CN112190277A - Data fitting method for CT reexamination of new coronary pneumonia - Google Patents
Data fitting method for CT reexamination of new coronary pneumonia Download PDFInfo
- Publication number
- CN112190277A CN112190277A CN202011238084.4A CN202011238084A CN112190277A CN 112190277 A CN112190277 A CN 112190277A CN 202011238084 A CN202011238084 A CN 202011238084A CN 112190277 A CN112190277 A CN 112190277A
- Authority
- CN
- China
- Prior art keywords
- area
- data
- image
- time
- density
- 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
- 206010035664 Pneumonia Diseases 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 31
- 210000004072 lung Anatomy 0.000 claims abstract description 57
- 230000003902 lesion Effects 0.000 claims abstract description 52
- 230000008859 change Effects 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000012552 review Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 4
- 208000025721 COVID-19 Diseases 0.000 description 3
- 241000711573 Coronaviridae Species 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000010444 Acidosis Diseases 0.000 description 1
- 206010001052 Acute respiratory distress syndrome Diseases 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 206010027417 Metabolic acidosis Diseases 0.000 description 1
- 208000034486 Multi-organ failure Diseases 0.000 description 1
- 206010035737 Pneumonia viral Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 208000013616 Respiratory Distress Syndrome Diseases 0.000 description 1
- 206010040070 Septic Shock Diseases 0.000 description 1
- 201000000028 adult respiratory distress syndrome Diseases 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 208000017574 dry cough Diseases 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 231100000225 lethality Toxicity 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 208000029744 multiple organ dysfunction syndrome Diseases 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000036303 septic shock Effects 0.000 description 1
- 208000009421 viral pneumonia Diseases 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5294—Devices using data or image processing specially adapted for radiation diagnosis involving using additional data, e.g. patient information, image labeling, acquisition parameters
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Optics & Photonics (AREA)
- Biophysics (AREA)
- High Energy & Nuclear Physics (AREA)
- Veterinary Medicine (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pulmonology (AREA)
Abstract
The invention discloses a data fitting method for CT reexamination of new coronary pneumonia, which comprises the following steps: s1, obtaining a reexamination lung CT image of the new coronary pneumonia patient through a CT detection instrument, extracting a new coronary pneumonia focus area in the reexamination lung CT image of the patient, and recording the generation time, area and density data of the new coronary pneumonia focus area CT image to generate a reexamination data report. The time sequence-based lesion area change curve and the time sequence-based lesion density change curve function are obtained by utilizing the curve fitting function, and the past change condition and the future time of a lesion can be simultaneously mastered, so that the future trend of the lesion under the treatment scheme can be predicted in the early and middle stages of the treatment scheme, whether the scheme is effective or not can be judged, the condition delay of a patient under the scheme is avoided, and the trial and error cost is reduced.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a data fitting method for CT reexamination of new coronary pneumonia.
Background
The novel coronavirus pneumonia (Corona Virus Disease 2019, COVID-19) is called as new coronavirus pneumonia for short, the world health organization is named as '2019 coronavirus Disease', the pneumonia caused by 2019 novel coronavirus infection is mainly manifested by fever, dry cough and weakness, severe cases mostly have dyspnea after one week, severe patients rapidly progress to acute respiratory distress syndrome, septic shock, metabolic acidosis which is difficult to correct, coagulation dysfunction, multi-organ failure and the like, and the medicine has strong lethality and infectivity.
The current reliable detection mode of the new coronary pneumonia prompts the imaging performance of viral pneumonia for the lung CT image examination, so that the focus detection of the new coronary pneumonia is carried out on a patient, the treatment of the new coronary pneumonia is an inaccurate treatment scheme at present, and needs to be continuously searched in the treatment process.
At present, a doctor judges the development condition of a focus through a plurality of lung CT images, only can master the change condition of the focus in the past, and cannot master the future condition of the focus, namely, the future change trend of the focus under the current treatment scheme cannot be mastered, so that the effect of the current treatment scheme cannot be reasonably judged, the treatment scheme needs to be continuously observed, and the condition of a patient is delayed if the treatment scheme is invalid, so that the trial and error cost of the treatment scheme is too high, and the time is long.
Disclosure of Invention
The invention aims to provide a data fitting method for CT reexamination of new coronary pneumonia, and aims to solve the technical problems that in the prior art, the future change trend of a focus under the current treatment scheme cannot be mastered, and whether the current treatment scheme is effective or not cannot be reasonably judged, so that the trial-and-error cost of the treatment scheme is too high and the time is long.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a data fitting method for CT review of new coronary pneumonia comprises the following steps:
s1, obtaining a reexamination lung CT image of the new coronary pneumonia patient through a CT detection instrument, extracting a new coronary pneumonia focus area in the reexamination lung CT image of the patient, and recording the generation time, area and density data of the new coronary pneumonia focus area CT image to generate a reexamination data report;
s2, retrieving all historical data reports formed by the generation time, area and density data of the CT image of the new coronary pneumonia lesion area in the historical lung CT images of the reexamination patient in each time period from the historical report database according to the personal information of the patient;
s3, performing time sequence fitting on the area and density data in the review data report and all historical data reports in each time period to obtain a fitted curve of the area and density of the new coronary pneumonia lesion based on time sequence transformation;
s4, predicting and rechecking the subsequent rehabilitation progress of the new coronary pneumonia lesion of the patient according to the fitted curve of the area and the density, and transmitting the prediction result to an inquiry terminal for the inquiry of the patient and a doctor;
and S5, storing the review data report into the historical report database, combining the review data report into a part of the historical data report of each time period to fill the fitting data amount, and providing the functions of storing and reading.
As a preferred embodiment of the present invention, in S1, the specific process of extracting a new coronary pneumonia lesion region in a review lung CT image of a patient and recording the area and density of the new coronary pneumonia lesion is as follows:
s101, decomposing a reexamined lung CT image of a patient into a plurality of pixel points according to a grid mode and obtaining a pixel value of each pixel point;
s102, comparing pixel values of a plurality of pixels with a pixel threshold of a normal lung CT image in sequence, and reserving pixels exceeding the pixel threshold of the normal lung CT image;
s103, summing the areas of all the pixel points exceeding the pixel point threshold of the normal lung CT image to obtain the area of a focus area; and averaging all pixel point pixel values of which all pixels exceed the pixel point threshold of the normal lung CT image to obtain the density of the focus area.
As a preferred embodiment of the present invention, in S101, the specific step of decomposing the lung CT image of the reexamined patient into a plurality of pixel points in a grid manner includes:
s1011, defining the distances between the adjacent transverse grid points and the distances between the adjacent longitudinal grid points to be L;
s1012, taking a straight line where the vertex on the lung tissue in the CT image of the lung of the reexamined patient as a horizontal coordinate axis, and taking a straight line where the left vertex is as a vertical coordinate axis;
s1013, performing horizontal grid drawing on the horizontal axis of coordinates according to L, performing horizontal grid drawing on the vertical axis of coordinates according to L, and performing horizontal coordinate marking on the horizontal axis of coordinates to (x1, x2, x3 …, xn), where n is the number of horizontal grid points, and performing vertical coordinate marking on the vertical axis of coordinates to (y1, y2, y3 …, ym), where m is the number of vertical grid points;
and S1014, decomposing the CT image of the lung of the reexamined patient into n × m pixel points of a rectangular grid with coordinates (xn, ym), and marking the pixel value at the midpoint position of the rectangular grid as the pixel value of the pixel point as Wi, wherein i is (n, m).
As a preferable mode of the present invention, in S1013, the starting point plotted in horizontal grid on the horizontal axis of the coordinate is located at the intersection of the vertical axis of the coordinate and the horizontal axis of the coordinate, the ending point is located at the closest distance to the right side of the straight line where the right vertex of the lung tissue in the CT image of the lung of the review patient is located, the starting point plotted in vertical grid on the vertical axis of the coordinate is located at the intersection of the vertical axis of the coordinate and the horizontal axis of the coordinate, and the ending point is located at the closest distance to the lower side of the straight line where the lower vertex.
As a preferred scheme of the present invention, in S102, pixel values of a plurality of pixels are sequentially compared with a pixel threshold of a normal lung CT image, and pixels exceeding the pixel threshold of the normal lung CT image are retained:
and sequentially comparing the pixel Wi of the pixel (xn, ym) with the pixel threshold mark W threshold value, and recording all the pixels in Wi > W threshold value, wherein the pixels of all the pixels are marked as (W1, W2, W3, …, Wk), and k is the number of the pixels.
In a preferred embodiment of the present invention, in S103, the area of each pixel is L × L in accordance with the area of the rectangular grid, the area of the lesion region is marked as S ═ k × L, and the density of the lesion region is marked as S ═ k × L.
As a preferred aspect of the present invention, in S3, the CT image generation time, area and density data in the review data report and the CT image generation time, area and density data in the history data report of all the time periods form a time-series data set, which is marked as { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) }, where j is the sum of the report total numbers of the review data report and the history data report.
As a preferable aspect of the present invention, in S3, the specific step of performing time-series fitting on the area and density data in the review data report and all the historical data reports of each period is as follows:
s301, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } time and area data { (T1, S1), (T2, S2), …, (Tj, Sj) }, obtaining a time-series-based lesion area change curve using a curve fitting function, where the function is expressed as Sj ═ f (Tj), where f represents a function sign;
s302, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } middle time and density data { (T1, P1), (T2, P2), …, (Tj, Pj) }, and obtaining a time-series-based lesion density change curve function by using a curve fitting function, which is expressed as Pj ═ f (Tj), where f represents a function sign.
As a preferred embodiment of the present invention, in S4, the manner for predicting the subsequent rehabilitation progress of the patient from the new coronary pneumonia lesion based on the fitted curve is:
extending the time sequence from the current reexamination time to infinity in the future, extending a focus area change curve based on the time sequence along with the time sequence to obtain the focus area change curve form of the time sequence in the future, obtaining the change trend of the focus area of new coronary pneumonia in the future, obtaining the focus area value of specific time in the future, and substituting the specific time into Sj (f) (Tj) for operation to obtain the focus area value;
and (3) extending the time sequence from the current reexamination time to infinity in the future, extending a focus density change curve based on the time sequence along with the time sequence to obtain the focus density change curve form of the time sequence in the future, obtaining the change trend of the focus density of the new coronary pneumonia in the future, obtaining the focus density value of a specific time in the future, and substituting the specific time into Pj (f) (Tj) for operation to obtain the focus density value.
As a preferred scheme of the present invention, the S1, S2, S3, S4, and S5 are established in a distributed data processing system constructed by a plurality of servers and a computer host for performing operation processing and data storage, the query terminal in S4 is an intelligent terminal device equipped with a query login portal, the query login portal is a web page, a software APP, or a applet, and the query login portal and the distributed data processing system perform data exchange and service interaction through network communication.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the time sequence data set is formed by reviewing the CT image generation time, the area and the density data in the data report and the CT image generation time, the area and the density data in the historical data report of all time periods, the time sequence-based lesion area change curve and the time sequence-based lesion density change curve function are obtained by using the curve fitting function, and the past change condition and the future time of a lesion can be simultaneously mastered, so that the future trend of the lesion under the treatment scheme can be predicted in the early and middle stages of the treatment scheme, whether the scheme is effective or not can be judged, the condition delay of a patient under the scheme is avoided, and the trial and error cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow chart of a data fitting method provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a review CT image decomposed into a plurality of pixel grids according to an embodiment of the present invention;
FIG. 3 is a time-based focal area variation curve function according to an embodiment of the present invention;
FIG. 4 is a time-based lesion density variation curve function according to an embodiment of the present invention.
The reference numerals in the drawings denote the following, respectively:
1-lung tissue; 2-review the focus area in the CT image.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a data fitting method for CT review of new coronary pneumonia, which comprises:
s1, obtaining a reexamination lung CT image of the new coronary pneumonia patient through a CT detection instrument, extracting a new coronary pneumonia focus area in the reexamination lung CT image of the patient, and recording the generation time, area and density data of the new coronary pneumonia focus area CT image to generate a reexamination data report;
s2, retrieving all historical data reports formed by the generation time, area and density data of the CT image of the new coronary pneumonia lesion area in the historical lung CT images of the reexamination patient in each time period from the historical report database according to the personal information of the patient;
s3, performing time sequence fitting on the area and density data in the review data report and all historical data reports in each time period to obtain a fitted curve of the area and density of the new coronary pneumonia lesion based on time sequence transformation;
s4, predicting the follow-up rehabilitation progress of the newly-investigated patient coronary pneumonia lesion according to the fitted curve of the area and the density, and transmitting the prediction result to an inquiry terminal for the inquiry of a doctor;
and S5, storing the review data report into the historical report database, combining the review data report into a part of the historical data report of each time period to fill the fitting data amount, and providing the functions of storing and reading.
In S1, the specific process of extracting a new coronary pneumonia lesion region in a review lung CT image of a patient and recording the area and density of the new coronary pneumonia lesion is as follows:
s101, decomposing a reexamined lung CT image of a patient into a plurality of pixel points according to a grid mode and obtaining a pixel value of each pixel point;
s102, comparing pixel values of a plurality of pixels with a pixel threshold of a normal lung CT image in sequence, and reserving pixels exceeding the pixel threshold of the normal lung CT image;
s103, summing the areas of all the pixel points exceeding the pixel point threshold of the normal lung CT image to obtain the area of a focus area; and averaging all pixel point pixel values of which all pixels exceed the pixel point threshold of the normal lung CT image to obtain the density of the focus area.
As shown in fig. 2, in S101, the specific steps of decomposing the lung CT image of the review patient into a plurality of pixel points in a grid manner are as follows:
s1011, defining the distances between the adjacent transverse grid points and the distances between the adjacent longitudinal grid points to be L;
the smaller L is, the smaller the area of the formed grid point is, the closer the grid point is, the area and the density of the focus area obtained by calculation on the basis of the area and the density are close to real values, but the calculation amount is increased along with the area and the density, so that the value of L can be set and adjusted as required in actual use.
S1012, taking a straight line where the vertex on the lung tissue in the CT image of the lung of the reexamined patient as a horizontal coordinate axis, and taking a straight line where the left vertex is as a vertical coordinate axis;
s1013, performing horizontal grid drawing on the horizontal axis of coordinates according to L, performing horizontal grid drawing on the vertical axis of coordinates according to L, and performing horizontal coordinate marking on the horizontal axis of coordinates to (x1, x2, x3 …, xn), where n is the number of horizontal grid points, and performing vertical coordinate marking on the vertical axis of coordinates to (y1, y2, y3 …, ym), where m is the number of vertical grid points;
and S1014, decomposing the CT image of the lung of the reexamined patient into n × m pixel points of a rectangular grid with coordinates (xn, ym), and marking the pixel value at the midpoint position of the rectangular grid as the pixel value of the pixel point as Wi, wherein i is (n, m).
In S1013, the starting point plotted in horizontal grid on the horizontal axis of the coordinate is located at the intersection point of the vertical axis of the coordinate and the horizontal axis of the coordinate, the ending point is located at the closest distance on the right side of the straight line where the right vertex of the lung tissue in the CT image of the lung of the review patient is located, the starting point plotted in vertical grid on the vertical axis of the coordinate is located at the intersection point of the vertical axis of the coordinate and the horizontal axis of the coordinate, and the ending point is located at the closest distance on the lower side of the straight line where.
In S102, the pixel values of the pixels are sequentially compared with the pixel threshold of the normal lung CT image, and the pixels exceeding the pixel threshold of the normal lung CT image are retained:
and sequentially comparing the values of the pixels Wi of the pixels (xn, ym) with the pixel threshold mark W threshold, and recording all the pixels in Wi > W threshold, wherein the pixels of all the pixels are marked as (W1, W2, W3, … and Wk), and k is the number of the pixels.
In S103, the area of each pixel point is L × L consistent with the area of the rectangular grid, the area of the lesion region is labeled as S × k × L, and the density of the lesion region is labeled as density.
In S3, the CT image generation time, area and density data in the review data report and the CT image generation time, area and density data in all the historical data reports for each period constitute data having a time-series data set labeled { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) }, where j is the sum of the total number of reports for the review data report and the historical data report.
In S3, the specific step of performing time-series fitting on the area and density data in the review data report and all the historical data reports of each period is as follows:
s301, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } time and area data { (T1, S1), (T2, S2), …, (Tj, Sj) }, obtaining a time-series-based lesion area change curve using a curve fitting function, where the function is expressed as Sj ═ f (Tj), where f represents a function sign;
s302, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } time-and-density data { (T1, P1), (T2, P2), …, (Tj, Pj) }, and obtaining a time-series-based lesion density variation curve using a curve fitting function, which is represented by Pj ═ f (Tj), where f represents a function sign.
The curve fitting function can be fitted by using a curve fitting function toolbox in MATLAB (matrix laboratory) integrated software or other operation software with the same calculation function, and specifically comprises the following steps: the method comprises the steps of inputting { (T1, S1), (T2, S2), …, (Tj, Sj) } to a curve fitting function toolbox, outputting a time-series-based lesion area change curve and a function Sj ═ f (Tj), and inputting { (T1, P1), (T2, P2), …, (Tj, Pj) } to the curve fitting function toolbox, and outputting a time-series-based lesion area change curve and a function Sj ═ f (Tj).
In S4, the method for predicting the subsequent rehabilitation progress of the patient for reviewing the new coronary pneumonia lesion according to the fitted curve is as follows:
extending the time sequence from the current reexamination time to infinity in the future, extending a focus area change curve based on the time sequence along with the time sequence to obtain the focus area change curve form of the time sequence in the future, obtaining the change trend of the focus area of new coronary pneumonia in the future, obtaining the focus area value of specific time in the future, and substituting the specific time into Sj (f) (Tj) for operation to obtain the focus area value;
and (3) extending the time sequence from the current reexamination time to infinity in the future, extending a focus density change curve based on the time sequence along with the time sequence to obtain the focus density change curve form of the time sequence in the future, obtaining the change trend of the focus density of the new coronary pneumonia in the future, obtaining the focus density value of a specific time in the future, and substituting the specific time into Pj (f) (Tj) for operation to obtain the focus density value.
As shown in fig. 3 and 4, the lesion area change curve shape in the future time series and the lesion density change curve shape in the future time series are in a descending trend, which indicates that the current treatment plan is effective, and by using Sj ═ f (tj) ═ 0 and Pj ═ f (tj) ═ W threshold, if the time point T area at which the lesion area is restored to 0 is obtained, the density is restored to the pixel threshold time point T density of the normal lung CT image, and the larger value of the T area and the T density is taken as the time point at which the patient is cured, thereby ensuring that the lesion area at the curing time point is restored to 0 and the density is restored to the pixel threshold value of the normal lung CT image, and if Sj ═ f (tj) cannot be 0 and Pj ═ f (tj) cannot be the W threshold, the time point at which Sj ═ f (tj) is infinitely close to 0 and Pj ═ f (tj) is infinitely close to the W threshold is calculated as the curing time point.
The lesion area change curve form of the future time sequence or the lesion density change curve form of the future time sequence is in an ascending trend, which indicates that the current treatment scheme is invalid.
S1, S2, S3, S4 and S5 are established in a distributed data processing system which is formed by a plurality of servers and a computer host and are used for operation processing and data storage, when the distributed system with huge diagnosis data volume of new coronary pneumonia patients cannot be loaded, the operation host is only required to be accessed into the distributed system to expand the operation volume and the storage volume so as to bear large data volume calculation, the patient waiting volume is huge in the period of the new coronary pneumonia patients with serious illness, and the distributed system provides realized hardware support for ensuring that each patient can obtain fair medical diagnosis resources.
The inquiry terminal in the S4 is an intelligent terminal device provided with an inquiry login portal, the inquiry login portal is a webpage, a software APP or a small program, the hospital can install the access login portal into a hospital computer for seeing a doctor to check the lesion area and density change curve trend of a patient based on time sequence, and the inquiry login portal and the distributed data processing system perform data exchange and service interaction through network communication.
According to the invention, the time sequence data set is formed by reviewing the CT image generation time, the area and the density data in the data report and the CT image generation time, the area and the density data in the historical data report of all time periods, the time sequence-based lesion area change curve and the time sequence-based lesion density change curve function are obtained by using the curve fitting function, and the past change condition and the future time of a lesion can be simultaneously mastered, so that the future trend of the lesion under the treatment scheme can be predicted in the early and middle stages of the treatment scheme, whether the scheme is effective or not can be judged, the condition delay of a patient under the scheme is avoided, and the trial and error cost is reduced.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A data fitting method for CT reexamination of new coronary pneumonia is characterized by comprising the following steps: the method comprises the following steps:
s1, obtaining a reexamination lung CT image of the new coronary pneumonia patient through a CT detection instrument, extracting a new coronary pneumonia focus area in the reexamination lung CT image of the patient, and recording the generation time, area and density data of the new coronary pneumonia focus area CT image to generate a reexamination data report;
s2, retrieving all historical data reports formed by the generation time, area and density data of the CT image of the new coronary pneumonia lesion area in the historical lung CT images of the reexamination patient in each time period from the historical report database according to the personal information of the patient;
s3, performing time sequence fitting on the area and density data in the review data report and all historical data reports in each time period to obtain a fitted curve of the area and density of the new coronary pneumonia lesion based on time sequence transformation;
s4, predicting and rechecking the subsequent rehabilitation progress of the new coronary pneumonia lesion of the patient according to the fitted curve of the area and the density, and transmitting the prediction result to an inquiry terminal for the inquiry of the patient and a doctor;
and S5, storing the review data report into the historical report database, combining the review data report into a part of the historical data report of each time period to fill the fitting data amount, and providing the functions of storing and reading.
2. The method of claim 1, wherein the method comprises the following steps: in S1, the specific process of extracting a new coronary pneumonia lesion region in a review lung CT image of a patient and recording the area and density of the new coronary pneumonia lesion is as follows:
s101, decomposing a reexamined lung CT image of a patient into a plurality of pixel points according to a grid mode and obtaining a pixel value of each pixel point;
s102, comparing pixel values of a plurality of pixels with a pixel threshold of a normal lung CT image in sequence, and reserving pixels exceeding the pixel threshold of the normal lung CT image;
s103, summing the areas of all the pixel points exceeding the pixel point threshold of the normal lung CT image to obtain the area of a focus area; and averaging all pixel point pixel values of which all pixels exceed the pixel point threshold of the normal lung CT image to obtain the density of the focus area.
3. The method of claim 2, wherein the method comprises the following steps: in the step S101, the specific steps of decomposing the lung CT image of the reexamined patient into a plurality of pixel points in a grid manner are as follows:
s1011, defining the distances between the adjacent transverse grid points and the distances between the adjacent longitudinal grid points to be L;
s1012, taking a straight line where the vertex on the lung tissue in the CT image of the lung of the reexamined patient as a horizontal coordinate axis, and taking a straight line where the left vertex is as a vertical coordinate axis;
s1013, performing horizontal grid drawing on the horizontal axis of coordinates according to L, performing horizontal grid drawing on the vertical axis of coordinates according to L, and performing horizontal coordinate marking on the horizontal axis of coordinates to (x1, x2, x3 …, xn), where n is the number of horizontal grid points, and performing vertical coordinate marking on the vertical axis of coordinates to (y1, y2, y3 …, ym), where m is the number of vertical grid points;
and S1014, decomposing the CT image of the lung of the reexamined patient into n × m pixel points of a rectangular grid with coordinates (xn, ym), and marking the pixel value at the midpoint position of the rectangular grid as the pixel value of the pixel point as Wi, wherein i is (n, m).
4. The method of claim 3, wherein the method comprises the following steps: in S1013, the starting point plotted in horizontal grid on the horizontal axis of the coordinate is located at the intersection of the vertical axis of the coordinate and the horizontal axis of the coordinate, the ending point is located at the closest distance to the right side of the straight line where the right vertex of the lung tissue in the CT image of the lung of the review patient is located, the starting point plotted in vertical grid on the vertical axis of the coordinate is located at the intersection of the vertical axis of the coordinate and the horizontal axis of the coordinate, and the ending point is located at the closest distance to the lower side of the straight line where the lower vertex.
5. The method of claim 4, wherein the method comprises the following steps: in S102, pixel values of a plurality of pixels are sequentially compared with a pixel threshold of the normal lung CT image, and pixels exceeding the pixel threshold of the normal lung CT image are retained:
and sequentially comparing the pixel Wi of the pixel (xn, ym) with the pixel threshold mark W threshold value, and recording all the pixels in Wi > W threshold value, wherein the pixels of all the pixels are marked as (W1, W2, W3, …, Wk), and k is the number of the pixels.
6. The method of claim 5, wherein the method comprises the following steps: in S103, the area of each pixel point is L × L when the area of each pixel point is consistent with the area of the rectangular grid, the area of the lesion area is marked as S × k × L, and the density of the lesion area is marked as L × L.
7. The method of claim 6, wherein in step S3, the CT image generation time, area and density data in the review data report and the CT image generation time, area and density data in all the historical data reports of each time period have a time-series data set, which is marked as { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) }, where j is the sum of the total number of the review data reports and the historical data reports.
8. The method of claim 7, wherein in step S3, the specific steps of performing time-series fitting on the area and density data in the review data report and all the historical data reports of each period are as follows:
s301, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } time and area data { (T1, S1), (T2, S2), …, (Tj, Sj) }, obtaining a time-series-based lesion area change curve using a curve fitting function, where the function is expressed as Sj ═ f (Tj), where f represents a function sign;
s302, extracting { (T1, S1, P1), (T2, S2, P2), …, (Tj, Sj, Pj) } middle time and density data { (T1, P1), (T2, P2), …, (Tj, Pj) }, and obtaining a time-series-based lesion density change curve function by using a curve fitting function, which is expressed as Pj ═ f (Tj), where f represents a function sign.
9. The method of claim 8, wherein in step S4, the method for predicting the subsequent rehabilitation progress of the newly-investigated patient' S coronary pneumonia lesion according to the fitting curve is as follows:
extending the time sequence from the current reexamination time to infinity in the future, extending a focus area change curve based on the time sequence along with the time sequence to obtain the focus area change curve form of the time sequence in the future, obtaining the change trend of the focus area of new coronary pneumonia in the future, obtaining the focus area value of specific time in the future, and substituting the specific time into Sj (f) (Tj) for operation to obtain the focus area value;
and (3) extending the time sequence from the current reexamination time to infinity in the future, extending a focus density change curve based on the time sequence along with the time sequence to obtain the focus density change curve form of the time sequence in the future, obtaining the change trend of the focus density of the new coronary pneumonia in the future, obtaining the focus density value of a specific time in the future, and substituting the specific time into Pj (f) (Tj) for operation to obtain the focus density value.
10. The data fitting method for CT reexamination of new coronary pneumonia as claimed in claim 1, wherein S1, S2, S3, S4 and S5 are established in a distributed data processing system constructed by a plurality of servers and a computer host for operation processing and data storage, the query terminal in S4 is an intelligent terminal device installed with a query login portal, the query login portal is a webpage, a software APP or a small program, and the query login portal and the distributed data processing system perform data exchange and service interaction through network communication.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011238084.4A CN112190277A (en) | 2020-11-09 | 2020-11-09 | Data fitting method for CT reexamination of new coronary pneumonia |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011238084.4A CN112190277A (en) | 2020-11-09 | 2020-11-09 | Data fitting method for CT reexamination of new coronary pneumonia |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112190277A true CN112190277A (en) | 2021-01-08 |
Family
ID=74033073
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011238084.4A Pending CN112190277A (en) | 2020-11-09 | 2020-11-09 | Data fitting method for CT reexamination of new coronary pneumonia |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112190277A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113570567A (en) * | 2021-07-23 | 2021-10-29 | 无锡祥生医疗科技股份有限公司 | Method and device for monitoring target tissue in ultrasonic image and storage medium |
CN113854996A (en) * | 2021-09-03 | 2021-12-31 | 华中科技大学同济医学院附属协和医院 | Lung function assessment method for patient in convalescent stage of new coronary pneumonia |
CN116627946A (en) * | 2023-06-01 | 2023-08-22 | 中山市人民医院 | Method and system for establishing diabetic foot data model |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5072384A (en) * | 1988-11-23 | 1991-12-10 | Arch Development Corp. | Method and system for automated computerized analysis of sizes of hearts and lungs in digital chest radiographs |
CN102429679A (en) * | 2011-09-09 | 2012-05-02 | 华南理工大学 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
US20150112710A1 (en) * | 2012-06-21 | 2015-04-23 | Battelle Memorial Institute | Clinical predictive analytics system |
CN110021430A (en) * | 2019-04-09 | 2019-07-16 | 科大讯飞股份有限公司 | A kind of the attribute information prediction technique and device of lesion |
CN110969622A (en) * | 2020-02-28 | 2020-04-07 | 南京安科医疗科技有限公司 | Image processing method and system for assisting pneumonia diagnosis |
CN111047591A (en) * | 2020-03-13 | 2020-04-21 | 北京深睿博联科技有限责任公司 | Focal volume measuring method, system, terminal and storage medium based on deep learning |
CN111400401A (en) * | 2020-03-12 | 2020-07-10 | 江苏荣泽信息科技股份有限公司 | Electronic medical record storage system based on block chain |
CN111462100A (en) * | 2020-04-07 | 2020-07-28 | 广州柏视医疗科技有限公司 | Detection equipment based on novel coronavirus pneumonia CT detection and use method thereof |
CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
CN111657985A (en) * | 2020-06-30 | 2020-09-15 | 杭州依图医疗技术有限公司 | Lung image information processing method, lung image information display method and readable storage medium |
CN111815608A (en) * | 2020-07-13 | 2020-10-23 | 北京小白世纪网络科技有限公司 | New coronary pneumonia patient recovery time prediction method and system based on deep learning |
-
2020
- 2020-11-09 CN CN202011238084.4A patent/CN112190277A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5072384A (en) * | 1988-11-23 | 1991-12-10 | Arch Development Corp. | Method and system for automated computerized analysis of sizes of hearts and lungs in digital chest radiographs |
CN102429679A (en) * | 2011-09-09 | 2012-05-02 | 华南理工大学 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
US20150112710A1 (en) * | 2012-06-21 | 2015-04-23 | Battelle Memorial Institute | Clinical predictive analytics system |
CN110021430A (en) * | 2019-04-09 | 2019-07-16 | 科大讯飞股份有限公司 | A kind of the attribute information prediction technique and device of lesion |
CN110969622A (en) * | 2020-02-28 | 2020-04-07 | 南京安科医疗科技有限公司 | Image processing method and system for assisting pneumonia diagnosis |
CN111400401A (en) * | 2020-03-12 | 2020-07-10 | 江苏荣泽信息科技股份有限公司 | Electronic medical record storage system based on block chain |
CN111047591A (en) * | 2020-03-13 | 2020-04-21 | 北京深睿博联科技有限责任公司 | Focal volume measuring method, system, terminal and storage medium based on deep learning |
CN111462100A (en) * | 2020-04-07 | 2020-07-28 | 广州柏视医疗科技有限公司 | Detection equipment based on novel coronavirus pneumonia CT detection and use method thereof |
CN111539944A (en) * | 2020-04-28 | 2020-08-14 | 安徽科大讯飞医疗信息技术有限公司 | Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium |
CN111657985A (en) * | 2020-06-30 | 2020-09-15 | 杭州依图医疗技术有限公司 | Lung image information processing method, lung image information display method and readable storage medium |
CN111815608A (en) * | 2020-07-13 | 2020-10-23 | 北京小白世纪网络科技有限公司 | New coronary pneumonia patient recovery time prediction method and system based on deep learning |
Non-Patent Citations (1)
Title |
---|
余建明等: "《放射医学技术 高级教程 2017版》", 31 October 2016, 出版发行 : 中华医学电子音像出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113570567A (en) * | 2021-07-23 | 2021-10-29 | 无锡祥生医疗科技股份有限公司 | Method and device for monitoring target tissue in ultrasonic image and storage medium |
CN113854996A (en) * | 2021-09-03 | 2021-12-31 | 华中科技大学同济医学院附属协和医院 | Lung function assessment method for patient in convalescent stage of new coronary pneumonia |
CN113854996B (en) * | 2021-09-03 | 2024-02-23 | 华中科技大学同济医学院附属协和医院 | Method for evaluating pulmonary function of patient in new coronal pneumonia convalescence |
CN116627946A (en) * | 2023-06-01 | 2023-08-22 | 中山市人民医院 | Method and system for establishing diabetic foot data model |
CN116627946B (en) * | 2023-06-01 | 2024-02-06 | 中山市人民医院 | Method and system for establishing diabetic foot data model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112190277A (en) | Data fitting method for CT reexamination of new coronary pneumonia | |
Annarumma et al. | Automated triaging of adult chest radiographs with deep artificial neural networks | |
CN111274425B (en) | Medical image classification method, device, medium and electronic equipment | |
CN112401915A (en) | Image fusion comparison method for CT (computed tomography) reexamination of new coronary pneumonia | |
CN104217132A (en) | Expert system and diagnosis and treatment system for patient recovery | |
CN1839392A (en) | Automated regional myocardial assessment for cardiac imaging | |
CN112669925A (en) | Report template for CT (computed tomography) reexamination of new coronary pneumonia and forming method | |
CN116110597B (en) | Digital twinning-based intelligent analysis method and device for patient disease categories | |
US20230401466A1 (en) | Method for temporal knowledge graph reasoning based on distributed attention | |
CN111178428B (en) | Cartilage damage classification method, cartilage damage classification device, computer equipment and storage medium | |
CN115512817A (en) | Doctor recommendation method and device based on child telemedicine | |
CN113793681B (en) | Hospital multi-stage medical index quality control method and system | |
CN108122005B (en) | Method for classifying clinical medicine levels | |
Wang et al. | Self adaptive global-local feature enhancement for radiology report generation | |
CN110570425A (en) | Lung nodule analysis method and device based on deep reinforcement learning algorithm | |
CN112766314B (en) | Anatomical structure recognition method, electronic device, and storage medium | |
Tang et al. | Work like a doctor: Unifying scan localizer and dynamic generator for automated computed tomography report generation | |
CN108320788A (en) | Hospital business analysis method and device | |
Xu et al. | Reinforced medical report generation with x-linear attention and repetition penalty | |
CN113177923B (en) | Medical image content identification method, electronic equipment and storage medium | |
CN115588492A (en) | Diagnosis guiding method and system based on artificial intelligence | |
CN115700789A (en) | Pneumonia preliminary examination triage system based on multi-modal medical data | |
CN116994695A (en) | Training method, device, equipment and storage medium of report generation model | |
CN114121213A (en) | Anesthesia medicine information rechecking method and device, electronic equipment and storage medium | |
CN111968111A (en) | Method and device for identifying visceral organs or artifacts of CT (computed tomography) image |
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 |
Application publication date: 20210108 |
|
RJ01 | Rejection of invention patent application after publication |