CN111681749A - Pathology department standardized work management and diagnosis consultation system and method - Google Patents
Pathology department standardized work management and diagnosis consultation system and method Download PDFInfo
- Publication number
- CN111681749A CN111681749A CN202010573185.0A CN202010573185A CN111681749A CN 111681749 A CN111681749 A CN 111681749A CN 202010573185 A CN202010573185 A CN 202010573185A CN 111681749 A CN111681749 A CN 111681749A
- Authority
- CN
- China
- Prior art keywords
- patient
- pathological
- pathology
- module
- corpus data
- 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
- 230000007170 pathology Effects 0.000 title claims abstract description 189
- 238000003745 diagnosis Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000001575 pathological effect Effects 0.000 claims abstract description 194
- 201000010099 disease Diseases 0.000 claims abstract description 58
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 58
- 238000007726 management method Methods 0.000 claims abstract description 49
- 239000011159 matrix material Substances 0.000 claims abstract description 48
- 238000010827 pathological analysis Methods 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 114
- 208000037919 acquired disease Diseases 0.000 claims description 14
- 230000000474 nursing effect Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000002059 diagnostic imaging Methods 0.000 claims description 9
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000003902 lesion Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000009223 counseling Methods 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 6
- 238000011888 autopsy Methods 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- 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
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of medical diagnosis consultation, and discloses a pathological department standardized work management and diagnosis consultation system and a method, wherein the pathological department standardized work management and diagnosis consultation system comprises: patient's disease information acquisition module, patient's disease image acquisition module, medical personnel information acquisition module, central control module, information management module, image enhancement module, pathology data processing module, pathological diagnosis module, scheduling module, consultation module, data storage module, display module. According to the invention, through the pathology data processing module, related personnel can know the similarity of the pathology reports of the patients to be processed more conveniently, so that the patient pathology representation matrix gives pathological indication to the related personnel; the pathological image of the patient to be identified is input into the preset pathological image model of the patient through the pathological diagnosis module, the diagnosis result is obtained, the accuracy rate of the process is high, the speed is high, the workflow of doctors in the patient pathology department is greatly shortened, and the labor cost is saved.
Description
Technical Field
The invention belongs to the technical field of medical diagnosis consultation, and particularly relates to a pathological department standardized work management and diagnosis consultation system and method.
Background
Currently, the pathology department is one of the indispensable departments of the large-scale comprehensive hospital, and the main task of the pathology department is to undertake pathological diagnosis work in the medical treatment process, including biopsy, cast-off and fine needle puncture cytology examination and autopsy examination, so as to provide clear pathological diagnosis for clinic, determine the nature of diseases and find out the cause of death. Because the pathological diagnosis report is not a pictorial description, but a clear name of the disease, clinicians mainly determine the therapeutic principles, estimate prognosis, and explain clinical symptoms and clear causes of death based on the pathological report. This authority of pathological diagnosis determines its central role in all diagnostic tools, and therefore the quality of pathological diagnosis has a great influence not only on the relevant departments but also on the overall medical quality of the hospital. However, most of the pathological relevant data of the patients in the current pathological department standardized work management and diagnosis consultation system are presented in the form of text data, the information of the text is relatively scattered, the guidance effect on doctors is relatively small, and the effect of the text data on the representation and depiction of the patients is relatively poor; meanwhile, the pathological images of the patient are low in digitization and informatization degree and poor in diagnosis quality.
In summary, the problems and disadvantages of the prior art are: the prior pathological department standardized work management and diagnosis consultation system mostly presents the pathological relevant data of patients in the form of text data, the information of the text is relatively scattered, the guidance effect on doctors is relatively small, and the effect of the text data on the representation and the depiction of the patients is relatively poor; meanwhile, the pathological images of the patient are low in digitization and informatization degree and poor in diagnosis quality.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a pathological department standardized work management and diagnosis consultation system and method.
The invention is realized in such a way that a pathology department standardization work management and diagnosis consultation method comprises the following steps:
step one, acquiring disease condition information of a patient by using patient information acquisition equipment through a patient disease information acquisition module; the medical imaging equipment is used for acquiring the disease images of the patient through the disease image acquisition module of the patient.
Acquiring information of doctors and nursing staff of a pathology department by using medical staff information acquisition equipment through a medical staff information acquisition module; and the central control module controls the normal work of each module of the pathology department standardized work management and diagnosis consultation system by using the central processing unit.
Step three, enhancing the acquired disease images of the patient by an image enhancement module through an image enhancement program; and managing the acquired patient disease condition information and the medical care personnel information by using an information management program through an information management module.
Acquiring a plurality of pathological reports of the patient to be processed by using a data processing program through a pathological data processing module; and preprocessing the plurality of pathological reports of the patients to be processed to obtain a plurality of pieces of pathological corpus data of the patients.
And fifthly, aiming at each piece of pathological corpus data of the patients, carrying out vector transformation on each word in each piece of pathological corpus data of the patients by using a bag-of-word model to obtain a word vector of each word in the pathological corpus data of the patients.
Step six, performing weighted summation on all word vectors to obtain the patient pathology vectors in the patient pathology corpus data; and a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix.
And seventhly, performing dimensionality reduction on the patient pathology matrix, determining a patient pathology representation matrix corresponding to the plurality of to-be-processed patient pathology reports, wherein each row vector in the patient pathology representation matrix represents a representation vector of the to-be-processed patient pathology report, and processing pathology report data.
Step eight, diagnosing the pathology of the patient by using a diagnosis program through a pathology diagnosis module; the scheduling module is used for scheduling doctors and nursing staff in the pathology department by using a scheduling program.
Step nine, acquiring a plurality of pathological pictures of the patient as a training set, wherein the pathological pictures of the patient correspond to a first diagnosis result; training a neural network model by using the training set to obtain a second diagnosis result; and if the first diagnosis result is different from the second diagnosis result, adjusting parameters of the neural network model until the first diagnosis result is the same as the second diagnosis result.
Step ten, acquiring pathological images and patient information of a patient to be identified by using medical imaging equipment through a consultation module; inputting the pathological image of the patient to be identified into a preset pathological image model of the patient, and outputting a diagnosis result of the pathological image of the patient to be identified by the pathological image model of the patient; and generating a diagnosis report according to the diagnosis result and the patient information by utilizing a consultation program.
Step eleven, storing the acquired disease information, disease images, medical care information, scheduling results and consultation information by a data storage module through a memory; and the display is used for displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information through the display module.
Further, in the sixth step, the weighted summation is performed on all the word vectors to obtain the front of the patient pathology vector in the patient pathology corpus data; the method further comprises the following steps: and determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed.
Further, the method for performing weighted summation on all word vectors to obtain the patient pathology vector in the piece of patient pathology corpus data includes: and carrying out weighted summation on all the word vectors by using the weights corresponding to the word vectors to obtain the pathological vector of the pathological corpus data of the patient.
Further, the method for determining the weight corresponding to each word vector according to the plurality of pathological reports of the patient to be processed comprises the following steps:
(I) calculating to obtain target reverse frequency according to the total number of files of the pathological reports of the patients to be processed and the number of files of target words corresponding to target word vectors in the pathological reports of the patients to be processed;
(II) calculating the occurrence frequency of the target word in each pathological report of the patient to be processed according to the target word;
and (III) calculating to obtain the weight of the target word vector according to the target reverse frequency and the target word frequency.
Further, in the sixth step, the method for performing vector conversion on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of to-be-processed patient pathology reports includes:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; and a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix.
Further, the method for performing vector transformation on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of to-be-processed patient pathology reports specifically includes:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; calculating the average value of all word vectors in the pathological corpus data to obtain the pathological vector of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a first patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed; weighting and summing all word vectors in the pathological corpus data of the patient to obtain the pathological vectors of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a second patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; a third patient pathology matrix is formed by a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data;
and carrying out weighted summation on the first patient pathology matrix, the second patient pathology matrix and the third patient pathology matrix to obtain a pathology matrix.
Further, in step ten, before acquiring the pathological image of the patient to be identified, the method further includes:
(1) scanning pathological sections of a patient with a first resolution to obtain a pathological image of the first patient;
(2) determining at least one local area of the pathological image of the first patient as a suspected lesion area;
(3) scanning the suspected lesion area with a second resolution to obtain a pathological image of a second patient, wherein the second resolution is higher than the first resolution;
(4) taking the second patient pathology image as a patient pathology image to be identified;
the acquiring the pathological image of the patient to be identified further comprises:
1) carrying out gray level processing on the pathological image of the patient to be identified to obtain the pathological gray level image of the patient to be identified;
2) carrying out noise removal and filtering processing on the pathological gray level image of the patient to be identified to obtain a distortion-free pathological gray level image of the patient to be identified;
3) and identifying a region with a gray mean value smaller than a preset gray value in the undistorted patient pathology gray image to be identified, and assigning the region with the gray mean value smaller than the preset gray value in the undistorted patient pathology gray image to be black.
Another object of the present invention is to provide a pathology department standardized work management and diagnosis consultation system applying the pathology department standardized work management and diagnosis consultation method, the pathology department standardized work management and diagnosis consultation system comprising:
the patient disease information acquisition module is connected with the central control module and is used for acquiring the disease condition information of the patient through patient information acquisition equipment;
the patient disease image acquisition module is connected with the central control module and is used for acquiring a patient disease image through medical imaging equipment;
the medical staff information acquisition module is connected with the central control module and is used for acquiring information of doctors and nursing staff in a pathology department through medical staff information acquisition equipment;
the central control module is connected with the patient disease information acquisition module, the patient disease image acquisition module, the medical staff information acquisition module, the information management module, the image enhancement module, the pathological data processing module, the pathological diagnosis module, the scheduling module, the consultation module, the data storage module and the display module and is used for controlling the normal work of each module of the pathology department standardized work management and diagnosis consultation system through the central processing unit;
the information management module is connected with the central control module and is used for managing the acquired disease condition information of the patient and the information of the medical care personnel through an information management program;
the image enhancement module is connected with the central control module and is used for enhancing the acquired disease images of the patient through an image enhancement program;
the pathological data processing module is connected with the central control module and is used for processing the pathological report data through a data processing program;
the pathological diagnosis module is connected with the central control module and is used for diagnosing the pathology of the patient through a diagnosis program;
the scheduling module is connected with the central control module and is used for scheduling doctors and nursing staff in the pathology department through a scheduling program;
the consultation module is connected with the central control module and is used for diagnosing and consulting through a consultation program;
the data storage module is connected with the central control module and used for storing the acquired disease information, disease images, medical care information, scheduling results and consultation information through the memory;
and the display module is connected with the central control module and used for displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information through the display.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the method for job management and diagnostic consultation in clinical discipline specification when executed on an electronic device.
It is another object of the present invention to provide a computer-readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the method for standardized work management and diagnostic consultation for clinical departments.
By combining all the technical schemes, the invention has the advantages and positive effects that: according to the invention, the pathological report of the patient to be processed is structured through the pathological data processing module, and then the structured data is subjected to vector conversion, so that the pathological report of the patient to be processed can be digitally presented, and then the patient pathological matrix is subjected to dimension reduction processing, so that the matrix with low dimension is low in dimension, and the digital presentation can be more convenient for relevant personnel to know the similarity of the pathological reports of the patients to be processed, and therefore, the pathological representation matrix of the patients can provide the relevant personnel with pathological indication effect for the patients; meanwhile, the pathological image of the patient to be identified is input into the preset pathological image model of the patient through the pathological diagnosis module, the diagnosis result is obtained, the accuracy rate of the process is high, the speed is high, the workflow of a doctor in a patient pathology department can be greatly shortened, and the labor cost is saved.
Drawings
Fig. 1 is a flowchart of a method for standardized job management and diagnosis consultation in a pathology department according to an embodiment of the present invention.
FIG. 2 is a block diagram of a system for standardized job management and diagnostic consultation for a pathology department, according to an embodiment of the present invention;
in the figure: 1. a patient condition information acquisition module; 2. a patient disease image acquisition module; 3. a medical staff information acquisition module; 4. a central control module; 5. an information management module; 6. an image enhancement module; 7. a pathology data processing module; 8. a pathological diagnosis module; 9. a scheduling module; 10. a consultation module; 11. a data storage module; 12. and a display module.
Fig. 3 is a flowchart of a method for processing pathology report data by a data processing program according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for determining a weight corresponding to each word vector according to the multiple pathology reports of the patient to be processed according to an embodiment of the present invention.
Fig. 5 is a flow chart of a method for diagnosing a pathology in a patient using a diagnostic procedure according to an embodiment of the present invention.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for standardized operation management and diagnosis consultation in pathology department provided by the embodiment of the present invention includes the following steps:
s101, acquiring disease condition information of a patient by using patient information acquisition equipment through a patient disease information acquisition module; the medical imaging equipment is used for acquiring the disease images of the patient through the disease image acquisition module of the patient.
S102, information of doctors and nursing staff in the pathology department is collected through the medical staff information collecting module by using the medical staff information collecting equipment.
S103, controlling the normal work of each module of the pathology department standardized work management and diagnosis consultation system by using a central processing unit through a central control module.
S104, managing the information of the patient and the medical care personnel by using an information management program through an information management module; and enhancing the acquired disease images of the patient by an image enhancement program through an image enhancement module.
S105, processing the pathology report data by a pathology data processing module through a data processing program; the patient pathology is diagnosed by a pathology diagnosis module using a diagnostic program.
S106, scheduling the doctors and the nursing staff of the pathology department by using a scheduling program through a scheduling module; and diagnosis consultation is carried out by utilizing a consultation program through a consultation module.
And S107, storing the acquired disease information, disease images, medical care information, scheduling results and consultation information by using a memory through a data storage module.
And S108, displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information by using the display through the display module.
As shown in fig. 2, the system for standardized job management and diagnosis consultation for pathology department provided by the embodiment of the present invention includes: patient's disease information acquisition module 1, patient's disease image acquisition module 2, medical personnel information acquisition module 3, central control module 4, information management module 5, image enhancement module 6, pathological data processing module 7, pathological diagnosis module 8, scheduling module 9, consultation module 10, data storage module 11, display module 12.
The patient disease information acquisition module 1 is connected with the central control module 4 and is used for acquiring disease condition information of the patient through patient information acquisition equipment;
the patient disease image acquisition module 2 is connected with the central control module 4 and is used for acquiring a patient disease image through medical imaging equipment;
the medical staff information acquisition module 3 is connected with the central control module 4 and is used for acquiring information of doctors and nursing staff of a clinical department through medical staff information acquisition equipment;
the central control module 4 is connected with the patient disease information acquisition module 1, the patient disease image acquisition module 2, the medical staff information acquisition module 3, the information management module 5, the image enhancement module 6, the pathological data processing module 7, the pathological diagnosis module 8, the scheduling module 9, the consultation module 10, the data storage module 11 and the display module 12, and is used for controlling the normal work of each module of the pathology department standardized work management and diagnosis consultation system through a central processing unit;
the information management module 5 is connected with the central control module 4 and is used for managing the acquired patient disease condition information and the medical staff information through an information management program;
the image enhancement module 6 is connected with the central control module 4 and is used for enhancing the acquired disease images of the patient through an image enhancement program;
the pathological data processing module 7 is connected with the central control module 4 and is used for processing the pathological report data through a data processing program;
a pathological diagnosis module 8 connected with the central control module 4 and used for diagnosing the pathology of the patient through a diagnosis program;
the scheduling module 9 is connected with the central control module 4 and is used for scheduling doctors and nursing staff in the pathology department through a scheduling program;
the consultation module 10 is connected with the central control module 4 and is used for carrying out diagnosis consultation through a consultation program;
the data storage module 11 is connected with the central control module 4 and used for storing acquired disease information, disease images, medical care information, scheduling results and consultation information through a memory;
and the display module 12 is connected with the central control module 4 and is used for displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information through a display.
The invention is further described with reference to specific examples.
Example 1
Fig. 1 shows a standardized work management and diagnosis consultation method for pathology department according to an embodiment of the present invention, and fig. 3 shows a preferred embodiment of the standardized work management and diagnosis consultation method for pathology department according to an embodiment of the present invention, where the method for processing pathology report data by a data processing program includes:
s201, acquiring a plurality of pathological reports of patients to be processed through a data processing program; and preprocessing the plurality of pathological reports of the patients to be processed to obtain a plurality of pieces of pathological corpus data of the patients.
And S202, performing vector conversion on the plurality of pieces of patient pathology corpus data to obtain a patient pathology matrix of the plurality of to-be-processed patient pathology reports.
And S203, performing dimension reduction on the patient pathology matrix, and determining a patient pathology representation matrix corresponding to the plurality of to-be-processed patient pathology reports, wherein each row vector in the patient pathology representation matrix represents a representation vector of the to-be-processed patient pathology report.
The step of performing vector transformation on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of pieces of to-be-processed patient pathology reports provided by the embodiment of the invention includes:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient;
weighting and summing all the word vectors to obtain the pathological vector of the patient in the pathological corpus data of the patient; and a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix.
Before performing weighted summation on all word vectors to obtain the patient pathology vector in the patient pathology corpus data, the method provided by the embodiment of the invention further includes: and determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed.
The step of performing weighted summation on all word vectors to obtain the patient pathology vector in the patient pathology corpus data provided by the embodiment of the invention comprises the following steps: and carrying out weighted summation on all the word vectors by using the weights corresponding to the word vectors to obtain the pathological vector of the pathological corpus data of the patient.
As shown in fig. 4, the method for determining a weight corresponding to each word vector according to the multiple pathology reports of the patient to be processed provided by the embodiment of the present invention includes:
s301, calculating to obtain target reverse frequency according to the total number of the files of the plurality of pathological reports of the patient to be processed and the number of the files of the target words corresponding to the target word vectors in the plurality of pathological reports of the patient to be processed.
And S302, calculating the frequency of the target word according to the occurrence frequency of the target word in each pathological report of the patient to be processed.
And S303, calculating to obtain the weight of the target word vector according to the target reverse frequency and the target word frequency.
The method for performing vector conversion on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of pieces of to-be-processed patient pathology reports, provided by the embodiment of the invention, comprises the following steps:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; and a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix.
The method for performing vector conversion on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of pieces of to-be-processed patient pathology reports provided by the embodiment of the invention specifically comprises the following steps:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; calculating the average value of all word vectors in the pathological corpus data to obtain the pathological vector of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a first patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed; weighting and summing all word vectors in the pathological corpus data of the patient to obtain the pathological vectors of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a second patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; a third patient pathology matrix is formed by a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data;
and carrying out weighted summation on the first patient pathology matrix, the second patient pathology matrix and the third patient pathology matrix to obtain a pathology matrix.
Example 2
Fig. 1 shows a standardized work management and diagnosis consultation method for pathology department according to an embodiment of the present invention, and fig. 5 shows a preferred embodiment of the method for diagnosing pathology of a patient through a diagnosis program according to an embodiment of the present invention, which includes:
s401, acquiring pathological images and patient information of a patient to be identified through medical imaging equipment.
S402, inputting the pathological image of the patient to be identified into a preset pathological image model of the patient, and outputting a diagnosis result of the pathological image of the patient to be identified by the pathological image model of the patient.
And S403, generating a diagnosis report according to the diagnosis result and the patient information.
The acquisition process of the pathological image model of the patient provided by the embodiment of the invention comprises the following steps:
acquiring a plurality of pathological pictures of a patient as a training set, wherein the pathological pictures of the patient correspond to a first diagnosis result;
training a neural network model by using the training set to obtain a second diagnosis result; and if the first diagnosis result is different from the second diagnosis result, adjusting parameters of the neural network model until the first diagnosis result is the same as the second diagnosis result.
The method for acquiring the pathological image of the patient to be identified comprises the following steps:
(1) scanning pathological sections of a patient with a first resolution to obtain a pathological image of the first patient;
(2) determining at least one local area of the pathological image of the first patient as a suspected lesion area;
(3) scanning the suspected lesion area with a second resolution to obtain a pathological image of a second patient, wherein the second resolution is higher than the first resolution;
(4) and taking the second patient pathology image as a patient pathology image to be identified.
The method for acquiring the pathological image of the patient to be identified further comprises the following steps:
1) carrying out gray level processing on the pathological image of the patient to be identified to obtain the pathological gray level image of the patient to be identified;
2) carrying out noise removal and filtering processing on the pathological gray level image of the patient to be identified to obtain a distortion-free pathological gray level image of the patient to be identified;
3) and identifying a region with a gray mean value smaller than a preset gray value in the undistorted patient pathology gray image to be identified, and assigning the region with the gray mean value smaller than the preset gray value in the undistorted patient pathology gray image to be black.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A pathology department standardization work management and diagnosis consultation method is characterized by comprising the following steps:
step one, acquiring disease condition information of a patient by using patient information acquisition equipment through a patient disease information acquisition module; acquiring a patient disease image by using medical imaging equipment through a patient disease image acquisition module;
acquiring information of doctors and nursing staff of a pathology department by using medical staff information acquisition equipment through a medical staff information acquisition module; the central control module utilizes a central processor to control the normal work of each module of the pathology department standardized work management and diagnosis consultation system;
step three, enhancing the acquired disease images of the patient by an image enhancement module through an image enhancement program; managing the acquired patient disease condition information and the medical care personnel information by an information management module through an information management program;
acquiring a plurality of pathological reports of the patient to be processed by using a data processing program through a pathological data processing module; preprocessing the plurality of patient pathology reports to be processed to obtain a plurality of pieces of patient pathology corpus data;
step five, aiming at each piece of pathological corpus data of the patients, carrying out vector transformation on each word in each piece of pathological corpus data of the patients by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patients;
step six, performing weighted summation on all word vectors to obtain the patient pathology vectors in the patient pathology corpus data; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix;
seventhly, performing dimensionality reduction on the patient pathology matrix, determining a patient pathology representation matrix corresponding to the plurality of to-be-processed patient pathology reports, wherein each row vector in the patient pathology representation matrix represents a representation vector of the to-be-processed patient pathology report, and processing pathology report data;
step eight, diagnosing the pathology of the patient by using a diagnosis program through a pathology diagnosis module; scheduling doctors and nursing staff in a pathology department by using a scheduling program through a scheduling module;
step nine, acquiring a plurality of pathological pictures of the patient as a training set, wherein the pathological pictures of the patient correspond to a first diagnosis result; training a neural network model by using the training set to obtain a second diagnosis result; if the first diagnosis result is different from the second diagnosis result, adjusting parameters of the neural network model until the first diagnosis result is the same as the second diagnosis result;
step ten, acquiring pathological images and patient information of a patient to be identified by using medical imaging equipment through a consultation module; inputting the pathological image of the patient to be identified into a preset pathological image model of the patient, and outputting a diagnosis result of the pathological image of the patient to be identified by the pathological image model of the patient; generating a diagnosis report according to the diagnosis result and the patient information by utilizing a consultation program;
step eleven, storing the acquired disease information, disease images, medical care information, scheduling results and consultation information by a data storage module through a memory; and the display is used for displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information through the display module.
2. The pathology department standardized work management and diagnosis consultation method according to claim 1, wherein in the sixth step, said weighted summation of all the word vectors is performed to obtain the patient pathology vectors in the piece of patient pathology corpus data; the method further comprises the following steps: and determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed.
3. The pathology department standardized work management and diagnosis consultation method according to claim 2, wherein said method of weighted summation of all word vectors to obtain the patient pathology vector in the piece of patient pathology corpus data comprises: and carrying out weighted summation on all the word vectors by using the weights corresponding to the word vectors to obtain the pathological vector of the pathological corpus data of the patient.
4. The pathology department standardized work management and diagnosis consultation method according to claim 2, characterized in that said method of determining the weight corresponding to each word vector from said plurality of patient pathology reports to be processed comprises:
(I) calculating to obtain target reverse frequency according to the total number of files of the pathological reports of the patients to be processed and the number of files of target words corresponding to target word vectors in the pathological reports of the patients to be processed;
(II) calculating the occurrence frequency of the target word in each pathological report of the patient to be processed according to the target word;
and (III) calculating to obtain the weight of the target word vector according to the target reverse frequency and the target word frequency.
5. The pathology department standardized work management and diagnosis consultation method according to claim 1, wherein in the sixth step, said method of vector-transforming said plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of said plurality of to-be-processed patient pathology reports comprises:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; and a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data form a patient pathology matrix.
6. The pathology department standardized work management and diagnosis consultation method according to claim 5, wherein the method for performing vector transformation on the plurality of pieces of patient pathology corpus data to obtain the patient pathology matrix of the plurality of to-be-processed patient pathology reports specifically comprises:
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; calculating the average value of all word vectors in the pathological corpus data to obtain the pathological vector of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a first patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, carrying out vector transformation on each word in each piece of pathological corpus data of the patient by using a word bag model to obtain a word vector of each word in the pathological corpus data of the patient; determining the weight corresponding to each word vector according to the plurality of pathological reports of the patients to be processed; weighting and summing all word vectors in the pathological corpus data of the patient to obtain the pathological vectors of the patient in the pathological corpus data of the patient; a plurality of patient pathology vectors corresponding to the plurality of pieces of patient pathology corpus data form a second patient pathology matrix;
aiming at each piece of pathological corpus data of the plurality of pieces of patient pathological corpus data, vector conversion is carried out on each piece of pathological corpus data of the patient by using a bag-of-word model, and a sentence vector of the pathological corpus data of the patient is obtained; a third patient pathology matrix is formed by a plurality of sentence vectors corresponding to the plurality of pieces of patient pathology corpus data;
and carrying out weighted summation on the first patient pathology matrix, the second patient pathology matrix and the third patient pathology matrix to obtain a pathology matrix.
7. The pathology department standardized work management and diagnosis consultation method according to claim 1, characterized in that in the tenth step, before said acquisition of pathological images of said patient to be identified, it further comprises:
(1) scanning pathological sections of a patient with a first resolution to obtain a pathological image of the first patient;
(2) determining at least one local area of the pathological image of the first patient as a suspected lesion area;
(3) scanning the suspected lesion area with a second resolution to obtain a pathological image of a second patient, wherein the second resolution is higher than the first resolution;
(4) taking the second patient pathology image as a patient pathology image to be identified;
the acquiring the pathological image of the patient to be identified further comprises:
1) carrying out gray level processing on the pathological image of the patient to be identified to obtain the pathological gray level image of the patient to be identified;
2) carrying out noise removal and filtering processing on the pathological gray level image of the patient to be identified to obtain a distortion-free pathological gray level image of the patient to be identified;
3) and identifying a region with a gray mean value smaller than a preset gray value in the undistorted patient pathology gray image to be identified, and assigning the region with the gray mean value smaller than the preset gray value in the undistorted patient pathology gray image to be black.
8. A pathology department standardized work management and diagnosis consultation system applying the pathology department standardized work management and diagnosis consultation method according to any one of claims 1 to 7, comprising:
the patient disease information acquisition module is connected with the central control module and is used for acquiring the disease condition information of the patient through patient information acquisition equipment;
the patient disease image acquisition module is connected with the central control module and is used for acquiring a patient disease image through medical imaging equipment;
the medical staff information acquisition module is connected with the central control module and is used for acquiring information of doctors and nursing staff in a pathology department through medical staff information acquisition equipment;
the central control module is connected with the patient disease information acquisition module, the patient disease image acquisition module, the medical staff information acquisition module, the information management module, the image enhancement module, the pathological data processing module, the pathological diagnosis module, the scheduling module, the consultation module, the data storage module and the display module and is used for controlling the normal work of each module of the pathology department standardized work management and diagnosis consultation system through the central processing unit;
the information management module is connected with the central control module and is used for managing the acquired disease condition information of the patient and the information of the medical care personnel through an information management program;
the image enhancement module is connected with the central control module and is used for enhancing the acquired disease images of the patient through an image enhancement program;
the pathological data processing module is connected with the central control module and is used for processing the pathological report data through a data processing program;
the pathological diagnosis module is connected with the central control module and is used for diagnosing the pathology of the patient through a diagnosis program;
the scheduling module is connected with the central control module and is used for scheduling doctors and nursing staff in the pathology department through a scheduling program;
the consultation module is connected with the central control module and is used for diagnosing and consulting through a consultation program;
the data storage module is connected with the central control module and used for storing the acquired disease information, disease images, medical care information, scheduling results and consultation information through the memory;
and the display module is connected with the central control module and used for displaying the acquired real-time data of the disease information, the disease image, the medical care information, the scheduling result and the consultation information through the display.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing a method of clinical practice normative job management and diagnostic counseling as claimed in any one of claims 1 to 7 when executed on an electronic device.
10. A computer readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the method of pathology department standardized work management and diagnostic counseling according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010573185.0A CN111681749A (en) | 2020-06-22 | 2020-06-22 | Pathology department standardized work management and diagnosis consultation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010573185.0A CN111681749A (en) | 2020-06-22 | 2020-06-22 | Pathology department standardized work management and diagnosis consultation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111681749A true CN111681749A (en) | 2020-09-18 |
Family
ID=72436765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010573185.0A Pending CN111681749A (en) | 2020-06-22 | 2020-06-22 | Pathology department standardized work management and diagnosis consultation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111681749A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838559A (en) * | 2021-09-15 | 2021-12-24 | 王其景 | Medical image management system and method |
| CN115206512A (en) * | 2022-09-15 | 2022-10-18 | 武汉大学人民医院（湖北省人民医院） | Hospital information management method and device based on Internet of things |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160267226A1 (en) * | 2013-11-26 | 2016-09-15 | Koninklijke Philips N.V. | System and method for correlation of pathology reports and radiology reports |
| CN106295173A (en) * | 2016-08-09 | 2017-01-04 | 孙珠蕾 | The standardization work management of a kind of Pathology Deparment and diagnosis consulting systems soft ware |
| CN110335256A (en) * | 2019-06-18 | 2019-10-15 | 广州智睿医疗科技有限公司 | A kind of pathology aided diagnosis method |
| CN110517747A (en) * | 2019-08-30 | 2019-11-29 | 志诺维思（北京）基因科技有限公司 | Pathological data processing method, device and electronic equipment |
| CN110517760A (en) * | 2019-08-29 | 2019-11-29 | 上海盛巨信息技术有限公司 | The data processing method and device that doctor arranges an order according to class and grade |
| CN110570937A (en) * | 2019-09-17 | 2019-12-13 | 上海劳勤信息技术有限公司 | Method for scheduling by doctors and assistants |
-
2020
- 2020-06-22 CN CN202010573185.0A patent/CN111681749A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160267226A1 (en) * | 2013-11-26 | 2016-09-15 | Koninklijke Philips N.V. | System and method for correlation of pathology reports and radiology reports |
| CN106295173A (en) * | 2016-08-09 | 2017-01-04 | 孙珠蕾 | The standardization work management of a kind of Pathology Deparment and diagnosis consulting systems soft ware |
| CN110335256A (en) * | 2019-06-18 | 2019-10-15 | 广州智睿医疗科技有限公司 | A kind of pathology aided diagnosis method |
| CN110517760A (en) * | 2019-08-29 | 2019-11-29 | 上海盛巨信息技术有限公司 | The data processing method and device that doctor arranges an order according to class and grade |
| CN110517747A (en) * | 2019-08-30 | 2019-11-29 | 志诺维思（北京）基因科技有限公司 | Pathological data processing method, device and electronic equipment |
| CN110570937A (en) * | 2019-09-17 | 2019-12-13 | 上海劳勤信息技术有限公司 | Method for scheduling by doctors and assistants |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838559A (en) * | 2021-09-15 | 2021-12-24 | 王其景 | Medical image management system and method |
| CN115206512A (en) * | 2022-09-15 | 2022-10-18 | 武汉大学人民医院（湖北省人民医院） | Hospital information management method and device based on Internet of things |
| CN115206512B (en) * | 2022-09-15 | 2022-11-15 | 武汉大学人民医院（湖北省人民医院） | Hospital information management method and device based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5952835B2 (en) | Imaging protocol updates and / or recommenders | |
| US20090204437A1 (en) | System and method for improving diagnoses of medical image reading | |
| US11195610B2 (en) | Priority alerts based on medical information | |
| EP2798549B1 (en) | Imaging examination protocol update recommender | |
| JP6208243B2 (en) | Morbidity assessment device, morbidity assessment method, and morbidity assessment program | |
| US12072944B2 (en) | Systems and methods for dynamic data processing and graphical user interface processing | |
| US7418120B2 (en) | Method and system for structuring dynamic data | |
| JP2007280229A (en) | Similar case retrieval device, similar case retrieval method and program | |
| JP5732015B2 (en) | Graph creating apparatus, graph creating method, and graph creating program | |
| US20190189270A1 (en) | Hospital information apparatus, hospital information system, and hospital information processing method | |
| JP7552845B2 (en) | Information processing device, medical image display device, and program | |
| JP6049194B2 (en) | Graph display device, method of operating graph display device, and graph display program | |
| JP2007307290A (en) | Medical image reading system | |
| JP7102999B2 (en) | Information collection processing equipment, information collection processing method and program | |
| US20110145274A1 (en) | Exemplary Data Guidance in a Multi-Modality Data Viewer | |
| CN111681749A (en) | Pathology department standardized work management and diagnosis consultation system and method | |
| JP2009059381A (en) | Medical diagnosis support method and device, and diagnosis support information recording medium | |
| US20130322710A1 (en) | Systems and methods for computer aided detection using pixel intensity values | |
| JP7013841B2 (en) | Interpretation report analysis device and program | |
| US8005278B2 (en) | System and method for patient acuity driven workflow using computer-aided diagnosis of medical images | |
| JP7415787B2 (en) | medical imaging system | |
| US20070083849A1 (en) | Auto-learning RIS/PACS worklists | |
| JP2008217426A (en) | Case registration system | |
| CN108984587B (en) | Information processing apparatus, information processing method, information processing system, and storage medium | |
| JP3284122B2 (en) | Medical diagnosis support system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200918 |