Processing method and processing device for medical image and scanning equipment

Abstract

The invention relates to the technical field of image processing, and discloses a medical image processing method and device and scanning equipment. The processing method comprises the steps of obtaining an initial scanning image of a to-be-dissected structure; performing region-of-interest segmentation on the initial scanning image to obtain contour information and target position information of the region-of-interest; generating an irregular shimming frame matched with the anatomical form of the region of interest based on the contour information of the region of interest and the target position information; and overlapping and displaying the irregular shimming frame on the positioning image. According to the invention, the accuracy of shimming frame determination can be improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, such as a processing method and apparatus for medical images, and a scanning device. Background Technology

[0002] Currently, magnetic resonance imaging (MRI), as one of the core non-invasive and high-resolution imaging technologies in modern medical imaging, has been widely used in the diagnosis and clinical evaluation of diseases in multiple anatomical sites such as the brain and heart. The quality of an MRI image is directly related to the uniformity of the magnetic field in the region of interest being imaged. Before the formal scan, the extent of the region of interest must be determined and a shimming frame must be set. Then, the uniformity of the magnetic field within the frame is optimized using a shimming algorithm. Therefore, the accuracy and fit of the shimming frame become key factors determining the final image quality.

[0003] In related technologies, deep learning models such as convolutional neural networks (CNN) are used to learn from a large number of clinical cases to automatically segment regions of interest, and then medical image segmentation techniques are used to determine the shimming box.

[0004] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art: In related technologies, the shimming frames determined by medical image segmentation techniques are mostly regular shapes such as rectangles and cuboids. These shapes have low morphological matching with irregular anatomical structures such as the human heart and liver, and are prone to including irrelevant areas or missing key areas of interest, leading to poor shimming results or incorrect scanning orientation. Therefore, improving the accuracy of shimming frame determination has become an urgent technical problem to be solved.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0007] This disclosure provides a method and apparatus for processing medical images, as well as a scanning device, which can improve the accuracy of shimming frame determination.

[0008] In some embodiments, a method for processing medical images includes: acquiring an initial scan image of a structure to be dissected; segmenting the initial scan image into a region of interest (ROI) to obtain contour information and target location information of the ROI; generating an irregular shimming bounding box adapted to the anatomical morphology of the ROI based on the contour information and target location information of the ROI; and superimposing the irregular shimming bounding box onto the positioning image.

[0009] Optionally, the processing method further includes: obtaining an adjusted irregular shim frame in response to an adjustment operation on the irregular shim frame.

[0010] Optionally, in response to the adjustment operation of the irregular shimming frame, the obtained adjusted irregular shimming frame includes: in response to the adjustment command, displaying the irregular shimming frame as an envelope polyhedron corresponding to the polygon envelope; and in response to the operation on the envelope polyhedron, obtaining the adjusted irregular shimming frame.

[0011] Optionally, the processing method further includes: verifying whether the adjusted irregular shimming box conforms to the anatomical structure features of the region of interest and / or the preset segmentation model experience threshold; if it does not conform to the anatomical structure features or exceeds the segmentation model experience threshold, outputting a prompt message to the operator to confirm whether to restore the irregular shimming box to its original state.

[0012] Optionally, the contour information of the region of interest is represented as a binarized mask.

[0013] Optionally, before segmenting the region of interest in the initial scan image, the processing method further includes: confirming whether non-rigid body motion has occurred in the current scanning scene where the initial scan image is acquired, compared to the historical scanning scene for the same anatomical structure; if no non-rigid body motion has occurred and no rescan command has been issued, then confirming that subsequent steps directly reuse the historical initial scan image or the contour information and target location information of the region of interest obtained by segmenting the region of interest in the historical initial image.

[0014] In some embodiments, a medical image processing apparatus includes: an acquisition module configured to acquire an initial scan image of a structure to be dissected; a segmentation module configured to segment the initial scan image into a region of interest (ROI) to obtain contour information and target location information of the ROI; a generation module configured to generate an irregular shimming frame adapted to the anatomical morphology of the ROI based on the contour information and target location information of the ROI; and a display module configured to overlay and display the irregular shimming frame on the localization image.

[0015] In some embodiments, a processing apparatus for medical images includes a processor and a memory storing program instructions, the processor being configured to execute the processing method for medical images as described above when the program instructions are executed.

[0016] In some embodiments, the scanning device includes: a device body; and a processing apparatus for medical images as described above, disposed on the device body.

[0017] The processing method, processing apparatus, and scanning device for medical images provided in this disclosure can achieve the following technical effects: In this embodiment, when scanning the structure to be dissected, after acquiring the initial scan image of the structure, the region of interest (ROI) is segmented to determine the contour information and target location information of the ROI. Then, based on the binarized mask and the target location information, an irregular shimming box adapted to the anatomical morphology of the ROI is generated. Since the binarized mask can accurately delineate the irregular contour of the structure to be dissected, the generated irregular shimming box can more accurately cover the key areas of the structure to be dissected compared to the regular shimming box determined by related technologies. After determining the irregular shimming box, it is superimposed on the positioning image to allow the operator to visually observe the fit between the shimming box and the boundary of the structure to be dissected, facilitating adjustments. This approach retains the objectivity of automatic segmentation by deep learning models while incorporating clinical experience, effectively correcting segmentation deviations in the shimming boxes obtained by automatic segmentation and effectively avoiding poor shimming effects or scanning orientation errors caused by poor shimming box adaptation. Therefore, this embodiment can improve the accuracy of shimming box determination.

[0018] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0019] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein: Figure 1 This is a schematic diagram of a scanning device provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of a medical image processing method provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of another method for processing medical images provided in an embodiment of this disclosure; Figure 4 This is a schematic diagram of another method for processing medical images provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of a medical image processing apparatus provided in an embodiment of this disclosure; Figure 6This is a schematic diagram of another medical image processing apparatus provided in an embodiment of this disclosure. Detailed Implementation

[0020] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0021] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0022] Unless otherwise stated, the term "multiple" means two or more.

[0023] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, the A / B feature means: A or B.

[0024] The term "and / or" describes an association between objects, and the feature indicates that there can be three relationships. For example, A and / or B, the feature indicates three relationships: A or B, or A and B.

[0025] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in the present disclosure can be combined with each other.

[0027] like Figure 1 As shown, the scanning device 100 provided in this embodiment includes a device body 110 and a processing device 500 (600) for medical images. The processing device 500 (600) for medical images is disposed on the device body 110.

[0028] Understandably, the scanning device 100 also includes a display device 120 that is electrically connected to the processing device 500 (600) for medical images and is interactive with the operator.

[0029] Optionally, the medical image processing device 600 includes a processor that can acquire an initial scan image of the anatomical structure to be analyzed, and segment the initial scan image into a region of interest (ROI) to determine the contour information and target location information of the ROI. Based on the contour information and target location information of the ROI, an irregular shimmed bounding box adapted to the anatomical morphology of the ROI can be generated and superimposed on the positioning image.

[0030] In conjunction with the aforementioned scanning device, this disclosure provides a method for processing medical images, wherein the processor executing the processing method can be one of the aforementioned processors, such as... Figure 2 As shown, the processing method includes: S201, The processor acquires the initial scan image of the structure to be dissected.

[0031] Specifically, by having the scanning components of the scanning device scan the anatomical structure to be dissected according to a set scanning sequence, k-space data of the anatomical structure can be obtained. By reconstructing the k-space data into an image, an initial scan image can be obtained.

[0032] S202, the processor performs region of interest segmentation on the initial scanned image to obtain the contour information and target location information of the region of interest.

[0033] Specifically, the region of interest is the key area of ​​interest isolated from the initial scan image.

[0034] Specifically, the region of interest is segmented into the initial scanned image using a segmentation model.

[0035] Alternatively, the segmentation model can employ a deep learning segmentation network, such as UNET, VNET, or a variant of the network with an added attention mechanism.

[0036] Specifically, the contour information of the region of interest is used to describe the shape and boundaries of the region of interest.

[0037] Optionally, the contour information of the region of interest is represented as a binarized mask.

[0038] Specifically, the binarized mask is a binary image obtained after segmenting the initial scanned image. In the binarized mask, the pixel value of the region of interest is usually set to 1, and the pixel value of the background region is set to 0. Therefore, the binarized mask obtained by segmenting the initial scanned image can be used as contour information to highlight the shape and boundary of the region of interest.

[0039] Specifically, the target location information of the region of interest includes: the position coordinates, size, and orientation of the region of interest in the initial scanned image. The position coordinates can be the center coordinates of the bounding rectangle of the region of interest, and the size can be the size of the field of view (FOV). In some embodiments, the target location information of the region of interest may also include body part information, such as the region of interest being the heart or liver.

[0040] S203, the processor generates an irregular shimming frame that adapts to the anatomical shape of the region of interest based on the contour information and target location information of the region of interest.

[0041] Specifically, the shape and boundaries of the region of interest (ROI) can be described based on its contour information, and its location can be described based on the target location information. Therefore, based on the contour and target location information of the ROI, an irregular shimming frame adapted to the ROI can be generated. When generating the irregular shimming frame, its shape needs to closely match the anatomical morphology of the ROI to ensure effective magnetic field uniformity correction during shimming scanning.

[0042] S204, the processor overlays an irregular shimming frame onto the positioning image.

[0043] Specifically, a localization image is a roughly identifiable image of the anatomical structure to be dissected, obtained by using a scanning device with a lower resolution and faster scanning method. Unlike the initial scan image, the localization image does not need to have high resolution and detailed anatomical information, but it does need to clearly show the main outline and location of the structure to be dissected.

[0044] Specifically, based on the contour information of the region of interest and the target location information, the image is registered with the localization image. After registration, an irregular shimming frame is superimposed on the localization image. The superimposed image can simultaneously display the localization information of the structure to be dissected and the shape and position of the irregular shimming frame. The operator can observe the image to determine whether the shimming frame is appropriate, and adjust the position, size and shape of the shimming frame if it is inappropriate to ensure that it accurately covers the region of interest.

[0045] In this embodiment, when scanning the structure to be dissected, after acquiring the initial scan image of the structure, the region of interest (ROI) is segmented to determine the contour information and target location information of the ROI. Then, based on the binarized mask and the target location information, an irregular shimming box adapted to the anatomical morphology of the ROI is generated. Since the binarized mask can accurately delineate the irregular contour of the structure to be dissected, the generated irregular shimming box can more accurately cover the key areas of the structure to be dissected compared to the regular shimming box determined by related technologies. After determining the irregular shimming box, it is superimposed on the positioning image to allow the operator to visually observe the fit between the shimming box and the boundary of the structure to be dissected, facilitating adjustments. This approach retains the objectivity of automatic segmentation by deep learning models while incorporating clinical experience, effectively correcting segmentation deviations in the shimming boxes obtained by automatic segmentation and effectively avoiding poor shimming effects or scanning orientation errors caused by poor shimming box adaptation. Therefore, this embodiment can improve the accuracy of shimming box determination.

[0046] This disclosure provides another method for processing medical images, such as... Figure 3 As shown, the processing method includes: S301, The processor acquires the initial scan image of the structure to be dissected.

[0047] S302, the processor performs region of interest segmentation on the initial scanned image to obtain the contour information and target location information of the region of interest.

[0048] S303, the processor generates an irregular shimming frame that adapts to the anatomical shape of the region of interest based on the contour information and target location information of the region of interest.

[0049] S304, the processor overlays an irregular shimming frame onto the positioning image.

[0050] S305, the processor responds to the adjustment operation of the irregular shim frame and obtains the adjusted irregular shim frame.

[0051] Specifically, the operator can manipulate the irregular shimming frame superimposed on the positioning image through the display device of the scanning equipment. For example, the operator can adjust the size of the shimming frame to better cover the region of interest, move the position of the shimming frame to accurately align it with the target region, or rotate the shimming frame to adapt to a specific orientation of the region of interest. After the operator completes the adjustments, the processor will determine the final irregular shimming frame based on the operator's results.

[0052] Specifically, if the operator makes adjustments to the irregular shim frame, it indicates that the operator has reservations about parts of the determined irregular shim frame. Therefore, in this case, the irregular shim frame can be adjusted in response to the adjustment operation.

[0053] Optionally, in response to the adjustment operation of the irregular shimming frame, the obtained adjusted irregular shimming frame includes: in response to the adjustment command, displaying the irregular shimming frame as an envelope polyhedron corresponding to the polygon envelope; and in response to the operator's operation on the envelope polyhedron, obtaining the adjusted irregular shimming frame.

[0054] Specifically, upon receiving the adjustment instruction, the irregular shimming frame is displayed as an envelope polyhedron corresponding to the polygonal envelope line, allowing the operator to precisely adjust the irregular shimming frame by adjusting each node of the envelope polyhedron.

[0055] Alternatively, if the operator makes no adjustments, the irregular shimming frame can be directly used as the basis for subsequent shimming scans.

[0056] Specifically, if the operator makes no adjustment to the irregular shimming frame, it indicates that the operator approves of the determined irregular shimming frame. Therefore, in this case, the irregular shimming frame can be directly used as the basis for subsequent shimming correction.

[0057] Optionally, after obtaining the adjusted irregular shimming frame, the processor can also perform shimming correction according to the adjusted irregular shimming frame to obtain the magnetic resonance image of the structure to be dissected.

[0058] Specifically, based on the information from the adjusted irregular shimming frame, specific magnetic field correction pulses or magnetic field parameters can be applied to the region of interest (ROI) during the scanning process to improve the magnetic field homogeneity of the RPI. After shimming adjustment, the scanning device performs magnetic resonance (MRI) scanning on the anatomical structure according to preset scanning parameters, acquiring MRI signals. Finally, by reconstructing and processing the acquired signals, an MRI image of the anatomical structure is obtained. Because of the shimming scanning process, the magnetic field homogeneity of this image is improved, resulting in higher image quality and a clearer display of the anatomical details and lesion information of the structure.

[0059] In this embodiment, after the irregular shim box is superimposed on the positioning image, it also responds to the operator's adjustment operation on the irregular shim box and adjusts it accordingly. This preserves the objectivity of the automatic segmentation by the deep learning model while incorporating human clinical experience, effectively correcting the segmentation deviation of the shim box obtained by automatic segmentation.

[0060] In some embodiments, obtaining an initial scan image of the structure to be dissected includes: acquiring reference scan data of the structure to be dissected through a scan sequence; and reconstructing the reference scan data into an image that meets the input format requirements of the segmentation model, as the initial scan image.

[0061] Specifically, in the field of medical imaging, different scanning sequences have different imaging parameters and signal acquisition methods. Therefore, it is necessary to acquire reference scan data of the structure to be dissected through scanning sequences.

[0062] Optionally, the scanning sequence can be a fast localization (smartscout) sequence, typically a fast 3D gradient echo sequence or a fast 3D spin echo sequence. It should be noted that the scanning sequence is not limited to these; any sequence can be used as long as the reference scan data obtained from the scanning sequence can provide 3D information about the structure to be dissected.

[0063] Specifically, the reference scan data is the k-space data directly captured by the scanning device, i.e., the raw signal data of magnetic resonance imaging.

[0064] Specifically, the reference scan data is abstract signal data that cannot be directly recognized by deep learning segmentation models. Therefore, it is necessary to reconstruct the reference scan data into an image that meets the input format requirements of the segmentation model, and use it as the initial scan image.

[0065] Optionally, the reference scan data can be converted into a two-dimensional or three-dimensional visualization image as the initial scan image using a magnetic resonance image reconstruction algorithm (such as Fourier transform).

[0066] In this embodiment, reference scan data of the structure to be dissected, acquired through a scanning sequence, is reconstructed into an image that meets the input format requirements of the segmentation model and used as the initial scan image. This ensures that the subsequent segmentation model can directly perform image segmentation processing on the initial scan image, which helps to guarantee the accuracy of subsequent image segmentation.

[0067] In some embodiments, segmenting the region of interest (ROI) of the initial scanned image includes: if the initial scanned image is a 2D image sequence, segmenting the 2D image sequence using a segmentation model, and then stitching together the contour information and target location information of the ROI, wherein the 2D image sequence includes multiple 2D images; if the initial scanned image is a 3D image, segmenting the 3D image using a segmentation model, and then directly outputting the contour information and target location information of the ROI.

[0068] Specifically, 2D images are two-dimensional slices that cannot directly reflect the three-dimensional spatial shape of the region of interest. A 2D image sequence consists of multiple 2D images. Therefore, when the initial scanned image is a 2D image, it is necessary to segment the 2D image using a segmentation model and then stitch together the contour information and target location information of the region of interest.

[0069] Specifically, 3D images are continuous three-dimensional volume data, already containing complete three-dimensional spatial information of the region of interest. Therefore, when the initial scanned image is a 3D image, the contour information and target location information of the region of interest in the 3D image can be directly extracted using a segmentation model.

[0070] In this embodiment, before performing image segmentation on the initial scanned image, it is first determined whether the initial scanned image is a 2D image or a 3D image, and then the initial scanned image is segmented according to the method corresponding to the image type. This helps to improve the accuracy of determining the contour information and target location information of the region of interest.

[0071] In some embodiments, the processing method further includes: verifying whether the adjusted irregular shimming frame conforms to the anatomical structure features of the region of interest and / or the preset segmentation model experience threshold; if it does not conform to the anatomical structure features or exceeds the segmentation model experience threshold, outputting a prompt message to the operator to confirm whether to restore the irregular shimming frame to its original state.

[0072] Specifically, if the adjusted irregular shim frame does not conform to the anatomical features of the region of interest and the preset segmentation model's empirical threshold, it indicates that the operator's adjusted irregular shim frame is within an unreasonable parameter range. If subsequent scanning procedures are performed based on this shim frame, it may lead to artifacts and decreased clarity in the obtained magnetic resonance images. Therefore, in this case, a prompt message needs to be output to the operator to confirm whether to revert to the original irregular shim frame.

[0073] Specifically, two buttons, "Yes" and "No," can be set in the prompt message window. If the operator clicks the "Yes" button, the shimming frame will be restored to its previous state; if the operator clicks the "No" button, the currently adjusted shimming frame will be retained.

[0074] In this embodiment, after obtaining the adjusted irregular shimming frame, it is verified whether it conforms to the anatomical features of the region of interest and / or the empirical threshold of the segmentation model, so as to accurately judge the rationality of the adjusted irregular shimming frame and avoid the impact of mismatch on subsequent scanning and image quality.

[0075] This disclosure provides another method for processing medical images, such as... Figure 4 As shown, the processing method includes: S401, the processor acquires the initial scan image of the structure to be dissected.

[0076] S402, the processor confirms whether non-rigid body motion has occurred in the current scanning scene where the initial scan image is acquired, compared to historical scanning scenes targeting the same anatomical structure.

[0077] Specifically, non-rigid body motion refers to complex movements such as deformation and twisting of parts of the patient's body.

[0078] Specifically, the initial scan image obtained from the current scan can be registered with historical initial scan images of the same anatomical structure. If differences such as local deformation or distortion exist between the images during the registration process that cannot be eliminated by simple rigid body transformation, it can be determined that the patient has undergone non-rigid body motion.

[0079] S403, if the processor does not perform non-rigid body motion and does not issue a rescan command, it confirms that subsequent steps will directly reuse the historical initial scan image or the contour information and target position information of the region of interest obtained by segmenting the historical initial image into a region of interest.

[0080] Specifically, when it is confirmed that the patient has not undergone non-rigid body movement, it indicates that the current initial scan image and the historical initial scan image have a high degree of consistency in the anatomical structure, and the image quality is relatively reliable. In this case, the contour information and target location information of the region of interest obtained after segmentation of the historical initial scan image still have high reference value and can be directly reused. Therefore, if the patient has not undergone non-rigid body movement and the operator has not issued a rescan command, the contour information and target location information of the region of interest corresponding to the historical initial scan image can be directly reused.

[0081] S404, when the patient undergoes non-rigid body movement, the processor performs region of interest segmentation on the initial scan image to obtain the contour information and target location information of the region of interest.

[0082] S405, the processor generates an irregular shimming frame that adapts to the anatomical shape of the region of interest based on the contour information and target location information of the region of interest.

[0083] S406, the processor overlays irregular shimming frames onto the positioning image.

[0084] In this embodiment, before performing image segmentation on the initial scan image, it is first determined whether the patient has any non-rigid body motion relative to the historical scan scene of the same anatomical structure. If there is no non-rigid body motion and the operator does not request a rescan, the contour information and target position information of the region of interest from the segmented initial scan image are directly reused, without performing image segmentation on the initial scan image again. This helps save computational resources and processing time, improving the efficiency of obtaining magnetic resonance images. Of course, in other embodiments, images can also be reused.

[0085] Combination Figure 5 As shown, this disclosure provides a medical image processing apparatus 500, including: an acquisition module 501, a segmentation module 502, a generation module 503, and a display module 504. The acquisition module 501 is configured to acquire an initial scan image of the structure to be dissected. The segmentation module 502 is configured to segment the initial scan image into a region of interest (ROI) to obtain the contour information and target location information of the RIO. The generation module 503 is configured to generate an irregular shimmed bounding box adapted to the anatomical morphology of the RIO based on the contour information and target location information of the RIO. The display module 504 is configured to overlay and display the irregular shimmed bounding box on the localized image.

[0086] Combination Figure 6 As shown, this disclosure provides a medical image processing apparatus 600, including a processor 601 and a memory 602. Optionally, the apparatus may further include a communication interface 603 and a bus 604. The processor 601, communication interface 603, and memory 602 can communicate with each other via the bus 604. The communication interface 603 can be used for information transmission. The processor 601 can call logical instructions in the memory 602 to execute the medical image processing method of the above embodiment.

[0087] Furthermore, the logic instructions in the aforementioned memory 602 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0088] The memory 602, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 601 executes functional applications and data processing by running the program instructions / modules stored in the memory 602, that is, it implements the medical image processing method in the above embodiments.

[0089] The memory 602 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 602 may include high-speed random access memory and may also include non-volatile memory.

[0090] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described processing method for medical images.

[0091] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and other media capable of storing program code.

[0092] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0093] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] The methods and products disclosed in the embodiments herein (including but not limited to devices and equipment) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for processing medical images, characterized in that, include: Obtain initial scan images of the structure to be dissected; The region of interest (ROI) is segmented into the initial scanned image to obtain the contour information and target location information of the ROI. Based on the contour information of the region of interest and the target location information, an irregular shimming box is generated that is adapted to the anatomical shape of the region of interest. An irregular shim frame is overlaid on the positioning image.

2. The processing method according to claim 1, characterized in that, Also includes: In response to the adjustment operation of the irregular shim frame, the adjusted irregular shim frame is obtained.

3. The processing method according to claim 2, characterized in that, In response to the adjustment operation on the irregular shim frame, the obtained adjusted irregular shim frame includes: In response to the adjustment command, the irregular shim frame is displayed as an envelope polyhedron corresponding to the polygonal envelope. In response to operations on the envelope polyhedron, an adjusted irregular shim frame is obtained.

4. The processing method according to claim 2, characterized in that, Also includes: Verify whether the adjusted irregular shimming frame conforms to the anatomical structure features of the region of interest and / or the preset empirical threshold of the segmentation model; If the anatomical structure does not conform to the characteristics or exceeds the empirical threshold of the segmentation model, a prompt message is output to the operator to confirm whether to restore the irregular shimming frame before adjustment.

5. The processing method according to any one of claims 1 to 4, characterized in that, The contour information of the region of interest is represented as a binarized mask.

6. The processing method according to any one of claims 1 to 4, characterized in that, The initial scanned image is either a 3D image or a 2D image sequence.

7. The processing method according to any one of claims 1 to 4, characterized in that, Before performing region-of-interest segmentation on the initial scanned image, the processing method also includes: Confirm whether non-rigid body motion occurs in the current scanning scenario where the initial scan image is acquired, compared to historical scanning scenarios targeting the same anatomical structure. If no non-rigid body motion occurs and no rescan command is issued, then subsequent steps will directly reuse the historical initial scan image or the contour information and target location information of the region of interest obtained by segmenting the historical initial image into a region of interest.

8. A processing apparatus for medical images, characterized in that, include: The acquisition module is configured to acquire initial scan images of the structure to be dissected. The segmentation module is configured to segment the region of interest (ROI) of the initial scanned image to obtain the contour information and target location information of the ROI. The generation module is configured to generate an irregular shimming frame that adapts to the anatomical morphology of the region of interest based on the contour information and target location information of the region of interest. The display module is configured to overlay irregular shims onto the positioning image.

9. A processing apparatus for medical images, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when executing the program instructions, perform the processing method for medical images as described in any one of claims 1 to 7.

10. A scanning device, characterized in that, include: Equipment body; The processing apparatus for medical images as described in claim 8 or 9 is disposed on the device body.

Images