CN116724357A - Medical image contour sketching method, device and system - Google Patents
Medical image contour sketching method, device and system Download PDFInfo
- Publication number
- CN116724357A CN116724357A CN202080108244.5A CN202080108244A CN116724357A CN 116724357 A CN116724357 A CN 116724357A CN 202080108244 A CN202080108244 A CN 202080108244A CN 116724357 A CN116724357 A CN 116724357A
- Authority
- CN
- China
- Prior art keywords
- medical image
- sketching
- target
- sketched
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000004891 communication Methods 0.000 claims description 20
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 14
- 206010028980 Neoplasm Diseases 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000001959 radiotherapy Methods 0.000 description 3
- 210000001015 abdomen Anatomy 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 235000014510 cooky Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
Abstract
Medical image contour sketching method, device and system: acquiring a medical image to be sketched of a first target device (11); inputting the medical image to be sketched into a target sketching model; carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result; pushing the sketching result to a second target device (12), wherein the second target device (12) and the first target device (11) are the same device or different devices. And the medical image of the patient is automatically contoured through the target contoured model, and finally, the contoured result is pushed to the second target device (12), so that the accuracy of the medical image contoured is improved and the contoured efficiency is improved compared with the manual contoured operation in the related art.
Description
The application relates to the technical field of artificial intelligent medical images, in particular to a medical image contour sketching method, device and system.
In the tumor treatment process, the accurate sketching of a target area, the accurate design of a treatment plan and the accurate irradiation are indispensable in three links. The accurate sketching of the target area is a precondition, once the target area sketches a problem, the two later links can both have corresponding problems, which can lead to the increase of the secondary distant transfer rate of the patient, the decrease of the total survival rate and seriously affect the life quality of the patient. Therefore, it is very important to ensure the accuracy of the target delineation.
In recent years, throughout medical institutions, more and more medical devices are automatically operated, but in the process of medical image contour sketching, for example, target area sketching, the medical image contour sketching and treatment planning are completed on one device in the related art, and the sketching is required to be performed manually, so that the sketching efficiency is low.
Disclosure of Invention
Accordingly, one of the technical problems to be solved by the embodiments of the present application is to provide a medical image contour tracing method, apparatus, system and storage medium for overcoming the above-mentioned drawbacks.
In a first aspect, an embodiment of the present application provides a medical image contouring method, including: acquiring a medical image to be sketched of first target equipment; inputting the medical image to be sketched into a target sketching model; carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result; and pushing the sketching result to second target equipment, wherein the second target equipment and the first target equipment are the same equipment or different equipment.
In a second aspect, an embodiment of the present application provides a medical image contouring method, including: automatically acquiring at least one medical image to be sketched; inputting the at least one medical image to be sketched into a target sketching model, wherein the target sketching model is a trained deep neural network model; automatically outlining the at least one medical image to be outlining by utilizing the target outlining model to obtain at least one outlining result; and automatically pushing the at least one sketching result.
In a third aspect, an embodiment of the present application provides a medical image contouring method, including: medical images to be sketched acquired from different devices; inputting the medical image to be sketched into a target sketching model; carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result; pushing the sketching result to the different device.
In a fourth aspect, an embodiment of the present application provides a medical image contouring apparatus, including: a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to implement the method of any of the embodiments of the present application.
In a fifth aspect, embodiments of the present application provide a medical image contouring system, the system comprising: the medical image contouring apparatus of the fourth aspect, and a first target device and a second target device, the second target device being the same device or different devices from the first target device.
In a sixth aspect, embodiments of the present application provide a storage medium storing computer executable instructions that, when executed, implement the method described in any of the embodiments of the present application.
The application provides a medical image contour sketching method, a device, a system and a storage medium: acquiring a medical image to be sketched of first target equipment; inputting the medical image to be sketched into a target sketching model; carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result; and pushing the sketching result to second target equipment, wherein the second target equipment and the first target equipment are the same equipment or different equipment. According to the application, the medical image of the patient is automatically contoured through the target contoured model, and finally the contoured result is pushed to the target equipment, so that compared with the manual contoured method in the related art, the contoured accuracy of the medical image is improved, and the contoured efficiency is also improved.
Some specific embodiments of the application will be described in detail hereinafter by way of example and not by way of limitation with reference to the accompanying drawings. The same reference numbers will be used throughout the drawings to refer to the same or like parts or portions. It will be appreciated by those skilled in the art that the drawings are not necessarily drawn to scale. In the accompanying drawings:
FIG. 1 is a schematic diagram of a medical image contouring system according to an embodiment of the present application;
FIG. 2 is a flow chart of a medical image contouring method provided by an embodiment of the present application;
FIG. 3 is a schematic diagram showing a sketching progress provided in an embodiment of the present application;
fig. 4 is a schematic diagram of a structure of an electronic device according to an embodiment of the present application.
FIG. 5 is a schematic diagram of a medical image contouring system according to an embodiment of the present application;
fig. 6 is a schematic diagram of another medical image contouring system according to an embodiment of the present application.
The implementation of the embodiments of the present application will be further described below with reference to the accompanying drawings.
For easy understanding, the present solution first briefly introduces a medical image contouring system to which the medical image contouring method is applied.
A schematic diagram of a medical image contouring system is given with reference to fig. 1, the system comprising a medical image contouring device 10 for contouring a medical image and obtaining a contouring result; a first target device 11 and a second target device 12, wherein the first target device 11 may be used for storing non-sketched medical images and the second target device 12 may be used for receiving the sketching result sent by the medical image sketching means 10. It should be noted that the first target device and the second target device may be the same device or different devices, and fig. 1 shows a case where the first target device and the second target device are different devices.
The following describes a medical image contour sketching method applied to the medical image contour sketching system, and an embodiment of the present application provides a medical image contour sketching method, as shown in fig. 2, including the following steps:
step 101, acquiring a medical image to be sketched of a first target device.
In this embodiment, the medical image contouring device acquires a medical image to be contoured of the first target device, where the medical image to be contoured may be one or a group of lesion images captured in advance, such as a CT image (Computed Tomography, electronic computed tomography), or an MRI image (Magnetic Resonance Imaging ), or an ultrasound image, or may be a medical image obtained by other forms.
In this embodiment, the first target device is one of multiple devices, and the first target device may be one of multiple devices in a certain hospital or one of multiple devices in a different hospital, which is not limited in this embodiment. Illustratively, the first target device may be a server locally disposed in a hospital, such as a treatment planning system (Treatment Planning System, TPS) server, a tumor information management system (Oncology Information System, OIS) server, an image server, or the like, and may be a client, such as: computers, mobile terminals (e.g., cell phones, notebook computers), etc.
The embodiment for acquiring the medical image to be sketched of the first target equipment by the medical image sketching device comprises the following steps:
in a first embodiment, the medical image contouring apparatus acquires a medical image to be contoured of a first target device by receiving the medical image to be contoured pushed by the first target device.
In a second embodiment, the medical image contouring apparatus automatically acquires a medical image to be contoured from a first target device.
Taking the example that the first target device is a TPS server, the medical image contour sketching device may receive a medical image to be sketched pushed by the TPS server of the hospital (that is, the TPS server actively pushes the medical image to be sketched to the medical image contour sketching device), or may actively and automatically acquire the medical image to be sketched from the TPS server.
The two embodiments for acquiring the medical image to be sketched of the first target device will be described in detail below.
For the first embodiment, before receiving the medical image to be sketched pushed by the first target device, the medical image sketching device establishes communication connection with the first target device, and then receives the medical image to be sketched sent by the first target device. The medical image contouring device may, for example, establish a communication connection with the first target device according to the IP and the port number of the first target device through a DICOM communication protocol, and then receive the medical image to be contoured sent by the first target device.
For the second embodiment, before the medical image contour sketching device automatically acquires the medical image to be sketched from the first target device, firstly querying the medical image which is not sketched in the first target device, then acquiring the medical image which is not sketched, and taking the acquired medical image which is not sketched as the medical image to be sketched. Before querying an undepicted medical image in a first target device, the medical image contouring means needs to pre-establish a communication connection with the first target device. Similar to the first embodiment, the communication connection with the first target device may be established according to the IP and the port number of the first target device through the DICOM communication protocol, and then the medical image to be sketched may be automatically searched and acquired from the first target device.
In a second embodiment, when querying whether an undepicted medical image exists in the first target device, the medical image contour sketching apparatus may query whether each medical image in the first target device has a corresponding sketching file, if the first medical image in the first target device does not have a corresponding sketching file, it indicates that the first medical image is the undepicted medical image, and the medical image contour sketching apparatus needs to acquire the first medical image and sketch the first medical image. If a corresponding sketching file exists in a first medical image in the medical images in the first target equipment, the first medical image is a sketched medical image, and the medical image outline sketching device does not need to acquire the first medical image.
It should be noted here that "first" of the "first medical images" herein is only for distinguishing medical images, and indicates one or more medical images among the medical images stored by the first target device, and does not indicate the number or order of medical images.
It should be noted that the at least one medical image to be sketched may be a medical image of a patient from a different hospital, or may be a medical image of a different patient in the same hospital.
After the target sketching model is utilized to carry out automatic sketching on the medical image to be sketched, and a sketching result is obtained, the medical image sketching device can also automatically acquire the next medical image to be sketched and carry out automatic sketching on the next medical image to be sketched. Here, the next medical image to be sketched may be the medical image to be sketched of the first target device, or may be the medical image to be sketched of another device different from the first target device.
Before the medical image to be sketched of the first target device is acquired, the medical image outline sketching device can adjust the sequence of the medical image to be sketched according to sequence adjustment information input by a target user.
The target user is a doctor A of the hospital A, data communication can be carried out between a user side used by the doctor A and the medical image contour drawing device, patient information under the name of the doctor A can be displayed on the user side used by the doctor A, and according to actual requirements, the doctor A can adjust the sequence of the patients through a control displayed on a display interface of the user side, such as an up-shift or down-shift or top-set button; the user side obtains the sequence adjustment information of the buttons triggered by the doctor A and sends the sequence adjustment information to the medical image contour drawing device, and the medical image contour drawing device adjusts the sequence of the medical images to be drawn of the corresponding patient after receiving the sequence adjustment information (such as up-shift, down-shift or top-set information).
It should be noted that, for doctor a of the general user hospital a, the authority is to adjust the medical image to be sketched of the patient under the name of the doctor a, but not adjust the medical images to be sketched corresponding to the patients of other doctors, so that only the patient information of the doctor a is displayed on the user terminal display interface of the doctor a, and only the medical image to be sketched of the patient under the name of the doctor a can be adjusted.
For example, assume that the corresponding identification of 10 medical images to be delineated is "0-1-2-3-4-5-6-7-8-9", wherein the medical images identified as 2, 5, 7 are from patient 1, patient 2, and patient 3 of doctor A of hospital A, the remaining images are from other doctors, if the order adjustment information entered by doctor A is to set patient 3 on top, i.e., the patient order is adjusted to: patient 3, patient 1, patient 2, respectively, changed in order to "0-1-7-3-4-2-6-5-8-9".
Of course, the authority of the target user may be set as required, for example, the target user is an administrator of the hospital first, and the order of the patients of all doctors of the hospital first may be adjusted, which is not particularly limited herein.
Step 102, inputting the medical image to be sketched into a target sketching model.
Here, the target delineation model may be a pre-trained neural network model. In short, the neural network model is obtained by optimizing and training based on a deep neural network algorithm by utilizing as many medical image samples as possible and accurate sketching results corresponding to the medical image samples.
In an embodiment, the medical image contouring device embeds a target contouring model, and after the medical image to be contoured of the first target device is acquired, the medical image contouring device inputs the medical image to be contoured into the target contouring model for automatic contouring.
In another embodiment, the medical image contour sketching device includes a plurality of (i.e. at least two) sketching models, before the medical image to be sketched is input into the target sketching model, the target sketching model needs to be determined from the plurality of sketching models, and in more detail, the medical image contour sketching device determines the target sketching model corresponding to the object to be sketched in the plurality of sketching models based on the object to be sketched in the medical image to be sketched.
Here, the plurality of sketching models may be generated according to the object to be sketched, and different sketching models may sketch different objects.
In an example, the object to be delineated comprises one or more of a tumor, a body organ or tissue, or the like. If the object to be sketched in the medical image to be sketched comprises a tumor, its corresponding target sketching model comprises a sketching model for the tumor, if the object to be sketched in the medical image to be sketched comprises a body organ, such as a heart, its corresponding target sketching model comprises a sketching model for the heart, if the object to be sketched in the medical image to be sketched comprises both a target region and a body organ, such as a heart, its corresponding target sketching model comprises a sketching model for the target region and a sketching model for the heart.
In another example, the object to be sketched includes one or more of a head, a head-neck, a chest, an abdomen, a leg, and the like. If the object to be sketched in the medical image to be sketched comprises a head, the corresponding target sketching model comprises a sketching model aiming at the head, if the object to be sketched in the medical image to be sketched comprises a head and a neck, the corresponding target sketching model comprises a sketching model aiming at the head and the neck, and if the object to be sketched in the medical image to be sketched comprises the head and the neck and the chest, the corresponding target sketching model comprises a sketching model aiming at the head and the neck and a sketching model aiming at the chest.
And 103, automatically outlining the medical image to be sketched by utilizing the target sketching model to obtain a sketching result.
After the medical image to be sketched is input into the target sketching model, the medical image outline sketching device utilizes the target sketching model to carry out automatic outline sketching on the medical image to be sketched, and a sketching result is obtained.
Further, the medical image contour sketching device can perform automatic contour sketching on the medical image to be sketched through the following steps of:
and automatically sketching the outline of the object to be sketched in the medical image to be sketched by utilizing the target sketching model to obtain a sketching result.
It should be noted that, the sketching result includes at least one outline of the sketching object, for example, if the object to be sketched includes a tumor and a lung, the target sketching model may be a sketching model for the tumor and the lung, and the outlines of the tumor and the lung in the medical image to be sketched are sketched automatically by using the models to obtain the sketching result, where the sketching result includes the outlines of the tumor and the lung; if the object to be sketched comprises a chest, the target sketching model can be a sketching model aiming at the chest, the chest in the medical image to be sketched is automatically sketched by using the models to obtain a sketching result, and the sketching result comprises outlines of all organs and tissues in the chest and can also comprise outlines of tumors.
In order to improve the sketching speed, the medical image sketching device can also utilize a target sketching model to simultaneously and automatically sketch a plurality of medical images to be sketched in parallel, so as to obtain a plurality of sketching results. For example, a plurality of medical images to be sketched, the object to be sketched being a head, and a plurality of medical images to be sketched, the object to be sketched being a chest, may be sketched in parallel; of course, the medical images to be sketched can be divided into a plurality of groups, and each group of target sketching models respectively sketches the medical images corresponding to the respective groups.
In this embodiment, the medical image contour sketching device may sketch a plurality of acquired medical images to be sketched in parallel, or may sketch the medical images sequentially in a certain order, which is not limited in this embodiment. For example, if the medical image to be delineated is an abdominal image of 5 different patients such as ABCDE, the medical image contouring device may automatically delineate the 5 medical images to be delineated simultaneously using a target delineation model for delineating the abdomen.
Further, for a target user, such as doctor A, in the multiple users, communication connection can be established between the user end used by the target user and the medical image delineation device, so as to check the delineation conditions of the medical images of all the corresponding patients.
In more detail, the target user can input login information through the user terminal, and the medical image contour tracing device acquires the login information of the target user and judges whether the login information of the target user is correct. The login information comprises a password or a face image or an iris image.
When the login information of the target user is confirmed to be correct, the sketching progress information of the medical image corresponding to the target user is sent to the user side of the target user, and the sketching progress information comprises at least one of the following information: (1) A sketched medical image list, a non-sketched medical image list, and a sketched failed medical image list; (2) sketching progress of medical images corresponding to the target user; (3) a delineating progress of the medical image being delineated. Therefore, the sketching progress information can be displayed on the interface of the user side of the target user, and the target user can know the sketching condition of the medical images of all patients through the sketching progress information.
When the login information of the target user is incorrect, the prompt information of login failure is sent to the user side of the target user, and the user side of the target user displays the prompt information of login failure. Here, the interface of the user side may be a displayed web interface, a program interface, or the like.
It should be noted that, for a patient who fails in delineating, the medical image delineating device may further analyze the cause of the failure in delineating and send the result to the user side of the target user, and after the target user modifies, the medical image is sent to the medical image delineating device again for delineating.
Optionally, the medical image contour sketching device sends the sketching progress information to the user side of the target user once every preset time. For example, the sketched progress information may be sent every 30 seconds, so that the displayed sketched progress information may be refreshed every 30 seconds.
It should be noted that, the drawing progress information obtained by the medical image drawing device may be actively sent by the target user through the user side, or may be automatically sent by the user side after the target user logs in the user side.
The above-mentioned sketching progress information of the medical image may be displayed in a manner of a cookie or a progress bar, as shown in fig. 3, the left diagram of fig. 3 shows a schematic diagram of displaying the sketching progress of the medical image being sketched in a manner of a cookie, and the right diagram shows a schematic diagram of displaying the sketching progress of the medical image being sketched in a manner of a progress bar.
For example, assuming that the doctor A of the target user corresponds to the medical images of 8 patients, if the sketching progress information is a sketched medical image list, a non-sketched medical image list and a sketched medical image list, displaying the sketched medical image list, the non-sketched medical image list and the sketched medical image list on a user terminal used by the doctor A of the target user; if the sketching progress information is the sketching progress of the medical image corresponding to the doctor A of the target user, as shown in fig. 2, wherein 'completed' indicates that the medical image of 6 patients is sketched (accounting for 75%), 'unfinished' indicates that the medical image of 2 patients is not sketched or is not sketched (25%), and the sketching failure is 0 (not shown); if the sketching progress information is a sketching progress for the medical image being sketched (assuming that the 2 nd patient is currently being sketched), then "completed" in fig. 3 indicates that 75% of the medical image is currently being sketched, and 25% remains undepicted (i.e., unfinished).
For the target user, the sketching result of the target patient can be checked based on the communication connection between the user side used by the target user and the medical image sketching device. Here, in more detail, the target user may send request information through the user side to request to view the sketching result of the target patient, the medical image sketching device obtains the request information of the target user, obtains the sketching result of the target patient corresponding to the target user according to the request information, and sends the sketching result of the target patient to the user side of the target user, and the user side of the target user receives and displays the sketching result of the target patient.
Step 104, pushing the sketching result to a second target device, wherein the second target device and the first target device are the same device or different devices.
In this embodiment, the medical image contour sketching device performs automatic contour sketching on the medical image to be sketched by using a target sketching model, and pushes the sketching result to the second target device after the sketching result is obtained.
Here, the second target device may be the same device or different devices from the first target device, and the second target device may be a server locally disposed in a hospital, for example, a TPS server, an OIS server, an image server, or may be a user side, for example: computers, mobile terminals (e.g., cell phones, notebook computers), etc.
When the second target device is the same device as the first target device, the first target device is illustratively the same server of the same hospital as the second target device, e.g., a TPS server. The medical image contour sketching device acquires a medical image to be sketched from a TPS server local to a hospital, performs automatic contour sketching, and feeds back a sketching result to the TPS server of the hospital.
When the second target device and the first target device are different devices, in an example, the first target device and the second target device may be different servers of the same hospital, for example, the first target device may be an image server of the hospital first storing medical images to be sketched, the second target device may be a TPS server of the hospital first for confirming the sketched result of the automatic sketching and making a treatment plan of the patient according to the sketched result, in another example, the first target device and the second target device may be servers of different hospitals, for example, the first target device may be a server of the hospital first storing medical images to be sketched, the second target device may be a server of the hospital second, the second target device may be used for confirming the sketched result of the automatic sketching and making a treatment plan according to the sketched result, so that medical resource sharing can be achieved, and medical resource distribution imbalance is reduced.
The medical image contour sketching device can encapsulate the sketching result according to the DICOM protocol and send the encapsulated sketching result to the second target equipment, so that pushing of the sketching result is safer and more reliable.
Further, the user can manually adjust the sketching result of the automatic sketching.
And the medical image of the patient is automatically contoured through the target contoured model, and finally, the contoured result is pushed to the second target device, so that the contoured accuracy of the medical image is improved and the contoured efficiency is also improved compared with the manual contoured operation in the related art.
In an alternative embodiment, the medical image contour sketching device may automatically acquire at least one medical image to be sketched, and then input the at least one medical image to be sketched into a target sketching model, where the target sketching model is a trained deep neural network model; then, automatically outlining the at least one medical image to be outlining by utilizing the target outlining model to obtain at least one outlining result; and finally, automatically pushing the at least one sketching result. The above-mentioned alternative embodiment can realize the full-process automation of acquiring, sketching and pushing the medical image, does not need manual participation, and greatly improves the sketching efficiency.
The medical image contour sketching device does not actively send a sketching result to a user side of a target user, and when the user wants to view the sketching result, the user side of the target user sends request information to the medical image contour sketching device, and the medical image contour sketching device receives the request information of the target user, wherein the request information is used for requesting to view the sketching result of a target patient; according to the request information, acquiring a sketching result of the target patient from at least one sketching result; and then sending the sketching result of the target patient to the user side of the target user. Therefore, in the whole sketching flow, only when a user needs to request to check the sketching result, the sketching result is fed back to the user side of the user for checking, and the checking process does not have any influence on the sketching.
In another optional embodiment, the medical image contour sketching device may obtain medical images to be sketched from different devices, then input the medical images to be sketched into a target sketching model, and then perform automatic contour sketching on the medical images to be sketched by using the target sketching model to obtain a sketching result; and finally, pushing the sketching result to different equipment. The medical image to be sketched comes from different equipment, and after the medical image outline sketching device finishes automatic sketching, the sketching result is pushed back to the different equipment, so that the sharing of resources is realized.
Based on the medical image contouring method described in the above embodiment, an embodiment of the present application provides a medical image contouring device, as shown in fig. 4, including: a processor (processor) 402; and a memory (memory) 404 configured to store computer-executable instructions that, when executed, cause the processor 402 to implement the methods described in any of the embodiments of the present application.
Optionally, the medical image contouring device may further include a bus 406 and a communication interface (Communications Interface) 408, and the processor 402, the communication interface 408, and the memory 404 may communicate with each other via the communication bus 406.
A communication interface 408 for communicating with other devices.
The processor 402 may be a Central Processing Unit (CPU), or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
The memory 404, which may comprise high-speed RAM memory, may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Based on the medical image contouring method described in the above embodiments, embodiments of the present application provide a storage medium storing computer-executable instructions that, when executed, implement the method described in any of the embodiments of the present application.
In an alternative embodiment, the medical image contouring means may be a local server. In this embodiment, the target sketching model may be a convolutional neural network model, which is built in the medical image contour sketching device, when the target sketching model is set in the local server, after the local server sketches the medical image through the convolutional neural network model in the medical image contour sketching device, the obtained sketching result may be temporarily stored in the local server, and if the stored sketching result is more, the target sketching result may be transferred to the cloud server. For example, the sketching results in the local server may be transmitted to the cloud server of the hospital for storage based on the communication connection established between the cloud server and the local server.
In another alternative embodiment, the medical image contouring device may be a cloud server. That is, the target sketching model may be set in the cloud server, after the cloud server sketches the medical image through the convolutional neural network model (target sketching model), the obtained sketching result may be stored in the cloud server, when a doctor or other management staff in the hospital wants to view the sketching result, the sketching result in the cloud server may be transmitted to the user side of the doctor corresponding to the hospital according to the ID number of the user doctor based on the communication connection established between the cloud server and the user side of the doctor, so that the doctor can read, write or use the sketching result. Optionally, after the cloud server draws the medical image through the convolutional neural network model and obtains the sketching result, the cloud server can automatically push the sketching result to a local server of a hospital to realize backup of the sketching result, so that the efficiency of checking the sketching result by medical staff of the corresponding hospital can be improved, the problem that the speed is low when a plurality of medical staff of different hospitals check the sketching result from the cloud server is avoided, and the fact that the sketching result is timely obtained from the local server when the cloud server fails can be ensured, so that the production of a treatment plan is prevented from being delayed.
The embodiment of the application provides a medical image contour sketching system. Here, the system is described by way of two examples:
optionally, as shown in fig. 5, fig. 5 is a schematic diagram of a medical image contouring system provided in the present embodiment. In a first example, a medical image contouring system includes: a medical image delineating means 30, and a first target device 31 and a second target device 32. A first target device 31 for storing non-delineated medical images and selecting at least one non-delineated medical image to send to the medical image contouring means; a second target device 32 for receiving the delineation result sent by the medical image delineation apparatus.
In this embodiment, the medical image contouring device 30 is a cloud server, and the first target device 31 stores medical images, which are not delineated, of a hospital, and may be the same hospital or different hospitals, and fig. 5 shows a case where the first target device 31 belongs to different hospitals. The first target device 31 may actively send the medical image to be sketched to the medical image sketching apparatus 30, and after the medical image is received by the medical image sketching apparatus 30, the medical image is used as a medical image to be sketched, and the medical images to be sketched are automatically sketched through a target sketching model, so as to obtain a sketching result. The medical image delineation device 30 may then send the obtained delineation result to the second target device 32, and of course, the medical image delineation device 30 may also send the obtained delineation result to the first target device 31, which is not limited in this embodiment.
Optionally, in a second example, as shown in fig. 6, fig. 6 is a schematic diagram of another medical image contouring system provided in this embodiment, where the medical image contouring system includes: the medical image contouring device 30 'and the first target equipment 31', wherein the first target equipment 31 'is used for storing medical images which are not contoured and receiving the contoured result sent by the medical image contouring device 30'.
In the present embodiment, the medical image contouring apparatus 30' is exemplified by the local server 1 of the first hospital, and the first target device 31' may be other local servers of the first hospital, and it is understood that the first target device 31' may be plural, and only one local server 2 is illustrated in the figure as an example. The medical image contour sketching device 30 '(the first hospital local server 1) may actively acquire an undepicted medical image from the first target device 31' (the first hospital local server 2), or the first target device 31 'may actively send the undepicted medical image to the medical image contour sketching device 30', which is not limited in this embodiment. The medical image contour sketching device 30' uses the obtained medical image which is not sketched as the medical image to be sketched, and automatically sketches the medical image to be sketched through the target sketching model to obtain a sketching result. The medical image delineation device 30 'may then send the resulting delineation result to the first target apparatus 31'.
It should be noted that, the first target device 31' may communicate with a plurality of user terminals 33' of the hospital, and the doctor may log in an ID number of the doctor on any user terminal 33', and then obtain, from the first target device 31', a sketching result of a medical image of the patient corresponding to the ID number through the user terminal 33' for viewing and using. Alternatively, the doctor may log in his own account number on his own user terminal, for example, a mobile phone, and obtain, from the first target device 31', a sketching result of the medical image of the patient under his own name for viewing and use.
Optionally, the systems of the above two examples may further include a user side (in fig. 5 corresponding to the first example, a radiotherapy device is taken as an example, and in fig. 6 corresponding to the second example, a computer is taken as an example), and the user side 33 in fig. 5 may be configured to obtain the sketching result from the medical image sketching device 30, the first target device 31, or the second target device 32; the user terminal 33' in fig. 6 may be configured to obtain the delineation result from the medical image delineation device 30' or the first target equipment 31 '. The doctor can make a treatment plan for the patient according to the obtained sketching result. It should be noted that, each first target device 31 may communicate with a user side (illustrated as a radiotherapy device in the drawing) of at least one corresponding hospital, and it is understood that 2 radiotherapy devices in fig. 5 are only examples.
Based on the medical image contouring method described in the above embodiments, embodiments of the present application provide a storage medium storing computer-executable instructions that, when executed, implement the method described in any of the embodiments of the present application.
Thus, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.
The method set forth in the above embodiment may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular transactions or implement particular abstract data types. The application may also be practiced in distributed computing environments where transactions are performed by remote processing devices that are connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (21)
- A medical image contouring method, the method comprising:acquiring a medical image to be sketched of first target equipment;inputting the medical image to be sketched into a target sketching model;carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result;and pushing the sketching result to second target equipment, wherein the second target equipment and the first target equipment are the same equipment or different equipment.
- The method of claim 1, wherein the acquiring the medical image to be sketched of the first target device comprises:a medical image to be delineated is automatically acquired from a first target device.
- The method of claim 2, wherein the automatically acquiring the medical image to be sketched from the first target device comprises:querying medical images which are not sketched in the first target device;and acquiring the undepicted medical image, and taking the undepicted medical image as the medical image to be sketched.
- The method of claim 3, wherein prior to the querying the non-delineated medical image in the first target device, the method further comprises:and establishing a communication connection with the first target equipment through a DICOM communication protocol.
- The method of claim 3, wherein the querying of the non-delineated medical image in the first target device comprises:inquiring a medical image in the first target device, and if a first medical image in the medical images does not have a corresponding sketching file, determining that the first medical image is an undepicted medical image.
- The method of claim 5, wherein the sketch file is an Rt struct file.
- The method of claim 1, wherein the acquiring the medical image to be sketched of the first target device comprises:and receiving the medical image to be sketched pushed by the first target equipment.
- The method of claim 7, wherein receiving the medical image to be sketched pushed by the first target device comprises:establishing a communication connection with the first target device;and receiving the medical image to be sketched sent by the first target equipment.
- The method of claim 1, wherein prior to inputting the medical image to be delineated into a target delineation model, further comprising:and determining a target sketching model corresponding to the object to be sketched in at least one sketching model based on the object to be sketched in the medical image to be sketched.
- The method of claim 1, wherein the medical image to be sketched is a plurality of medical images;correspondingly, the automatic contour sketching is performed on the medical image to be sketched by using the target sketching model to obtain a sketching result, which comprises the following steps:And automatically outlining a plurality of medical images to be outlining in parallel by utilizing the target outlining model to obtain a plurality of outlining results.
- The method of claim 1, wherein the target delineation model is a trained deep neural network model.
- The method of claim 1, wherein pushing the sketch result to the second target device comprises:and packaging the sketching result according to a DICOM protocol, and automatically pushing the packaged sketching result to the second target equipment.
- The method according to claim 1, wherein the method further comprises:acquiring request information of a target user, wherein the request information is used for requesting to check a sketching result of the target patient;according to the request information, a sketching result of a target patient corresponding to the target user is obtained;and sending the sketching result of the target patient to the user side of the target user.
- The method according to claim 1, wherein the method further comprises:sending the sketching progress information of the medical image corresponding to the target user to a user side of the target user, wherein the sketching progress information comprises at least one of the following information:A sketched medical image list, a non-sketched medical image list, and a sketched failed medical image list;the sketching progress of the medical image corresponding to the target user;the medical image being sketched is sketched on schedule.
- A medical image contouring method, the method comprising:automatically acquiring at least one medical image to be sketched;inputting the at least one medical image to be sketched into a target sketching model, wherein the target sketching model is a trained deep neural network model;automatically outlining the at least one medical image to be outlining by utilizing the target outlining model to obtain at least one outlining result;and automatically pushing the at least one sketching result.
- [ correction 20.01.2021 according to rules 91 ]]The method of claim 15, wherein the method further comprises:receiving request information of a target user, wherein the request information is used for requesting to check a sketching result of the target patient;acquiring the sketching result of the target patient from the at least one sketching result according to the request information;and sending the sketching result of the target patient to the user side of the target user.
- A medical image contouring method, the method comprising:medical images to be sketched acquired from different devices;inputting the medical image to be sketched into a target sketching model;carrying out automatic contour sketching on the medical image to be sketched by utilizing the target sketching model to obtain a sketching result;pushing the sketching result to the different device.
- [ correction according to rules 91, 20.01.2021] a medical image contouring device comprising: a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to implement the method of any of the preceding claims 1-17.
- The apparatus of claim 18, wherein the medical image contouring means is a local server or a cloud server.
- A medical image contouring system, the system comprising: the medical image contouring apparatus of claim 17, and a first target device and a second target device, the second target device being the same device or a different device than the first target device.
- The system of claim 20, wherein the system further comprises a client.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/140393 WO2022140990A1 (en) | 2020-12-28 | 2020-12-28 | Medical image contour drawing method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116724357A true CN116724357A (en) | 2023-09-08 |
Family
ID=82259841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080108244.5A Pending CN116724357A (en) | 2020-12-28 | 2020-12-28 | Medical image contour sketching method, device and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116724357A (en) |
| WO (1) | WO2022140990A1 (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3496814B1 (en) * | 2016-08-11 | 2021-03-10 | Koninklijke Philips N.V. | Medical product configured to be used for image based radiotherapy planning |
| US10878576B2 (en) * | 2018-02-14 | 2020-12-29 | Elekta, Inc. | Atlas-based segmentation using deep-learning |
| CN110827961B (en) * | 2018-08-10 | 2022-08-23 | 北京连心医疗科技有限公司 | Automatic delineation method, device and storage medium for adaptive radiotherapy structure |
| CN109637652A (en) * | 2018-11-21 | 2019-04-16 | 北京全域医疗技术有限公司 | A kind of remote collaboration hook Target process and system based on cloud |
| CN111599445A (en) * | 2020-05-14 | 2020-08-28 | 安徽慧软科技有限公司 | Full-automatic CT image processing system for automatic drawing |
-
2020
- 2020-12-28 WO PCT/CN2020/140393 patent/WO2022140990A1/en active Application Filing
- 2020-12-28 CN CN202080108244.5A patent/CN116724357A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022140990A1 (en) | 2022-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9471748B2 (en) | Method for sharing medical image data based on cloud platform, cloud platform and system | |
| CN108367161B (en) | Radiotherapy system, data processing method and storage medium | |
| CN107566343A (en) | Physical examination circuit based on electronic map guides accessory system and method | |
| CN108461129A (en) | A kind of medical image mask method, device and user terminal based on image authentication | |
| US9390230B2 (en) | Radiation treatment planning apparatus and method thereof | |
| CN112022191B (en) | Positioning method and system | |
| WO2023078309A1 (en) | Method and apparatus for extracting target feature point, and computer device and storage medium | |
| CN109887077B (en) | Method and apparatus for generating three-dimensional model | |
| CN112401919B (en) | Auxiliary positioning method and system based on positioning model | |
| CN112336996A (en) | Radiotherapy target area automatic delineation system based on deep neural network | |
| CN114707742A (en) | Artificial intelligence prediction method and system for adaptive radiotherapy strategy | |
| CN116724357A (en) | Medical image contour sketching method, device and system | |
| CN108742678A (en) | Method for registering images, device and computer readable storage medium | |
| CN110534174B (en) | Radiotherapy plan analysis device, storage medium and equipment | |
| US20180085083A1 (en) | Optimization of image acquisition parameters for registration with reference image | |
| CN109124635B (en) | Model generation method, magnetic resonance imaging scanning method and system | |
| US20180137245A1 (en) | Automated transfer of patient data to a medical imaging apparatus | |
| CN109659026A (en) | Disease kind analysis method and device, storage medium, the computer equipment of artificial intelligence | |
| CN110674695B (en) | Service providing method, device, equipment and medium based on identity information identification | |
| CN108478227A (en) | A kind of method and apparatus of determining drug and its dose value | |
| US20160324468A1 (en) | System, method and apparatus for post-operative bariatric weight loss performance tracking | |
| CN114494484A (en) | Training method of data recognition model, data recognition method, device and equipment | |
| CN112116971A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112037886A (en) | Radiotherapy plan making device, method and storage medium | |
| EP4343708A1 (en) | Method and apparatus for training machine learning models, computer device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |