Motion detection method and apparatus for perfusion scanning procedure, ct scanning device

Abstract

The application relates to the medical imaging technical field and discloses a motion detection method and device for a perfusion scanning process and a CT scanning device, wherein the motion detection method comprises the following steps: acquiring an image of a current scanning circle; performing skull region segmentation on the image of the current scanning circle to obtain a skull mask image of the current scanning circle; comparing the skull mask image of the current scanning circle with a target skull mask image to determine an overlapping degree index; and determining the motion condition of the patient's head according to the overlapping degree index. The image reconstructed by the current scanning circle is acquired in real time during the scanning process, the image of the current scanning circle is subjected to skull region segmentation to obtain a skull mask image, and the overlapping degree index of the skull mask image of the current scanning circle and the target skull mask image is determined, so that the motion condition of the patient's head can be quantitatively evaluated, and the motion detection accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, such as a motion detection method and device for perfusion scanning process, and CT scanning equipment. Background Technology

[0002] CT (Computed Tomography) head perfusion scanning is an important technique in medical imaging used to assess cerebral hemodynamics, and is widely used in the diagnosis and assessment of diseases such as acute stroke and brain tumors. By intravenously injecting a contrast agent into the patient, a continuous, dynamic CT scan of the brain is performed as the contrast agent flows through the cerebral blood vessels, acquiring multiple sets of tomographic images. Specific algorithms are then used to calculate parameters such as cerebral blood flow, cerebral blood volume, and mean transit time, providing a basis for clinical diagnosis. During CT head perfusion scanning, the patient needs to keep their head still for a period of time to ensure the spatial consistency of the acquired tomographic images. If the patient moves their head during the scan, spatial misalignment can occur between tomographic images acquired at different time points, resulting in motion artifacts. This affects the accuracy of subsequent parameter calculations, potentially leading to clinical diagnostic errors, and in severe cases, requiring a rescan. This not only increases the patient's radiation exposure dose but also reduces medical efficiency.

[0003] In related technologies, a motion detection-based CT scan assistance method is disclosed. By acquiring video stream data of the target object, performing inter-frame difference processing on adjacent frames of the video stream data, judging the result of the inter-frame difference processing, and determining that the target object has moved if the result of the inter-frame difference processing is greater than the binarization threshold of the difference image.

[0004] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art: The relevant technologies detect motion only through the external movement of the target object, resulting in low accuracy.

[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 motion detection method and apparatus, and a CT scanning device for the perfusion scanning process, to improve the accuracy of motion detection.

[0008] In some embodiments, the motion detection method for the perfusion scanning process includes: acquiring an image of the current scan circle; segmenting the skull region of the image of the current scan circle to obtain a skull mask image of the current scan circle; comparing the skull mask image of the current scan circle with a target skull mask image to determine an overlap index; and determining the motion of the patient's head based on the overlap index.

[0009] Optionally, the image of the current scanning circle is segmented into a skull region to obtain a skull mask image of the current scanning circle, including: determining the pixel value of each pixel in the image of the current scanning circle; classifying pixels with pixel values ​​greater than a first preset threshold as skulls to determine the skull region; generating a skull mask image of the current scanning circle based on the determined skull region; wherein, the first preset threshold is adaptively determined based on the image of the current scanning circle in the following manner: traversing all possible candidate thresholds to segment the image of the current scanning circle into a skull region and a background region; for each candidate threshold, determining the number of pixels and the average pixel value of the skull region and the background region, and determining the inter-class variance of the skull region and the background region based on the number of pixels and the average pixel value; determining the candidate threshold that maximizes the inter-class variance as the first preset threshold.

[0010] Optionally, the target skull mask image can be obtained as follows: the skull mask image of the previous scan circle can be obtained as the target skull mask image; or, the skull mask image of the initial scan circle can be obtained as the target skull mask image.

[0011] Optionally, the skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: determining a first comparison region in the skull mask image of the current scanning circle and a second comparison region in the target skull mask image corresponding to the first comparison region; determining the total number of intersection pixels and the total number of union pixels of the first comparison region and the second comparison region; and determining the overlap index based on the ratio of the total number of intersection pixels to the total number of union pixels.

[0012] Optionally, the skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: determining a first comparison region in the skull mask image of the current scanning circle and a second comparison region in the target skull mask image corresponding to the first comparison region; determining the first centroid coordinates of the first comparison region and the second centroid coordinates of the second comparison region; and determining the overlap index based on the Euclidean distance between the first centroid coordinates and the second centroid coordinates.

[0013] Optionally, determining the patient's head movement based on the overlap index includes: determining that the patient's head remains stationary when the overlap index is greater than or equal to a second preset threshold; or determining that the patient's head has moved when the overlap index is first less than the second preset threshold; wherein, when the patient's head is determined to remain stationary, perfusion scanning continues; when the patient's head is determined to move, at least one of the following actions is taken: providing non-obstructive visual cues on the scanning operation interface and recording them; issuing an audible and visual alarm and displaying a prominent prompt on the scanning operation interface; pausing perfusion scanning.

[0014] Optionally, the motion detection method for the perfusion scanning process further includes: providing a non-blocking visual prompt on the scanning operation interface and recording it when the overlap index is first less than a second preset threshold but greater than or equal to a third preset threshold; or, issuing an audible and visual alarm and displaying a prominent prompt on the scanning operation interface when the overlap index is first less than the third preset threshold; or pausing the perfusion scanning when the overlap index remains less than the third preset threshold.

[0015] Optionally, the motion detection method for the perfusion scanning process further includes: inserting markers into the raw data or fully reconstructed images of the perfusion scan based on the movement of the patient's head; wherein the markers reflect the movement of the head.

[0016] In some embodiments, the motion detection device for the perfusion scanning process includes a processor and a memory storing program instructions. The processor is configured to execute the motion detection method for the perfusion scanning process as described above when the program instructions are executed.

[0017] In some embodiments, the CT scanning device includes: a CT scanning device body; and a motion detection device for the perfusion scanning process, as described above, which is mounted on the CT scanning device body.

[0018] The motion detection method and apparatus for perfusion scanning process and the CT scanning equipment provided in this disclosure can achieve the following technical effects: In this embodiment, by acquiring the reconstructed image of the current scan circle in real time during the scanning process, and since the CT value of the skull is typically much higher than that of soft tissue and other background areas, accurate skull region segmentation can be achieved, obtaining a skull mask image. By determining the overlap index between the skull mask image of the current scan circle and the target skull mask image, the patient's head movement can be quantitatively assessed, thereby improving the accuracy of motion detection. Furthermore, by calculating the overlap index in real time, the movement can be assessed immediately during the scanning process, allowing for timely intervention and reducing invalid data acquisition and patient radiation exposure caused by patient head movement.

[0019] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0020] 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 motion detection method for a perfusion scanning process provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of another motion detection method for a perfusion scanning process provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of another motion detection method for a perfusion scanning process provided in an embodiment of this disclosure; Figure 4 This is a schematic diagram of another motion detection method for a perfusion scanning process provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of another motion detection method for a perfusion scanning process provided in an embodiment of this disclosure; Figure 6 This is a schematic diagram of a motion detection device method for a perfusion scanning process provided in an embodiment of this disclosure. Detailed Implementation

[0021] 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.

[0022] The terms "first," "second," etc., used in the technical solutions described in this application 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.

[0023] Unless otherwise stated, the term "multiple" means two or more.

[0024] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0025] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0026] 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.

[0027] Combination Figure 1 As shown, this disclosure provides a motion detection method for a perfusion scanning process. The execution entity of the motion detection method can be a processor, and the motion detection method includes: S101, the processor acquires the image of the current scan circle.

[0028] S102, the processor performs skull region segmentation on the image of the current scan circle to obtain the skull mask image of the current scan circle.

[0029] S103, the processor compares the skull mask image of the current scanning circle with the target skull mask image to determine the overlap index.

[0030] S104, the processor determines the movement of the patient's head based on the overlap index.

[0031] In this embodiment, by acquiring the reconstructed image of the current scan circle in real time during the scanning process, and since the CT value of the skull is typically much higher than that of soft tissue and other background areas, accurate skull region segmentation can be achieved, obtaining a skull mask image. By determining the overlap index between the skull mask image of the current scan circle and the target skull mask image, the patient's head movement can be quantitatively assessed, thereby improving the accuracy of motion detection. Furthermore, by calculating the overlap index in real time, the movement can be assessed immediately during the scanning process, allowing for timely intervention and reducing invalid data acquisition and patient radiation exposure caused by patient head movement.

[0032] Optionally, acquiring the image of the current scan circle includes: reconstructing the image of the current scan circle using a full scan reconstruction or a half scan reconstruction method to obtain a reconstructed image.

[0033] Optionally, after obtaining the image of the current scan circle, the image can be preprocessed to reduce noise.

[0034] In this embodiment, before performing further skull region segmentation on the image, noise reduction processing can be performed first. Noise reduction preprocessing effectively removes random noise from the image, making it clearer, improving image quality, and providing a clearer image foundation for subsequent processing. The noise-reduced image can more accurately reflect the skull region, reducing missegmentation caused by noise and improving the accuracy of the skull mask image.

[0035] Optionally, the image of the current scanning circle is segmented into a skull region to obtain a skull mask image of the current scanning circle, including: determining the pixel value of each pixel in the image of the current scanning circle; classifying pixels with pixel values ​​greater than a first preset threshold as skulls to determine the skull region; and generating a skull mask image of the current scanning circle based on the determined skull region.

[0036] Combination Figure 2 As shown, this disclosure provides another motion detection method for a perfusion scanning process, including: S201, the processor acquires the image of the current scan circle.

[0037] S202, the processor determines the pixel value of each pixel in the image of the current scan circle.

[0038] S203, the processor classifies pixels with pixel values ​​greater than a first preset threshold as skulls and determines the skull region.

[0039] S204, the processor generates a skull mask image for the current scan circle based on the determined skull region.

[0040] S205, the processor compares the skull mask image of the current scanning circle with the target skull mask image to determine the overlap index.

[0041] S206, the processor determines the movement of the patient's head based on the overlap index.

[0042] In this embodiment, for the image of the current scan circle, each pixel has a corresponding pixel value, i.e., a CT value. If the pixel value is greater than a first preset threshold, the pixel is classified as a skull region; if the pixel value is less than or equal to the first preset threshold, the pixel is classified as a non-skull region. Based on the above classification results, a skull mask image for the current scan circle is generated. In the mask image, the pixel value of the skull region is usually set to 1, and the pixel value of the non-skull region is set to 0. In this way, the skull region is clearly identified in the mask image. The threshold-based segmentation method is simple to calculate, fast to process, and can be applied in real time to the image of each scan circle in the CT scanning process. By reasonably selecting the threshold, the skull can be effectively distinguished from other regions such as soft tissue, ensuring accurate extraction of the skull region. The skull mask image can clearly represent the contour and position of the skull.

[0043] Optionally, the first preset threshold is adaptively determined based on the image of the current scan circle as follows: traversing all possible candidate thresholds, the image of the current scan circle is divided into a skull region and a background region; for each candidate threshold, the number of pixels and the average pixel value of the skull region and the background region are determined, and the inter-class variance of the skull region and the background region is determined based on the number of pixels and the average pixel value; the candidate threshold that maximizes the inter-class variance is determined as the first preset threshold.

[0044] In this embodiment, during CT perfusion scanning, the pixel value distribution of the image may change due to variations in contrast agent concentration, adjustments to scanning equipment parameters, or patient physiological differences. Therefore, it is necessary to adaptively determine the optimal first preset threshold based on the image of the current scanning circle. To determine the optimal threshold corresponding to the image of the current scanning circle, all candidate thresholds can be traversed. For each candidate threshold, pixels with values ​​greater than the candidate threshold are identified as the skull region, and pixels with values ​​less than the candidate threshold are identified as the background region. The inter-class variance between the skull region and the background region corresponding to each candidate threshold is calculated, thereby determining the candidate threshold that maximizes the inter-class variance as the first preset threshold. By maximizing the inter-class variance, the optimal first preset threshold can be found, maximizing the difference between the skull region and the background region, thereby improving segmentation accuracy.

[0045] Optionally, the inter-class variance of the skull region and the background region can be calculated using the following formula:

[0046] Where, σ 2 For the variance between classes, N f N represents the number of pixels in the skull region. b μ is the number of pixels in the background area. f The mean pixel value of the skull region, μ b This represents the average pixel value of the background area.

[0047] Optionally, the first preset threshold is 450 HU.

[0048] Optionally, the image of the current scanning circle is segmented into a skull region, including: segmenting the skull region of the image of the current scanning circle using a traditional image processing algorithm or a deep learning-based image segmentation algorithm.

[0049] In this embodiment, in addition to the threshold segmentation method, other traditional image processing algorithms, such as region growing, edge detection, and deep learning-based image segmentation methods, can also be used to extract the skull region. Region growing can adapt to complex skull shapes and irregular boundaries, and the segmentation results can be flexibly controlled by adjusting the growth conditions. Edge detection can accurately extract skull boundaries, especially suitable for images with clear boundaries, and has a certain robustness to noise and small grayscale changes. Deep learning-based image segmentation methods can learn complex image features, have high segmentation accuracy, do not require manual setting of thresholds or parameters, reduce human intervention, and can adapt to different scanning conditions and individual patient differences.

[0050] Optionally, the motion detection method for the perfusion scanning process further includes: after obtaining the skull mask image, fine-tuning the skull mask image by extracting the maximum connected components and performing morphological operations.

[0051] In this embodiment, the skull mask image obtained directly after skull region segmentation may contain issues such as noise points, incomplete skull boundaries, and redundant regions. Therefore, further processing of the skull mask image is required. Extracting the maximum connected component can remove isolated noise points and non-skull regions, while retaining the main skull regions. Morphological operations, such as erosion, dilation, opening, and closing operations, can remove noise, smooth boundaries, and fill small holes. After fine-tuning, the final skull mask image can more accurately represent the skull region and is more suitable for subsequent motion detection.

[0052] Optionally, the target skull mask image can be obtained as follows: the skull mask image of the previous scan circle can be obtained as the target skull mask image; or, the skull mask image of the initial scan circle can be obtained as the target skull mask image.

[0053] In this embodiment, different target skull mask images can be selected to adapt to different detection requirements. The skull mask image from the previous scan cycle enables real-time motion detection, while the skull mask image from the initial scan cycle enables cumulative motion detection.

[0054] Optionally, the skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: determining a first comparison region in the skull mask image of the current scanning circle and a second comparison region in the target skull mask image corresponding to the first comparison region; determining the total number of intersection pixels and the total number of union pixels of the first comparison region and the second comparison region; and determining the overlap index based on the ratio of the total number of intersection pixels to the total number of union pixels.

[0055] Combination Figure 3 As shown, this disclosure provides another motion detection method for a perfusion scanning process, including: S301, the processor acquires the image of the current scan circle.

[0056] S302, the processor performs skull region segmentation on the image of the current scan circle to obtain the skull mask image of the current scan circle.

[0057] S303, the processor determines a first comparison region in the skull mask image of the current scanning circle, and a second comparison region in the target skull mask image corresponding to the first comparison region.

[0058] S304, the processor determines the total number of intersection pixels of the first comparison region and the total number of union pixels of the second comparison region.

[0059] S305, the processor determines the overlap index based on the ratio of the total number of intersection pixels to the total number of union pixels.

[0060] S306, the processor determines the movement of the patient's head based on the overlap index.

[0061] In this embodiment, a first comparison region is determined from the skull mask image of the current scanning circle, typically the entire skull mask image or a specific portion thereof. Then, a second comparison region corresponding to the first comparison region is found in the target skull mask image. The total number of pixels in both the first and second comparison regions that are skull regions is determined as the total number of intersection pixels; the total number of pixels in at least one of the first and second comparison regions that are skull regions is determined as the total number of union pixels. The overlap index is determined based on the ratio of the total number of intersection pixels to the total number of union pixels, IOU (Intersection over Union). The IOU value typically ranges from 0 to 1; the closer the value is to 1, the greater the overlap index between the two skull mask images, indicating less patient head movement; the closer the value is to 0, the smaller the overlap index, indicating greater patient head movement. By calculating the IOU value, the degree of skull region overlap between the current and target scanning circles can be quantitatively assessed, thereby accurately determining whether the patient's head has moved and the magnitude of the movement. Through pixel-level comparison, minute head movements can be accurately detected, improving the sensitivity and accuracy of motion detection.

[0062] Optionally, the ratio of the total number of intersection pixels to the total number of union pixels is directly proportional to the overlap index.

[0063] Optionally, the skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: determining a first comparison region in the skull mask image of the current scanning circle and a second comparison region in the target skull mask image corresponding to the first comparison region; determining the first centroid coordinates of the first comparison region and the second centroid coordinates of the second comparison region; and determining the overlap index based on the Euclidean distance between the first centroid coordinates and the second centroid coordinates.

[0064] Combination Figure 4 As shown, this disclosure provides another motion detection method for a perfusion scanning process, including: S401, the processor acquires the image of the current scan circle.

[0065] S402, the processor performs skull region segmentation on the image of the current scan circle to obtain the skull mask image of the current scan circle.

[0066] S403, the processor determines a first comparison region in the skull mask image of the current scan circle, and a second comparison region in the target skull mask image corresponding to the first comparison region.

[0067] S404, the processor determines the first centroid coordinates of the first comparison region and the second centroid coordinates of the second comparison region.

[0068] S405, the processor determines the overlap index based on the Euclidean distance between the first and second centroid coordinates.

[0069] S406, the processor determines the movement of the patient's head based on the overlap index.

[0070] In this embodiment, after determining the first and second comparison regions, the overlap index can be determined using the centroid coordinate method. By traversing all pixels in the first comparison region, the first centroid coordinate of the skull region is found, and similarly, by traversing all pixels in the second comparison region, the second centroid coordinate of the skull region is found. Based on the Euclidean distance between the first and second centroid coordinates, the positional change of the skull region's centroid can be quantitatively represented, thereby accurately assessing the amplitude of the patient's head movement. The larger the calculated Euclidean distance, the smaller the corresponding overlap index, indicating a greater patient head movement. Compared to pixel-based overlap methods, the centroid coordinate method focuses more on detecting changes in skull position.

[0071] Optionally, the Euclidean distance between the coordinates of the first centroid and the coordinates of the second centroid is inversely proportional to the overlap index.

[0072] Optionally, determining the patient's head movement based on the overlap index includes: determining that the patient's head remains stationary when the overlap index is greater than or equal to a second preset threshold; or determining that the patient's head has moved when the overlap index is first less than the second preset threshold; wherein, when the patient's head is determined to remain stationary, perfusion scanning continues; when the patient's head is determined to move, at least one of the following actions is taken: providing non-obstructive visual cues on the scanning operation interface and recording them; issuing an audible and visual alarm and displaying a prominent prompt on the scanning operation interface; pausing perfusion scanning.

[0073] In this embodiment, a second preset threshold accurately distinguishes whether the patient's head is moving. The threshold can be flexibly adjusted according to different clinical needs and scanning conditions, improving the system's adaptability. When the patient's head remains stationary, the system continues scanning, ensuring the continuity of the scanning process and data integrity, avoiding unnecessary interruptions. When the patient's head moves slightly, non-blocking prompts and recording allow monitoring of the patient's condition and appropriate measures to be taken without affecting the scanning progress, reducing the impact of artifacts caused by slight movements. When the patient's head moves significantly, audible and visual alarms and prominent prompts quickly draw attention to the significant movement. The operator can then decide whether to immediately stop the scan or ignore the alarm and continue scanning based on the scanning progress, providing greater flexibility and allowing for timely intervention, such as pausing the scan or adjusting the patient's posture, to reduce the impact of motion artifacts on diagnosis. In cases of severe head movement, the scan is automatically paused to avoid collecting invalid data, reduce the patient's radiation exposure, and improve system safety.

[0074] Optionally, the motion detection method for the perfusion scanning process further includes: providing a non-blocking visual prompt on the scanning operation interface and recording it when the overlap index is first less than a second preset threshold but greater than or equal to a third preset threshold; or, issuing an audible and visual alarm and displaying a prominent prompt on the scanning operation interface when the overlap index is first less than the third preset threshold; or, pausing the perfusion scanning when the overlap index remains less than the third preset threshold.

[0075] In this embodiment, by setting multiple thresholds, the occurrence of movement is subdivided into slight movement, significant movement, and severe movement, which can more accurately describe the patient's head movement state and avoid the limitations of a single threshold judgment. The scanning process responds differently to different levels of movement, and the response is related to the degree of movement; in cases of severe movement, the scan can be terminated.

[0076] Optionally, the motion detection method for the perfusion scanning process further includes: inserting markers into the raw data or fully reconstructed images of the perfusion scan based on the movement of the patient's head; wherein the markers reflect the movement of the head.

[0077] After obtaining the raw data or complete reconstructed images of the CT head perfusion scan, markers are inserted into the raw data or complete reconstructed images according to the patient's head movement to indicate that there are quality problems in the data for that time period; the marked data are then corrected or removed.

[0078] Combination Figure 5 As shown, this disclosure provides another motion detection method for a perfusion scanning process, including: S501, the processor acquires the image of the current scan circle.

[0079] S502, the processor performs skull region segmentation on the image of the current scan circle to obtain the skull mask image of the current scan circle.

[0080] S503, the processor compares the skull mask image of the current scan circle with the target skull mask image to determine the overlap index.

[0081] S504, the processor determines the movement of the patient's head based on the overlap index.

[0082] The S505 processor inserts markers into the raw data of the perfusion scan or the fully reconstructed image based on the patient's head movement.

[0083] In this embodiment, specific markers are inserted into the raw data corresponding to the scan circles where motion was detected. These markers can be timestamps, motion flags, or other metadata used to identify data quality issues that may exist during that time period due to patient head movements. Corresponding markers are also inserted into the reconstructed images. These markers can be image annotations, specific pixel values, or image metadata for subsequent processing software to recognize.

[0084] Optionally, the motion detection method for the perfusion scanning process further includes: correcting or removing the labeled data from the raw data or the fully reconstructed image of the perfusion scan.

[0085] In this embodiment, the software in the post-processing workstation automatically identifies these markers and takes corresponding processing measures based on the marker information. For example, when loading marked data, the software automatically prompts the user that the data for that time period may be degraded due to motion. The prompt information may include the time point of the motion, the affected image range, and the possible degree of impact. In the image viewing interface, images affected by motion are specially marked, such as highlighted, bordered, or annotated, so that the user can quickly identify the affected images. In addition, the software can automatically call motion correction algorithms to correct images affected by motion. The motion correction algorithm can use image registration, interpolation, or other techniques according to the type and degree of motion to restore the image quality as much as possible. If motion correction cannot effectively improve the image quality, the software can choose to remove images or data affected by motion. The removed data can be recorded in the log for subsequent analysis.

[0086] The motion detection method for perfusion scanning provided in this disclosure requires no external equipment, has low computational load, and strong anti-interference capabilities, enabling real-time and accurate detection of patient head movements during scanning. During the scanning process, the doctor can choose to issue a timely alert upon detecting motion or automatically stop the scan, thereby reducing invalid data acquisition and patient radiation exposure to a certain extent. This disclosure embodiment can reliably detect motion within the first scan circle after motion occurs and trigger an alarm, while effectively avoiding false alarms caused by changes in contrast agent concentration.

[0087] Combination Figure 6 As shown, this embodiment of the disclosure provides a motion detection device 600 for a perfusion scanning process, including a processor 601 and a memory 602. Optionally, the device 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 motion detection method for the perfusion scanning process described in the above embodiment.

[0088] 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.

[0089] 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 motion detection method for the perfusion scanning process in the above embodiments.

[0090] 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.

[0091] This disclosure provides a CT scanning device, including: a CT scanning device body, and the aforementioned motion detection device for the perfusion scanning process. The motion detection device for the perfusion scanning process is installed in the CT scanning device body. The installation relationship described herein is not limited to placement inside the CT scanning device, but also includes installation connections with other components of the CT scanning device, including but not limited to physical connections, electrical connections, or signal transmission connections. Those skilled in the art will understand that the motion detection device for the perfusion scanning process can be adapted to any feasible CT scanning device body, thereby realizing other feasible embodiments.

[0092] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the motion detection method described above for a perfusion scanning process.

[0093] 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, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code.

[0094] 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 technical solutions described herein. As used in the technical solutions described herein, 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 herein refers to any and all possible combinations of one or more of the associated listed elements. 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.

[0095] 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.

[0096] 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.

[0097] 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 motion detection method for a perfusion scanning process, characterized in that, include: Get the image of the current scan circle; Segment the skull region of the image in the current scan circle to obtain the skull mask image of the current scan circle; The skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index; The patient's head movement was determined based on the overlap index.

2. The motion detection method according to claim 1, characterized in that, Segment the skull region of the image in the current scan circle to obtain the skull mask image of the current scan circle, including: Determine the pixel value of each pixel in the image of the current scan circle; Pixels with pixel values ​​greater than a first preset threshold are classified as skulls to determine the skull region. Generate a skull mask image for the current scan circle based on the determined skull region; The first preset threshold is adaptively determined based on the image of the current scan circle as follows: Iterate through all possible candidate thresholds to segment the image of the current scan circle into the skull region and the background region; For each candidate threshold, determine the number of pixels and the mean pixel value of the skull region and the background region, and determine the inter-class variance of the skull region and the background region based on the number of pixels and the mean pixel value; The candidate threshold that maximizes the inter-class variance is determined as the first preset threshold.

3. The motion detection method according to claim 1, characterized in that, Obtain the target skull mask image as follows: Obtain the skull mask image from the previous scan circle as the target skull mask image; or, The skull mask image of the initial scan circle is obtained as the target skull mask image.

4. The motion detection method according to claim 1, characterized in that, The skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: Determine the first comparison region in the skull mask image of the current scanning circle, and the second comparison region in the target skull mask image corresponding to the first comparison region; Determine the total number of pixels at the intersection of the first and second comparison regions, and the total number of pixels in the union of the two regions; The overlap index is determined by the ratio of the total number of intersection pixels to the total number of union pixels.

5. The motion detection method according to claim 1, characterized in that, The skull mask image of the current scanning circle is compared with the target skull mask image to determine the overlap index, including: Determine the first comparison region in the skull mask image of the current scanning circle, and the second comparison region in the target skull mask image corresponding to the first comparison region; Determine the first centroid coordinates of the first comparison region and the second centroid coordinates of the second comparison region; The overlap index is determined based on the Euclidean distance between the coordinates of the first and second centroids.

6. The motion detection method according to claim 1, characterized in that, The patient's head movement was determined based on the overlap index, including: If the overlap index is greater than or equal to the second preset threshold, the patient's head is determined to remain stationary; or, If the overlap index is less than the second preset threshold for the first time, it is determined that the patient's head has moved; If the patient's head remains stationary, the perfusion scan continues; if the patient's head moves, at least one of the following actions is taken: providing non-obstructive visual cues on the scanning interface and recording them; issuing an audible and visual alarm and displaying a prominent prompt on the scanning interface; or pausing the perfusion scan.

7. The motion detection method according to claim 6, characterized in that, Also includes: If the overlap index is initially less than the second preset threshold but greater than or equal to the third preset threshold, a non-blocking visual prompt will be displayed on the scanning interface, and the result will be recorded; or, If the overlap index falls below the third preset threshold for the first time, an audible and visual alarm will be triggered, and a prominent prompt will appear on the scanning operation interface; or, If the overlap index remains below the third preset threshold, the perfusion scan is paused.

8. The motion detection method according to any one of claims 1 to 7, characterized in that, Also includes: Based on the patient's head movement, markers are inserted into the raw data of the perfusion scan or the fully reconstructed image; where the markers reflect the head movement.

9. A motion detection device for a perfusion scanning process, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when running the program instructions, execute the motion detection method for a perfusion scanning process as described in any one of claims 1 to 8.

10. A CT scanning device, characterized in that, include: The CT scanning equipment itself; The motion detection device for the perfusion scanning process as described in claim 9 is installed on the CT scanning equipment body.

Images