CN112863699B - ESD preoperative discussion system based on mobile terminal - Google Patents
ESD preoperative discussion system based on mobile terminal Download PDFInfo
- Publication number
- CN112863699B CN112863699B CN202011638238.9A CN202011638238A CN112863699B CN 112863699 B CN112863699 B CN 112863699B CN 202011638238 A CN202011638238 A CN 202011638238A CN 112863699 B CN112863699 B CN 112863699B
- Authority
- CN
- China
- Prior art keywords
- focus
- discussion
- esd
- water column
- preoperative
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Robotics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Endoscopes (AREA)
Abstract
The invention provides an ESD preoperative discussion system based on a mobile terminal, belonging to the technical field of ESD preoperative analysis, wherein an evaluation classification module traverses patient records of a plan for developing an ESD operation, and obtains an indication evaluation classification result according to an ESD indication evaluation classification standard; the preoperative discussion application module selects medical record information of a patient needing preoperative discussion according to the indication evaluation classification result and initiates a preoperative discussion request; the preoperative discussion participation module receives a participation request of a doctor user, and allows the doctor user to join a preoperative discussion if the participation request meets the operation qualification of corresponding medical record information, so that an ESD preoperative pathology discussion result is obtained. The invention forms a mobile discussion system which is convenient to operate and operate, extracts the relevant information of the corresponding endoscope information system database, accurately evaluates the classification of ESD operation indications, screens the patients which accord with the ESD indications, avoids the over-treatment of the patients which are not suitable for the endoscope operation, reduces the occurrence probability of the operation complications and provides guarantee for the medical safety.
Description
Technical Field
The invention relates to the technical field of ESD preoperative analysis, in particular to an ESD preoperative discussion system based on a mobile terminal.
Background
The preoperative discussion is to discuss the case operation indication, the operation mode, the expected effect, the operation risk, the treatment plan and the like of the operation to be performed by a doctor before the operation of a patient is performed, so as to realize personalized treatment, achieve the purposes of reducing the operation risk and guaranteeing the operation safety, accumulate the treatment experience of difficult and complicated cases and improve the diagnosis and treatment level. Pre-operative discussion has become a routine procedure prior to surgery.
With the progress of endoscopic technology, Endoscopic Submucosal Dissection (ESD) is used as a minimally invasive surgery for treating digestive tract lesions under an endoscope, and through the development of years, the technology of the endoscopic submucosal dissection is mature day by day, and currently, endoscopic dissection is recommended as a preferred treatment mode for early gastric cancer by international multiple guidelines and consensus. Compared with the traditional surgical operation, the digestive endoscopy for treating early gastric cancer has the advantages of small wound, less complications, quick recovery, low cost and the like, and the curative effect is equivalent to that of the surgical operation. However, even in the early stage of ESD treatment, there are also complications such as bleeding, perforation, and residue, and the requirement for endoscope operation technique is high, and the need for strict indication is also high.
The ESD operation is mostly carried out in the digestive system currently, most endoscope doctors often ignore the preoperative discussion and are limited in individual thinking, accurate judgment is difficult to make when the condition in the operation is inconsistent with the preoperative expectation, the physician often needs to turn to superior doctors, even misjudgment is generated by the endoscope doctors, the treatment effect of a patient is influenced, and the patient cannot benefit.
Disclosure of Invention
The invention aims to provide a mobile-terminal-based ESD pre-operation discussion system which can conveniently provide doctors for performing WSD pre-operation discussion, synthesize various factors and accurately screen ESD indication patients so as to solve at least one technical problem in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a mobile terminal-based ESD pre-operation discussion system, which comprises:
the evaluation and classification module is used for traversing the patient record of the ESD operation, extracting an endoscope examination diagnosis report, an endoscope image and a pathological diagnosis report, and calculating to obtain an indication evaluation and classification result according to an ESD indication evaluation and classification standard;
the preoperative discussion application module is used for selecting medical record information of a patient needing preoperative discussion according to the indication evaluation classification result and initiating a preoperative discussion request according to the medical record information;
and the preoperative discussion participation module is used for receiving a participation request of a doctor user, and allowing the doctor user to join the preoperative discussion if the participation request accords with the operation qualification of the corresponding medical record information, so as to obtain an ESD preoperative pathology discussion result.
Preferably, the system further comprises: the inquiry and backtracking module is used for inquiring and backtracking the pathology of the similar patients, analyzing the postoperative pathological results of the patients subjected to the ESD operation and evaluating whether the patients are cured excision or non-cured excision; prompt the non-curative excision in time and add treatment in time.
Preferably, the evaluation sub-module comprises a lesion size calculation unit, a judgment unit, a type identification unit and an evaluation unit;
the focus size calculating unit is used for calculating the focus size by using a water column formed by an endoscope water spraying function as a reference object;
the judging unit is used for judging whether the focus is combined with the ulcer by utilizing the deep learning neural network model;
the type identification unit is used for automatically identifying a 'differentiation' word from the pathological diagnosis result text information of the patient, traversing the text information before and after the 'differentiation' word and searching to obtain a focus differentiation type;
and the evaluation unit is used for obtaining the evaluation classification result of the ESD operation indication of the patient according to the size of the focus, whether the focus is combined with the ulcer and the focus differentiation type.
Preferably, the lesion size calculation unit includes: the device comprises a first image acquisition subunit, a water column identification subunit, a first calculation subunit and a second calculation subunit;
the first image acquisition subunit is used for acquiring an image of the digestive tract containing lesions and water columns under the endoscope;
the water column identification subunit is used for identifying the water column profile contained in the image by utilizing the trained water column profile identification model; pre-labeling a water column outline of an acquired image, performing mask processing, and training the water column outline to be a water column outline recognition model as training data;
the first calculation subunit is used for carrying out angular point detection on the identified water column outline and calculating the intersection width of the water column and the digestive tract mucosa according to the detected angular point and the water column outline;
and the second calculating subunit is used for obtaining the actual size of the circumscribed rectangle of the focus according to the corresponding relation between the image pixels and the actual size and by combining the intersection width of the water column and the digestive tract mucosa, so as to obtain the final focus size.
Preferably, the first calculation subunit is configured to: the method comprises the steps of identifying an angular point on one side of a junction of a water column and a focus mucosa according to a water column outline, taking a plurality of points on an opposite outline, performing linear fitting on the basis of the plurality of points to obtain an opposite fitted straight line, projecting the identified angular point onto the fitted straight line, and obtaining the distance between a projection point and the angular point, namely the width of intersection of the water column and the focus mucosa.
Preferably, a Mask R-CNN neural network is adopted to train the water column outline recognition model.
Preferably, the judging unit includes a second image collecting subunit, a lesion region identifying subunit, and a secondary verifying subunit;
the second image acquisition subunit is used for acquiring a sample image with a focus area;
the focus area identification subunit is used for identifying a focus area in the sample image by using the trained focus area identification model; performing focus region labeling on an acquired sample image with a focus region, and training a focus region identification model as a training set;
the secondary verification subunit is used for verifying whether the identified lesion area is combined with ulcer by using a trained verification classification model; and marking an ulcer focus region and a non-ulcer focus region of the identified focus region, and training the verification classification model as a training set.
Preferably, the lesion region identification model is trained using a YOLOv3 neural network.
Preferably, the verification classification model is trained using a MobileNetV2 convolutional neural network.
Preferably, the medical record information comprises patient complaints, basic patient data, preoperative common endoscopic images, amplified endoscopic images, stained endoscopic images, ultrasonic endoscopic images and CT images.
The invention has the beneficial effects that: a mobile discussion system convenient to operate and operate is formed, the relevant information of a corresponding endoscope information system database is extracted conveniently by combining the characteristics of the ESD operation, and the classification of the ESD operation indications is accurately evaluated so as to accurately screen the patients meeting the ESD indications, avoid the patients unsuitable for the endoscope operation from being over-treated, reduce the occurrence probability of the operation complications and provide guarantee for medical safety.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a functional block diagram of an ESD pre-operation discussion system based on a mobile terminal according to an embodiment of the present invention.
Fig. 2 is a functional block diagram of an evaluation classification module of the ESD pre-operation discussion system based on the mobile terminal according to an embodiment of the present invention.
Fig. 3 is a functional block diagram of a lesion size calculating unit of the mobile terminal-based ESD pre-operation discussion system according to an embodiment of the present invention.
Fig. 4 is a functional block diagram of a determining unit of the ESD pre-operation discussion system based on the mobile terminal according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by way of the drawings are illustrative only and are not to be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the purpose of facilitating an understanding of the present invention, the present invention will be further explained by way of specific embodiments with reference to the accompanying drawings, which are not intended to limit the present invention.
It should be understood by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements shown in the drawings are not necessarily required to practice the invention.
Examples
As shown in fig. 1, an embodiment of the present invention provides a mobile-end-based ESD pre-operation discussion system, which includes:
the evaluation and classification module is used for traversing the patient record of the ESD operation, extracting an endoscope examination diagnosis report, an endoscope image and a pathological diagnosis report, and calculating to obtain an indication evaluation and classification result according to an ESD indication evaluation and classification standard;
the preoperative discussion application module is used for selecting medical record information of a patient needing preoperative discussion according to the indication evaluation classification result and initiating a preoperative discussion request according to the medical record information;
and the preoperative discussion participation module is used for receiving a participation request of a doctor user, and allowing the doctor user to join the preoperative discussion if the participation request accords with the operation qualification of the corresponding medical record information, so as to obtain an ESD preoperative pathology discussion result.
The system further comprises: the inquiry and backtracking module is used for inquiring and backtracking the pathology of the similar patients, analyzing the postoperative pathological results of the patients subjected to the ESD operation and evaluating whether the patients are cured excision or non-cured excision; prompt the non-curative excision in time and add treatment in time.
As shown in fig. 2, the evaluation sub-module includes a lesion size calculation unit, a determination unit, a type recognition unit, and an evaluation unit;
the focus size calculating unit is used for calculating the focus size by using a water column formed by an endoscope water spraying function as a reference object;
the judging unit is used for judging whether the focus is combined with the ulcer by utilizing the deep learning neural network model;
the type identification unit is used for automatically identifying a 'differentiation' word from the pathological diagnosis result text information of the patient, traversing the text information before and after the 'differentiation' word and searching to obtain a focus differentiation type;
and the evaluation unit is used for obtaining the evaluation classification result of the ESD operation indication of the patient according to the size of the focus, whether the focus is combined with the ulcer and the focus differentiation type.
As shown in fig. 3, the lesion size calculation unit includes: the device comprises a first image acquisition subunit, a water column identification subunit, a first calculation subunit and a second calculation subunit;
the first image acquisition subunit is used for acquiring an image of the digestive tract containing lesions and water columns under the endoscope;
the water column identification subunit is used for identifying the water column profile contained in the image by utilizing the trained water column profile identification model; pre-labeling a water column outline of an acquired image, performing mask processing, and training the water column outline to be a water column outline recognition model as training data;
the first calculation subunit is used for carrying out angular point detection on the identified water column outline and calculating the intersection width of the water column and the digestive tract mucosa according to the detected angular point and the water column outline;
and the second calculating subunit is used for obtaining the actual size of the circumscribed rectangle of the focus according to the corresponding relation between the image pixels and the actual size and by combining the intersection width of the water column and the digestive tract mucosa, so as to obtain the final focus size.
The first computing subunit is configured to: the method comprises the steps of identifying an angular point on one side of a junction of a water column and a focus mucosa according to a water column outline, taking a plurality of points on an opposite outline, performing linear fitting on the basis of the plurality of points to obtain an opposite fitted straight line, projecting the identified angular point onto the fitted straight line, and obtaining the distance between a projection point and the angular point, namely the width of intersection of the water column and the focus mucosa.
And training the water column outline recognition model by adopting a Mask R-CNN neural network.
As shown in fig. 4, the determining unit includes a second image collecting subunit, a lesion region identifying subunit, and a secondary verifying subunit;
the second image acquisition subunit is used for acquiring a sample image with a focus area;
the focus area identification subunit is used for identifying a focus area in the sample image by using the trained focus area identification model; performing focus region labeling on an acquired sample image with a focus region, and training a focus region identification model as a training set;
the secondary verification subunit is used for verifying whether the identified lesion area is combined with ulcer by using a trained verification classification model; and marking an ulcer focus region and a non-ulcer focus region of the identified focus region, and training the verification classification model as a training set.
And training the lesion area identification model by using a YOLOv3 neural network.
The verification classification model was trained using a MobileNetV2 convolutional neural network.
The medical record information comprises patient complaints, patient basic data, preoperative common endoscope images, amplified endoscope images, dyed endoscope images, ultrasonic endoscope images and CT images.
In this embodiment, the above-mentioned mobile-terminal-based ESD pre-operative discussion system is utilized to implement the patient ESD pre-operative discussion, and the specific method is as follows:
the method comprises an artificial intelligence classification evaluation step, a preoperative discussion application step, an opinion analysis and submission step and a discussion result query and backtrack step.
Step 1: and carrying out artificial intelligence group classification evaluation by using an evaluation classification module.
The evaluation and classification module automatically traverses the patient record of the planned ESD operation, and automatically evaluates and classifies the ESD indication evaluation and classification standard through the data such as an endoscope examination diagnosis report, an endoscope image, a pathological diagnosis report and the like.
The ESD indication evaluation classification standard is as follows:
for absolute indications: (1) non-invasive tumors, regardless of lesion size; (2) the diameter of the focus is less than or equal to 2cm, and the mucosa cancer is not combined with the differentiation type mucosa cancer with ulcer.
For the relative indications: (1) the diameter of the focus is more than 2cm, and the mucosa cancer is differentiated without combined ulcer; (2) the diameter of the focus is less than or equal to 3cm, and the mucosa cancer is differentiated when the ulcer is combined; (3) and in undifferentiated type mucosal carcinoma with the diameter less than or equal to 2cm and without combined ulcer; (4) differentiation type superficial submucosal carcinoma with lesion diameter less than or equal to 3cm (SMI, infiltration depth of submucosal layer less than or equal to 500 μm)
For pre-operative evaluation of ESD, there are 3 important bases: 1 is the size of the lesion; it 2 is whether the lesion is combined with ulcer; it 3 is the type of differentiation of the lesion.
For lesion size assessment, the following are divided: less than or equal to 2 cm; greater than 2 cm; less than or equal to 3 cm; and more than 3 cm. In digestive endoscopy, the angle and the distance of the acquired focus image cannot reach the unified standard due to the fact that the digestive tract is not relatively static but continuously creeps, and meanwhile, the size of the focus cannot be accurately measured due to the fact that the lens of the digestive endoscope is distorted and distance measuring means are not available.
The existing assessment of the size of the focus depends on the estimation of the visual experience of an endoscopist, but the estimation of the visual experience is not objective and rigorous for the situation that the size of the focus is used as an important parameter for the assessment of the surgical treatment scheme.
Therefore, in the embodiment, the water column formed by the endoscope water spraying function is used as a reference object, and the size of the focus can be accurately calculated by a computer, so that the problem of measuring the size of the focus required by the pre-operation evaluation of the ESD is well solved.
In this embodiment, whether the lesion is combined with the ulcer is automatically determined by using a deep learning neural network model based on an artificial intelligence image recognition technique.
For the differentiation type of the lesion, in this embodiment, the differentiation type is automatically obtained from the pathological diagnosis result by information extraction and text processing techniques.
And finally, obtaining the ESD operation indication evaluation classification result of a specific case according to the size of the focus, whether the ulcer is combined and the 3 evaluation standard results of the focus differentiation types.
The artificial intelligence evaluation process of the ESD operation indication evaluation classification result comprises the following steps:
step 1.1: the focus diameter is automatically identified, measured and calculated by using a focus size calculation unit
In this example, the endoscope water column was used as a reference to measure lesion size, specifically:
step 1.1-1: acquiring an image of the digestive tract under the endoscope, which comprises a lesion and a water column, by using a first image acquisition subunit:
the data is a digestive tract endoscope sample image with a water column outline labeled in advance; and performing mask processing on the sample image in the data.
1.1-2: identifying the water column profile contained therein by means of a water column identification subunit:
and training a Mask R-CNN neural model by adopting the training data subjected to Mask processing to obtain a water column outline recognition model.
1.1-3: calculating the intersecting width of the water column and the focus by utilizing a first calculating subunit:
and carrying out corner detection on the identified water column profile. Calculating the intersection width of the water column and the digestive tract mucosa according to the detected angular point and the water column outline, wherein the specific method comprises the following steps:
identifying an angular point on one side of a junction of the water column and the focus mucosa according to the water column profile; taking a plurality of points on the profile line of the opposite side, and performing straight line fitting based on the plurality of points to obtain a fitted straight line of the opposite side; and projecting the identified angular points onto a fitting straight line, wherein the distance between the obtained projection points and the angular points is the intersection width of the water column and the focus mucosa.
1.1-4: and obtaining the actual size of the length and the width of the circumscribed rectangle of the focus by utilizing the first calculating subunit according to the corresponding relation between the image pixel and the actual size and combining the intersecting width of the water column and the mucosa of the digestive tract.
Step 1.2: automatically identifying whether the focus is combined with the ulcer by using a judging unit
The system adopts a deep learning neural network model to automatically identify the focus in the digestive tract endoscope image and verify whether the focus area is combined with ulcer, and specifically comprises the following steps:
step 1.2-1: and collecting a sample image with a focus by using a second image collecting subunit, and marking training data.
Step 1.2-2: the focus area is identified by using a focus area identification subunit, wherein a focus area identification model is trained by using a training data set manufactured in the last step, in the embodiment, a Yolov3 target detection model is adopted to identify the ulcer focus area under the endoscope, TensorT is used for acceleration, the time consumption of each frame of image inference is as low as 10ms, and the requirement of real-time video image intelligent inference of the digestive endoscopy can be met.
Step 1.2-3: and performing secondary verification on whether the lesion area is combined with the ulcer by using a secondary verification subunit. Arranging a focus area training sample, cutting out a focus area from the sample image collected in the step 1, and classifying the image into two categories: ulcers, non-ulcers; training an ulcer image two-classification recognition model by using MobileNet V2, wherein MobileNet V2 is a lightweight convolutional neural network, and can reach the performance of 100FPS and meet the requirement of real-time video image intelligent inference of a digestive endoscope; and (3) after the endoscope image calls the YOLOV3 model in the step 2 to identify the focus, cutting out a focus area according to the coordinate position of the image, calling a binary model, and further verifying whether the focus area is combined with ulcer.
Step 1.3: automatically acquiring lesion differentiation type by using type identification unit
In this embodiment, a pathological diagnosis result is automatically obtained from medical record data of a patient through information extraction and text processing technologies, a "differentiation" pattern is automatically identified from the pathological diagnosis result text information, and then the text before and after the differentiation pattern is traversed to search for a specific differentiation type of the lesion diagnosis.
Step 1.4: calculating to obtain ESD operation indication evaluation classification result of specific case
In this embodiment, based on the size of the lesion, whether the lesion is combined with ulcer, and the differentiation type result of the lesion obtained in the above steps, the assessment and classification result of the indication is calculated according to the "classification standard for ESD indication assessment".
Step 2: performing preoperative discussion application by using a preoperative discussion application module:
based on the above artificial intelligence classification evaluation results, the physician selects the patient to be discussed preoperatively, and organizes the medical record information for the preoperative discussion, which specifically includes: patient's chief complaint, basic data, picture and text data such as ordinary endoscope before the art, enlarged endoscope, dyed endoscope, ultrasonic endoscope, CT, laboratory inspection data in the HIS system. After the data organization is complete, a preoperative discussion application process is initiated through the system.
And step 3: and performing preoperative discussion opinion analysis and submission by using a preoperative discussion participation module:
in the module, pre-stored pre-operation discussion rules are required to invite at least 3 doctors meeting operation qualification to participate in discussion, and after the pre-operation discussion application in the previous step is initiated, the system selects the doctors participating in discussion to participate in the pre-operation discussion according to the pre-operation discussion rules of an initiator and default rules of the system.
The doctors participating in the discussion can carry out pre-operation discussion on the mobile terminal of the mobile phone through the system, the discussion process supports voice and text input, and the time meeting discussion can be appointed or the message discussion can be carried out according to different time of each person. The anesthesia method, the type of the instrument, the surgical incision strategy and the post-operative care required before the surgical operation will be discussed and illustrated.
And 4, step 4: and (3) utilizing a query and backtracking module to query and backtrack discussion results:
and the database query and backtracking functions of the same type of patients are supported, so that the related experience is favorably accumulated. Meanwhile, according to an input eCURE postoperative grading system, the postoperative pathological results are intelligently analyzed, whether the postoperative pathological results are curative excision or non-curative excision is evaluated, prompt is timely given to the non-curative excision on the system, and timely treatment is added.
In summary, the ESD preoperative discussion system based on the mobile terminal according to the embodiment of the present invention captures information of relevant data of patient cases by artificial intelligence assistance and combining with the characteristics of the ESD operation, and intelligently evaluates the classification of ESD operation indications. The problem that the size of a focus is difficult to measure accurately and the judgment parameters which are excessively estimated based on the visual experience of an endoscope physician are not objective and strict is solved, and meanwhile, the artificial intelligence technology is adopted to automatically judge whether the focus is combined with ulcer and focus differentiation type parameters, so that an accurate basis for judging the pre-operation adaptive disease of the ESD is provided for the physician. On the basis of accurately screening patients according with ESD indications, the system simultaneously provides complete flow management and process information record for ESD preoperative discussion, forms a mobile discussion system convenient for doctors to operate and operate, avoids the patients unsuitable for endoscopic surgery from being excessively treated, is beneficial to reducing intraoperative complications, and provides guarantee for medical safety.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
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.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to the specific embodiments shown in the drawings, it is not intended to limit the scope of the present disclosure, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive faculty based on the technical solutions disclosed in the present disclosure.
Claims (7)
1. A mobile-based ESD pre-operative discussion system, comprising:
the evaluation and classification module is used for traversing the patient record of the ESD operation, extracting an endoscope examination diagnosis report, an endoscope image and a pathological diagnosis report, and calculating to obtain an indication evaluation and classification result according to an ESD indication evaluation and classification standard; the evaluation classification module comprises a focus size calculation unit, a judgment unit, a type identification unit and an evaluation unit;
the focus size calculating unit is used for calculating the focus size by using a water column formed by an endoscope water spraying function as a reference object;
the judging unit is used for judging whether the focus is combined with the ulcer by utilizing the deep learning neural network model; the judging unit comprises a second image acquisition subunit, a focus area identification subunit and a secondary verification subunit;
the second image acquisition subunit is used for acquiring a sample image with a focus area;
the focus area identification subunit is used for identifying a focus area in the sample image by using the trained focus area identification model; performing focus region labeling on an acquired sample image with a focus region, and training a focus region identification model as a training set;
the secondary verification subunit is used for verifying whether the identified lesion area is combined with ulcer by using a trained verification classification model; marking an ulcer focus region and a non-ulcer focus region of the identified focus region, and training the verification classification model as a training set;
the type identification unit is used for automatically identifying a 'differentiation' word from the pathological diagnosis result text information of the patient, traversing the text information before and after the 'differentiation' word and searching to obtain a focus differentiation type;
the evaluation unit is used for obtaining the evaluation and classification result of the ESD operation indication of the patient according to the size of the focus, whether the focus is combined with the ulcer and the focus differentiation type;
the preoperative discussion application module is used for selecting medical record information of a patient needing preoperative discussion according to the indication evaluation classification result and initiating a preoperative discussion request according to the medical record information;
the preoperative discussion participation module is used for receiving a participation request of a doctor user, and allowing the doctor user to join a preoperative discussion if the participation request accords with the operation qualification of corresponding medical record information, so as to obtain an ESD preoperative pathology discussion result;
the inquiry and backtracking module is used for inquiring and backtracking the pathology of the similar patients, analyzing the postoperative pathological results of the patients subjected to the ESD operation and evaluating whether the patients are cured excision or non-cured excision; prompt the non-curative excision in time and add treatment in time.
2. The mobile-end-based ESD pre-operative discussion system of claim 1, wherein the lesion size calculation unit comprises: the device comprises a first image acquisition subunit, a water column identification subunit, a first calculation subunit and a second calculation subunit;
the first image acquisition subunit is used for acquiring an image of the digestive tract containing lesions and water columns under the endoscope;
the water column identification subunit is used for identifying the water column profile contained in the image by utilizing the trained water column profile identification model; pre-labeling a water column outline of an acquired image, performing mask processing, and training the water column outline to be a water column outline recognition model as training data;
the first calculation subunit is used for carrying out angular point detection on the identified water column outline and calculating the intersection width of the water column and the digestive tract mucosa according to the detected angular point and the water column outline;
and the second calculating subunit is used for obtaining the actual size of the circumscribed rectangle of the focus according to the corresponding relation between the image pixels and the actual size and by combining the intersection width of the water column and the digestive tract mucosa, so as to obtain the final focus size.
3. The mobile-based ESD pre-operative discussion system of claim 2, wherein the first computing subunit is configured to: the method comprises the steps of identifying an angular point on one side of a junction of a water column and a focus mucosa according to a water column outline, taking a plurality of points on an opposite outline, performing linear fitting on the basis of the plurality of points to obtain an opposite fitted straight line, projecting the identified angular point onto the fitted straight line, and obtaining the distance between a projection point and the angular point, namely the width of intersection of the water column and the focus mucosa.
4. The mobile-terminal-based ESD pre-operative discussion system according to claim 2, wherein the water column profile recognition model is trained using a Mask R-CNN neural network.
5. The mobile-end-based ESD pre-operative discussion system of claim 1, wherein the lesion area identification model is trained using YOLOv3 neural network.
6. The mobile-based ESD pre-operative discussion system of claim 1, wherein the verification classification model is trained using a MobileNetV2 convolutional neural network.
7. The mobile-terminal-based ESD preoperative discussion system according to claim 1, wherein the medical record information includes patient complaints, patient basic data, preoperative general endoscopic images, magnified endoscopic images, stained endoscopic images, ultrasonic endoscopic images, CT images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011638238.9A CN112863699B (en) | 2020-12-31 | 2020-12-31 | ESD preoperative discussion system based on mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011638238.9A CN112863699B (en) | 2020-12-31 | 2020-12-31 | ESD preoperative discussion system based on mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112863699A CN112863699A (en) | 2021-05-28 |
| CN112863699B true CN112863699B (en) | 2021-09-07 |
Family
ID=76001353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011638238.9A Active CN112863699B (en) | 2020-12-31 | 2020-12-31 | ESD preoperative discussion system based on mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112863699B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI789932B (en) * | 2021-10-01 | 2023-01-11 | 國泰醫療財團法人國泰綜合醫院 | Imaging detection method and device for colorectal polyps and system thereof |
| CN115778546B (en) * | 2023-02-07 | 2023-05-09 | 武汉楚精灵医疗科技有限公司 | Intelligent auxiliary method and device for endoscopic submucosal dissection and related equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2784743A1 (en) * | 2013-03-29 | 2014-10-01 | Canon Kabushiki Kaisha | Conference support system, conference support method, and program |
| CN105787253B (en) * | 2016-01-22 | 2018-08-21 | 王中显 | A kind of electronic medical record system for integrating hospital work flow |
| CN111091562B (en) * | 2019-12-23 | 2020-12-01 | 山东大学齐鲁医院 | Method and system for measuring size of digestive tract lesion |
-
2020
- 2020-12-31 CN CN202011638238.9A patent/CN112863699B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112863699A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110600122B (en) | Digestive tract image processing method and device and medical system | |
| US9107569B2 (en) | Medical instrument for examining the cervix | |
| Zulkifley et al. | Pterygium-Net: a deep learning approach to pterygium detection and localization | |
| CN112863699B (en) | ESD preoperative discussion system based on mobile terminal | |
| US20220172828A1 (en) | Endoscopic image display method, apparatus, computer device, and storage medium | |
| Motta et al. | Vessel optimal transport for automated alignment of retinal fundus images | |
| CN112465772B (en) | Fundus colour photographic image blood vessel evaluation method, device, computer equipment and medium | |
| CN111341437B (en) | Digestive tract disease judgment auxiliary system based on tongue image | |
| CN114299072B (en) | Artificial intelligence-based anatomy variation identification prompting method and system | |
| Wang et al. | A method of ultrasonic image recognition for thyroid papillary carcinoma based on deep convolution neural network | |
| CN107658028A (en) | A kind of method for obtaining lesion data, identification lesion method and computer equipment | |
| CN114372951A (en) | Nasopharyngeal carcinoma positioning and segmenting method and system based on image segmentation convolutional neural network | |
| Sun et al. | A novel gastric ulcer differentiation system using convolutional neural networks | |
| CN108427988A (en) | A kind of alimentary canal anatomical position identification device | |
| CN117218127B (en) | Ultrasonic endoscope auxiliary monitoring system and method | |
| CN117524441A (en) | Method and device for detecting surgical quality | |
| CN116703837B (en) | MRI image-based rotator cuff injury intelligent identification method and device | |
| CN111281355B (en) | Method and equipment for determining pulse acquisition position | |
| WO2019092723A1 (en) | System and method for determining pathological status of a laryngopharyngeal area in a patient | |
| CN115024816A (en) | Cold circulation microwave tumor ablation system | |
| CN111179264A (en) | Method and device for producing restored image of specimen, specimen processing system, and electronic device | |
| Bernal et al. | Towards intelligent systems for colonoscopy | |
| CN111209801A (en) | Traditional Chinese medicine fat tongue identification method and device | |
| Kauppi et al. | A framework for constructing benchmark databases and protocols for retinopathy in medical image analysis | |
| Kuo et al. | Automatic and quantitative measurement of laryngeal video stroboscopic images |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |