Medical image display device, medical image display method and storage medium

Abstract

The objective is to provide a medical image display device, a medical image display method, and a storage medium that improve the visual recognition of gaze direction in medical images. The solution involves a medical image display device comprising an acquisition unit, a gaze detection unit, and a display control unit. The acquisition unit acquires a medical image including the eyeball of at least one of the subjects. The gaze detection unit detects the gaze direction of the eyeball included in the medical image. The display control unit determines a display mode of the medical image based on the gaze direction of the eyeball and displays the medical image on a display unit according to the determined display mode.

Description

[0001] Related applications:

[0002] This application claims priority to U.S. Patent Application No. 17 / 180098, filed February 19, 2021, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The embodiments described in this specification generally relate to medical image display devices, medical image display methods, and computer-readable non-volatile storage media for displaying medical images, such as images of patients suspected of having a stroke. Background Technology

[0004] Stroke is a life-threatening medical condition that sometimes requires emergency medical intervention. Typically, a non-contrast CT scan (NCCT) is sometimes performed first in the diagnosis of stroke. NCCT results are sometimes used to rule out hemorrhagic stroke from the perspective of causes. NCCT results are sometimes used to rule out conditions with similar symptoms to stroke, such as seizures and brain tumors. NCCT results are sometimes used to identify, for example, dense vessels showing thrombi and / or to determine ischemia.

[0005] Subsequent CT angiography (CTA), which combines CT scans with contrast agent infusion, is sometimes used to confirm the initial diagnosis and / or to obtain further information that helps determine the course of treatment.

[0006] One cause of ischemic stroke is, for example, the presence of a large blood vessel blockage. Large blood vessel blockage is an acute obstruction of both the anterior and posterior circulation.

[0007] If a patient has a large blood vessel blockage, thrombectomy is sometimes the appropriate treatment. Mechanical thrombectomy restores blood flow by removing the thrombus that is obstructing blood flow using a thrombectomy device inserted through an intravascular catheter. Sometimes, it is necessary to transfer the patient to a hospital capable of performing thrombectomy to receive this treatment. Sometimes, an emergency assessment of a large blood vessel blockage is required to determine if thrombectomy is necessary.

[0008] Determining which patients have large vessel blockages and are suitable candidates for potentially life-saving thrombectomy can constitute a crucial part of the clinical workflow for stroke. The growing evidence of the benefits of endovascular thrombectomy continues to drive the need for the rapid identification of potentially suitable patients.

[0009] According to American Heart Association (AHA) guidelines, intracranial vascular imaging is generally required to determine whether a patient has large vessel blockage. Several issues arise in connection with this. Sometimes there is a lack of expertise available for interpreting images during vascular assessment. Sometimes the timing of contrast agent administration is problematic or it becomes a non-diagnostic study. Some patients have contraindications to iodine contrast agents used in vascular assessment. Furthermore, intracranial vascular assessment is not routinely performed in all hospitals.

[0010] In non-contrast evaluation, the presence of a given imaging feature sometimes indicates the presence of occlusion. While signs of occlusion can be highly specific, they can be low in sensitivity. One such imaging feature is the hyper-dense artery sign (HAS) in non-contrast computed tomography (NCCT). Another such feature is the susceptibility vessel sign (SVS) in T2* gradient recalled echo (GRE) magnetic resonance study (MRI).

[0011] Clinical triage criteria are sometimes used to indicate the presence of large vessel blockage. Examples of clinical criteria that may be used in LVO triage include the Rapid Arterial Occlusion Evaluation (RACE) criteria and the Cincinnati Prehospital Stroke Scale.

[0012] Studies have shown that ocular deviation can identify patients with a high likelihood of large vessel blockage. Ocular deviation is included as a factor in most clinical criteria used for LVO triage (such as RACE or Cincinnati).

[0013] In some situations, non-contrast imaging features or clinical triage criteria are sometimes insufficient in terms of sensitivity and specificity when identifying all potentially suitable candidates for thrombus removal.

[0014] Several currently available LVO triage methods identify potential LVOs through CTA assessment. In such currently available LVO triage methods, the LVO is directly presented. Summary of the Invention

[0015] The problem that the invention aims to solve:

[0016] One of the problems to be solved by the embodiments disclosed in this specification and the accompanying drawings is to improve the visual recognition of the direction of gaze in medical images. However, the problems to be solved by the embodiments disclosed in this specification and the accompanying drawings are not limited to the above-mentioned problems. Problems corresponding to the various configurations shown in the embodiments described below can also be identified as other problems.

[0017] Methods used to solve problems:

[0018] The medical image display device according to the embodiment includes an acquisition unit, a gaze detection unit, and a display control unit. The acquisition unit acquires a medical image including the eyeball of at least one of the subjects. The gaze detection unit detects the gaze direction of the eyeball included in the medical image. The display control unit determines the display mode of the medical image based on the gaze direction of the eyeball and displays the medical image on the display unit in the determined display mode. Attached Figure Description

[0019] Here, the embodiments are described as examples not intended to be limiting, and are shown in the following figures.

[0020] Figure 1 This is a schematic diagram of the apparatus involved in the implementation.

[0021] Figure 2 This is a flowchart illustrating a general outline of the method involved in the implementation.

[0022] Figure 3 This is a schematic diagram of the notification involved in the implementation method.

[0023] Figure 4 This is a schematic diagram of the user interface involved in the implementation method.

[0024] Figure 5 This is a schematic diagram of the user interface involved in the implementation method.

[0025] Figure 6 This is a schematic diagram of the user interface involved in an implementation of persistent eye deviation.

[0026] Figure 7 This is a schematic diagram of the user interface involved in an implementation with high-density blood vessels.

[0027] Figure 8 This is a diagram of a patient's eye that highlights the direction of their gaze, according to the implementation method.

[0028] Figure 9 This is a diagram of a patient's eye that highlights the direction of their gaze, according to the implementation method.

[0029] Figure 10This is a diagram of a patient's eye that highlights the direction of their gaze, according to the implementation method. Detailed Implementation

[0030] The medical image display device described in the following embodiments includes an acquisition unit, a gaze detection unit, and a display control unit. The acquisition unit acquires a medical image containing the eyeball of at least one of the subjects. The gaze detection unit detects the gaze direction of the eyeball contained in the medical image. The display control unit determines a display mode of the medical image based on the gaze direction of the eyeball and displays the medical image on a display unit in the determined display mode.

[0031] One embodiment provides an image display device (medical image display device) equipped with a processing circuit. The processing circuit is configured to receive medical image data including the performance of at least one eye of a subject, process the medical image data to determine the gaze direction of the at least one eye of the subject, and select a display mode for displaying the medical image data based on the determined gaze direction.

[0032] One embodiment provides a method comprising: receiving medical image data containing the performance of at least one eye of a subject; processing the medical image data to determine the gaze direction of the at least one eye of the subject; and selecting a display mode for displaying the medical image data based on the determined gaze direction.

[0033] exist Figure 1 The diagram schematically illustrates a medical image processing apparatus 10 according to an embodiment. The medical image processing apparatus 10 is configured to process and display medical images of a patient or other subject. The medical image processing apparatus 10 is sometimes also referred to as an image display device or image display apparatus (medical image display device).

[0034] In this example, the medical image processing apparatus 10 includes a computing device 12 that functions as a personal computer (PC) or workstation. The computing device 12 is connected to a display device 16, such as a screen, and one or more input devices 18, such as a computer keyboard and mouse. In some embodiments, the display device 16 is a touchscreen that also functions as an input device 18. The computing device 12 is connected to a data storage unit 20.

[0035] The medical image processing apparatus 10 is connected to a CT scanner 14 configured to perform non-contrast CT scans (NCCT) and CT angiography (CTA) scans on patients or other subjects in order to obtain volumetric medical imaging data. In this embodiment, each scan includes a brain scan. In other embodiments, any suitable part of the body can be scanned.

[0036] In alternative implementations, the data can be obtained using any suitable medical device and / or acquisition method. The CT scanner 14 can also be replaced or supplemented by one or more scanners configured to obtain 2D or 3D imaging data using any suitable image diagnostic method. Examples of such scanners include CT scanners, cone-beam CT scanners, magnetic resonance imaging (MRI) scanners, X-ray scanners, ultrasound scanners, positron emission tomography (PET) scanners, or single-photon emission computed tomography (SPECT) scanners.

[0037] Data obtained using the CT scanner 14 is stored in the data storage unit 20 and provided to the computing device 12. In other embodiments, the computing device 12 may also obtain the data directly from the CT scanner 14. In alternative embodiments, the medical image processing device 10 replaces the data storage unit 20 by receiving medical imaging data and / or medical images from one or more other data storage units (not shown) in addition to the data storage unit 20. For example, the medical image processing device 10 may also receive medical imaging data from one or more remote data storage units, which may form part of a Picture Archiving and Communication System (PACS), or other information systems such as clinical examination value archiving, electronic medical record (EMR) systems, or admission discharge and transfer (ADT) systems. Here, the medical image processing device 10, which implements the function of receiving medical imaging data and / or medical images, is an example of an acquisition unit.

[0038] The computing device 12 includes a central processing unit (CPU) 22. The computing device 12 automatically or semi-automatically provides processing resources for processing the dataset. In this embodiment, the dataset includes medical imaging data.

[0039] The computing device 12 includes, for example: a feature detection circuit 23 configured to detect areas of high-density blood vessels (thrombi) and process imaging data to determine one or more imaging features; a gaze detection circuit 24 configured to determine the direction of the gaze; a notification circuit 25 configured to establish markers for potential thrombus removal candidates; a drawing circuit 26 configured to draw an image based on the imaging data; and a display circuit 28 configured to select and position the drawn view on the display screen 16 or any suitable display. Here, the feature detection circuit 23 is an example of a feature detection unit. The gaze detection circuit 24 is an example of a gaze detection unit. The notification circuit 25 is an example of a notification unit. The drawing circuit 26 is an example of an image processing unit. The display circuit 28 is an example of a display control unit. The display device 16 (display screen 16) is an example of a display unit.

[0040] In this embodiment, circuits 23, 24, 25, 26, and 28 are each installed on the computing device 12 via a computer program, wherein the computer program has computer-readable instructions executable to perform the method of the embodiment. However, in other embodiments, the various circuits may also be installed as one or more application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs). In this embodiment, circuits 23, 24, 25, 26, and 28 are each installed as part of CPU 22. In alternative embodiments, circuits 23, 24, 25, 26, and 28 may also be installed individually, or may form part of two or more CPUs. In other embodiments, at least a portion of the method may also be executed on one or more graphics processing units (GPUs).

[0041] Additionally, the computing device 12 includes a hard disk drive and other components of a PC, including RAM, ROM, a data bus, an operating system containing various device drivers, and hardware including a graphics card. For clarity, in Figure 1 Such a component is not shown in the document.

[0042] Figure 1 The system is configured to execute by Figure 2 The flowchart outlines a series of stages.

[0043] In phase 30, a non-contrast CT (NCCT) scan of the brain is performed to identify patients suspected of having a stroke. Performing a non-contrast CT scan of the brain is a routine clinical procedure in cases of suspected stroke.

[0044] The volumetric data obtained by NCCT scanning is provided to the data storage unit 20, and then from the data storage unit 20 to the feature detection circuit 23 and the gaze detection circuit 24. In other embodiments, the feature detection circuit 23 and the gaze detection circuit 24 may also obtain a collection of volumetric NCCT data from any suitable data storage unit. NCCT data may also be obtained by the feature detection circuit 23 and the gaze detection circuit 24 at any suitable time after the NCCT scan. In these cases, the feature detection circuit 23 and the gaze detection circuit 24 can be exemplified as an acquisition unit.

[0045] In stage 32, feature detection circuit 23 performs high-density vessel detection processing. High-density vessel detection processing includes processing the volumetric NCCT data received in stage 30 to determine the presence of a high-density arterial sign (HAS) within the NCCT scan. HAS is sometimes also referred to as a high-density vascular sign.

[0046] exist Figure 2 In the implementation of this method, high-density vascular detection processing is performed using a convolutional neural network, for example, by the method described below: Lisowska A., Beveridge E., Muir K. and Poole I. Thrombus Detection in CT Brain Scans using a Convolutional Neural Network. DOI:10.5220 / 0006114600240033 In Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2017), pages 24-33.

[0047] In other embodiments, any suitable high-density blood vessel detection method can be used. For example, any suitable image analysis method can be used to automatically detect high-density blood vessels. The relevant portions of the patient's anatomical structure can also be displayed to the user.

[0048] In other embodiments, the feature detection circuit 23 may also be configured to detect one or more non-contrast imaging features associated with occlusion. For example, in some embodiments, magnetic resonance imaging (MRI) data is obtained in stage 30 instead of CT data. The MRI data includes, for example, T2* gradient refocusing echo (GRE) MRI assessment. In such embodiments, high-density vascular detection processing includes, for example, processing the MRI data to determine the presence of magnetically susceptible vessels (SVS) in the MRI data.

[0049] It is known that in non-contrast evaluation, the presence of HAS and SVS in a given imaging modality implies high specificity but low sensitivity, indicating the presence of blockage.

[0050] In this embodiment, when the feature detection circuit 23 detects HAS in the NCCT data, it determines that a region with high-density blood vessels exists. The feature detection circuit 23 can infer the location of the region with high-density blood vessels.

[0051] In stage 34, in response to the detection of areas with high-density vessels, notification circuit 25 designates the patient as a potential thrombus removal candidate. Designating a patient as a potential thrombus removal candidate can also be interpreted as marking the patient as a potential LVO patient, or marking the patient as a potential thrombus removal patient. Notification circuit 25 can also add the patient to the working list. Notification circuit 25 can also, as described in reference... Figure 3 As will be described later, mobile notifications for LVO candidates will be issued.

[0052] The drawing circuit 26 draws a drawing image 36 representing a slice aligned with the previous loop, based on the NCCT data. The drawing image 36 is aligned with the slice of NCCT data that is most likely to contain occlusion imaging features.

[0053] The display circuit 28 displays the plotted slice 36 on the display screen 16 or any suitable display. In several embodiments, areas of detected high-density blood vessels are highlighted on the plotted image 36. For example, areas of detected high-density blood vessels can be represented by a different color than other parts of the plotted image 36. Alternatively, areas of detected high-density blood vessels can be outlined in the plotted image 36.

[0054] As described below with reference to stage 60, the plotted image 36 can be used for evaluations performed by clinicians.

[0055] In some embodiments, if the feature detection circuit 23 does not detect a region of high-density blood vessels in stage 32, stages 34 and / or 36 may be omitted. In other embodiments, the slice aligned with the anterior circulation is drawn and displayed even if no high-density blood vessels are detected. In some embodiments, an indication that no high-density blood vessels were detected may also be displayed to the user.

[0056] In stage 38, the gaze detection circuit 24 performs gaze detection processing. This gaze detection processing includes processing the NCCT scan data to obtain an inference of the gaze direction for at least one eye of the patient. In this embodiment, gaze detection is performed regardless of the result of the high-density vessel detection processing. In other embodiments, gaze detection may be omitted, for example, if high-density vessels have already been detected. Gaze detection can be performed after, before, or simultaneously with the high-density vessel detection processing in stage 32.

[0057] When we mention "eye" below, we are referring to the pupil, also known as the eyeball. In the case of binoculars, it is conceivable that both eyes are looking in the same direction.

[0058] The output of the gaze detection processing includes a classification of the gaze direction in the NCCT data into one of three categories. In category 1, the gaze is tilted to the right. In category 2, the gaze is tilted to the left. In category 3, the gaze is neither tilted to the left nor to the right, or the gaze is unknown. In the following descriptions, the classification is referred to as right, left, neither left nor right / unknown.

[0059] In clinical practice, clinical visual deviation of the eyes is well-documented as a symptom of stroke. This clinical deviation is known as Prevost's sign. Visual deviation is defined as an equal and persistent deviation of both eyes from the midline towards the same side. In cases where present, the eyes deviate towards the hemisphere of the brain affected by the stroke. The affected hemisphere is the side opposite to the side of the body exhibiting symptoms such as paralysis or facial ptosis.

[0060] The eye's gaze angle is defined, for example, relative to the plane opposite to the patient's skull. The gaze angle can be determined, for example, by methods described in: Kobayashi, M., Horizontal gaze deviation on computedtomography: the visual criterion and lesion characteristics in ischemic stroke. Acta Neurol Belg (2018) 118:581. https: / / doi.org / 10.1007 / s13760-018-0949-1 or Spokoyny, Ilana et al., Visual Determination of Conjugate Eye Deviation on Computed Tomography Scan Predicts Diagnosis of Stroke Code Patients, Journal of Stroke and Cerebrovascular Diseases, Volume 25, Issue 12, 2809-2813.

[0061] In some embodiments, the gaze detection circuit 24 can, for example, return a numerical value as the gaze angle. Depending on whether the gaze direction is left, right, or neither left nor right / unknown, the gaze angle may be returned additionally or alternatively.

[0062] In this embodiment, a trained model is used to determine whether the eyes are tilted to the right, left, or neither / unknown. The trained model is, for example, a deep learning classifier. For instance, an R-CNN (Regions with Convolutional Neural Network features) method, similar to that described in R. Girshick, J. Donahue, T. Darrell, J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014, can also be used. In other embodiments, any suitable method can be used to determine whether the gaze direction is left, right, or neither / unknown. For example, any suitable image analysis method can be used to classify the gaze direction. The relevant parts of the patient's biological structure can also be determined and displayed to the user.

[0063] In several situations, the brain can be scanned from an anatomical region scanned using a CT scanner, excluding the patient's eyes. At least in such cases, for example, visual direction can be determined based on biological structures other than the eyeball. For instance, compression of the extraocular muscles can indicate the direction of vision.

[0064] The output of stage 38 is a judgment on whether the line of sight is left, right, neither left nor right, or unknown.

[0065] exist Figure 2 In stage 40, CT scanner 14 acquires an angiographic CT scan (CTA scan) of the patient's brain.

[0066] Volumetric data from the CTA scan is provided to the data storage unit 20 and then from the data storage unit 20 to the gaze detection circuit 24. In other embodiments, the gaze detection circuit 24 may also obtain a set of volumetric CTA data from any suitable data storage unit. The gaze detection circuit 24 may also obtain the CTA data at any suitable time after the CTA scan is performed.

[0067] In stage 42, the gaze detection circuit 24 performs gaze detection processing on the CTA scan data. This gaze detection processing includes processing the CTA scan data to infer the gaze direction of at least one eye of the patient. The gaze detection circuit 24 outputs a classification of gaze direction as right, left, or neither left nor right / unknown.

[0068] In other embodiments, the gaze detection circuit 24 may, for example, return a numerical value as the gaze angle. It may also additionally or alternatively return the gaze angle based on the determination that the gaze direction is left, right, or neither left nor right / unknown.

[0069] In this embodiment, a trained model is used to determine whether the eye is tilted to the right, to the left, or neither / unknown. In some embodiments, considering that contrast-enhanced data is used instead of non-contrast-enhanced data to perform this determination, the trained model may also be different from the trained model used in stage 38. In other embodiments, the same trained model may be used in both stages 38 and 42.

[0070] The output of stage 42 is a judgment on whether the line of sight of the CTA data is left, right, neither left nor right, or unknown.

[0071] In stage 44, the gaze detection circuit 24 compares the gaze direction determined in stage 38 with the gaze direction determined in stage 42. If the gaze direction determined in stage 42 is the same as the gaze direction determined in stage 38, the gaze detection circuit 24 determines that a persistent gaze deviation has occurred. In response to the determination that a persistent gaze deviation has occurred, Figure 2 The method proceeds to stages 46 and 50. Stage 50 may be omitted if it is determined that there is no persistent deviation in the line of sight. In some embodiments, part or all of stage 46 may also be omitted.

[0072] In stage 46, notification circuit 25 designates the patient as a potential thrombus removal candidate based on the fact that the line of sight is the same in both CTA and NCCT data. If the patient has already been designated as a potential thrombus removal candidate in stage 34, notification circuit 25 does not change this designation.

[0073] Persistent ocular deviation involving both NCCT and CTA has shown good sensitivity and specificity for large vessel occlusion (Attenhofer et al, The Sustained DeyeCOM Sign As a Predictor of large vessel occlusions and Stroke Mimics, J. Stroke Cerebrovasc Dis. 2018 June; 27(6); 1466-1470). Persistent ocular deviation has been used as an indicator that patients are potential candidates for thrombectomy. Figure 2 Used in the method.

[0074] The rendering circuit 26 receives indications of the ocular region within the volumetric NCCT data and / or CTA data from the gaze detection circuit 24. For example, the ocular region can be represented by a bounding box obtained through segmentation. Based on the volumetric NCCT data and / or CTA data, the rendering circuit 26 renders at least one image 48 representing the ocular region. In this embodiment, the rendered image 48 represents a portion of the body axis slice of the head passing through the lens of the eye.

[0075] The display circuit 28 displays at least one drawn image 48 of the eye region on the display screen 16. This at least one drawn image 48 can provide a quick view of the line of sight. This at least one drawn image 48 can provide a brief overview of the eye included to indicate the side suspected of being blocked.

[0076] By displaying a brief overview of the eyes, clinicians can be guided to the hemisphere of the brain corresponding to the direction of the gaze. Clinicians may also use left / right brain indications to determine if there is a blockage.

[0077] In other embodiments, derivative measurements associated with visual deviation may also be displayed. For example, the deviation angle may be displayed. In still other embodiments, any other clinical information may be displayed.

[0078] Reference Figure 8 (a)~ Figure 10 (c) Various methods of displaying the view of the line of sight are further described below. Derivative measurements or other clinical information may also be added to any of the lines of sight described below. Figure 1 Start displaying.

[0079] In stage 50, the drawing circuit 26 draws the set of CTA views 52, 54, 56, and 58. The display circuit 28 displays the CTA views 52, 54, 56, and 58 on the display screen 16, for example, according to display rules such as a hanging protocol. The display of the CTA views can be optimized to make congestion identifiable.

[0080] CTA views 52, 54, 56, and 58 are stroke views based on landmarks within the CTA. Stroke views can be views that evaluate specific anatomical and vascular regions of the brain associated with stroke. View 56 (first view) is the anterior circulation, views 54 and 58 (second and third views) are views of the two posterior circulations, and view 52 (fourth view) is a view of the collateral circulation. CTA views 52, 54, 56, and 58 are displayed according to selected display parameters. The images in CTA views 52, 54, 56, and 58 are aligned relative to the biological structure. The image is slabbed at a selected thickness with a window level set to a selected value. The selected values ​​for thickness and window level can be considered optimal values ​​for the biological structure of the viewed object and / or the lesion of the viewed object.

[0081] In this embodiment, only CTA views 52, 54, 56, and 58 are displayed when persistent eye deviation is detected. If persistent eye deviation is detected, a first display mode displaying CTA views 52, 54, 56, and 58 is used. If persistent eye deviation is not detected, a second display mode not displaying CTA views 52, 54, 56, and 58 is used. The display circuit 28 is configured to display a scan most suitable for a given result or reference.

[0082] In other embodiments, for example, refer to Figure 6 , 7 As described later, display circuit 28 displays both the plotted image 36 aligned with the previous loop and CTA views 52, 54, 56, and 58, but the display type varies depending on the detected gaze deviation. In the case of detected persistent gaze deviation, a first display mode is used: CTA views 52, 54, 56, and 58 are displayed as large main images, while the plotted image 36, including the plotted image aligned with the previous loop, is displayed as a smaller image, such as a thumbnail. In the case of no detected persistent gaze deviation, a second display mode is used: the plotted image 36, including the plotted image aligned with the previous loop, is displayed as a large main image, while CTA views 52, 54, 56, and 58 are displayed as smaller images, such as thumbnails. To observe the smaller images more closely, clinicians can, for example, click on the smaller images to select them.

[0083] Alternatively, the display method can be based on the time of obtaining the scan, or, for example, the interval between the time of obtaining the scan using the elapsed time between scans.

[0084] If high-density vascularity is detected in stage 32, the clinician evaluates image 36, which includes a slice aligned with the anterior circulation, in stage 60. If persistent ocular deviation is detected in stage 44, the clinician evaluates CTA views 52, 54, 56, and 58. Images 36, 52, 54, 56, and 58 may be the most relevant images suggested to the clinician in the initial evaluation. The clinician discusses thrombectomy for this patient. The clinician, for example, determines that the patient is suitable for thrombectomy. The clinician, for example, chooses to transfer the patient.

[0085] Pre-set criteria for thrombectomy and / or transfer can also be used. Panel 62, displaying the thrombectomy and / or transfer criteria, can also be shown to clinicians. Thrombolysis and / or transfer criteria and their display on panel 62 are referenced. Figures 4-7 To be discussed later.

[0086] Figure 3 It can be used as Figure 2 The notification processing 70 is performed as part of stage 36 or stage 46. In this embodiment, the notification processing 70 includes a list of LVO candidate jobs or a move notification.

[0087] Mobile notifications include messages sent to mobile devices, such as smartphones 72. These messages indicate a need for urgent evaluation of potential thrombus removal candidates.

[0088] The workflow notification includes indicators present in workflow 74. The workflow includes a list of patients whose data constitutes the evaluation subjects. An indicator is added to one of the patients, indicating that the patient needs urgent evaluation. In some embodiments, the workflow may also be reordered so that patients identified as needing urgent evaluation move upwards in the patient list.

[0089] Mobile notifications or workflow notifications can also include summary information about the patient's status.

[0090] For example, if a clinician receives a notification such as a mobile notification or workflow notification, they can decide to prioritize evaluating patients who received that notification. This can reduce the time until the patient is evaluated. Alternatively, it can reduce the time between obtaining a scan and treatment, such as thrombectomy.

[0091] Figure 2 and Figure 3This method can provide clues based on clinical relevance to determine the presence of large vessel occlusion and identify thrombus removal candidates in patients with acute stroke. It involves continuous gaze detection on consecutive images. Figure 2 In this method, the continuous images contain both NCCT data and CTA data. Figure 2 The method also identifies non-contrast imaging features associated with the occlusion. Cases are flagged based on persistent ocular deviation or the presence of occlusion imaging features as high-density vascular signs in this embodiment. Clinicians are notified if a patient is known to meet the criteria for potential thrombus removal candidates.

[0092] Alternatively, a display method can be selected to rapidly process the evaluation of potential thrombus removal candidates. Clinicians can be presented with the most relevant information first. This allows clinicians to use the most relevant information when assessing the presence of blockage.

[0093] The medical image processing device 10 provides relevant information to clinicians without directly detecting LVO.

[0094] In some embodiments, additional pre-defined connotations or exclusion criteria may also be combined with the reference. Figure 2 and Figure 3 The methods described above can also be used, for example, ASPECTS or ICH. See below for reference. Figures 4-7 This describes the implementation method.

[0095] Figure 4 This refers to the elements of a user interface that display information to users such as clinicians. The user interface can be displayed on any suitable screen, such as a monitor screen 16. Figure 4 It also indicates that the smartphone 72 displays notification messages.

[0096] The user interface includes panel 62. Two views 82 and 84 of the patient's eye region are displayed on panel 62. The first view 82 is obtained by drawing image data from a first scan obtained at a first moment. Figure 4 In the illustrated embodiment, the first scan is an NCCT scan. The patient's eye deviates to the left in the first scan. To indicate eye deviation, a plus sign (+) is displayed next to the first view 82. The plus sign can also be displayed if the eye deviates to the right. A minus sign (-) can be displayed if there is no eye deviation.

[0097] In other embodiments, any suitable one or more indicators of eye deviation can be used. To highlight or emphasize eye deviation, any suitable visual effect, such as a reference, can also be used. Figure 8 (a)~ Figure 10 (c) Visual effects described later.

[0098] The second view 84 is obtained by plotting image data from the second scan obtained at the second moment. Figure 4 In the illustrated embodiment, the second scan is a CTA scan. The patient's eye shows the same deviation in the second scan as in the first scan. The patient's eye consistently shows deviation in both scans, therefore two plus signs are displayed next to the second view 84. In other embodiments, any suitable one or more indicators can be used to represent persistent deviation. Any suitable visual effects can also be used to highlight persistent deviation.

[0099] Views 82 and 84 are body-axis slices aligned with the lens of the patient's eye to show the affected side in each scan. Views 82 and 84 provide a brief overview of the eye for two consecutive scans at two consecutive moments, drawn as two consecutive images. It is known that patients with LVO are more likely to have it when ocular deviation persists across two images. Views 82 and 84 can also be views from any two consecutive scans and images. Figure 4 In this implementation, the two consecutive scans are NCCT and CTA.

[0100] In other embodiments, one or both scans may be MRI scans. In several embodiments, the scan comprises two MRI sequences that are visually perceptible to the eye. The SVS of high-density vessels is replaced with GRE.

[0101] In other implementations, the scan may be a 3D localization scan obtained at time 1 and an NCCT scan obtained at time 2. When performing a CT scan of a region of the patient's body, a three-dimensional (3D) localization scan is generally performed first. A 3D localization scan can have a large field of view for local scanning of the area. A 3D localization scan can also include a low-resolution scan of a large area of ​​the patient's body, such as the entire body. By using an NCCT 3D localization scan followed by an NCCT scan, a solution for NCCT-only reference centers can also be provided.

[0102] In several embodiments, the first scan is an optical image obtained by an optical camera within a scanner. Ocular deviation is determined using the optical image and subsequent scans. In several embodiments, to determine ocular deviation, a camera, such as an AI camera, is used in the imaging process, and the ocular deviation in the dynamic image obtained by the camera is compared with the ocular deviation in subsequent scans.

[0103] By ensuring that the first and second views 82 and 84 of the eye region are always present, the user can be shown the side with the abnormality. Alternatively, no results can be output to the user; for example, instead of an explicit indication that the patient may have LVO, the user can be shown the side with the abnormality. In several situations, the necessary conditions for obtaining regulatory approval may differ between systems that display a diagnosis and those that do not. Providing the user with relevant information without a diagnosis may be important for obtaining regulatory approval. Since the tool avoids Computer Aided Detection (CADe), regulatory approval may not be difficult to obtain.

[0104] exist Figure 4 In this section, panel 62 also contains information related to baselines for factors other than eye deviation. Figure 4 In this implementation, the baseline is related to intracerebral hemorrhage (ICH), occlusion, Alberta Stroke Program Early CT (ASPECTS) score, and collaterals. Element 90 in the first display shows the ICH score. Element 92 in the second display shows occlusion information. Element 94 in the third display shows the ASPECTS score. Element 96 in the fourth display shows collaterals. Elements 90, 92, 94, and 96 in the first through fourth displays, along with views 82 and 84, can be considered together as a set of clinically relevant information provided to determine the presence of LVO and thrombus removal candidates in acute stroke patients.

[0105] To provide a complete LVO triage solution, other reference points (ICH, occlusion, ASPECTS, collaterals) are considered in combination with the line-of-sight deviations shown in views 82 and 84 of the first and second views. In several embodiments, the hospital can also select which reference-related information to display and form the display. The selection of which reference-related information to display can also be based on the imaging capabilities available, such as imaging capabilities available in the hospital or imaging capabilities available to the individual patient.

[0106] exist Figure 4 In this implementation, if the results associated with display elements 90, 92, 94, and 96 meet the criteria for thrombus removal or transfer, display elements 90, 92, 94, and 96 are marked with green. For example, when the ICH score meets the prescribed criteria for thrombus removal or transfer, display element 90 becomes green. Figure 4 It is black and white, therefore green is in Figure 4 This was not reflected in the text.

[0107] In other embodiments, any suitable method may be used to indicate that the results of display elements 90, 92, 94, and 96 meet the criteria for thrombus removal or hospital transfer. For example, any suitable color, line type, shape, or shading, or any suitable visual effect or other effect may be used.

[0108] If the results of all factors represented by display elements 90, 92, 94, and 96 meet the criteria for thrombus removal or transfer, notification 100 is displayed on panel 62. Figure 4 In the example, the notification text reads "Urgent evaluation, thrombus removal candidate." The display of notification 100 can serve as a reason for clinicians to urgently evaluate a patient's imaging to determine whether the patient is a thrombus removal candidate.

[0109] Figure 5 This indicates examples of contradictory or missing results from thrombus removal or transfer criteria. Panel 62 contains... Figure 4 The same applies to views 82 and 84 in the first and second views, as well as display elements 90, 92, 94, and 96. (For example...) Figure 4 As shown, the plus sign in view 82 and the two plus signs in view 84 indicate persistent ocular deviation.

[0110] exist Figure 5 In the example shown, both the ICH result and the occlusion result meet the criteria for thrombus removal or hospital transfer. Display elements 90 and 92 are marked with green (green in...). Figure 5 (Not shown in the image). Green indicates that the intrinsic criterion is met. The intrinsic criterion indicates that the blockage is at a given location.

[0111] The ASPECTS score, determined by the algorithm, indicates contraindications to thrombectomy or hospital transfer. Element 94 is marked in red (red in...). Figure 5 (Not shown in the text, but instead represented by a thick outer frame).

[0112] exist Figure 5 In the implementation of the method, if any of the results of display elements 90, 92, 94, and 96 is contraindicated for thrombus removal or hospital transfer, the display element can be marked in red.

[0113] Even when other criteria are met, contraindications can sometimes arise. For example, although obstruction may be present, treatment may be excluded based on other imaging features such as poor collateral circulation, or other clinical information.

[0114] In other embodiments, any suitable method can be used to indicate that the results of display elements 90, 92, 94, and 96 are contraindicated for thrombus removal or transfer criteria. For example, any suitable color, line type, shape, or shading, or any suitable visual effect or other effect can be used.

[0115] exist Figure 5 In the illustrated embodiment, an appropriate scan or result cannot be used to provide information related to the collateral branch. To indicate that the result is unusable, display element 96 is grayed out. In other embodiments, a display element may also be grayed out if no appropriate result can be used for a factor associated with one of the display elements 90, 92, 94, or 96. In other embodiments, any suitable method may be used to indicate that the result of a factor associated with display elements 90, 92, 94, or 96 cannot be used. In several embodiments, the display element may be completely hidden. In other embodiments, any suitable color, line type, shape, or shading, or any suitable visual effect or other effect may be used.

[0116] The baseline summary (in this embodiment, ICH, occlusion, ASPECTS, and collateral branches) can be evaluated as a checklist for clinicians to examine all relevant information. Regardless of whether the baseline is automated, clinicians can examine all relevant information.

[0117] Figure 6 This demonstrates the interaction of the clinician on panel 62. Panel 62 displays the first and second views 82 and 84 of the patient's ocular region, and display elements 90, 92, 94, and 96 representing the ICH score, occlusion, ASPECTS score, and collateral circulation, respectively. Visual deviation is shown in both the first and second views 82 and 84, additionally indicated by a plus sign in the first view 82 and two plus signs in the second view 84. All factors associated with display elements 90, 92, 94, and 96 that meet the criteria for thrombus removal or transfer are highlighted in green (in...). Figure 6 (Not shown in the image).

[0118] Clinicians evaluate factors represented by display elements 90, 92, 94, and 96 (ICH, occlusion, ASPECTS, collateral vessels) corresponding to thrombus removal or transfer criteria. If a clinician selects display elements 90, 92, 94, or 96, for example, by clicking on a display element, relevant information is displayed to the clinician. For example, appropriate imaging may be shown.

[0119] Figure 6This indicates that a clinician, for example, clicked on display element 92 and selected the blockage. A shading effect is applied to display element 92 to indicate that display element 92 has been selected. In other embodiments, any suitable visual indication may be used to indicate that one of display elements 90, 92, 94, and 96 has been selected.

[0120] If a clinician selects one of the baselines (ICH, occlusion, ASPECTS, collateral), the display circuit 28 selects the most appropriate scan to display the view of that baseline. Figure 6 In the example shown, the patient has persistent ocular deviation but no high-density vessels. If the clinician selects display element 92 and chooses occlusion, display circuit 28 displays a set of stroke views 52, 54, 56, and 58 for immediate assessment of critical LVO locations within the vascular structure.

[0121] The display circuitry also highlights the view of the eyes corresponding to the scan of the frontal view. The frontal scan is highlighted in such a way that information about the eyes and the left / right side is always emphasized.

[0122] exist Figure 6 In the stroke view obtained from the second (CTA) scan, the second view 84 of the eye is highlighted. Figure 6 In this example, the second view 84 is highlighted using a halo effect around it. In other embodiments, any suitable visual effects or other effects may be used to highlight the scan of the view object.

[0123] Apart from the stroke views 52, 54, 56, and 58 provided to the clinician, all other scans can be displayed in normal view. For example, slice 36 aligned with the anterior circulation is displayed as a small thumbnail image available for the clinician to choose from. Figure 6 middle.

[0124] When a clinician begins to evaluate a benchmark and selects display elements associated with one or more benchmarks, the display circuit 28 selects the most appropriate scan to display a view of that benchmark. For example, if ICH is selected, the display circuit 28 automatically displays NCCT, or in this embodiment, displays GRE obtained from an MRI scan. The most appropriate scan to display can be based on the workflow and imaging used. The selection of the most appropriate scan to display can also be set by the hospital.

[0125] Figure 7In cases where the patient does not exhibit persistent ocular deviation but has high-density vascularity, the clinician selects the occlusion from panel 62. Panel 62 displays the patient's first and second views 82, 84, and display elements 90, 92, 94, 96 that represent the criteria for thrombectomy or transfer. All criteria of display elements 90, 92, 94, 96 that meet the criteria for thrombectomy or transfer are highlighted in green (in...). Figure 7 (Not shown in the image).

[0126] In the patient's first view 82, a deviation is observed as indicated by a plus sign next to the first view 82. In the patient's second view 84, no deviation is observed. A minus sign is present next to the second view 84. The gaze detection circuit 24 determines that there is no persistent gaze deviation.

[0127] If the clinician selects display element 92 showing occlusion, the display circuit 28 selects the most appropriate scan. Since the patient does not have persistent visual deviation but has high-density vascular signs, the NCCT scan is selected as the most appropriate scan for initial display. To indicate that the NCCT scan is being displayed in the view, the first view 82 is highlighted. Figure 7 In the image, first view 82 is highlighted by the halo effect surrounding it.

[0128] In this embodiment, the NCCT scan is displayed by showing the output of a preset slice 36 aligned with the slice most likely to be identified in the previous loop. Slice 36 is selected as the slice most likely to identify high-density vessels. The rendering circuit 26 selects the most likely slice 36, thereby minimizing the required scrolling and reducing the amount of scrolling required between images.

[0129] In several embodiments, the display of slice 36 may include segmentation of high-density blood vessels. In several embodiments, the display of slice 36 may also include labeling of high-density blood vessels. In several cases, the presence or absence of segmentation and / or labeling may be determined by a limiting method.

[0130] exist Figure 7 In some embodiments, after displaying the high-density blood vessel view, preset stroke views 52, 54, 56, and 58 can also be used. Clinicians can display one or more of the stroke views 52, 54, 56, and 58 by selecting from thumbnail views or by any suitable method. The most appropriate preset stroke view can be selected based on the location of the high-density blood vessels. In some embodiments, the display circuit 28 automatically selects the most appropriate preset stroke view based on predetermined rules. In some embodiments, the preset stroke view can be determined by the clinician.

[0131] exist Figure 6 and Figure 7 In the illustrated embodiment, display circuitry 28 selects the most appropriate scan and view for the selected reference. When occlusion is selected, and there is high-density vessel without persistent visual deviation, display circuitry 28 uses the alignment of the slice with the highest probability of containing circulation in the non-contrast scan for immediate evaluation of imaging features related to the occlusion. When occlusion is selected, and there is persistent visual deviation, display circuitry 28 displays a demonstration of the stroke view in CTA for immediate evaluation of vascular structure. In cases where neither high-density vessel nor persistent visual deviation is detected, an initial view of the NCCT scan is displayed. The initial view of the NCCT scan is, for example, the initial display of the NCCT scan when loaded onto the viewer. In other embodiments, any suitable one or more views may be displayed.

[0132] Different scans can be displayed for different baselines. Different scans can be displayed for different results. Display circuit 28 also selects the most appropriate view for each scan (e.g., stroke view).

[0133] Panel 62 provides an interactive display of information associated with thrombus removal or transfer criteria. In some embodiments, a summary view may be added to or alternatively provided to panel 62. Prompt messages may be determined and presented to the user in summary form. For example, the information may also be displayed as a report or other non-interactive view.

[0134] Figure 8 (a)~ Figure 8 (c) and Figure 9 (a)~ Figure 10 (c) A method of displaying the line of sight on the user interface to highlight persistent deviation across scans. By highlighting persistent deviation, users such as clinicians can quickly identify persistent deviation and rapidly assess whether a patient is a candidate for thrombectomy or transfer. According to Figure 8 (a)~ Figure 8 (c) and Figure 9 (a)~ Figure 10 (c) The eye's display can also be replaced with... Figures 4-7 Views 82 and 84 are shown.

[0135] Figure 8 (a)~ Figure 8 (c) A user interface in an implementation that uses shadows to highlight the viewing direction.

[0136] exist Figure 8 (a)~ Figure 8In the figures of (c), the gaze detection circuit 24 segments the eyeballs 112, 114 and lenses 116, 118 of each eye. The gaze detection circuit 24 can also use any suitable segmentation. The rendering circuit 26 renders the image with each segmented eyeball 112, 114 having an outer frame attached. The segmented lenses 116, 118 are each... Figure 8 (a)~ Figure 8 (c) The image is represented by graphic elements as whitewash elements.

[0137] Ocular deviation is represented by the shadows cast on the segmented eyeball. Figure 8 In (a), the patient's rightward eye deviation is represented by a shading containing a diagonal line aligned with the direction of the gaze. Figure 8 (b) does not use bias or shadows. Figure 8 In (c), the patient's leftward eye deviation is represented by a shading containing a diagonal line aligned with the direction of the line of sight.

[0138] In other embodiments, any suitable graphic element may be used to emphasize the eyeball and / or lens. Any suitable pattern or visual feature may also be used to highlight the direction of gaze. For example, an arrow may be used to indicate the direction of gaze.

[0139] In several embodiments, different colors are used to represent different scans, so that the color used to draw the eye varies across different scans at different times. When drawing the eye in the image derived from the scan at time 1, a first color can be used. When drawing the eye in the image derived from the scan at time 2, a second color can be used. When drawing the eye in the image derived from the scan at time 3, a third color can be used. Colors can also be combined with other visual effects, such as shadows.

[0140] Figure 9 (a)~ Figure 10 (c) User interface in an implementation that uses both shadows and colors to highlight the viewing direction. Figure 9 (a)~ Figure 10 (c) No color is shown; it is black and white.

[0141] A single image 120 is used to represent the patient's ocular region. Two or more scans obtained at various times (e.g., NCCT and CTA scans) are registered together so that they can be displayed on the same image.

[0142] The slider 130 displays time and is used to switch between views of two or more scans. The user moves the indicator 132 on the slider 130 to change the view displaying different time periods. Figure 9 (a)~ Figure 9 In embodiment (c), the scale of slider 130 represents the elapsed time since the first scan, represented by time = 0. In other embodiments, the scale of slider 130 may also represent the actual scan time.

[0143] Figure 9 (a) and Figure 9 (b) Indicates an example of persistent bias (DeyeCOM+ / +). Figure 9 In (a), the baseline scan is represented. As shown by slider 130, the baseline scan represents ocular deviation at time = 0. It is used for eye detection and lens segmentation, and is employed to highlight the patient's eye in the baseline scan. Figure 9 (a)~ Figure 9 In embodiment (c), an outer frame is added to each eyeball 122, 124, and an outer frame is added to each lens 126, 128. In other embodiments, any suitable method for highlighting the eyeballs and / or lenses may be used.

[0144] exist Figure 9 In (a), the direction of eye deviation in the baseline scan is indicated by red and white shading aligned with the line of sight (red in...). Figure 9 (Not visually discernible in (a)). A red plus sign is displayed at time = 0 on slider 130. Slider indicator 132 is at time = 0.

[0145] exist Figure 9 In (b), indicator 132 moves to the position of time = +2 minutes, and image 120 represents the second scan obtained 2 minutes after the baseline scan. Eye detection and segmentation in the second scan are registered to the baseline scan. In the second scan, the direction of eye deviation is indicated by green and white shading aligned with the line of sight (green in...). Figure 9 (b) Not visually identifiable. Additionally, a green plus sign is displayed at time = +2 minutes on slider 130. Outlines are added to the eyeballs 122, 124 and the lenses 125, 128.

[0146] exist Figure 9 (a) and Figure 9 In embodiment (b), if the indicator 132 of the slider 130 is moved between time 0 and +2 minutes, the color of the image 120 fades between red at 0 and green at +2 minutes. The displayed image may fade between the image represented at 0 and the image represented at +2 minutes.

[0147] Users can easily understand whether the gaze deviation is persistent. Users can move the indicator 132 back and forth on the slider 130 to switch between the baseline scan and the second scan. By using color, users can easily distinguish between the baseline scan and the second scan. The color can also gradually change over time. The slider 130 and the changing color provide a visual representation of gaze deviation in the baseline scan and the second scan.

[0148] In other embodiments, there is no gradation between images. In some embodiments, the image at 0 minutes can be superimposed on the image at +2 minutes. In still other embodiments, any suitable visual method can be used to combine or transform the image at 0 minutes with the image at +2 minutes.

[0149] In some situations, a baseline scan and a second scan may be performed consecutively, with a follow-up scan taken at a longer interval after the second scan. Follow-up scans may not be urgent, but may be used to confirm whether the acute illness has resolved.

[0150] Figure 9 (c) shows an example of a follow-up scan. The follow-up scan is registered together with the baseline scan. In image 120, the result of the follow-up scan is shown at the time the user slides the indicator 132 of slider 130 to the follow-up scan position. Figure 9 In (c), the follow-up scan time is +23 hours, which is 23 hours after the baseline scan. Slider 130 may also not be given as a linear scale. Instead, the scale of slider 130 can be selected in a way that easily distinguishes scan times of 0, +2 minutes, and +23 hours, all corresponding to the same scale.

[0151] exist Figure 9 (c) In the follow-up scan, no ocular deviation was observed. The eyes were stained blue (in...). Figure 9 (c) Not shown in blue). No shading is applied. The minus sign is displayed along with the time +23 hours on slider 130 (in...). Figure 9 (c) does not indicate blue).

[0152] By sliding the indicator 132 along the slider 130, the user can switch between two or more scans to confirm eye deviation across multiple moments. The image can also be gradually changed between different scans.

[0153] Figure 10 (a) and Figure 10 (b) Except for the absence of cases of persistent bias (DeyeCOM+ / -), the performance was similar to Figure 9 (a) and Figure 9 (b) Same display. Figure 10 (a) Represents the image 120 at time = 0. Figure 10 (a) For example, baseline scans such as NCCT scans, and Figure 9 (a) Same. The indicator 132 of the slider 130 is at time = 0. Eye deviation is indicated by the red and white shading of the eyeballs 122 and 124 (in...). Figure 10 (Not shown in red in (a)). The shadow is aligned with the direction of the gaze. A plus sign is used at time = 0 to indicate eye deviation.

[0154] exist Figure 10 In (b), image 120 shows a second scan, such as a CTA scan, at time = +2 minutes. The second scan was registered to Figure 10 (a) Baseline. The indicator 132 of the slider 130 is at time = +2 minutes.

[0155] exist Figure 10 In (b), there is no visual deviation. The eyeball is processed with varying shades of green, which represents the moment (in) Figure 10 (b) Green is not shown. A grayscale version representing the shadow on the eyeball. The grayscale shadow indicates to the user that there was previously a gaze deviation but it no longer exists. In other implementations, any suitable method can be used to visually represent the direction of the gaze or changes in the direction of the gaze.

[0156] A minus sign is displayed at the point where the time for slider 130 is +2 minutes.

[0157] If the user moves the indicator 132 of slider 130 between time = 0 and time = +2 minutes, a color gradient is applied between the shaded scans to indicate the change in viewing direction between the image shaded with red and white at time = 0 and the image shaded with green and gray at time = +2 minutes. On the user interface, a color gradient between the shaded scans can be applied to confirm the change in viewing direction.

[0158] Figure 10 (c) shows the results of the follow-up scan within image 120. The follow-up scan was registered to Figure 10 (a) Baseline. Follow-up scans were acquired at +23 hours. Visual deviation is not shown on the follow-up scans. Eyeballs were processed using blue light intensity (in... Figure 10 (c) is not shown in blue), and a blue minus sign is shown at the time of slider 130 = +23 hours.

[0159] exist Figure 9 (a)~ Figure 10 In embodiment (c), data is registered, the eye and lens are segmented, and colors that can be distinguished between scans are assigned. If the indicator 132 of the slider 130 moves between moments, the image 120 gradually transitions between images from different scans.

[0160] As Figure 9 (a)~ Figure 9 In example (c), a scan is performed using a specific time interval (0, +2 minutes, +23 hours), but in other implementations, a scan can be performed at any suitable time. Any suitable time interval and time range can also be displayed.

[0161] In several implementations, the geometry of the eye is shown to move, and thus morphing across scans. For example, the representation of the lens may shift from a first position in a baseline scan to a second position in a second scan. The representation of the lens may be shifted using a sequential approach so that the eye appears to rotate between the first and second positions.

[0162] In several embodiments, if a user performs a trigger action, the sequence of two or more scanned images automatically cycles between the scanned views. For example, the trigger action could be hovering over image 120 or hovering over slider 130. The two or more scanned images can automatically cycle back and forth. Automatic cycling may include gradations between images. Automatic cycling may include distortions between images. In several embodiments, the dynamic image of the gradation or distortion sequence can be automatically saved as a screenshot. The dynamic image can be saved to data storage unit 20 or any other suitable data storage unit. The dynamic image can be saved to a PACS.

[0163] exist Figure 9 (a)~ Figure 10 In embodiment (c), the segmented lens and the segmented eye are respectively outlined with solid lines in image 120. In other embodiments, the outlines of the lens and / or the eye can be visualized with different line types for each scan. For example, the lens and eye in the baseline scan can be outlined with solid lines, while the lens and eye in the second scan can be outlined with dashed lines.

[0164] Can be compared with reference Figure 2 and Figure 3 The same method described above, and the same method as the reference. Figures 4 to 10(c) The same interface described above is used for processing and displaying any suitable data. For example, any suitable one or more medical devices can be used to process data such as CT data, cone-beam CT data, X-ray data, ultrasound data, MR data, PET data, or SPECT data. Any suitable first and second scans can be used. The scan can be a scan of any suitable patient or other subject. The displayed images and data can be evaluated by any suitable user, such as any suitable clinician or researcher. In some embodiments, images or manifestations of the patient's eyes may be displayed instead of images or manifestations of the patient's single eye.

[0165] One embodiment provides a medical imaging apparatus. This medical imaging apparatus includes a method for prompting clinically relevant information for marking potential LVO / thrombus removal patients, at least a portion of which includes (persistent) visual deviation.

[0166] Alternatively, image parsing methods that also identify the associated parts of the organism's structure and display them to the user can be used to automatically detect this eye deviation.

[0167] Image analysis methods can also be used to automatically detect high-density blood vessels, and can also identify related parts of biological structures and display them to the user.

[0168] It can also automatically decide to optimize the CTA view so that people can identify congested areas and prompt the user.

[0169] It can also detect / display other clinically relevant information.

[0170] Alternatively, you can decide to present a summary to the user (such as a report or other non-interactive view).

[0171] This demo can be set up as a UI.

[0172] Notifications can also be sent to users (e.g., via smartphones, layouts, and summary information).

[0173] The tasks in the work list are assigned priority based on the automatically detected information.

[0174] You can also include direct LVO detection or other CADes in the display.

[0175] It can also display derivative measurements related to visual deviation or any other clinical information.

[0176] The data can also be registered, and the glasses and lens can be segmented and colored to distinguish each scan.

[0177] The user interface can be set to gradually change between colored scans so that the user is aware of changes in the direction of the view.

[0178] The geometry of the eye can also be deformed across scans to represent motion instead of grayscale transitions.

[0179] Alternatively, the sequence can automatically cycle back and forth as the user hovers over the view.

[0180] Dynamic images of gradient / deformation sequences can also be automatically saved to PACS as screenshots.

[0181] In the report, the lens and the outline of the eye from the two scans can also be visualized using different line types for each scan (e.g., one with solid lines and the other with dashed lines).

[0182] One embodiment provides an image display device (medical image display device) equipped with a processing circuit. The processing circuit is configured to receive medical image data containing at least a patient's eye, and control the display mode of the medical image data based on the viewing angle of the patient's eye.

[0183] The processing circuit can also be further configured to accept multiple medical image data scanned at at least two different times, and control the display method of the multiple medical image data based on the time of scan.

[0184] The processing circuit can also be further configured to accept multiple medical image data scanned at at least two different times, and control the display method of the multiple medical image data based on the interval between the times.

[0185] One embodiment provides a medical data processing apparatus equipped with processing circuitry. This processing circuitry is configured to receive first medical imaging data from a first scan representing a subject, automatically process the first medical imaging data to determine a first line of sight for the subject, receive second medical imaging data from a subsequent second scan representing the subject, automatically process the second medical imaging data to determine a second line of sight for the subject, and, using the first and second line of sight, determine whether the subject is a potential candidate for large vessel occlusion (LVO) or thrombus removal based on whether persistent eye deviation has occurred. If the subject is determined to be a potential candidate for LVO or thrombus removal, the user is notified that the subject is a potential candidate for LVO or thrombus removal.

[0186] The processing circuit may further be configured to display a first image of the eye region of the subject drawn based on the first medical imaging data, and / or a second image of the eye region of the subject drawn based on the second medical imaging data.

[0187] The processing circuit can also be further configured to process the first medical imaging data and / or the second medical imaging data in order to obtain at least one image feature, and can also determine whether the subject is a potential candidate for LVO or thrombus removal based on the at least one image feature.

[0188] The at least one image feature may also include at least one of the following: non-angiographic image features, high-density vessels, high-density arterial sign (HAS), and magnetically sensitive vessel sign (SVS).

[0189] The processing circuit may also be further configured to display at least one image representing an anatomical region containing the at least one image feature, the at least one image being drawn based on the first medical imaging data and / or the second medical imaging data.

[0190] The processing circuit can also be further configured to select and display at least one image for user evaluation, wherein the at least one image is selected so that a person can identify the blockage.

[0191] The at least one image used for evaluation may also contain multiple computed tomography angiography (CTA) views.

[0192] The at least one image used for evaluation may also contain multiple stroke views.

[0193] The processing circuit can also be further configured to display multiple benchmarks for LVO / thrombus removal to the user.

[0194] The processing circuit can also be further configured to automatically determine whether the subject meets at least some of the multiple criteria, and display to the user an indication of whether the subject meets each criterion.

[0195] The processing circuit can also be further configured to prioritize the workflow based on the determination of persistent visual deviation and / or based on other information obtained by processing the first medical imaging data and / or the second medical imaging data.

[0196] Sending the notification may also include sending it to mobile devices such as smartphones.

[0197] Alternatively, the first scan could be a non-contrast CT (NCCT) scan, and the second scan could be a contrast-enhanced CT scan. Alternatively, the first scan could be an NCCT scan, and the second scan could be an NCCT scan. Alternatively, the first scan could be an MRI scan, and the second scan could be an MRI scan. Alternatively, the first scan could be optical imaging processing, and the second scan could be a CT scan or an MRI scan. Alternatively, the first scan could be video imaging processing, and the second scan could be a CT scan or an MRI scan.

[0198] The processing circuit can also be further configured to automatically process the first medical imaging data and / or the second medical imaging data in order to detect LVO. It can also determine whether the subject is a potential candidate for LVO or thrombus removal based on the detection of LVO.

[0199] Specific circuits are described in this specification, but in alternative embodiments, one or more functions of these circuits can be provided by a single processing resource or other component, or the functions provided by a single circuit can be provided by combining two or more processing resources or other components. A reference to a single circuit includes multiple components that provide the functions of that circuit, without limitation on whether such components are separated from each other. A reference to multiple circuits includes a single component that provides the functions of those circuits.

[0200] According to at least one embodiment described above, the visual recognition of the direction of gaze in medical images can be improved.

[0201] The above description illustrates specific embodiments, but these embodiments are merely illustrative and are not intended to limit the scope of the invention. The novel embodiments described above can be implemented in various other ways, and various omissions, substitutions, and modifications can be made to the described embodiments without departing from the spirit of the invention. The appended claims and their equivalents are intended to cover these ways or modifications, all of which are included within the scope and spirit of the invention.

Claims

1. A medical image display device, wherein, have: The acquisition unit acquires two medical images, each containing at least one eyeball of the subject, obtained from two consecutive scans, one non-contrast scan and one angiography scan. The gaze detection unit detects the gaze direction of the eyeballs contained in the two medical images respectively; as well as The display control unit, based on the gaze directions of the two eyeballs detected from the two medical images respectively, determines the display mode of the medical image related to the subject from at least one of the two consecutive scans, and displays the medical image related to the subject on the display unit in the determined display mode. The gaze detection unit determines whether there is a leftward or rightward deviation in the eye's gaze direction based on the two medical images. If the determined gaze deviation is consistent across the two medical images, it is determined that the eye's gaze direction has a persistent deviation. If the system determines that there is a persistent deviation in the direction of the eye's gaze, the display control unit determines the display mode as a first display mode, in which the medical image based on the angiography scan is displayed as the main image. If it is determined that there is no persistent deviation in the direction of the eye's gaze, the display control unit determines the display mode as the second display mode, in which the medical image based on the non-contrast scan is displayed as the main image.

2. The medical image display device as described in claim 1, wherein, The display control unit determines the display mode of the medical images related to the subject based on the time at which one of the two medical images is obtained or the interval between the times when the two medical images are obtained.

3. The medical image display device as described in claim 1, wherein, It also has: The feature detection unit detects at least one imaging feature contained in the medical image obtained in the non-contrast scan. The display control unit also determines the display mode of the medical image related to the subject based on the detected at least one imaging feature.

4. The medical image display device as described in claim 3, wherein, The at least one imaging feature includes at least one of high-density vascular sign, high-density arterial sign, and magnetically sensitive vascular sign.

5. The medical image display device as described in claim 3, wherein, The feature detection unit detects at least one imaging feature based on the medical image obtained in the non-contrast scan.

6. The medical image display device as claimed in claim 3, wherein, The display control unit determines the display method of medical images related to the subject that are displayed on the anatomical region where the at least one imaging feature has been detected.

7. The medical image display device as described in claim 3, wherein, It also has: The notification unit issues a notification to an external device in accordance with the eye's line of sight or the detected at least one imaging feature.

8. The medical image display device as claimed in claim 1, wherein, It also has: The notification department detects blockages in large blood vessels based on the medical images obtained in the non-contrast scan.

9. The medical image display device as claimed in claim 1, wherein, It also has: The image processing unit, based on the medical image obtained in the non-contrast scan, draws an image representing the region containing the eyeball. The display control unit displays an image representing the area containing the eyeball on the display unit.

10. The medical image display device as claimed in claim 1, wherein, The gaze detection unit segments the region of at least one eyeball contained in each of the two medical images. The display control unit displays an image showing the segmented eyeball of at least one of the eyes on the display unit.

11. The medical image display device as claimed in claim 10, wherein, The display control unit performs at least one of the following: Displaying the lens of at least one of the segmented eyeballs; and The direction of the gaze of at least one of the segmented eyeballs is highlighted.

12. The medical image display device as claimed in claim 9, wherein, The image processing unit draws an image representing the region containing the eyeball based on each of the two medical images. The display control unit uses different visual effects to display the area containing the eyeball at each of the two different times when the two medical images are obtained.

13. The medical image display device as claimed in claim 12, wherein, The display control unit performs at least one of the following: Different colors are used on the segmented eyeballs at the two different times to achieve different visual effects; At the two different times, different lines are used to add outer frames to the segmented eyeballs to achieve different visual effects. as well as In response to user input, a gradient is applied between the different visual effects at the two different times.

14. The medical image display device as claimed in claim 9, wherein, The image processing unit draws an image representing the region containing the eyeball based on each of the two medical images obtained at two different times. The display control unit performs at least one of the following: The display of the deformation of the geometry of the eyeball of at least one of the subjects between the two different times is determined as a way of displaying medical images related to the subject. In response to user input, a method is determined to display images representing the eyeballs of at least one eye in a cyclical manner between the two different times, as a display mode of medical images related to the subject; and A dynamic image of the image representing the eyeball of at least one of the two different moments is drawn and output.

15. A method for displaying medical images, wherein, Includes the following steps: Two medical images of at least one eyeball of the subject are obtained from two consecutive scans, one non-contrast scan and one angiography scan. The direction of the eye's gaze is detected in the two medical images respectively; and Based on the gaze directions of the two eyeballs detected from the two medical images, a display method is determined for the medical image related to the subject from at least one of the two consecutive scans. The medical image related to the subject is then displayed on the display unit in the determined display method. The steps for detecting the direction of the line of sight include the following: For each of the two medical images, it is determined whether the eye's gaze direction is deviated to the left or right. If the determined gaze deviation is consistent across the two medical images, it is determined that the eye's gaze direction has a persistent deviation. The step of displaying medical images related to the subject on the display unit includes the following steps: If it is determined that there is a persistent deviation in the direction of the eye's gaze, the display mode is determined to be the first display mode, in which the medical image based on the angiography scan is displayed as the main image. If it is determined that there is no persistent deviation in the direction of the eye's gaze, the display mode is determined to be the second display mode, in which the medical image based on the non-contrast scan is displayed as the main image.

16. A computer-readable non-volatile storage medium with a stored program, wherein, This program is used to make the computer perform the following processes: Two medical images of at least one eyeball of the subject are obtained from two consecutive scans, one non-contrast scan and one angiography scan. The direction of the eye's gaze is detected in the two medical images respectively; and Based on the gaze directions of the two eyeballs detected from the two medical images, a display method is determined for the medical image related to the subject from at least one of the two consecutive scans. The medical image related to the subject is then displayed on the display unit in the determined display method. The process of detecting the direction of the gaze includes the following steps: For each of the two medical images, it is determined whether the eye's gaze direction is deviated to the left or right. If the determined gaze deviation is consistent across the two medical images, it is determined that the eye's gaze direction has a persistent deviation. The process of displaying medical images related to the subject on the display unit includes the following processes: If it is determined that there is a persistent deviation in the direction of the eye's gaze, the display mode is determined to be the first display mode, in which the medical image based on the angiography scan is displayed as the main image. If it is determined that there is no persistent deviation in the direction of the eye's gaze, the display mode is determined to be the second display mode, in which the medical image based on the non-contrast scan is displayed as the main image.

Images