Image data processing platform and method, computer equipment and storage medium

Abstract

The invention provides an image data processing platform and method, computer equipment and a storage medium. The platform comprises an AI PACS system and an RIS system. The AI PACS system is used for performing standardized and formatted conversion on the acquired AI analysis result, generating structured report data and synchronizing the structured report data to the RIS system; the RIS system is used for displaying the structured report data in the display interface through the first window; the structured report data is used for indicating a focus identifier and focus information corresponding to the focus identifier; in response to an operation of clicking the lesion identifier by the user, creating a new second window in the display interface; and the AI PACS system is also used for displaying target image data corresponding to the focus identifier through the second window. In the embodiment of the invention, the AI PACS system and the RIS system can exchange information bidirectionally, so that the report generation efficiency and the report auditing efficiency are improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to an image data processing platform, method, computer equipment and storage medium. Background Art

[0002] In the field of medical imaging diagnosis, traditional Picture Archiving and Communication Systems (PACS) are mainly used to store, retrieve, transmit and consult medical imaging data, while Radiology Information System (RIS) is used to manage radiology appointment registration, report writing, etc. With the development of artificial intelligence technology, artificial intelligence (AI) technology is increasingly used in medical imaging analysis. AI technology can assist doctors in achieving faster and more accurate lesion location, identification and quantification.

[0003] In the related technologies, the AI ​​system, PACS system and RIS system are independent of each other and have low integration. Reporting doctors and reviewing doctors need to switch between multiple systems many times when working. For example, the reporting doctor needs to check the original image data in the PACS system, then switch to the AI ​​system to view the AI ​​results, and finally edit it through the RIS system based on the traditional report template to generate the report text. For another example, the reviewing doctor needs to view the report text in the RIS system, then switch to the AI ​​system and PACS system for review, and finally review the report text in the RIS system. During the above report generation and review process, the linkage between systems is poor, and the report generation method is relatively cumbersome, resulting in low report generation efficiency and poor user experience. Summary of the invention

[0004] In view of the above problems, the embodiments of the present invention provide an image data processing platform, method, computer device and storage medium to solve the problems in the prior art of poor linkage between systems, cumbersome report generation method, resulting in low report generation efficiency and poor user experience.

[0005] An embodiment of the present invention provides an image data processing platform, which includes an artificial intelligence image archiving and communication system AIPACS system and a radiology information system RIS system;

[0006] The AIPACS system is used to perform standardized and formatted conversion on the acquired AI analysis results, generate structured report data, and synchronize the structured report data to the RIS system;

[0007] The RIS system is used to display the structured report data in a first window in a display interface; the structured report data is used to indicate a lesion identifier and lesion information corresponding to the lesion identifier; in response to a user clicking on the lesion identifier, a second window is created in the display interface;

[0008] The AIPACS system is also used to display the target image data corresponding to the lesion identification through the second window; the AIPACS system stores the association relationship between the lesion identification and the target image data; the first window is used to display the operation interface of the RIS system, and the second window is used to display the operation interface of the AIPACS system.

[0009] In a possible implementation, the AIPACS system includes:

[0010] An AI data collaboration module, configured to perform standardized and formatted conversion on the AI ​​analysis result through at least one preset diagnostic information description template to generate a target AI analysis result;

[0011] A report processing module is used to generate structured report data according to the target AI analysis results and a preset report template, and synchronize the structured report data to the RIS system.

[0012] In a possible implementation, the AI ​​data collaboration module is further used to associate the lesion identifier with the target image data, and to generate and store an association relationship between the lesion identifier and the target image data.

[0013] In a possible implementation, the report processing module is further used to update the structured report data in response to a report editing operation input by a user, generate updated structured report data, and synchronize the updated structured report data to the RIS system.

[0014] In a possible implementation, the report processing module is further configured to update the report template in response to a template editing operation input by a user, and generate an updated report template.

[0015] In a possible implementation, the target AI analysis result includes target image data, and the AI ​​data collaboration module is further used to process the target image data through an image post-processing algorithm to generate three-dimensional post-processed image data.

[0016] In a possible implementation, the AIPACS system further includes an intelligent review module, and the intelligent review module is used to display at least one of the original image data, the target image data, and the three-dimensional post-processed image data through the second window.

[0017] In a possible implementation, the target AI analysis result includes a positive result, the first window is further used to display a lesion key information list, and the second window is further used to display a lesion list; when the target AI analysis result is a positive result, the lesion list includes at least one lesion selection control;

[0018] The RIS system is also used to update the structured report and the lesion key information list in response to the user's editing operation on the lesion selection control, and generate an updated structured report and an updated lesion key information list.

[0019] In a second aspect, an embodiment of the present invention provides an image data processing method, which is applied to an image data processing platform, wherein the image data processing platform includes an AIPACS system and a RIS system; the method includes:

[0020] Standardize and format the acquired AI analysis results to generate structured report data, and synchronize the structured report data to the RIS system;

[0021] Displaying the structured report data in a first window in a display interface; the structured report data is used to indicate a lesion identifier and lesion information corresponding to the lesion identifier;

[0022] In response to the user clicking on the lesion marker, a second window is created in the display interface; the first window is used to display the operation interface of the RIS system, and the second window is used to display the operation interface of the AIPACS system; the target image data corresponding to the lesion marker is displayed through the second window; the AIPACS system stores the association relationship between the lesion marker and the target image data.

[0023] In a third aspect, the present invention provides a computer device comprising one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the computer device, enable the computer device to perform the image data processing method as described in the second aspect.

[0024] In the technical solution provided by the embodiment of the present invention, the AIPACS system and the RIS system can exchange information bidirectionally without switching between multiple systems. In other words, the image data processing platform can realize real-time synchronization of structured report data through the forward linkage from the AIPACS system to the RIS system; and can realize rapid film reading and rapid review of structured report data through the reverse linkage from the RIS system to the AIPACS system. The AIPACS system and the RIS system can be efficiently linked, thereby improving the efficiency of report generation and report review, and improving the user experience.

[0025] In the embodiment of the present invention, the relevant data streams in the AIPACS system and the RIS system are reconstructed according to the workflow to form a complete image data processing process. Two-way data interaction is formed in the report review process and the film reading process, thereby improving the intelligence level of the image data processing platform.

[0026] In the embodiment of the present invention, when data in the AIPACS system or the RIS system is updated, the corresponding data in the other system is also updated accordingly, thereby ensuring data consistency between the AIPACS system and the RIS system and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the structure of an image data processing platform provided by an embodiment of the present invention.

[0028] Figure 2 A schematic diagram of a display interface provided by an embodiment of the present invention.

[0029] Figure 3 A schematic diagram of another display interface provided by an embodiment of the present invention.

[0030] Figure 4 The present invention provides a flowchart of an image data processing method according to an embodiment of the present invention.

[0031] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer and more understandable, the present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Figure 1A schematic diagram of the structure of an image data processing platform provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the image data processing platform includes an AIPACS system 1 and a RIS system 2. The AIPACS system 1 is used to perform standardized and formatted conversion on the acquired AI analysis results, generate structured report data, and synchronize the structured report data to the RIS system 2. The RIS system 2 is used to display the structured report data through a first window in the display interface; the structured report data is used to indicate the lesion identification and the lesion information corresponding to the lesion identification; in response to the user clicking the lesion identification, a second window is newly created in the display interface. The AIPACS system 1 is also used to display the target image data corresponding to the lesion identification through a second window; the AIPACS system 1 stores the association relationship between the lesion identification and the target image data; the first window is used to display the operation interface of the RIS system, and the second window is used to display the operation interface of the AI ​​PACS system.

[0034] In an embodiment of the present invention, the target AI analysis result includes a positive result or a negative result. When the target AI analysis result is a negative result, the structured report data is used to indicate that the lesion identifier is empty and the lesion information corresponding to the lesion identifier is also empty; or, when the target AI analysis result is a positive result, the structured report data is used to indicate at least one lesion identifier and the lesion information corresponding to each lesion identifier.

[0035] In the embodiment of the present invention, an AI computing module is further provided inside the image data processing platform and outside the AIPACS system, and the AI ​​computing module is used to generate AI analysis results. The AIPACS system can obtain the AI ​​analysis results from the AI ​​computing module, or the AIPACS system can directly obtain the AI ​​analysis results from the outside.

[0036] In an embodiment of the present invention, when a computer device creates a new second window in a display interface, a user can set the display mode of the first window and the second window based on actual use requirements. For example, the first window and the second window can be displayed on different displays respectively. Among them, the first window is displayed on the first display, and the second window is displayed on the second display. For another example, the first window and the second window can be displayed on the same display at the same time. In actual applications, the default sizes of the first window and the second window, as well as the default relative position relationship between the first window and the second window can be set based on actual use requirements. The default size of the first window can be the same as or different from the default size of the second window. For example, the first window is displayed above the second window in the form of a small window; or the second window is displayed above the first window in the form of a small window; or the first window and the second window do not overlap, and the first window and the second window are distributed left and right; or the first window and the second window do not overlap, and the first window and the second window are distributed up and down; or the first window and the second window do not overlap, and the first window and the second window are distributed diagonally. In actual applications, the default position relationship between the first window and the second window can be set to other relative position relationships based on actual use requirements, and the embodiment of the present invention does not limit this. Furthermore, during use, the size of the first window, the size of the second window, or the relative position relationship between the first window and the second window may be adjusted at any time, thereby improving the user experience.

[0037] In an embodiment of the present invention, at least one AI model is integrated into the AIPACS system, realizing the integration of the PACS system and the AI ​​system. The image data processing platform realizes the real-time synchronization of structured report data through the forward linkage between the AIPACS system and the RIS system; through the reverse linkage from the RIS system to the AI ​​PACS system, rapid film reading and rapid review of structured report data are realized. In other words, the image data processing platform realizes efficient linkage between the AI ​​system, the PACS system and the RIS system. At this time, the AIPACS system and the RIS system can exchange information bidirectionally, and the user does not need to switch repeatedly between multiple systems to realize the generation and review of structured report data, thereby improving the report generation efficiency and the user experience, thereby solving the problems of poor linkage between systems and cumbersome report generation methods in the prior art, resulting in low report generation efficiency and poor user experience.

[0038] Compared with the conventional PACS system, the AIPACS system provided by the embodiment of the present invention is provided with an AI data collaboration module. The AI ​​data collaboration module serves as a data link between the AI ​​computing module and the AIPACS system, making the data flow between the AI ​​computing module and the AIPACS system smoother and improving the user experience.

[0039] In the embodiment of the present invention, the target AI analysis result is the core data of the AIPACS system, and the AI ​​data collaboration module distributes the target AI analysis result to the report processing module and the intelligent review module respectively. Through the collaborative work of the three modules in the AIPACS system, doctors can be provided with efficient and intelligent image analysis and report generation services, which greatly improves the work efficiency and diagnostic accuracy of doctors.

[0040] In an embodiment of the present invention, the AIPACS system 1 includes an AI data collaboration module 11 and a report processing module 12, and the AI ​​data collaboration module 11 is data-connected to the report processing module 12. The AI ​​data collaboration module 11 is used to perform standardized and formatted conversion on the AI ​​analysis results through at least one preset diagnostic information description template to generate a target AI analysis result. Specifically, the target AI analysis result includes target image data and report data. Among them, the report data is the relevant data required to generate structured report data. The report processing module 12 is used to generate structured report data according to the target AI analysis results and a preset report template, and synchronize the structured report data to the RIS system 2.

[0041] Specifically, the AIPACS system is connected to multiple image data acquisition devices to obtain raw image data. The AI ​​data collaboration module 11 obtains raw image data from the PACS system, determines the target AI model from at least one integrated AI model according to the characteristics of the raw image data, inputs the raw image data into the target AI model, outputs the target image data, and displays the target image data through the second window. For example, the AI ​​model includes a lesion detection model, a lesion segmentation model, and a quantification model. The AI ​​analysis results include lesion area, long diameter, short diameter, average diameter, maximum area, volume, computed tomography (Computed Tomography, referred to as CT) average value, CT maximum value, and CT minimum value. In an embodiment of the present invention, the AI ​​data collaboration module directly obtains raw image data from the PACS system, does not rely on other devices or systems, ensures the integrity and accuracy of the raw image data during the data transmission process, and avoids the situation where the image data is leaked or mis-transmitted. At this time, the target AI analysis result is generated based on the raw image data, thereby ensuring the accuracy of the target AI analysis result, improving the AI ​​analysis efficiency, and thus improving the image data processing efficiency.

[0042] In an embodiment of the present invention, the AIPACS system is adapted to a universal standard protocol. The AI ​​calculation module provides the AI ​​analysis results to the PACS system and the RIS system in a standard form through the standard protocol, so that an organic connection is established between the AI ​​system, the PACS system, and the RIS system. Through the information interaction of the standard protocol, the AI ​​calculation process and the film reading process can be completely decoupled. At the same time, because of the standardization of the protocol, the AI ​​model is also interchangeable, so that the AIPACS system has higher flexibility and scalability.

[0043] In an embodiment of the present invention, the AIPACS system 1 also includes an intelligent review module 13, and the intelligent review module 13 is data-connected with the AI ​​data collaboration module 11 and the report processing module 12 respectively. After the AI ​​data collaboration module 11 generates the target AI analysis results, the report data is distributed to the report processing module 12, so that the report processing module 12 generates structured report data according to the report data and the report template; the target image data is distributed to the intelligent review module 13, so that the intelligent review module 13 displays the target image data through the second window. The report processing module 12 and the intelligent review module 13 are loaded and initialized based on the target AI analysis results, and interact in real time through a two-way communication mechanism. Since the report processing module 12 and the intelligent review module 13 process and load the same standardized information, a one-to-one corresponding relationship can be established between the lesion information of the two.

[0044] Specifically, during the film reading process, a duplex communication connection is established based on the WebSocket protocol mechanism to realize two-way information exchange between the report processing module 12 and the intelligent review module 13, so that the user's operation on the AI ​​information at one end is synchronized to the other end in real time, ensuring the data consistency between the report processing module 12 and the intelligent review module 13, so that users have a smoother user experience.

[0045] Specifically, the intelligent review module 13 is used to load the sequence list and draw the lesion information. Figure 2 A schematic diagram of a display interface provided by an embodiment of the present invention is shown as follows: Figure 2As shown, a sequence list is displayed on the left side of the display interface, and the sequence list includes three sequences, namely the first sequence, the second sequence and the third sequence. The user clicks on the optimal sequence in the sequence list, and the computer device responds to the user's operation of clicking the optimal sequence, and displays the structured report data corresponding to the optimal sequence through the RIS system according to the lesion list and lesion-related information corresponding to the optimal sequence. Among them, the optimal sequence is the sequence that is most conducive to the doctor's disease diagnosis. Different sequences have different imaging characteristics, and different sequences focus on different contents of observation. Therefore, different disease types correspond to different optimal sequences, and the optimal sequence can be determined according to the characteristics of the disease type. In practical applications, the optimal sequence can be a sequence or an optimal sequence combination composed of multiple sequences. In an embodiment of the present invention, based on the selected optimal sequence, the structured report data corresponding to the optimal sequence is displayed in the RIS system, that is, the structured report data that is most conducive to the doctor's diagnosis, so that the doctor can make a quick diagnosis and improve the doctor's diagnostic efficiency.

[0046] In the film reading scene, the display interface can display the target image data and the lesion list at the same time. When the target AI analysis result is a negative result, the lesion list is empty; or, when the target AI analysis result is a positive result, the lesion list includes at least one lesion selection control. The lesion selection control is an operable control identified by the lesion number. In response to the user clicking the lesion selection control, the computer device displays the target image data corresponding to the lesion selection control on the display interface, that is, the image data of the lesion corresponding to the lesion selection control is highlighted. For example, highlighting includes selecting the lesion corresponding to the lesion selection control through a detection frame, and highlighting the border of the detection frame to facilitate quick determination of the lesion location. In an embodiment of the present invention, film reading can be achieved only through the AIPACS system, without switching between the AI ​​system and the PACS system, thereby improving the user experience.

[0047] Figure 3 A schematic diagram of another display interface provided by an embodiment of the present invention, such as Figure 3 As shown, the lesion list includes five lesion selection controls, namely the first selection control, the second selection control, the third selection control, the fourth selection control and the fifth selection control. The lesion number of the first selection control is 1, the lesion number of the second selection control is 2, the lesion number of the third selection control is 3, the lesion number of the fourth selection control is 4, and the lesion number of the fifth selection control is 5. In response to the user clicking the second selection control, the computer device displays the target image data corresponding to the second selection control on the display interface. At this time, the second selection control is in the selected state, and the first selection control, the third selection control, the fourth selection control and the fifth selection control are in the unselected state.

[0048] like Figure 3 As shown, the film reading interface can also be provided with selection controls, scroll controls, movement controls, zoom controls, positioning controls, rotation controls, measurement controls, marking controls and reset controls, which are respectively used to realize the selection, scrolling, movement, zooming, positioning, rotation, measurement, marking and resetting of target image data.

[0049] like Figure 3 As shown, the display interface may also be provided with a hidden AI control, which is used to control the display state of the AI ​​analysis result. In response to the user clicking the operation of hiding the AI ​​control, the computer device hides the AI ​​analysis result and displays the original image data on the display interface.

[0050] In an embodiment of the present invention, the AI ​​data collaboration module 11 is also used to process the target image data through an image post-processing algorithm to generate three-dimensional post-processed image data. For example, the image post-processing algorithm is a three-dimensional reconstruction algorithm. In an embodiment of the present invention, the AI ​​data collaboration module 11 can perform in-depth analysis of the two-dimensional image data through an image post-processing algorithm and automatically generate three-dimensional post-processed image data. The three-dimensional post-processed image data can realize stereoscopic visualization of the lesion area, which is beneficial for doctors to observe and diagnose the lesion area, improve the comprehensiveness and accuracy of the diagnosis, and thus improve the diagnostic efficiency.

[0051] like Figure 3 As shown, the display interface may also be provided with an image post-processing control. In response to the user clicking the image post-processing control, the computer device processes the target image data through an image post-processing algorithm to generate three-dimensional post-processed image data.

[0052] like Figure 3 As shown, the display interface displays structured report data through the first window, and the structured report data includes five lesion identifiers and lesion information corresponding to each lesion identifier. Specifically, the lesion identifier is an operable control identified by the lesion number. The five lesion identifiers are the first lesion identifier, the second lesion identifier, the third lesion identifier, the fourth lesion identifier, and the fifth lesion identifier. Among them, the lesion number of the first lesion identifier is 1, the lesion number of the second lesion identifier is 2, the lesion number of the third lesion identifier is 3, the lesion number of the fourth lesion identifier is 4, and the lesion number of the fifth lesion identifier is 5. Lesion information includes imaging manifestations and diagnostic opinions. Among them, the imaging manifestations are the observation and description of the imaging manifestations of basic lesions; the diagnostic opinion is the diagnostic conclusion based on the imaging manifestations. For example, the imaging manifestations are "four solid nodules ①②③⑤ in the apical segment of the right upper lobe, and calcified nodules ④ in the inner segment of the right middle lobe" and other imaging manifestations. The diagnosis was "multiple micronodules in both lungs, Category 2. It is recommended to continue annual low-dose chest CT screening within 12 months. It is recommended to combine clinical practice and conduct further examinations if necessary."

[0053] Optionally, the first window is also used to display a list of key information on lesions. When the target AI analysis result is a negative result, the list of key information on lesions is empty; when the target AI analysis result is a positive result, the list of key information on lesions includes at least one key information display area, and each key information display area is used to display the key information of a lesion. For example, the key information on lesions includes lesion number, lesion nature, lesion size, lesion location, and lesion classification. In an embodiment of the present invention, a doctor can quickly understand the key information of a patient's lesion through the key information display area, thereby achieving rapid diagnosis, improving diagnostic efficiency, and improving the user experience.

[0054] like Figure 3 As shown, the lesion key information list includes five key information display areas, namely the first key information display area, the second key information display area, the third key information display area, the fourth key information display area and the fifth key information display area. The lesion number in the first key information display area is 1, the lesion number in the second key information display area is 2, the lesion number in the third key information display area is 3, the lesion number in the fourth key information display area is 4, and the lesion number in the fifth key information display area is 5.

[0055] In an embodiment of the present invention, the RIS system is also used to update the structured report and the lesion key information list in response to the user's editing operation on the lesion selection control, and generate an updated structured report and an updated lesion key information list. For example, the editing operation includes a deletion operation. After the lesion list is edited in the AIPACS system, the RIS system updates the structured report and the lesion key information list in real time, thereby ensuring the data consistency between the AIPACS system and the RIS system and improving the user experience.

[0056] Optionally, the first window is also provided with a sorting mode selection control. In response to the user clicking the sorting mode selection control, the computer device calls out a sorting mode option menu, and a plurality of sorting mode options are provided in the sorting mode option menu. In response to the user clicking the sorting mode option, the computer device switches the sorting mode of at least one key information display area to the sorting mode corresponding to the sorting mode. For example, there are four sorting mode options provided in the sorting mode option menu, which are sorting by lesion number; or sorting by lesion size; or sorting by lesion classification; or sorting in the order in which the lesion identification appears in the structured report data. For example, in the structured report data, the image performance is "four solid nodules ①②③⑤ in the apical segment of the right upper lobe, and calcified nodules ④ in the inner segment of the right middle lobe". That is, the order of appearance of the lesion identification in the structured report data is ①②③⑤④. When the user chooses to sort in the order in which the lesion identification appears in the structured report, the five key information display areas in the lesion key information list are sorted in the order of ①②③⑤④. In the embodiment of the present invention, the user can implement customized sorting of the key information display area through the sorting mode selection control, which can meet the working habits of different doctors and improve the user experience.

[0057] In an embodiment of the present invention, the image data processing platform can realize a bidirectional index between the AIPACS system and the RIS system. When the user selects the lesion selection control in the AIPACS system, the key information display area corresponding to the lesion selection control is highlighted in the RIS system to realize the pointing index from the AI ​​PACS system to the RIS system. When the user selects the key information display area in the RIS system, the lesion selection control corresponding to the key information display area is highlighted in the AIPACS system to realize the pointing index from the RIS system to the AIPACS system. Among them, the lesion selection control and the key information display area establish a corresponding relationship based on the same lesion number. For example, the lesion selection control with a lesion number of 2 corresponds to the key information display area with a lesion number of 2. Based on this, the impact data processing platform realizes a bidirectional index between the AIPACS system and the RIS system, and can realize rapid positioning through bidirectional indexing, thereby improving the user experience.

[0058] Optionally, the user can perform personalized marking of the key information of the lesion according to personal habits. For example, the lesion classification is used to indicate the degree of danger of the lesion. In practical applications, the lesions with a higher degree of danger can be marked as red, the lesions with a general degree of danger can be marked as yellow, and the lesions with a lower degree of danger can be marked as green. For another example, the size of the lesion can also reflect the degree of danger of the lesion to a certain extent, and the user can also perform personalized marking of the lesion size. In an embodiment of the present invention, the doctor can understand the patient's lesion condition more intuitively through personalized marking, and the personalized marking can be customized to meet the working habits of different doctors, thereby further improving the user experience.

[0059] like Figure 3 As shown, the first window can also be used to display report templates. A plurality of report templates are preset in the report processing module 12, and the report templates are divided based on the image type and the scanning part. Among them, the image types include CT, CT angiography (CT angiography, referred to as CTA), magnetic resonance examination (Magnetic Resonance, referred to as MR), X-ray, etc., and the scanning parts include chest, upper abdomen, head and neck, etc. For example, when the image type is CT and the scanning part is chest, the report template includes template A, template B and template C.

[0060] In the embodiment of the present invention, the report processing module 12 is further used to update the structured report data in response to the report editing operation input by the user, generate updated structured report data, and synchronize the updated structured report data to the RIS system 2.

[0061] like Figure 3 As shown, the first window may also be provided with a quick input button. In response to the user clicking the quick input button, the computer device pops up a quick input box. After the user edits and saves the structured report data in the quick input box, the structured report data is updated. In the embodiment of the present invention, the user can quickly edit the structured report data through the quick input button, thereby improving the report editing efficiency.

[0062] In an embodiment of the present invention, the report processing module 12 is also used to update the report template in response to a template editing operation input by the user, and generate an updated report template. For example, the template editing operation includes a template modification operation, a template addition operation, or a template deletion operation. In an embodiment of the present invention, the report processing module 12 supports the management and customization of report templates. Doctors can select different report templates according to their own needs to meet different reporting requirements, thereby improving the report processing efficiency and further improving the user experience.

[0063] In the embodiment of the present invention, the intelligent review module 13 is used to display at least one of the original image data, the target image data, and the three-dimensional post-processed image data through a display interface. In the embodiment of the present invention, the intelligent review module can realize the display of multiple image data, which can meet the user's diverse review needs for image data, thereby improving the user's experience.

[0064] In the embodiment of the present invention, the standard protocol implements structured storage of lesion-related information by defining key-value pairs. For example, lesion-related information includes lesion location, lesion size, lesion nature, 3D post-processing image data address and other information. At the same time, the standard protocol also stipulates the format, size and other information of 3D post-processing image data. It can realize fast and efficient query and call of data, which is conducive to ensuring the integrity and consistency of data.

[0065] In an embodiment of the present invention, the AI ​​data collaboration module 11 is also used to associate the lesion identification with the target image data, generate and store the association relationship between the lesion identification and the target image data. Specifically, a corresponding relationship is established between the target image data, the lesion selection control, the key information display area and the lesion identification based on the same lesion number. For example, the target image data, the lesion selection control, the key information display area and the lesion identification with the lesion number 2 all correspond one to one, that is, the target image data corresponding to the lesion number 2, the second lesion selection control, the second key information display area and the second lesion identification correspond. Among them, the target image data with the lesion number 2 refers to the target image data of the lesion area with the lesion number 2 highlighted.

[0066] In the embodiment of the present invention, the image data processing platform follows strict data security and privacy protection standards during data transmission and processing, and has extremely high security. Specifically, the security of medical information can be ensured when data is transmitted and processed between modules within the AIPACS system, and when data is transmitted and processed between the AIPACS system and the RIS system.

[0067] In the technical solution provided by the embodiment of the present invention, the AIPACS system and the RIS system can exchange information bidirectionally without switching between multiple systems. In other words, the image data processing platform can realize real-time synchronization of structured report data through the forward linkage from the AIPACS system to the RIS system; and can realize rapid film reading and rapid review of structured report data through the reverse linkage from the RIS system to the AIPACS system. The AIPACS system and the RIS system can be efficiently linked, thereby improving the efficiency of report generation and report review, and improving the user experience.

[0068] In the embodiment of the present invention, the relevant data streams in the AIPACS system and the RIS system are reconstructed according to the workflow to form a complete image data processing process. Two-way data interaction is formed in the report review process and the film reading process, thereby improving the intelligence level of the image data processing platform.

[0069] In the embodiment of the present invention, when data in the AIPACS system or the RIS system is updated, the corresponding data in the other system is also updated accordingly, thereby ensuring data consistency between the AIPACS system and the RIS system and improving the user experience.

[0070] Figure 4 A flowchart of an image data processing method provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the method includes:

[0071] Step 101: Standardize and format the acquired AI analysis results to generate structured report data, and synchronize the structured report data to the RIS system.

[0072] Each step in the embodiment of the present invention is executed by an image data processing platform installed on a computer device. The image data processing platform includes an AIPACS system and a RIS system. For a specific description, please refer to the embodiment of the above-mentioned image data processing platform. For the sake of simplicity, it will not be repeated here.

[0073] Step 102: Display structured report data in a first window in a display interface.

[0074] In this step, the structured report data is used to indicate the lesion identification and the lesion information corresponding to the lesion identification.

[0075] Step 103 : in response to the user clicking on the lesion mark, a second window is newly created in the display interface, and the target image data corresponding to the lesion mark is displayed in the second window.

[0076] In this step, the AIPACS system stores the association relationship between the lesion identification and the target image data.

[0077] In the technical solution provided by the embodiment of the present invention, the AIPACS system and the RIS system can exchange information bidirectionally without switching between multiple systems. In other words, the image data processing platform can realize real-time synchronization of structured report data through the forward linkage from the AIPACS system to the RIS system; and can realize rapid film reading and rapid review of structured report data through the reverse linkage from the RIS system to the AIPACS system. The AIPACS system and the RIS system can be efficiently linked, thereby improving the efficiency of report generation and report review, and improving the user experience.

[0078] In the embodiment of the present invention, the relevant data streams in the AIPACS system and the RIS system are reconstructed according to the workflow to form a complete image data processing process. Two-way data interaction is formed in the report review process and the film reading process, thereby improving the intelligence level of the image data processing platform.

[0079] In the embodiment of the present invention, when data in the AIPACS system or the RIS system is updated, the corresponding data in the other system is also updated accordingly, thereby ensuring data consistency between the AIPACS system and the RIS system and improving the user experience.

[0080] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the steps of the embodiment of the above-mentioned image data processing method. For a specific description, please refer to the embodiment of the above-mentioned image data processing method.

[0081] Figure 5 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the computer device 3 of this embodiment includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 301 executes the computer program 303, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0082] The computer device 3 may be a desktop computer, a notebook, a PDA, a cloud server or other electronic device. The computer device 3 may include but is not limited to a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 5 The computer device 3 is merely an example and does not limit the computer device 3 , and may include more or less components than those shown in the figure, or different components.

[0083] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0084] The memory 302 may be an internal storage unit of the computer device 3, for example, a hard disk or memory of the computer device 3. The memory 302 may also be an external storage device of the computer device 3, for example, a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. The memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store computer programs and other programs and data required by the electronic device.

[0085] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0086] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An image data processing platform, characterized in that: The image data processing platform includes an artificial intelligence image archiving and communication system AIPACS system and a radiology information system RIS system; The AIPACS system is used to perform standardized and formatted conversion on the acquired AI analysis results, generate structured report data, and synchronize the structured report data to the RIS system; The RIS system is used to display the structured report data in a first window in a display interface; the structured report data is used to indicate a lesion identifier and lesion information corresponding to the lesion identifier; in response to a user clicking on the lesion identifier, a second window is created in the display interface; The AIPACS system is also used to display the target image data corresponding to the lesion identification through the second window; the AIPACS system stores the association relationship between the lesion identification and the target image data; the first window is used to display the operation interface of the RIS system, and the second window is used to display the operation interface of the AIPACS system.

2. The image data processing platform according to claim 1, characterized in that: The AI ​​PACS system includes: An AI data collaboration module, configured to perform standardized and formatted conversion on the AI ​​analysis result through at least one preset diagnostic information description template to generate a target AI analysis result; A report processing module is used to generate structured report data according to the target AI analysis results and a preset report template, and synchronize the structured report data to the RIS system.

3. The image data processing platform according to claim 2, characterized in that: The AI ​​data collaboration module is also used to associate the lesion identification with the target image data, and generate and store the association relationship between the lesion identification and the target image data.

4. The image data processing platform according to claim 2, characterized in that: The report processing module is also used to update the structured report data in response to a report editing operation input by a user, generate updated structured report data, and synchronize the updated structured report data to the RIS system.

5. The image data processing platform according to claim 2, characterized in that: The report processing module is also used to update the report template in response to a template editing operation input by a user, and generate an updated report template.

6. The image data processing platform according to claim 2, characterized in that: The target AI analysis result includes target image data, and the AI ​​data collaboration module is also used to process the target image data through an image post-processing algorithm to generate three-dimensional post-processed image data.

7. The image data processing platform according to claim 6, characterized in that: The AI ​​PACS system further includes an intelligent review module, which is used to display at least one of the original image data, the target image data, and the three-dimensional post-processed image data through the second window.

8. The image data processing platform according to claim 1, characterized in that: The target AI analysis result includes a positive result, the first window is further used to display a lesion key information list, and the second window is further used to display a lesion list; when the target AI analysis result is a positive result, the lesion list includes at least one lesion selection control; The RIS system is also used to update the structured report and the lesion key information list in response to the user's editing operation on the lesion selection control, and generate an updated structured report and an updated lesion key information list.

9. A method for processing image data, characterized in that: Applied to an image data processing platform, the image data processing platform includes an AIPACS system and a RIS system; the method includes: Standardize and format the acquired AI analysis results to generate structured report data, and synchronize the structured report data to the RIS system; The structured report data is displayed in a display interface through a first window; the structured report data is used to indicate a lesion identifier and lesion information corresponding to the lesion identifier; in response to a user clicking on the lesion identifier, a second window is created in the display interface, and the target image data corresponding to the lesion identifier is displayed through the second window; the AIPACS system stores an association relationship between the lesion identifier and the target image data; the first window is used to display an operation interface of the RIS system, and the second window is used to display an operation interface of the AIPACS system.

10. A computer device, characterized in that: The computer device includes one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the computer device, enable the computer device to execute the image data processing method described in claim 9.

Images