A method and device for assisting film reading, and a computer-readable storage medium

Abstract

The present invention discloses an auxiliary film reading method, including: obtaining first image information; the first image information is part of the image information generated during the diagnosis and treatment process; extracting identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information; searching for access data carrying the identity information; and obtaining second image information corresponding to the identity information based on the access data. According to the present invention, the identity information related to the patient number is obtained and identified, and the access address of the corresponding third-party imaging system is automatically spliced ​​according to the identity information to generate access data. This can reduce the manual operation of doctors entering identity information one by one during the film reading process, and seamlessly integrate into the business process of doctors reading films and writing reports without providing additional interface capabilities, thereby improving the work efficiency of doctors while lowering the docking threshold.

Description

Technical Field

[0001] The present invention relates to the field of medical devices, and in particular to an auxiliary film reading method and device. Background Art

[0002] Currently, the common diagnostic process in clinical imaging is that doctors make a diagnosis based on the patient's imaging data and then write a report.

[0003] Usually, doctors first obtain the patient ID, and then enter the patient ID into the imaging system to view the image. During the operation, the doctor must manually open the imaging system, enter the patient ID information to retrieve the image data, and finally view it. In the above operation process, if there is a slight input error, it will cause great trouble. At present, facing the environment of over-tight medical resources, the above operation process is very cumbersome and has a great impact on the work efficiency of doctors.

[0004] In order to solve the problem of efficiency of radiologists in reading films and writing reports, many AI-assisted diagnosis products have appeared on the market, providing some third-party systems to give intelligent diagnosis suggestions based on images to assist doctors in diagnosis. The process has improved the efficiency of doctors in giving subjective experience to influence the diagnosis results. However, it has not changed the complex manual operation process of doctors entering patient information data.

[0005] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0006] The purpose of the present invention is to provide an auxiliary film reading method and device, which can identify key information in the patient's medical record, and automatically match the key information with the imaging material, seamlessly integrate into the doctor's film reading and report writing business process, and do not need to provide additional interfaces, thereby improving the doctor's work efficiency while lowering the connection threshold.

[0007] Another purpose of the present invention is to optimize the recognition accuracy of medical records of special styles through multiple rules, and to adapt to the medical record rules of different hospitals, which is highly practical.

[0008] To achieve the above object, the present invention provides an auxiliary film reading method, the method comprising:

[0009] Acquire first image information; the first image information is part of the image information generated during the diagnosis and treatment process;

[0010] Extracting identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information;

[0011] Searching for access data carrying the identity information;

[0012] Second image information corresponding to the identity identification information is obtained based on the access data.

[0013] Preferably, extracting identity information based on the first image information includes:

[0014] Acquire specific location information in the first image information;

[0015] Obtain identity information from the specific location information.

[0016] Preferably, extracting identity information based on the first image information includes:

[0017] Dividing the first image information into at least one area to be identified;

[0018] Acquire regional feature information of the area to be identified;

[0019] Determining whether the regional characteristic information includes identity information;

[0020] If so, obtain the identity information in the first image information.

[0021] Preferably, dividing the first image information into at least one area to be identified includes:

[0022] Get the area division rule information;

[0023] The first image information is divided based on the area division rule information.

[0024] Preferably, the method further comprises:

[0025] The regional feature information of the to-be-identified area is acquired in sequence according to the size of the target weight value, and the size of the target weight value represents the probability that the to-be-identified area contains identity identification information.

[0026] Preferably, before obtaining the identity information, the method further includes:

[0027] Obtaining at least one type of identification rule information of the identity identification information and a priority sequence of the identification rule information;

[0028] The first identification information obtained from the specific location information or the regional feature information is converted into identity identification information according to the identification rule information and the priority sequence.

[0029] Preferably, the identification rule information includes at least one of the following: a whitelist rule, a specific location rule, a forced conversion rule, and a length rule.

[0030] The present invention also discloses an auxiliary film reading device, the device comprising:

[0031] A first acquisition unit is used to acquire first image information; the first image information is part of the image information generated during the diagnosis and treatment process;

[0032] An information extraction unit, configured to extract identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information;

[0033] A data search unit, used to search for access data carrying the identity information;

[0034] An information access unit is used to obtain second image information corresponding to the identity information based on the access data.

[0035] Preferably, the device comprises:

[0036] A second acquisition unit, used to acquire at least one identification rule information of the identity identification information and a priority sequence of the identification rule information;

[0037] The data conversion unit is used to convert the first identification information obtained from the specific location information or the regional feature information into the identity identification information according to the identification rule information and the priority sequence.

[0038] The present invention further discloses a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of an auxiliary film reading method as described in any one of the above items are implemented.

[0039] Compared with the prior art, the present invention automatically obtains and identifies identity information related to the patient number, automatically splices the access address of the corresponding third-party imaging system according to the identity information to generate access data, and opens the imaging system through the host system for viewing or downloading. This can reduce the manual operation of doctors entering identity information one by one during the film reading process, and seamlessly integrate into the business process of doctors reading films and writing reports without providing additional interface capabilities, thereby improving the work efficiency of doctors and lowering the connection threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of an auxiliary film reading method according to an embodiment of the present invention;

[0041] Figure 2 is a flow chart of an auxiliary film reading method according to an embodiment of the present invention;

[0042] Figure 3 is a structural diagram of an auxiliary film reading device according to an embodiment of the present invention;

[0043] Figure 4 4 is a structural diagram of an auxiliary film reading device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific implementation modes.

[0045] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0046] like Figure 1 to Figure 2 As shown, according to a preferred embodiment of the present invention, a method for assisting image reading comprises:

[0047] Step 101, obtain the first image information; the first image information is part of the image information generated in the reporting system. In a specific embodiment, when a patient goes to a medical institution for medical treatment, the first step is usually the registration stage. At this stage, the hospital's backend system will generate a corresponding patient number according to the patient's identity, such as a random number generated according to the hospital number arrangement rules. The number is the patient's identity information in the hospital, and it has a one-to-one correspondence with the patient's identity. In the present invention, after registration, the number immediately matches the patient's identity throughout the medical treatment process, and can be displayed in the form of an image in the reporting system used by the doctor. The relevant image may specifically include information such as the patient number and medical treatment request. In a specific embodiment of the present invention, the first image information can be the image displayed in the reporting system mentioned in the above description, which is usually displayed in the display device in the form of an image. In another specific embodiment of the present invention, the first image information can also be the image information generated by the patient during the first visit or multiple previous medical treatments.

[0048] Step 102, extracting identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information. Specifically, the identity information can be the patient's ID number, patient number or other information that can represent the patient's identity, and corresponds to the patient's identity one-to-one. As mentioned above, in the acquired first image information, part of the image information or a certain position of the first image information contains identity information. Therefore, in this step, the identity information can be extracted from the first image information obtained in step 101 to identify the patient corresponding to the first image information, that is, the unique number of the patient corresponding to the first image information can be confirmed by the identity information.

[0049] Step 103, searching for access data carrying the identity information. The access data carrying the identity information may be pre-stored, and when it is needed, it can be directly retrieved according to the identity information; or it may be access data with the identity information generated according to request information carrying the identity information, for example, the identity information is concatenated with the access address to form the access data. Specifically, the access data carrying the identity information may be a URL address containing the patient number, which can be directly used to access a third-party system.

[0050] Step 104, based on the access data, obtain the second image information corresponding to the identity information. Specifically, in a third-party imaging system of various imaging data of the patient, the identity information and the second image information also have a corresponding relationship, which means that each second image information corresponds to an identity information, so the relevant second image information can be matched through the identity information. In a preferred embodiment of the present invention, the third-party imaging system provides a retrieval tool based on the patient number. The ability to access image information is provided through a URL address containing patient number information.

[0051] In other specific embodiments of the present invention, when the second image information corresponding to the identity information is obtained based on the access data, auxiliary diagnosis information can be given based on the recognition of the second image information according to artificial intelligence technology and returned to the host system and provided to the doctor for diagnosis.

[0052] Through the method described in the above embodiment of the present invention, after obtaining and identifying the identity information related to the patient number, the access address of the corresponding third-party imaging system is automatically spliced ​​according to the identity information to generate access data, and the imaging system is opened through the host system for viewing or downloading. This can reduce the manual operation of doctors entering identity information one by one during the film reading process, and seamlessly integrate into the business process of doctors reading films and writing reports without providing additional interface capabilities, thereby improving the work efficiency of doctors and lowering the connection threshold.

[0053] In the above specific embodiments of the present invention, preferably, the data storage information of PACS is obtained using the universal DICOM protocol. DICOM (Digital Imaging and Communications in Medicine) is a medical digital imaging and communication, and the DICOM network is a network protocol based on TCP / IP. The imaging device and the storage management device are connected through DICOM. The DICOM protocol is a universal protocol for data transmission within the hospital, and no additional interface needs to be developed.

[0054] In an embodiment of the present invention, a method for assisting image reading, extracting identity information based on the first image information, includes:

[0055] Acquire specific location information in the first image information;

[0056] Obtain identity information from the specific location information.

[0057] In a specific embodiment of the present invention, the identity information appears in a relatively fixed position in the relevant page of the reporting system, such as the upper left corner, or within a certain size range of the page, and can be specifically identified by a relative coordinate system. Since the position is relatively fixed, it can be called specific position information in the embodiment of the present invention. Specifically, the specific position information is obtained, and the specific position information includes the first image information. Subsequently, the identity information in the specific position information is obtained by text recognition. For example, the patient number in the first image information is extracted by an OCR tool. This step can be implemented using a variety of data extraction methods and is not limited to the embodiments of the present invention.

[0058] In an auxiliary film reading method described in an embodiment of the present invention, when the position of the identity information is not fixed, extracting the identity information based on the first image information also includes other implementation methods. Specifically, the first image information is first divided into at least one area to be identified. That is, the first image information is divided into multiple areas so that each area can be identified separately. In a specific embodiment, the first image information can be divided into equal parts, or divided according to whether the first image information contains feature information or not, wherein the inclusion of feature information indicates that the area has text or image content, and the area that does not contain feature information is usually a blank part.

[0059] The regional characteristic information of the area to be identified is obtained. The regional characteristic information represents the characteristic information corresponding to the divided area to be identified, that is, the content contained in the area to be identified. For example, the regional characteristic information corresponding to the area to be identified containing identity information includes identity information.

[0060] Determine whether the region characteristic information contains identity information. In this step, it is necessary to analyze and determine the region characteristic information corresponding to multiple regions to be identified, so as to find the region to be identified that contains identity information.

[0061] If yes, then the identity information in the first image information is obtained. When it is determined that a certain area feature information contains identity information, the identity information in the area to be identified is extracted, which is equivalent to obtaining the identity information in the first image information.

[0062] In an auxiliary image reading method described in an embodiment of the present invention, dividing the first image information into at least one area to be identified includes:

[0063] Get the area division rule information;

[0064] The first image information is divided based on the area division rule information.

[0065] In a specific embodiment of the present invention, different area division rules affect the efficiency of subsequently obtaining the area feature information of the area to be identified. Therefore, when there are multiple different area division rules, the corresponding area division rule information is obtained according to the needs, and the first image information is divided according to the area division rule information.

[0066] An auxiliary film reading method described in an embodiment of the present invention further includes:

[0067] The regional feature information of the to-be-identified area is acquired in sequence according to the size of the target weight value, and the size of the target weight value represents the probability that the to-be-identified area contains identity identification information.

[0068] In a specific embodiment, the target weight value is calculated based on the probability of the identity identification information appearing. For example, if the probability of the identity identification information appearing in the upper left corner of the page is high, then the target weight value of the area to be identified corresponding to the upper left corner is high. Therefore, in this step, the regional feature information of the area is first obtained, and it is first determined whether the regional feature information contains the identity identification information. If it does, there is no need to extract the regional feature information of the remaining area to be identified and the subsequent step of determining whether the regional feature information contains the identity identification information, so as to improve the recognition efficiency.

[0069] In an embodiment of the present invention, the auxiliary film reading method further comprises, before obtaining the identity information:

[0070] Step 201: Obtain at least one type of identification rule information of the identity identification information and a priority sequence of the identification rule information.

[0071] Specifically, when the identity information is information such as a patient number, the patient number is usually composed of English letters and numbers, and although the patient numbers of different hospitals are different, they generally have their own rules. In order to improve the recognition accuracy of the identity information, the present invention also provides a variety of recognition rules that can adjust the recognition results. When there are multiple recognition rules, different types of recognition rules have applicable priorities, so in this step, the recognition rule information and the priority sequence of the recognition rule information are first obtained for subsequent application.

[0072] Step 202, convert the first identification information obtained from the specific location information or regional characteristic information into identity identification information according to the identification rule information and the priority sequence. In a specific embodiment, the first identification information refers to the relevant content extracted from the specific location information or regional characteristic information. Specifically, the first identification information refers to information related to the identity identification information. For example, the first identification information is the identity identification information, or there is more than 50% similarity between the two. After the first identification information is obtained, the first identification information is the content extracted from the specific location information or regional characteristic information. The first identification information is first adjusted by the identification rule information to convert it into identity identification information. In a more specific embodiment, the conversion is performed according to the preferred sequence of each identification rule information. For example, the identification rule information with the preferred sequence in front is applied first.

[0073] In another preferred embodiment, when the first identification information is the identity identification information, the first identification information is directly used as the identity identification information without performing the processes of steps 201 and 202 .

[0074] In an auxiliary film reading method described in an embodiment of the present invention, the identification rule information includes at least one of the following: a whitelist rule, a specific location rule, a forced conversion rule, and a length rule.

[0075] The following is a similar explanation of different identification rule information.

[0076] The whitelist rule is specifically: only characters in the whitelist are retained, and characters not in the whitelist are discarded. In this way, some obvious recognition errors can be deleted during the recognition process to correct the recognition errors.

[0077] The specific position rule is specifically: forcibly converting the characters at the specific position in the first identification information into fixed characters. For example, in the actual hospital management process, each hospital system has its own specific numbering format, among which the more common one is the fixed prefix. For example, the patient numbers of some hospitals are all GZP000****, where **** are different numbers, but GZP000 is fixed. By setting such a rule, the first 6 digits of the recognition result can be fixed.

[0078] The forced conversion rule is as follows: the recognition result of a specific character is forced to be converted into another fixed character. In the recognition process example, the capital letter I and the number 1 are more likely to be misidentified. However, in a specific environment, the patient number may not contain I. Therefore, if the first recognition information of the original recognition contains I, it is actually a misjudgment and should be 1. In this way, the recognition result I can be directly converted to 1.

[0079] The length rule is specifically: forcibly truncating a character string of a fixed length from the front or back as the final recognition result, which can be used to remove noise in the recognition result.

[0080] In a preferred embodiment of the present invention, the above identification rule information has applicable priorities, specifically, whitelist rules take precedence over specific location rules, specific location rules take precedence over forced conversion rules, and forced conversion rules take precedence over length rules.

[0081] Of course, the specific embodiments of the present invention are not limited to the several types of identification rule information listed above, and other similar rules to the identification rule information described in the embodiments of the present invention should also fall within the scope of protection of the present invention.

[0082] The present invention also provides an auxiliary film reading device, such as Figure 3 As shown, the device comprises:

[0083] The first acquisition unit 301 is used to acquire first image information; the first image information is part of the image information generated during the diagnosis and treatment process;

[0084] An information extraction unit 302 is used to extract identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information;

[0085] A data search unit 303, used to search for access data carrying the identity information;

[0086] The information access unit 304 is used to obtain second image information corresponding to the identity information based on the access data.

[0087] An auxiliary film reading device according to an embodiment of the present invention, such as Figure 4 As shown, the device comprises:

[0088] The second acquisition unit 401 is used to acquire at least one identification rule information of the identity identification information and a priority sequence of the identification rule information;

[0089] The data conversion unit 402 is used to convert the first identification information obtained from the specific location information or the regional feature information into identity identification information according to the identification rule information and the priority sequence.

[0090] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of an auxiliary film reading method as described in any one of the above specific embodiments are implemented.

[0091] In summary, the embodiments of the present invention have the following advantages:

[0092] 1. It can be seamlessly integrated into the doctor's business process of reading films and writing reports, without the need for the PACS system to provide additional interface capabilities. It improves the doctor's work efficiency while lowering the integration threshold.

[0093] 2. In view of the particularity of patient numbers, special rules are provided to optimize the recognition accuracy. It can adapt to the patient numbering rules of different hospitals and has strong practicality.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] The foregoing description of specific exemplary embodiments of the present invention is for the purpose of illustration and demonstration. These descriptions are not intended to limit the present invention to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present invention and its practical application, so that those skilled in the art can realize and utilize various different exemplary embodiments of the present invention and various different selections and changes. The scope of the present invention is intended to be limited by the claims and their equivalents.

Claims

1. A method for assisting film reading, characterized in that: The method comprises: Acquire first image information; the first image information is part of the image information generated during the diagnosis and treatment process; Extracting identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information; Searching for access data carrying the identity information; Obtaining second image information corresponding to the identity information based on the access data; The step of extracting the identity information based on the first image information includes: Dividing the first image information into at least one area to be identified; Acquire regional feature information of the area to be identified; Determining whether the regional characteristic information includes identity information; If yes, obtaining the identity information in the first image information; Wherein, dividing the first image information into at least one area to be identified includes: Get the area division rule information; Divide the first image information based on the area division rule information; Wherein, the method further comprises: The regional feature information of the to-be-identified area is acquired in sequence according to the size of the target weight value, and the size of the target weight value represents the probability that the to-be-identified area contains identity identification information.

2. The method for assisting image reading as claimed in claim 1, characterized in that: Extracting identity information based on the first image information includes: Acquiring specific location information in the first image information; Obtain identity information from the specific location information.

3. The method for assisting image reading as claimed in claim 1, characterized in that: Before obtaining the identity information, the method further includes: Obtaining at least one type of identification rule information of the identity identification information and a priority sequence of the identification rule information; The first identification information obtained from the specific location information or the regional feature information is converted into identity identification information according to the identification rule information and the priority sequence.

4. The method for assisting image reading as claimed in claim 3, characterized in that: The identification rule information includes at least one of the following: a whitelist rule, a specific location rule, a forced conversion rule, and a length rule.

5. A device for assisting film reading, characterized in that: The device comprises: A first acquisition unit is used to acquire first image information; the first image information is part of the image information generated during the diagnosis and treatment process; An information extraction unit, configured to extract identity information based on the first image information; the identity information is used to identify the identity attribute of the first image information; A data search unit, used to search for access data carrying the identity information; An information access unit, configured to obtain second image information corresponding to the identity information based on the access data; The step of extracting the identity information based on the first image information includes: Dividing the first image information into at least one area to be identified; Acquire regional feature information of the area to be identified; Determining whether the regional characteristic information includes identity information; If yes, obtaining the identity information in the first image information; Wherein, dividing the first image information into at least one area to be identified includes: Get the area division rule information; Divide the first image information based on the region division rule information; The regional feature information of the to-be-identified area is acquired in sequence according to the size of the target weight value, and the size of the target weight value represents the probability that the to-be-identified area contains identity identification information.

6. The auxiliary film reading device according to claim 5, characterized in that: The device comprises: A second acquisition unit, used to acquire at least one identification rule information of the identity identification information and a priority sequence of the identification rule information; The data conversion unit is used to convert the first identification information obtained from the specific location information or the regional feature information into the identity identification information according to the identification rule information and the priority sequence.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the auxiliary film reading method according to any one of claims 1 to 4 are implemented.

Images