Medical imaging device and method of operation thereof

Abstract

The present application proposes an improved medical imaging device that enables timely communication of critical findings. The medical imaging device comprises an image acquisition unit adapted to acquire image data of a subject to be imaged. The medical imaging device further comprises a local data processing device having an artificial intelligence module (AI module) configured to automatically detect findings based on the acquired image data and determine a priority status of the detected findings. Furthermore, the medical imaging device comprises a notification module adapted to provide notification data including the detected findings when the determined priority status reaches or exceeds a notification threshold. The present application further proposes a medical imaging system, a method for operating the medical imaging device, a computer program element, and a computer-readable medium having the computer program element stored thereon.

Description

[Technical Field]

[0001] The present invention relates to medical imaging, and in particular to a medical imaging device, a method for operating a medical imaging device, a computer program element, and a computer readable medium. [Background technology]

[0002] In medical imaging, in particular, timely communication of critical findings in the subject being examined may be desirable. Timely communication of such findings may also be mandated by institutional, legal, or other requirements. For example, there may be different categories of notable or actionable findings that require recognition and / or communication within minutes, hours, or days. The minute-to-minute category, in particular, may require immediate action or at least immediate communication to avoid deterioration or death. Summary of the Invention [Problem to be solved by the invention]

[0003] Additionally, in medical imaging, the time lapse between image acquisition and its evaluation by a radiologist, physician, etc. can affect the overall time to treatment. Typically, radiologists, physicians, etc. work sequentially through a reading list or are guided by a manual prioritization process. This process can cause unnecessary delays in capturing findings, especially in the case of unexpected findings.

[0004] US Patent Application Publication No. 2008 / 0091473A1 describes a notification system for a medical imaging device, in which notifications are sent to indicate the progress or completion of an image process.

[0005] WO 2017 / 136762 discloses a system for processing medical diagnostic images for review by, for example, a physician or radiologist.

[0006] US Patent Application Publication No. 2014 / 358585 discloses an apparatus for performing communication of medically critical results.

[0007] US Patent Application Publication No. 2009 / 028403 discloses a system for analyzing source medical images of body organs.

[0008] US Patent Application Publication No. 2009 / 196479 discloses a system for prioritizing medical imaging scans.

[0009] US Patent Application Publication No. 2016 / 350919 discloses a system for processing electronic imaging data obtained from a medical imaging procedure.

[0010] Therefore, there may be a need to improve medical imaging with respect to time loss.The object of the present invention is solved by the subject matter of the attached independent claims, further embodiments of which are incorporated in the dependent claims, the attached drawings and the following description. [Means for solving the problem]

[0011] According to a first aspect, there is provided a medical imaging apparatus comprising: an image acquisition unit adapted to acquire image data of a subject to be imaged; a local data processing device having an artificial intelligence module (AI module) adapted to automatically detect findings based on the acquired image data and to determine a priority status of the detected findings; and a notification module adapted to provide notification data comprising at least the detected findings when the determined priority status reaches or exceeds a notification threshold.

[0012] The image acquisition unit may be adapted to acquire images of a region of interest of the subject to be imaged, and in particular may be adapted to use imaging techniques such as X-ray radiography, magnetic resonance CT, computer tomography, ultrasound, etc. The image acquisition unit may therefore interact with or comprise one or more of a processing unit, a data and / or image storage device, etc.

[0013] The local data processing device may be a suitable computing device comprising one or more of a processing unit, data and / or image storage, etc. The local data processing device may also be realized "on-system", i.e. in spatial proximity to the image acquisition unit, e.g., in a radiology department, without a remote data connection.

[0014] The AI ​​module may be realized by program instructions utilizing machine learning techniques, particularly deep learning techniques, that can be trained for that purpose. Furthermore, it may be adapted for image classification, which may enable automatic identification of one or more findings in image data. The findings may be medical, clinical, diagnostic, and / or anatomical findings. More specifically, the deep learning technique employed may be a convolutional neural network (CNN) consisting of one or more layers, e.g., convolutional layers, batch normalization layers, dense layers, etc., which may be optimized to process image data using techniques such as backpropagation. Furthermore, according to some embodiments, the AI ​​module may be adapted to classify the content of the image and automatically detect findings based on the classification. Optionally, the AI ​​module may be adapted to determine whether further examinations and / or treatments may be appropriate, which are added to the notification data. In particular, automatic detection of findings, particularly medical findings, may be achieved using the AI ​​module. Thus, the AI ​​module may have at least an input layer and an output layer. The AI ​​module receives image data through an input layer and can output findings and / or priority status of findings through an output layer. The AI ​​module processes the image data from the input layer to the findings and priority status on the output layer, and is oriented toward a multi-label classification problem. The image contained in the image data can be expressed as: The image in TIFF0007776986000001.tif744 is the ground truth label. TIFF0007776986000002.tif86, where the classification function, TIFF0007776986000003.tif820 is applied, which is for N training sample-label pairs, We use TIFF0007776986000004.tif631 to reduce a specific loss function l. The labels can be encoded as the following non-normal vectors for each image in the image data: TIFF0007776986000005.tif729 (M labels)

[0015] Furthermore, "no finding" can be encoded as an explicit additional label, thus having M=15 labels. Furthermore, after an initial calibration and exploration of the weighted loss function, e.g., positive / negative balancing can be performed. Furthermore, the class-averaged binary cross-entropy can be realized as follows: TIFF0007776986000006.tif17150

[0016] Furthermore, ResNet-50 and DenseNet-121 architectures can be implemented. AI modules can be trained, and thus weight initialization strategies can be implemented. This can be achieved with the help of random values, and thus AI modules can be trained from scratch. Furthermore, AI modules can be started from predefined values ​​from other AI modules. Furthermore, transfer learning approaches can be implemented with the help of off-the-shelf (OTS) and fine-tuning (FT).

[0017] Additionally, "Comparison of deep learning approaches for multi-label chest x-ray classification," January 29, 2019 by Baltruschat el al., is incorporated herein by reference.

[0018] The determination of the priority status is based on the findings, particularly medical findings, detected by the AI ​​module. The priority status can be determined based on the kind and / or type of the detected finding. The AI ​​module can detect findings that may be pneumothorax, for example. Furthermore, the local data processing device and / or the AI ​​module can determine the priority status by using a lookup table. The lookup table can have a result type on the input side and a priority indicator on the output side specifying whether a notification should be issued. For example, a pneumothorax finding is input to the input side of the lookup table, and a priority indicator indicating that a notification should be issued is output. Such a lookup table can be, for example, the American College of Radiology (ACR) Appropriateness Criteria.

[0019] As used herein, the term "priority status" can generally be understood as a distinction between whether a finding is critical and therefore must be treated, for example, within a very short time, and whether the finding does not need to be prioritized. Furthermore, the "priority status" indicates the urgency of processing the identified finding. For example, the priority status can have a higher value corresponding to a critical finding and therefore should have a high priority, or a lower value corresponding to a less critical finding and therefore should not have a high priority. Examples of critical findings can include at least symptoms such as pneumothorax, arterial dissection, etc. By way of example, a high priority status can refer to a flag or special identification as a serious finding. In other words, the AI ​​module can be adapted for automatic prioritization based on processing of acquired image data.

[0020] The notification module may be implemented by program instructions, electronic components, or a combination thereof. It may be implemented within a data processing device that also has an AI module. Alternatively, the notification module may be implemented in another data processing device, etc. In some embodiments, the notification module may include a communication data interface that enables a data connection via a data network, a telecommunications network, e.g., a cellular or mobile network, a wireless network, etc. In general, the notification module may be adapted to send and / or receive text messages, which may be provided as push messages, combined text-image messages, etc. For example, the notification may include a text-based description of a result that may be obtained from the AI ​​module. The notification may relate to or include a medical condition, a medical situation, and / or indicate a medical finding. The notification may be encrypted for data security.

[0021] In this description, the term "notification threshold" can relate to the pre-selection of critical findings, some of which may require generating a notification, while others may not, and the notification threshold allows these to be distinguished. Critical findings can be included in a list, flagged, etc.

[0022] An advantage of this medical device is that untimely and / or erroneously communicated findings, especially of critical and / or time-sensitive findings, can be overcome. More specifically, actionable findings can be detected directly during the image acquisition process, not just after presentation to a workstation or the like. Furthermore, automatic detection and prioritization of findings can enable timely notification of at least one potential finding to a radiologist, physician, or the like, for example, within minutes. At the time of notification, the subject may not yet have left the diagnostic location in the best case, thereby saving additional time for re-ordering the subject. Any additional tests that may be recommended due to the findings can then be performed promptly.

[0023] In one embodiment, the notification module is adapted to provide notification data to a local display of the device.

[0024] The local display device can be, for example, a display on a system operator console that is operated and / or monitored by a technician during imaging.

[0025] Thus, at least the technician can inform the radiologist. According to one embodiment, the notification module is adapted to provide notification data to the first remote terminal.

[0026] The remote terminal may be a remote but fixed device, such as a personal computer, or may be a portable device, such as a mobile phone, tablet computer, pager, etc. The remote terminal may be adapted to receive the notification data transmitted by the notification module via remote data transmission using an appropriate communication protocol. Furthermore, the remote terminal may be adapted to employ different notification or messaging technologies using different communication paths, such as push-up notification, email, short message service (SMS), etc.

[0027] Thus, radiologists or physicians can be proactively notified of the existence of critical findings without having to monitor a worklist, system operator console, etc. For example, physicians can be notified even if they are attending a staff meeting or on a break.

[0028] In one embodiment, the notification module is adapted to request an acknowledgement of receipt and / or a read confirmation for the notification data from the first remote terminal.

[0029] The data connection may be at least temporarily bidirectional. Read confirmation may be implemented in or provided by the messaging technology used for notification.

[0030] This may therefore allow for further follow-up action, particularly if the notification cannot be delivered to the intended recipient, for example the notification may be escalated to another recipient.

[0031] According to one embodiment, the notification module can be adapted to, if the read confirmation is not received within a specific period of time, again notify the first remote terminal via a second communication path different from the first communication path through which the read confirmation is not received within the specific period of time. The specific period of time can depend, for example, on the detected findings, the notification threshold, etc. Thus, a period of time can be minutes, hours, etc. In this description, the term "communication path" can refer to a specific communication technology such as email, SMS, etc.

[0032] Thus, a second attempt can be made to notify the intended recipient before the notification is escalated and an alternate recipient is called.

[0033] In one embodiment, if the read confirmation is not received within a certain period of time, the notification module is adapted to provide a notification to the second remote terminal.

[0034] In this way, the notification is escalated to another recipient so that as little time as possible is lost communicating the detected finding. According to one embodiment, the notification to at least the first remote terminal is logged in a log data record.

[0035] This can be useful primarily for documentation purposes, but can also be useful for quality assurance.

[0036] According to one embodiment, the AI ​​module is adapted to determine the spatial location of the finding within the imaged subject, and the determined spatial location is added to the notification data.

[0037] The AI ​​module can be configured to identify, classify, reassess, and / or determine one or more anatomical reference points, such as short lips, within the image data. Furthermore, the AI ​​module can be configured to calculate a distance related to a vector between the finding and the anatomical reference point, thereby determining the location of the finding within the subject. In one example, the AI ​​module can identify a short lip as a reference point. Furthermore, the finding can be set relative to the reference point, and a spatial location within the subject can be calculated. The spatial location can include a text base, etc.

[0038] Thus, the radiologist or physician can be informed of more advanced information, which facilitates the confirmation of the automatic detection performed by the AI ​​module.

[0039] In one embodiment, the AI ​​module is adapted to determine at least one image of the image data representing at least a portion and / or a partial view of the finding, and the determined image is at least partially added to the notification data.

[0040] Thus, the notification can be a combination of a text message and a picture message.

[0041] Thus, the radiologist or physician can be informed of more advanced information, which further facilitates timely confirmation of the automatic detections performed by the AI ​​module.

[0042] According to one embodiment, the AI ​​module may be adapted to determine a likelihood of detection indicating the likelihood that the detected finding has been correctly identified, and the determined likelihood of detection is added to the notification data.

[0043] The likelihood of detection can be determined by a machine learning algorithm, for example. For intuitive perception, the likelihood of detection can be displayed as a percentage, for example. The AI ​​module can be configured to identify findings in the image data. In other words, the AI ​​module can identify abnormalities in the image data and then calculate the likelihood of each type of abnormality, resulting in a finding. For example, the AI ​​module can identify abnormalities in the image data, for example, by classification, and calculate an 80% likelihood that the abnormality is a pneumothorax and a 20% likelihood that the abnormality is an arterial dissection. The AI ​​module can interpret the likelihood and describe the abnormality as a pneumothorax, resulting in a finding. The notification, in this example, indicates a finding of pneumothorax and its likelihood of 80%. Thus, the radiologist or physician can be notified of more advanced information. This further facilitates timely confirmation of the automatic detection performed by the AI ​​module.

[0044] In one embodiment, the AI ​​module can be adapted to perform the detection of findings and / or provide notification data solely via local data processing. Due to the direct data processing and elimination of other data processing instances, notifications can be provided within a particularly short period of time.

[0045] According to a second aspect, there is provided a medical imaging system comprising a medical imaging device according to the first aspect and a receiving device configured to receive notification data transmitted by the medical imaging device.

[0046] A receiving device may be, for example, a system operator console of a medical imaging device. Alternatively or additionally, if more than one receiving device is notified, the receiving device may be a remote terminal, for example, a remote, fixed or portable device.

[0047] In one embodiment, other remote clinical systems may be connected to the image acquisition unit of the medical imaging device, and the medical imaging system may be adapted to perform pre-processing of the images by local data processing means and to provide notification data to the received data before performing main processing of the image data by the clinical image archiving and communication system.

[0048] Other clinical systems can be picture archiving and communication systems (PACS), EMRs, etc., using communication standards such as DICOM or HL-7. By using direct data processing and eliminating other data processing instances, notifications can be provided within particularly short time periods.

[0049] According to a third aspect, there is provided a method of operating a medical imaging device, which method can be particularly performed using the medical imaging device according to the first aspect, comprising the steps of acquiring image data of a subject to be imaged by the imaging device, processing the acquired image data by an imaging device-side artificial intelligence module (AI module) of a local data processing device to automatically detect findings in the subject, determining a priority status of the findings detected by the AI ​​module, and providing a notification including at least the findings to the notification module if the determined priority status reaches or exceeds a notification threshold.

[0050] According to a fourth aspect, there is provided a computer program element for operating a medical imaging apparatus adapted to perform the method according to the third aspect when executed by a processing unit.

[0051] According to a fifth aspect, there is provided a computer readable medium having stored thereon a computer program element according to the fourth aspect.

[0052] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0053] Exemplary embodiments of the exemplary invention will now be described with reference to the accompanying drawings. [Brief explanation of the drawings]

[0054] [Figure 1] 1 is a diagram illustrating an embodiment of a medical imaging device in a side view. [Figure 2] FIG. 1 illustrates a block diagram of an exemplary operation of a medical imaging device. [Figure 3] FIG. 10 is a block diagram of another exemplary operation of a medical imaging device. [Figure 4] 1 is a flowchart of a method for imaging an object with an X-ray imaging system. DETAILED DESCRIPTION OF THE INVENTION

[0055] The drawings are merely schematic representations and serve only to illustrate embodiments of the invention, and identical or equivalent components are in principle provided with the same reference signs.

[0056] 1 illustrates a schematic diagram of a medical imaging apparatus 100, which in this embodiment is a computed tomography imaging scanner. The X-ray imaging system 100 comprises a stationary housing 110 and a gantry 120, which in this embodiment is rotatable through an angular range of approximately 360° around a subject support 130, which in this embodiment is a support table. In this embodiment, an imaging subject 140, e.g., a human patient, is placed on top of the subject support 130. The medical imaging apparatus 100 further comprises an image acquisition unit 150, which in this embodiment is configured to emit an X-ray radiation beam towards the subject 140 to be imaged, and which has a radiation source 160 configured to generate a radiation beam that is specifically directed towards an examination region. The radiation beam interacts with a region of interest of the subject 140, which is arranged within the examination region, and spatially varying absorption of the radiation is generated as the radiation passes through the examination region.

[0057] The medical imaging apparatus 100 in this embodiment further comprises an X-ray detector 170 configured to detect X-rays that have passed through the subject 140, in particular, an X-ray detector 170 configured to detect absorbed and attenuated radiation after passing through the examination region. In this embodiment, the radiation source 160 and the X-ray detector 170 are mounted on the gantry 120 and positioned opposite each other, so that the X-ray detector 170 continuously receives X-rays from the radiation source 160. The X-ray detector 170 may comprise a two-dimensional array of detector elements, although other embodiments may be contemplated.

[0058] The medical image 100 further comprises one or more computing means, and in this embodiment, the local data processing device 180 will be mainly described. In some embodiments, the data processing device 180 is connected to at least the X-ray detector 170 and / or the radiation source 160 to control them and / or acquire data at least therefrom, in particular from the X-ray detector 170. The data processing device 180 may also be formed by several subsystems, functional modules or units, software modules or units, etc. (not described in further detail here) and is configured to reconstruct an image of the object 140 based on the X-rays detected by the X-ray detector 170, in particular based on a plurality of acquired projection images of the object 140. In this embodiment, the data processing device 180 comprises at least one processor 181, at least one memory 182 for storing image data, and at least one memory 183 for storing one or more program elements.

[0059] The data processing device 180 further comprises an artificial intelligence module, AI module, which for better illustration is indicated by the reference numeral 184. The AI ​​module 184 has a data connection to the processor 181 and / or the X-ray detector 170 and receives image data already processed by the processor 181 or raw image data directly provided by the X-ray detector 170. The AI ​​module 184 further comprises one or more artificial neural networks, which may use one or more layers, e.g., convolutional layers, batch normalization layers, dense layers, backpropagation, etc., and may in particular be provided as convolutional neural networks (CNNs) adapted to process image data. Furthermore, according to some embodiments, the AI ​​module 184 may alternatively or additionally comprise deep learning algorithms and / or classification means, such as suitable classifiers. The CNNs, classifiers, etc. may be pre-trained with suitable training datasets. Furthermore, such training is performed during ongoing operation to further improve the detection results. The image data is provided to the AI ​​module 184 as input variables. Based on this, the AI ​​module 184 is adapted to automatically detect findings based on the acquired image data and determine a priority status of the detected findings. Furthermore, the AI ​​module 184 is adapted to determine a spatial location of the findings within the subject 140. The AI ​​module 184 is also adapted to determine at least one image of the image data representing at least a partial view of the findings. The AI ​​module 184 is further adapted to determine a likelihood of detection indicating the likelihood that the detected finding was correctly identified. The likelihood may be expressed as a percentage or another suitable unit of measurement.

[0060] 1 , the medical imaging device 100 further comprises a notification module 190 connected to the AI ​​module 184. The notification module 190 can be implemented in the data processing device 180 or may be implemented in another data processing device. In this embodiment, the notification module 190 comprises a communication data interface 191 configured to enable a data connection via a data network, a telecommunications network, e.g., a cellular or mobile network, a wireless network, etc. Furthermore, the notification module 190 is configured to send and / or receive text messages, combined text-image messages, etc., which may also be provided as push messages. Notification messages sent by the notification module 190 may be encrypted for data security.

[0061] As shown in FIG. 1 , the notification module 190 is configured to send the notification to a system operator console 192 of the medical imaging device 100, which is operated by a technician, medical support staff, etc. Alternatively or additionally, the notification module 190 is adapted to send the notification to a remote terminal 193, which in this embodiment is a mobile terminal such as a mobile phone. In particular, the terminal 193 can be carried by a radiologist, a doctor, etc. In this embodiment, the medical imaging device 100 is connected to a further remote clinical system 200, which in this embodiment is a Picture Archiving and Communication System (PACS), an EMR, etc., using a communication standard such as DICOM or HL-7. It is noted that the AI ​​module 184 is in particular adapted to perform pre-processing of the image data before providing the image data to the clinical system 200, where subsequent main processing of the image data is performed.

[0062] FIG. 2 shows a schematic block diagram of an exemplary notification operation of the medical imaging device 100, which notifies one or more of a system operator console 192 and a terminal 193 via a communication data interface 191. By way of example, a notification message from the notification module 190 includes one or more data fields, which in this embodiment are indicated by reference numerals 190A, 190B, and 190C, along with corresponding better-illustrated display fields. The display field 190A may include notification text such as "notification: Actionable Finding Detected for Patient ##; Pneumothorax in right lung (98%)." Thus, the notification may include text indicating the detected finding, the subject's 140 identification data, and the determined likelihood. It should be noted that the notification may also include additional data about the subject 140, such as age, gender, known clinical findings, etc. These data may be obtained by the AI ​​module 184, the patient information system, the clinical system 200, etc. Display field 190B can display one of the acquired images of subject 140, in particular the image of the finding. Display field 190C can display an enlarged view of the image of the finding. For example, suitable images, in particular meaningful images, to be sent with the notification are selected by AI module 184. These notification data are provided to notification module 190, which transmits the same to terminal 193 and / or operator console 192.

[0063] FIG. 3 shows a schematic block diagram of the generation and transmission of notifications to be sent by the notification module 190. As described above, acquired image data from the X-ray detector 170 and / or data processing device 180 is provided to the AI ​​module 184, which performs automatic processing of the image data with the aim of automatically detecting possible abnormalities and determining possible findings. The AI ​​module 184 determines whether the priority status of a finding reaches or exceeds a notification threshold, i.e., whether the finding is critical enough to trigger a notification action. If the AI ​​module 184 determines that a detected finding is critical or actionable and / or if the likelihood of detection is too low, the AI ​​module 184 generates some data content for the notification message to be sent. For example, the AI ​​module 184 generates a name for the finding, such as pneumothorax, the likelihood of detection, the spatial location of the finding, etc. In some embodiments, an appropriate picture representation of the finding is also determined and / or generated. The data content generated by the AI ​​module 184 is then provided to the notification module 190. In some embodiments, notification module 190 is adapted to use different notification or messaging technologies using different communication paths, such as push-up notification, email, or short message service (SMS). In this embodiment, notifications are sent to system operating console 192 and / or terminal 193. In some embodiments, notification module 190 requests an acknowledgment and / or read confirmation of receipt of notification data from remote terminal 193, as indicated by the double arrow in FIG. 3 . Thus, the data connection between system operating system console 192 and / or terminal 193 and notification module 190 is at least temporarily bidirectional. The read confirmation may be implemented in or provided by the messaging technology used for the notification. If a notification cannot be delivered to the intended recipient, the notification is escalated to another recipient, i.e., another terminal 193 (not shown).If the read confirmation is not received by the notification module 190 within a certain time, the terminal 193 again notifies the user via a second communication path, e.g., SMS, different from the first communication path, e.g., email, that the read confirmation was not received within the certain time. The specific time period may depend on the priority status of the detected finding, the notification threshold reached or exceeded, etc. Thus, the time period may be minutes, hours, etc. As shown in FIG. 3, the notification module 190 records the notification process in a data record 194.

[0064] 6 shows a flowchart of a method of operating the medical imaging device 100 and / or medical imaging system. In step S1, image data of the subject 140 is acquired, for example, by using the radiation source 160 and the X-ray detector 170.

[0065] In step S2, the AI ​​module 184 processes the acquired image data to automatically detect findings within the subject 140.

[0066] In step S3, the AI ​​module 184 determines the priority status of the detected findings.

[0067] In step S4, the AI ​​module 184 provides a notification including at least the naming of the finding to the notification module 190 if the determined priority status meets or exceeds a notification threshold.

[0068] In optional step S5, the notification module 190 sends the notification as a notification message to one or more of the system operator console 192 and the remote terminal 193.

[0069] In another exemplary embodiment of the invention, a computer program or a computer program element is provided, characterized in that it is adapted to perform, on a suitable system, the method steps of the method according to one of the previous embodiments.

[0070] Thus, the computer program element can be stored in a computer unit which can be part of an embodiment of the present invention. This computing unit can be adapted to execute or direct the execution of the steps of the above-mentioned method. Furthermore, the computing unit can be adapted to operate each component of the above-mentioned device. The computing unit can be adapted to operate automatically and / or to execute a user's order. The computer program can be loaded into the working memory of a data processor. The data processor can thus be equipped to execute the method of the present invention.

[0071] This exemplary embodiment of the present invention encompasses both computer programs that use the present invention from the beginning and computer programs that convert existing programs by modern means into programs that use the present invention.

[0072] Furthermore, the computer program element may provide all the steps necessary to carry out the procedures of the exemplary embodiments of the procedures described above.

[0073] According to a further exemplary embodiment of the present invention, a computer-readable medium, such as a CD-ROM, is presented, the computer-readable medium having stored thereon a computer program element, the computer program element being as described in the preceding section.

[0074] The computer program can be stored and / or distributed on a suitable medium (in particular, but not necessarily, a non-transitory medium), such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. However, the computer program can also be presented over a network such as the Internet and downloaded from such a network into the working memory of a data processor. According to a further exemplary embodiment of the invention, a medium is provided for making available a computer program element for downloading, the computer program element being configured to perform a method according to one of the aforementioned embodiments of the invention.

[0075] It should be noted that the embodiments of the present invention are described with reference to different subject matters. In particular, some embodiments are described with reference to method-type claims, and other embodiments are described with reference to apparatus-type claims. However, those skilled in the art will understand from the above and below description that, unless otherwise specified, any combination of features belonging to one type of subject matter, as well as any combination between features relating to different subject matters, is disclosed in the present application. However, all features can be combined to provide a synergistic effect greater than the simple sum of the features.

[0076] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered exemplary or explanatory and not restrictive. The invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the dependent claims.

[0077] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be interpreted as limiting their scope. [Explanation of symbols]

[0078] 100 Medical imaging equipment 110 Housing 120 Gantry 130 Subject Support 140 Imaging Target 150 Image Acquisition Unit 160 Radiation Source 170 X-ray detectors 180 Data Processing Means 181 processors 182 memory 183 memory 184 Artificial Intelligence Module 190 Notification Module 191 Communication Data Surface 192 System Operator Console 193 Remote Terminal 194 data records 200 Future Clinical Systems

Claims

[Claim 1] 1. A medical imaging device, comprising: a medical image acquisition unit for acquiring medical image data of a subject to be imaged; a local data processing device having an artificial intelligence (AI) module, the AI ​​module automatically detecting medical findings based on processing the acquired medical image data by classifying a content of the medical image data, the medical findings being indicated by abnormalities identified during the classification, and determining a priority status indicating an urgency of treatment for the detected medical findings; a notification module that provides notification data including the detected medical finding when the determined priority status meets or exceeds a notification threshold; and the AI ​​module is adapted to determine a likelihood of detection indicating a likelihood that the detected medical finding has been correctly identified; the determined likelihood of detection is added to the notification data. a medical imaging device; a receiving device for receiving notification data transmitted by the medical imaging device; 1. A medical imaging system comprising: and a separate remote clinical system connected to a medical image acquisition unit of the medical imaging device, the medical imaging system using the medical imaging device to perform pre-processing of the medical image data by the local data processing device, and providing the notification data to the receiving device before performing main processing of the medical image data by the remote clinical system. Medical imaging systems.

Images