Method and system for remote analysis of medical image records - Patents.com

Abstract

1. A method for remote analysis of one or more medical image records, comprising: receiving, at a first user workstation, a first medical image record; comparing the first medical image record with a standard image set to identify a similarity between the first medical image record and the standard image set; if the similarity exceeds a threshold, calculating a difference between the first medical image record and the standard image set by comparing the first medical image record with the standard image set; transferring the difference from the first user workstation to one or more computing devices; and reconstructing the first medical image record by combining the difference with the standard image set with a copy of the standard image set; and analyzing the first medical image record.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Patent Application No. 16 / 686,571, filed November 18, 2019, the contents of which are incorporated herein by reference in their entirety. The disclosed subject matter is directed to systems and methods for remote analysis of digital records, such as medical image records, in which portions of the medical image records can be transferred to a cloud-based artificial intelligence (AI) medical diagnostic engine for analysis. [Background technology]

[0002] Utilizing AI for medical diagnosis is becoming more common and important. An AI medical diagnosis engine (also referred to herein as an "AI engine") can receive one or more medical images and process them to perform a diagnosis. Images can be stored in a variety of formats, but a common format for image storage is Digital Imaging and Communications in Medicine (DICOM). DICOM is a standard that, among other things, can communicate medical images and associated metadata from imaging modalities (e.g., X-ray (or its digital counterparts: computed radiography (CR) and digital radiography (DR)), computed tomography (CT), and magnetic resonance imaging (MRI) machines) to at least one of a client device and remote storage.

[0003] AI engines can typically train themselves using large amounts of data and can operate faster than typical diagnostic applications. AI engines can continue to improve and refine after their first use. If the AI ​​engines were stored on individual computers (i.e., locally), each time the AI ​​engine is improved, the AI ​​engine would need to be upgraded on each computer that runs the AI ​​engine at each location. It is therefore beneficial to deploy the AI ​​engine on the cloud (i.e., remotely from each individual workstation), where it can be accessed by multiple users at different locations and more easily upgraded.

[0004] However, implementing an AI engine on the cloud can lead to several issues. First, the size of medical images that need to be uploaded to the cloud for review by the AI ​​engine can be large. This can take a lot of time, which can be problematic for medical situations where speed is important (e.g., diagnosing possible strokes). Second, uploading medical images to the cloud can pose security issues, even if personal data is removed before the images are uploaded.

[0005] Thus, there is a need for improved systems and methods for facilitating remote analysis of medical image records, particularly one that reduces the amount of data that needs to be uploaded to the cloud and one that improves security. Summary of the Invention [Problem to be solved by the invention]

[0006] The objects and advantages of the disclosed subject matter will be set forth in and apparent from the following description, as well as be learned by the practice of the disclosed subject matter. Additional advantages of the disclosed subject matter will be realized and attained by the methods and systems particularly pointed out in the written description and claims thereof, as well as in the appended drawings. [Means for solving the problem]

[0007] To achieve these and other advantages, and in accordance with the objectives of the disclosed subject matter, the disclosed subject matter is directed to a system and method for remote analysis of one or more medical image records, as embodied and broadly described herein. For example, a method for remote analysis of one or more medical image records includes receiving a first medical image record at a first user's workstation, comparing the first medical image record to a standard image set at the first user's workstation to identify similarities between the first medical image record and the standard image set, and if the similarities exceed a threshold, calculating differences between the first medical image record and the standard image set at the first user's workstation by comparing the first medical image record with the standard image set, transferring the differences from the first user's workstation to one or more computing devices having a copy of the standard image set, reconstructing the first medical image record by combining the differences with the standard image set, and analyzing the first medical image record by the one or more computing devices.

[0008] In accordance with the disclosed subject matter, the first medical image record can include one or more DICOM service object pair instances. The standard image set can include one or more standard images. The standard image set can include a plurality of standard images of the anatomical feature. The method can include generating the standard image set using the plurality of images of the anatomical feature. The plurality of images can include a normal image and an abnormal image of the anatomical feature. The method can include providing a warning to a user if the similarity falls below a threshold.

[0009] According to the disclosed subject matter, comparing the first medical image record to the standard image set can include determining that the first medical image record and the standard image set each correspond to similar anatomical features. Analyzing the first medical image record can include determining a medical diagnosis. The method can include sending an alert to the first user's workstation if the medical diagnosis is abnormal. Analyzing the first medical image record can include using an artificial intelligence (AI) engine stored on the one or more computing devices. The method can include sending an analysis of the first medical image record from the one or more computing devices to the first user's workstation.

[0010] In accordance with the disclosed subject matter, one or more computer readable non-transitory storage media embodying software are provided that, when executed, is operable to receive, at a first user's workstation, a first medical image record, compare, at the first user's workstation, the first medical image record with a standard image set to identify similarities between the first medical image record and the standard image set, and if the similarities exceed a threshold, identify, at the first user's workstation, differences between the first medical image record and the standard image set by comparing the first medical image record with the standard image set, transfer the differences from the first user's workstation to one or more computing devices having a copy of the standard image set, reconstruct the first medical image record by combining the differences with the standard image set, and analyze, by the one or more computing devices, the first medical image record.

[0011] In accordance with the disclosed subject matter, a system is provided that includes one or more processors and a memory coupled to the processors and including instructions executable by the processors that, when executed, are operable to receive, at a first user's workstation, a first medical image record, compare, at the first user's workstation, the first medical image record with a standard image set to identify similarities between the first medical image record and the standard image set, and if the similarities exceed a threshold, identify, at the first user's workstation, differences between the first medical image record and the standard image set by comparing the first medical image record with the standard image set, transfer the differences from the first user's workstation to one or more computing devices having a copy of the standard image set, reconstruct the first medical image record by combining the differences with the standard image set, and analyze, by the one or more computing devices, the first medical image record.

[0012] In accordance with the disclosed subject matter, a system for remote analysis of one or more medical image records is provided. The system can include a workstation having a processor including a pre-processing AI engine for processing a first medical image record and a memory that stores a first copy of a standard image set. The system can further include one or more computing devices operably coupled to the workstation, the one or more computing devices including an AI engine and an AI engine storage device that stores a second copy of the standard image set.

[0013] According to the disclosed subject matter, the workstation may further include a transceiver for transmitting the difference to the server. The difference may be calculated by a pre-processing AI engine by comparing the first medical image record with a first copy of the standard image set. The workstation may include a graphical user interface. The one or more computing devices may include a server processor. The server processor may be configured to combine the difference with a second copy of the standard image set to reconstruct the first medical image record. The system may include an imaging modality operably coupled to the workstation for transmitting the first medical image record from the imaging modality to the workstation. [Brief description of the drawings]

[0014] [Figure 1] 1 illustrates a hierarchy of medical image records as viewed by the present disclosure. [Diagram 2] 1 illustrates an architecture of a system for remote analysis of one or more medical image records according to the present disclosure. [Figure 3A] 1 illustrates an exemplary medical image record and a standard image according to the present disclosure. [Figure 3B] 1 illustrates an exemplary medical image record and a standard image according to the present disclosure. [Figure 4] This disclosure shows how the difference can be calculated using the medical image registration and a standard image. [Diagram 5]This disclosure shows how a medical image registration can be calculated using standard images and subtractions. [Figure 6] 1 is a flow chart of a method for remote analysis of one or more medical image records according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Reference will now be made in detail to various exemplary embodiments of the present disclosure, which are illustrated in the accompanying drawings. The methods and systems described herein can be used for remote analysis of one or more medical image records, such as medical records stored on a Picture Archiving and Communication Systems (PACS). A variety of records are suitable for use with the present disclosure, and the records can be stored in any system, for example, a Vendor Neutral Archive (VNA). As used in the detailed description and the appended claims, singular forms such as "a," "an," "the," and singular nouns are intended to include the plural unless the context clearly dictates otherwise.

[0016] For purposes of illustration, but not by way of limitation, the systems and methods are described herein with respect to the transfer and analysis of medical image records (referred to herein as "medical image records" or "records") stored in a PACS, specifically DICOM records. For example, and for purposes of illustration and not by way of limitation, with reference to FIG. 1, a medical image record referred to herein may include a single DICOM Service Object Pair (SOP) instance (also referred to as a "DICOM instance", "DICOM image", and "image") 1 (e.g., 1A-1H), one or more DICOM SOP instances 1 contained in one or more series 2 (e.g., 2A-D), one or more series 2 contained in one or more studies 3 (e.g., 3A, 3B), and one or more studies 3.

[0017] Referring to FIG. 2 for purposes of illustration and not limitation, the disclosed system 100 can include one or more computer devices defining a server 10, a user workstation 60, and an imaging modality 90. In accordance with the disclosed subject matter, the system 100 can be configured for remote analysis of one or more medical image records. The user workstation 60 can be coupled to the server 10 by a network. The network can be, for example, a local area network (LAN), a wireless LAN (WLAN), a virtual private network (VPN), or any other network that allows any radio frequency or wireless type connection. For example, the other radio frequency or wireless connection can include, but is not limited to, one or more network access technologies such as Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), General Packet Radio Service (GPRS), Enhanced Data GSM Environment (EDGE), Third Generation Partnership Project (3GPP) technologies (including Long Term Evolution (LTE), LTE-Advanced, 3G technologies, Internet of Things (IOT), Fifth Generation (5G), or new radio (NR) technologies). Other examples include Wideband and Code Division Multiple Access (WCDMA), Bluetooth, IEEE 802.11b / g / n or other 802.11 protocols, or other wired or wireless connections. Medical image records can be transferred between the server side 10 and the workstation 60 and rendered at the workstation 60. Further information regarding downloading and rendering of medical images can be found in U.S. Patent Application Serial No. 16 / 450,477, which is incorporated herein by reference.

[0018] The workstation 60 may take the form of any known client device. For example, the workstation 60 may be a computer such as a laptop or desktop computer, a personal data or digital assistant (PDA), or any other user device such as a mobile device or mobile portable media player or tablet. The server 10 may be a service point that provides processing, database, and communication facilities. For example, the server may include a dedicated rack mounted server, a desktop computer, a laptop computer, a set-top box, an integrated device that combines various features such as features of two or more of the above-mentioned devices, and the like. The server may vary in configuration or capabilities, but may include at least one of one or more processors, memories, and transceivers. The server may also include at least one of one or more mass storage devices, one or more power supplies, one or more wired or wireless network interfaces, one or more input / output interfaces, and one or more operating systems.

[0019] The workstation 60 can communicate with the imaging modality 90 either directly (e.g., via a wired connection) or remotely (e.g., via a network as described above) via the PACS. The imaging modality 90 can be any medical imaging modality capable of providing images that can be analyzed by the AI ​​engine, including, for example, X-ray (or its digital counterparts: computed radiography (CR) and digital radiography (DR)), mammogram, tomosynthesis, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and ultrasound imaging.

[0020] A user may be anyone authorized to access workstation 60, including any medical professional, medical technician, or patient. In an embodiment, a user authorized to communicate with the PACS and / or remote AI engine may have a username and / or password that can be used to log in or access workstation 60.

[0021] The server 10 may include an AI engine storage device 31, a server processor 32, and an AI engine 33. The server processor 32 may be any hardware or software used to execute computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer to modify its functions for a specific application into a dedicated computer, an application specific integrated circuit (ASIC), or other programmable digital data processing device, and instructions executed via a processor of a client station or other programmable data processing device transform their functions according to the embodiments herein by implementing the functions / operations specified in the block diagrams or operational blocks. In accordance with the disclosed subject matter, the server processor 32 may be a portable embedded microcontroller or microcomputer. For example, the server processor 32 may be implemented by any computational or data processing device, such as a central processing unit (CPU), a digital signal processor (DSP), an ASIC, a programmable logic device (PLD), a field programmable gate array (FPGA), a digital enhancement circuit, or equivalent devices, or a combination thereof. The server processor 32 may be realized as a single controller, or multiple controllers or processors.

[0022] The AI ​​engine 33 may be any engine capable of performing medical diagnosis using AI. The AI ​​engine may be developed (i.e., "trained") using one or more of deep learning, hierarchical learning, machine learning, decision tree learning, and inductive logic programming. Additionally or alternatively, the AI ​​engine 33 may be trained using tools or techniques for developing AI engines, such as TensorFlow®, Keras, Microsoft Azure®, Google Cloud® predictive API, or any similar tool. The AI ​​engine 33 may use a neural network, such as an artificial neural network, a forward propagation neural network, a recurrent neural network, a bidirectional recurrent neural network, a hierarchical recurrent neural network, a probabilistic neural network, a modular neural network, an associative neural network, a deep neural network, a convolutional neural network, a large memory storage and retrieval neural network, a Bayesian network, or an artificial neural network, or any combination of these or similar AI configurations. The AI ​​engine storage device 31 can store medical image records to be analyzed by the AI ​​engine 33, and can also store a standard image set 70. The standard image set 70 can be developed by the AI ​​engine 33 or by other smart systems. For example, the standard image set 70 can be developed by reviewing a large set of images by a machine learning algorithm (e.g., a deep learning algorithm). The standard image set 70 can include one or more standard images 71. For example, if the system 100 is intended to identify renal disease, the standard image set 70 can be generated based on reviewing hundreds or thousands of images kidneys, including, for example, normal (healthy) kidneys and abnormal (disease) kidneys. For example, to develop a standard image set 70 for CT images of the kidney, at least 5,000 cases may be reviewed, and each case may include 50 to 200 images.Thus, in this example, at least 250,000 images may be reviewed. Typically, review of more images may result in an improved standard image set 70. The standard image set 70 may be generated as part of the learning process of the AI ​​engine 33. The standard image set 70 may then include several standard images 71, which may be a set of common images of kidneys. As another example, but not limited to, if the AI ​​engine 33 is configured to detect stroke, the standard image set 70 may include multiple standard images 71 including brain images, such as CT brain scans. Because the standard image set 70 may be created using a large number of images, the standard image set 70 may account for differences in gender, age, origin, size variation, modality, brand of modality, image processing (e.g., W / L, zoom, or pan), image quality, or other issues. Additionally or alternatively, the standard image set 70 may include images whose attributes and features are similar to one or more of the training images. Although this disclosure describes generating the standard image set 70 in a particular manner, this disclosure contemplates that the standard image set 70 may be generated in any suitable manner.

[0023] The workstation 60 can transmit and receive one or more medical image records from the server 10 or the imaging modality 90 using the transceiver 63. The transceiver 63 may be independently a transmitter, a receiver, or both a transmitter and a receiver, or may be a unit or device that can be configured for both transmission and reception. In other words, the transceiver 63 can include any hardware or software that allows the workstation 60 to communicate with at least one of the server 10 and the imaging modality 90. The transceiver 63 can be either a wired transceiver or a wireless transceiver. If wireless, the transceiver 63 can be implemented as a remote radio head located on an antenna tower rather than located on the device itself. Although FIG. 2 shows only a single transceiver 63, the workstation 60 can include one or more transceivers 63.

[0024] The medical image records received at the workstation 60 may be cached in the memory 61 of the workstation 60. The memory 61 may be any other suitable storage device, such as a non-volatile storage medium, or a non-transitory computer-readable medium or storage medium. For example, the memory 61 may be a random access memory (RAM), a read-only memory (ROM), a hard disk drive (HDD), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or other solid-state memory technology. The memory 61 may be a compact disk read-only optical memory (CD-ROM), a digital versatile disk (DVD), any other optical storage, a magnetic cassette, a magnetic tape, a magnetic disk storage device or other magnetic storage device, or any other physical or material medium that can be used to tangibly store desired information or data or instructions and that can be accessed by a computer or processor. The memory 61 may be either removable or non-removable.

[0025] The medical image records received by the workstation 60 can be processed using one or more processors 62. The processor 62 can be any hardware or software used to execute computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer to modify its functions for a specific application to a special-purpose computer, ASIC, or other programmable digital data processing device, and the instructions executed via the processor of the client station or other programmable data processing device transform their functions according to the embodiments herein by implementing the functions / operations specified in the block diagrams or operational blocks. The processor 62 can be a portable embedded microcontroller or microcomputer. For example, the processor 62 can be embodied by any computational or data processing device, such as a CPU, DSP, ASIC, PLD, FPGA, digital enhancement circuit, or equivalent device, or a combination thereof. The processor 62 can be realized as a single controller, or multiple controllers or processors. The processor 62 can include a pre-processing AI engine 64.

[0026] The memory 61 may include a standard image set 70. The standard image set 70 stored in the memory 61 is the same as the standard image set 70 stored in the AI ​​engine storage device 31 of the server 10. In other words, a copy of the standard image set 70 is stored on both the workstation 60 and the server 10. The pre-processing AI engine 64 may use the standard image set 70 to process medical image records received by the workstation 60.

[0027] During operation, the workstation 60 may receive one or more medical image records to be analyzed, for example, series 2. The pre-processing AI engine 63 may compare each DICOM SOP Instance 1 in series 2 to each standard image 71 in the standard image set 70. The pre-processing AI engine 63 may determine a similarity between each DICOM SOP Instance 1 and each standard image 71. The similarity may be determined, for example, using a pixel-by-pixel comparison between the DICOM SOP Instance 1 and the standard image 71. A similarity score may be calculated for each DICOM SOP Instance 1, and if the similarity score exceeds a threshold, the DICOM SOP Instance 1 may be identified as similar. Factors that may be used in calculating the similarity score may include gender, age, image location, image orientation, image zoom, image quality, image type (i.e., modality), brand of imaging modality 90, or any suitable characteristic of the image. By way of example, and not by way of limitation, if the system is intended to detect kidney disease, the standard image set 70 may include images of all or a portion of a kidney. The pre-processing AI engine 63 can identify DICOM SOP Instances 1 in Series 2 that are similar to standard images 71 in the standard image set 70. For example, standard images 71 and DICOM SOP Instance 1 can include images having the same portion of a kidney. Identifying only certain DICOM SOP Instances 1 in Series 2 as similar can reduce the overall processing required. Although this disclosure describes identifying similarities in a particular manner, this disclosure contemplates identifying similarities in any suitable manner. If no DICOM SOP Instances 1 are identified as similar, a warning can be provided to the user, for example, on the GUI 100. The pre-processing AI engineer 63 can determine a difference 72 for each DICOM SOP Instance 1 identified as similar by comparing each DICOM SOP Instance 1 with at least one standard image 71. For example, the difference 72 can be calculated by subtracting the DICOM SOP Instance 1 from the standard image 71.The difference 72 for a given shape may contain less data than the entire DICOM SOP Instance 1. The workstation 60 may forward each difference 72 to the server 10, for example using the transceiver 63. If there is more than one standard image 71 in the standard image set 72, the workstation 60 may also send a reference to each difference 72 to identify which standard image 71 was used to create the difference 72. The server processor 32 may reconstruct each DICOM SOP Instance 1 identified as similar by combining each difference 72 with at least one standard image 71 from the standard image set 70 stored in the AI ​​engine storage device 31. Once the DICOM SOP Instance 1 to be evaluated is recreated on the server 10, the AI ​​engine 33 may analyze the image 1. For example, the AI ​​engine 33 may perform an AI diagnostic analysis on the image 1. The results of the AI ​​diagnostic analysis may be sent from the server 10 to the workstation 60. The results may be displayed on the GUI 100. If the result of the diagnosis is abnormal or there is an emergency, an alert may be sent to the workstation 60 and displayed on the GUI 100.

[0028] 2 and 3A-3B, for purposes of illustration and not limitation, the system 100 can be configured to identify stroke. Thus, the standard image set 70 can include at least two standard images 71 of the brain (only 71A, 71B are shown in the figures). The standard images 71 can be based, for example, on thousands of normal and abnormal brain scans (e.g., CT scans). The workstation 60 can receive a series 2E for analysis. The series 2E can include 200 DICOM SOP instances 1 (only 1I, 1J, 1K, 1L are shown in the figures) and can include 100 MB of data. The pre-processing AI engine 63 compares each DICOM SOP instance 1 with at least one standard image 71 in the standard image set 70. The pre-processing AI engine 63 finds that the DICOM SOP instances 1I and 1L are not similar to the standard images 71, and therefore the DICOM SOP instances 1I and 1L are discarded. In contrast, the pre-processing AI engine 63 finds that the DICOM SOP instances 1J and 1K are similar to at least one standard image 71. That is, the DICOM SOP instance 1J is similar to the standard image 71B, and the DICOM SOP instance 1K is similar to the standard image 71A. Overall, the pre-processing AI engine 63 identifies 140 DICOM SOP instances 1 that are considered similar (e.g., have a similarity score above a threshold or otherwise match the criteria required for further processing). The 140 DICOM SOP instances 1 may contain 70 MB of data, which is 30 MB less than the 200 DICOM SOP instances 1 that make up the entire series 2E. This allows the first similarity test to reduce the number of images that need to be further analyzed, speeding up the overall process. If one or more of the DICOM SOP instances 1 are not similar to the standard image 71, a warning may be sent to the user. For example, a warning may be displayed on the GUI 100.The warning may indicate that the DICOM SOP Instance 1 is not suitable for the AI ​​engine 33 and therefore the DICOM SOP Instance 1 will not be pre-processed or sent to the server 10.

[0029] Referring to FIG. 4 for purposes of illustration and not limitation, the pre-processing AI engine 63 compares the standard image 71C to the DICOM SOP instance 1M to identify the difference 72A. For example, the difference 72A is calculated by adding or subtracting the standard image 71C and the DICOM SOP instance 1M. For example, but not by way of limitation, the difference 72 can be calculated by subtracting the DICOM SOP instance 1 from the standard image 71 that is most similar to the DICOM SOP instance 1. As described above, the difference 71 can be transmitted from the workstation 60 to the server 10. The workstation 60 can also transmit a reference to the specific index number of the standard image 71 that was used to calculate the difference. For example, referring to FIG. 4 for purposes of illustration and not limitation, the workstation 60 can transmit information to the server 10 that the difference 72A was created using the standard image 71C. Additionally or alternatively, the pre-processing AI engine 63 can calculate the difference 72 and perform a compression process. For example, but not by way of limitation, the pre-processing AI engine 63 can compress the difference 72A, which can further reduce the data size. Alternatively or additionally, the pre-processing AI engine 63 can compress the standard image 71C and the DICOM SOP instance 1M and then calculate the difference A between them. Although this disclosure describes calculating the difference in a particular manner, this disclosure contemplates calculating the difference in any suitable manner. The difference 72A can then be transferred to the server 10.

[0030] 5 for purposes of illustration and not limitation, the server processor 32 can combine the standard image 71C stored on the server 10 by the AI ​​engine storage device 31 with the difference 72A transferred from the workstation 60 along with information regarding which standard image 71 (e.g., specifically the standard image 71C) and the difference 72A should be combined to recreate the DICOM SOP instance 1M. For example, the DICOM SOP instance 1M can be recreated by adding or subtracting the standard image 71C and the difference 72A. Additionally, as discussed above, decompression can be performed if compression was performed by the pre-processing AI engine 63. For example, decompression can be performed if one or more of the DICOM SOP instance 1M, the standard image 71C, or the difference 72A were initially compressed by the pre-processing AI engine 63. Although this disclosure describes recreating the medical image record in a particular manner, this disclosure contemplates recreating the medical image record in any suitable manner. If the server processor 32 encounters a problem recreating the image 71, an error message can be sent to the workstation 60.

[0031] The AI ​​engine 33 can analyze the recreated DICOM SOP Instance 1. For example, the AI ​​engine 33 can perform an AI diagnostic analysis on the DICOM SOP Instance 1. The results of the AI ​​diagnostic analysis can be transmitted from the server 10 to the workstation 60 and displayed on the GUI 100. If deemed necessary, an alert can be transmitted to the workstation 60. An alert can be transmitted, for example, if the analysis concludes that the patient is ill (abnormal) or if the analysis concludes that there is an urgent need for a particular treatment. For example, an alert can be transmitted if the AI ​​diagnostic analysis concludes that the patient is having a stroke.

[0032] According to the disclosed subject matter, since the DICOM SOP Instance 1 can be recreated using the standard image set 70, only the differences 72 need to be transferred to the server 10. Thus, since the differences 72 are smaller than the DICOM SOP Instance 1, less data needs to be transferred, and therefore the transfer of data from the workstation 60 to the server 10 can be faster. Furthermore, since only the differences 72 are transferred, the standard image set 70 acts as a key to regenerate the DICOM SOP Instance 1. That is, each DICOM SOP Instance 1 cannot be recreated without the differences 72, and the standard image set 70 is required to recreate and analyze the medical image record. This can increase the security of transferring medical image records for remote analysis, since a third party would need to obtain both the transferred differences 72 and the stored standard image set 70 to recreate the medical image record.

[0033] FIG. 6 illustrates an exemplary method 1000 for remote analysis of one or more medical image records. The method may begin at step 1100, where the method includes receiving a first medical image record at a first user's workstation. At step 1200, the method may include comparing the first medical image record to a standard image set at the first user's workstation to identify similarities between the first medical image record and the standard image set. At step 1300, the method may include calculating differences between the first medical image record and the standard image set at the first user's workstation by comparing the first medical image record to the standard image set if the similarities exceed a threshold. At step 1400, the method may include transferring the differences from the first user's workstation to one or more computing devices having a copy of the standard image set. At step 1500, the method may include reconstructing the first medical image record by the one or more computing devices by combining the differences with the standard image set. At step 1600, the method may include analyzing, by one or more computing devices, the first medical image record. In accordance with the disclosed subject matter, the method may repeat one or more steps of the method of FIG. 6 as needed. Although the present disclosure describes and illustrates certain steps of the method of FIG. 6 as occurring in a particular order, the present disclosure contemplates any suitable steps of the method of FIG. 6 occurring in any suitable order. Additionally, although the present disclosure describes and illustrates an exemplary method for remote analysis of one or more medical image records that includes certain steps of the method of FIG. 6, the present disclosure contemplates any suitable method for remote analysis of one or more medical image records that includes any suitable steps, and any suitable steps may include all, some, or none of the steps of the method of FIG. 6, as needed. Additionally, although the present disclosure describes and illustrates certain components, devices, or systems that perform certain steps of the method of FIG. 6, the present disclosure contemplates any suitable combination of any suitable components, devices, or systems that perform any suitable steps of the method of FIG. 6.

[0034] As described above in connection with certain embodiments, certain components, such as the server 10 and the workstation 60, may include a computer or multiple computers, processors, networks, mobile devices, clusters, or other hardware to perform various functions. Additionally, certain elements of the disclosed subject matter may be embodied in computer readable code that may be stored in a computer readable medium and that, when executed, may cause a processor to perform certain functions described herein. In these embodiments, the computer and / or other hardware plays an important role in enabling the system and method for displaying medical image records. For example, the presence of computers, processors, memory, storage, and network hardware provides the ability to display medical image records in a more efficient manner. Additionally, displaying medical image records cannot be accomplished with pen or paper since the information is received over a network in electronic form.

[0035] The subject matter and operations described herein can be implemented in digital electronic circuitry, or computer software, firmware, or hardware, or any combination of one or more of these, including the structures disclosed herein and their structural equivalents.Embodiments of the subject matter described herein can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a computer storage medium for execution by or to control the operation of a data processing apparatus.

[0036] A computer storage medium may be or may be included in a computer readable storage device, a computer readable storage substrate, a random or serial access memory array or device, or a combination of one or more of these. Additionally, a computer storage medium is not a carrier signal, but a computer storage medium can be the source or destination of computer program instructions encoded in an artificially generated carrier signal. A computer storage medium may also be or be included in one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices).

[0037] The term "processor" encompasses all kinds of apparatus, devices, and machines for processing data, including, by way of example, a programmable processor, a computer, a system on one or more chips, or a combination thereof. An apparatus may include application-specific logic circuitry, such as an FPGA or an ASIC. In addition to hardware, an apparatus may also include code that creates an execution environment for the computer program, such as code that constitutes a processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or one or more combinations thereof. The apparatus and execution environment may implement a variety of different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0038] A computer program (also called a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted, declarative or procedural languages, and can be arranged in any form, either as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program can correspond to a file in a file system, but this is not required. A program can be stored in part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in several cooperating files (e.g., files that store one or more modules, subprograms, or portions of code). A computer program can be arranged to be executed on one computer, or on several computers located at one site or distributed across several sites and interconnected by a communication network.

[0039] The processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs to perform operations by operating on input data and generating output. The processes and logic flows may also be performed by, and apparatus may be implemented using, special purpose logic circuitry such as, for example, an FPGA or an ASIC.

[0040] Processors suitable for executing a computer program may include, by way of example and not limitation, both general purpose and special purpose microprocessors. Devices suitable for storing computer program instructions and data may include all forms of non-volatile memory, media, and memory devices, including, by way of example and not limitation, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal hard disks or removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0041] Additionally, as noted above in connection with certain embodiments, certain components may communicate with certain other components, for example, via a network, such as a local area network or the Internet. To the extent not expressly stated above, the disclosed subject matter is intended to encompass both each transaction, including sending and receiving. Those skilled in the art will readily appreciate that with respect to the above features, when one component transmits, sends, or otherwise makes available to another component, the other component will receive or acquire it, whether or not it is explicitly stated.

[0042] In addition to the specific embodiments claimed below, the disclosed subject matter is also directed to other embodiments having any other possible combinations of the dependent features claimed below and the features disclosed above. Thus, the specific features presented in the dependent claims and disclosed above can be combined with each other in other possible combinations. Thus, the foregoing description of specific embodiments of the disclosed subject matter has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosed subject matter to the disclosed embodiments.

[0043] It will be apparent to those skilled in the art that various modifications and variations can be made in the methods and systems of the disclosed subject matter without departing from the spirit or scope of the disclosed subject matter. Thus, it is intended that the disclosed subject matter cover modifications and variations that come within the scope of the appended claims and their equivalents.

Claims

1. 1. A method for remote analysis of one or more medical image records, comprising: receiving a first plurality of medical image records at a first user workstation; comparing the first plurality of medical image records to a standard set of images using a pre-processing AI engine at the first user workstation to identify similarities between the first plurality of medical image records and the standard set of images, respectively; calculating, at the first user's workstation, a difference between the first medical image records and the standard image set by comparing only the first medical image records among the plurality of first medical image records for which the similarity exceeds a threshold value with the standard image set; transferring the differences from the first user's workstation to one or more computing devices having a copy of a standard image set; reconstructing, by the one or more computing devices, the first medical image record by combining the difference with the standard image set; analyzing the first medical image record by the one or more computing devices; A method of remote analysis comprising:

2. The method of claim 1 , wherein the first medical image record includes one or more Digital Imaging and Communications in Medicine (DICOM) Service Object Pair (SOP) instances.

3. The method of claim 1 , wherein the set of standard images comprises one or more standard images.

4. The method of claim 3 , wherein the standard image set includes a plurality of standard images of an anatomical feature.

5. The method of claim 4 , further comprising generating the standard image set using a plurality of images of the anatomical feature.

6. The method of claim 5 , wherein the plurality of images includes normal and abnormal images of the anatomical feature.

7. The method of claim 1 , further comprising providing a warning to the user if the similarity is below a threshold.

8. The method of claim 1 , wherein comparing the first medical image record to the standard image set comprises determining that the first medical image record and the standard image set each correspond to similar anatomical features.

9. The method of claim 1 , wherein analyzing the first medical image record comprises determining a medical diagnosis.

10. 10. The method of claim 9, further comprising sending an alert to a workstation of the first user if the medical diagnosis is abnormal.

11. The method of claim 1 , wherein analyzing the first medical image record comprises using an artificial intelligence (AI) engine stored on the one or more computing devices.

12. The method of claim 1 , further comprising transmitting the analysis of the first medical image record from the one or more computer devices to a workstation of the first user.

13. One or more computer-readable non-transitory storage media having software embodied thereon that, when executed, receiving a first plurality of medical image records at a first user workstation; comparing the first plurality of medical image records to a standard set of images using a pre-processing AI engine at the first user workstation to identify similarities between the first plurality of medical image records and the standard set of images, respectively; comparing, at the first user's workstation, only those first medical image records among the plurality of first medical image records for which the similarity exceeds a threshold value with the standard image set to identify differences between the first medical image records and the standard image set; transferring said differences from said first user's workstation to one or more computing devices having a copy of a standard image set; reconstructing, by the one or more computing devices, the first medical image record by combining the difference with the standard image set; analyzing the first medical image record by the one or more computing devices; Such a storage medium is executable.

14. 14. The medium of claim 13, wherein the first medical image record includes one or more Digital Imaging and Communications in Medicine (DICOM) Service Object Pair (SOP) instances.

15. The media of claim 13 , wherein the set of standard images includes one or more standard images.

16. The medium of claim 15 , wherein the standard image set includes a plurality of standard images of an anatomical feature.

17. The medium of claim 16 , further comprising generating the standard image set using a plurality of images of the anatomical feature.

18. The medium of claim 17 , wherein the plurality of images includes normal and abnormal images of the anatomical feature.

19. The medium of claim 13 , wherein the software is further operable to provide a warning to the user if the similarity is below a threshold.

20. 14. The medium of claim 13, wherein comparing the first medical image record to the standard image set includes determining that the first medical image record and the standard image set each correspond to similar anatomical features.

21. The medium of claim 13 , wherein analyzing the first medical image record comprises determining a medical diagnosis.

22. 22. The medium of claim 21, further comprising sending an alert to a workstation of the first user if the medical diagnosis is abnormal.

23. 14. The medium of claim 13, wherein analyzing the first medical image record comprises using an artificial intelligence (AI) engine stored on the one or more computing devices.

24. The medium of claim 13 , further comprising transmitting the analysis of the first medical image record from the one or more computing devices to a workstation of the first user.

25. 1. A system comprising one or more processors and a memory coupled to the processors and including instructions executable by the processors, the processor, when executing the instructions, receiving a first plurality of medical image records at a first user workstation; comparing the first plurality of medical image records to a standard set of images using a pre-processing AI engine at the first user workstation to identify similarities between the first plurality of medical image records and the standard set of images, respectively; comparing, at the first user's workstation, only those first medical image records among the plurality of first medical image records for which the similarity exceeds a threshold value with the standard image set to identify differences between the first medical image records and the standard image set; transferring said differences from said first user's workstation to one or more computing devices having a copy of a standard image set; reconstructing, by the one or more computing devices, the first medical image record by combining the difference with the standard image set; analyzing the first medical image record by the one or more computing devices; The system is operable to

26. 1. A system for remote analysis of one or more medical image records, comprising: a workstation and one or more computer devices operably coupled to the workstation; The workstation comprises: a memory for storing a first copy of a standard image set; a processor including a pre-processing AI engine for comparing the received first medical image records with a first copy of the standard image set to identify similarities between the first medical image records and the first copy of the standard image set, and for identifying differences between the first medical image records and the standard image set by comparing only the first medical image records among the plurality of first medical image records whose similarity exceeds a threshold value with the first copy of the standard image set; Equipped with The one or more computing devices, AI engine and an AI engine storage device that stores a second copy of the standard image set; Equipped with system.

27. 27. The system of claim 26, wherein the workstation further comprises a transceiver for transmitting the differences to a server.

28. 27. The system of claim 26, wherein the workstation further comprises a graphical user interface.

29. 30. The system of claim 26, wherein the one or more computing devices further comprise a server processor.

30. 30. The system of claim 29, wherein the server processor is configured to combine the differences with a second copy of the standard image set to reconstruct the first medical image record.

31. 27. The system of claim 26, further comprising an imaging modality operably coupled to the workstation for transmitting the first medical image record to the workstation.

Images