a semi-enclosed coil with a narrow signal collection area. It can only collect signals from the breast area in front of the chest, and the display of the axillary area (see the red arrow) is not ideal. Even if the number of coil channels is increased, traditional MRI cannot enhance the signal collection in the axillary area.

[0081] Therefore, on the basis of conventional breast coils, Figure 4 As shown, the back is covered with an abdominal soft coil, and a double coil is used to achieve a nearly full surround scan, collecting signals over a wider area. While shortening the scan time and improving clarity, it can also display the axillary area and obtain lymph node conditions.

[0082] Optionally, obtaining breast scan information corresponding to the enhanced T1WI stage 3 further includes:

[0083] After scanning a mask film, the contrast agent is directly injected, and the scanning start time after the contrast agent injection is determined according to the scanning duration of each phase to ensure that the 90th second is exactly located at the center of the K space, and the 90th second image is output as the breast scanning information corresponding to the enhanced T1WI 3 phase.

[0084] In a specific embodiment of the present specification, in order to optimize the scanning process and improve efficiency while ensuring the integrity and accuracy of diagnostic information in breast MRI examination, a specific enhanced sequence technology is used. This technology involves a K-space center filling strategy, which aims to shorten the overall examination time through a carefully designed scanning sequence while maintaining high-quality image diagnostic value. Specifically, after scanning the first phase mask (i.e., the baseline image before the contrast agent is injected), the contrast agent is injected immediately. Subsequently, the 90-second image acquisition period (i.e., the moment when the contrast agent reaches the peak concentration in the blood vessel) is arranged in the second phase scan. The advantage of this is that the central part of the K space (usually containing the main low-frequency information of the image, which is crucial to the overall contrast and structure of the image) is preferentially collected and filled at the moment of the contrast agent peak. In this way, not only can the key dynamic information of the contrast agent distribution be captured, but also the scanning time can be significantly shortened while ensuring image quality. Since the 90-second peak image is accurately placed in the second phase scan, while reducing the total scan time, the loss of diagnostic information caused by time compression is avoided. Therefore, this enhanced sequence optimization strategy not only improves the examination efficiency but also ensures the diagnostic accuracy and reliability of breast MRI examinations.

[0085] S120: inputting the breast scan information into the CS network topology model to obtain a breast target image;

[0086] Optionally, the S120 includes:

[0087] The breast target image includes a breast amplitude image and a breast function image;

[0088] Merging the multi-channel complex information of the object to be scanned corresponding to the breast scanning information to obtain single-channel complex information;

[0089] The single-channel complex information is converted into a breast amplitude image and / or a breast function image.

[0090] In a specific embodiment of the present specification, during a breast MRI (magnetic resonance imaging) examination, the breast scan information obtained usually contains complex information from multiple channels (such as signals received by multiple coils). This information not only carries the structural details of breast tissue, but also reflects its specific physiological function state. In order to more effectively utilize this information and generate images with clinical value, these complex information from different channels are merged and processed. This step involves operations such as addition or weighted average of complex signals, aiming to fuse multi-channel information into complex information of a single channel (or called a single channel). Through this processing, not only can the signal-to-noise ratio of the image be improved, but also image artifacts caused by differences between coils can be reduced. Next, the single-channel complex information obtained is used to further generate an amplitude image and / or a functional image of the breast. The breast amplitude image mainly reflects the anatomical structure and density distribution of breast tissue. It is similar to the grayscale information in traditional X-ray or CT images, but has higher soft tissue resolution and contrast. Breast functional images focus on displaying the physiological functional status of breast tissue, such as blood perfusion, metabolic activity, etc. This information is of great significance for evaluating the benign or malignant nature of breast lesions, angiogenesis, and treatment effects.

[0091] Specifically, breast amplitude images can be obtained by performing modular operations on single-channel complex information, while the generation of functional images may require more complex processing, such as using phase information to calculate blood oxygen level dependent (BOLD) images and perform dynamic perfusion imaging.

[0092] S130: performing noise reduction processing on the breast target image in the readout gradient direction, the slice selection gradient direction, and the phase encoding direction to obtain a noise-reduced breast target image to assist in the assessment and positioning of breast lesions.

[0093] In the specific implementation of this specification, during breast MRI imaging, obtaining high-quality breast target images is crucial for accurately evaluating breast lesions and their location. In order to improve image quality and reduce noise interference, a targeted noise reduction processing strategy is adopted to perform fine noise suppression on the breast target image in the readout gradient direction, the layer selection gradient direction, and the phase encoding direction.

[0094] In the readout gradient direction, advanced filtering techniques, such as adaptive filters or wavelet transforms, are used to effectively suppress high-frequency noise in the image while retaining the edge and detail information of breast tissue. This step helps to improve the clarity of the image, making the breast structure more distinct and easier for doctors to observe and analyze.

[0095] In the direction of the selected layer gradient, inter-layer denoising algorithms are used to target possible inter-layer interference or artifacts in the image. These algorithms can identify and eliminate noise caused by inter-layer coupling or device errors, ensuring that each layer of the image is independent of other layers, thereby improving the accuracy and reliability of the 3D reconstruction of the image.

[0096] For the noise in the phase encoding direction, phase correction and phase noise suppression techniques are used. These techniques can correct the phase error caused by magnetic field inhomogeneity or equipment error and reduce the random noise in the phase encoding process. Through this processing, the accuracy of the phase information in the image is ensured, which is particularly important for evaluating functional information such as blood perfusion and metabolic activity of breast tissue.

[0097] After the above noise reduction processing, the noise of breast target images after noise reduction is obtained. The noise of these images in the readout gradient direction, the layer selection gradient direction and the phase encoding direction is effectively controlled, and the image quality is significantly improved.

[0098] Breast lesions and breast target images with high positioning accuracy are input into the CS network topology structure model for training and optimizing the CS network topology structure model to improve its recognition and positioning capabilities for breast lesions, thereby achieving higher accuracy and robustness in practical applications.

[0099] In the present invention, by optimizing accelerated scanning parameters, such as reasonable repetition time, echo time, layer thickness, deflection angle and bandwidth settings, the method achieves efficient and fast breast imaging, significantly shortens the inspection time, and maintains high-quality image resolution. By using the CS network topology model, complex breast scanning information can be converted into accurate breast target images, including breast amplitude images and functional images, providing doctors with auxiliary diagnostic information. In addition, the method pays special attention to noise reduction processing, and performs fine noise suppression in the readout gradient direction, layer selection gradient direction and phase encoding direction to ensure the clarity and accuracy of the image. It is particularly worth mentioning that in the enhanced T1WI scan, the method ensures that the 90th second image is exactly located in the center of the K space by accurately controlling the scanning time after the contrast agent injection, thereby capturing the breast information at the peak moment of the contrast agent, which is of great value for assisting the evaluation of breast lesions and their positioning.

[0100] Figure 5 A schematic diagram of the principle of a breast magnetic resonance rapid scanning imaging device provided in an embodiment of this specification, the device may include:

[0101] An acquisition module 10 is used to perform accelerated scanning of axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences based on an artificial intelligence compressed sensing model to obtain breast scanning information of the person being examined;

[0102] An input module 20, used for inputting the breast scan information into the CS network topology model to obtain a breast target image;

[0103] The noise reduction module 30 is used to perform noise reduction processing on the breast target image in the readout gradient direction, the layer selection gradient direction, and the phase encoding direction to obtain a noise-reduced breast target image to assist in the assessment and positioning of breast lesions.

[0104] Optionally, imaging parameters for accelerated scanning are: repetition time of 5.3-3683 ms, echo time of 2.6-90 ms, layer thickness of 1-4 mm, deflection angle of 10-90 degrees, and bandwidth of 186.6-718.9 Hz / pixel.

[0105] Optionally, the obtaining of breast scanning information corresponding to the sagittal T1WI includes:

[0106] The examinee faces downward with his back facing upward, and his chest is placed in a semi-enclosed breast coil, and the back of the examinee is covered with an abdominal soft coil, so as to obtain the breast image of the examinee;

[0107] Determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline;

[0108] The person being examined is accelerated scanned based on the sagittal positioning line to obtain breast scan information corresponding to the sagittal T1WI.

[0109] Optionally, determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline, includes:

[0110] Determine the line between the points where the breast skin is inflected based on the breast image, and use it as a baseline;

[0111] A perpendicular line is determined based on the baseline and is used as the sagittal positioning line.

[0112] Optionally, obtaining breast scan information corresponding to the enhanced T1WI stage 3 further includes:

[0113] After scanning a mask film, the contrast agent is directly injected, and the scanning start time after the contrast agent injection is determined according to the scanning duration of each phase to ensure that the 90th second is exactly located at the center of the K space, and the 90th second image is output as the breast scanning information corresponding to the enhanced T1WI 3 phase.

[0114] Optionally, the input module 20 includes:

[0115] The breast target image includes a breast amplitude image and a breast function image;

[0116] Merging the multi-channel complex information of the object to be scanned corresponding to the breast scanning information to obtain single-channel complex information;

[0117] The single-channel complex information is converted into a breast amplitude image and / or a breast function image.

[0118] The functions of the device in the embodiment of the present invention have been described in the above method embodiment, so for details not provided in the description of this embodiment, please refer to the relevant description in the above embodiment, and no further description will be given here.

[0119] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0120] The following describes an electronic device embodiment of the present invention, which can be regarded as a specific physical implementation of the method and device embodiments of the present invention. The details described in the electronic device embodiment of the present invention should be regarded as a supplement to the above method or device embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above method or device embodiments.

[0121] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 6 The electronic device 300 according to the embodiment of the present invention is described. Figure 6 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0122] like Figure 6 As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different system components (including the storage unit 320 and the processing unit 310), a display unit 340, etc.

[0123] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 310 can perform the following steps: Figure 1 Steps shown.

[0124] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache memory unit 3202 , and may further include a read-only memory unit (ROM) 3203 .

[0125] The storage unit 320 may also include a program / utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0126] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0127] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable viewers to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0128] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 The method shown.

[0129] Figure 7 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification.

[0130] accomplish Figure 1 The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0131] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0132] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the viewer computing device, partially on the viewer device, as a stand-alone software package, partially on the viewer computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the viewer computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0133] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0134] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0135] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0136] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A breast magnetic resonance rapid scanning imaging method, characterized in that: include: Based on the artificial intelligence compressed sensing model, the axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences are accelerated to obtain the breast scan information of the person being examined; Inputting the breast scan information into the CS network topology model to obtain a breast target image; The breast target image is subjected to noise reduction processing in the readout gradient direction, the layer selection gradient direction, and the phase encoding direction to obtain a noise-reduced breast target image for assisting in the assessment and positioning of breast lesions.

2. The breast magnetic resonance rapid scanning imaging method according to claim 1, characterized in that: The imaging parameters of the accelerated scan are: repetition time 5.3-3683 ms, echo time 2.6-90 ms, slice thickness 1-4 mm, deflection angle 10-90 degrees, and bandwidth 186.6-718.9 Hz / pixel.

3. The breast magnetic resonance rapid scanning imaging method according to claim 2, characterized in that: Obtaining breast scan information corresponding to the sagittal T1WI, including: The examinee faces downward with his back facing upward, and his chest is placed in a semi-enclosed breast coil, and the back of the examinee is covered with an abdominal soft coil, so as to obtain the breast image of the examinee; Determining a baseline based on the breast image, and determining a sagittal positioning line based on the baseline; The person being examined is accelerated scanned based on the sagittal positioning line to obtain breast scan information corresponding to the sagittal T1WI.

4. The breast magnetic resonance rapid scanning imaging method according to claim 3, characterized in that: The step of determining a baseline based on the breast image and determining a sagittal positioning line based on the baseline comprises: Determine the line between the points where the breast skin is inflected based on the breast image, and use it as a baseline; A perpendicular line is determined based on the baseline and is used as the sagittal positioning line.

5. The breast magnetic resonance rapid scanning imaging method according to claim 4, characterized in that: Acquiring breast scan information corresponding to the enhanced T1WI3 stage also includes: After scanning a mask film, the contrast agent is directly injected, and the scanning start time after the contrast agent injection is determined according to the scanning duration of each phase to ensure that the 90th second is exactly located at the center of the K space, and the 90th second image is output as the breast scanning information corresponding to the enhanced T1WI 3 phase.

6. The breast magnetic resonance rapid scanning imaging method according to claim 5, characterized in that: The step of inputting the breast scan information into the CS network topology model to obtain a breast target image comprises: The breast target image includes a breast amplitude image and a breast function image; Merging the multi-channel complex information of the object to be scanned corresponding to the breast scanning information to obtain single-channel complex information; The single-channel complex information is converted into a breast amplitude image and / or a breast function image.

7. A breast magnetic resonance rapid scanning imaging device, characterized in that: include: The acquisition module is used to perform accelerated scanning of axial T1WI, diffusion, enhanced T1WI phase 3, and sagittal T1WI sequences based on an artificial intelligence compressed sensing model to obtain breast scan information of the person being examined; An input module, used for inputting the breast scan information into the CS network topology model to obtain a breast target image; The denoising module is used to perform denoising processing on the breast target image in the readout gradient direction, the layer selection gradient direction and the phase encoding direction to obtain the denoised breast target image to assist in the assessment and positioning of breast lesions.

8. An electronic device, wherein: The electronic device includes: processor; and, A memory storing computer executable instructions which, when executed, cause the processor to perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 6 is implemented.

Images