CN119151934B - Extracardiac operation monitoring system and method based on image processing - Google Patents
Extracardiac operation monitoring system and method based on image processing Download PDFInfo
- Publication number
- CN119151934B CN119151934B CN202411648175.3A CN202411648175A CN119151934B CN 119151934 B CN119151934 B CN 119151934B CN 202411648175 A CN202411648175 A CN 202411648175A CN 119151934 B CN119151934 B CN 119151934B
- Authority
- CN
- China
- Prior art keywords
- image
- inflammation
- incision
- healing
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 230000002169 extracardiac Effects 0.000 title claims abstract description 23
- 206010061218 Inflammation Diseases 0.000 claims abstract description 102
- 230000004054 inflammatory process Effects 0.000 claims abstract description 102
- 230000035876 healing Effects 0.000 claims abstract description 99
- 238000011156 evaluation Methods 0.000 claims abstract description 64
- 238000007781 pre-processing Methods 0.000 claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 238000006073 displacement reaction Methods 0.000 claims abstract description 13
- 210000000038 chest Anatomy 0.000 claims description 84
- 210000000115 thoracic cavity Anatomy 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 34
- 238000001514 detection method Methods 0.000 claims description 34
- 230000005856 abnormality Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000009792 diffusion process Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004321 preservation Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000002757 inflammatory effect Effects 0.000 claims description 3
- 230000002401 inhibitory effect Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 6
- 230000029058 respiratory gaseous exchange Effects 0.000 description 4
- 230000008961 swelling Effects 0.000 description 4
- 230000002123 temporal effect Effects 0.000 description 4
- 239000003086 colorant Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000002980 postoperative effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 208000012661 Dyskinesia Diseases 0.000 description 1
- 208000015592 Involuntary movements Diseases 0.000 description 1
- 206010044565 Tremor Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000007675 cardiac surgery Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000017311 musculoskeletal movement, spinal reflex action Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of image processing, in particular to an extracardiac operation monitoring system and method based on image processing. The method comprises the steps of obtaining a chest image of a patient, preprocessing the chest image of the patient through an improved image preprocessing algorithm to obtain a preprocessed chest image, calculating a cut healing progress evaluation value based on the preprocessed chest image through a healing progress evaluation algorithm, setting a cut healing speed threshold value and a standard progress value of the cut healing progress, judging whether the cut healing progress is abnormal or not, calculating an inflammation severity evaluation value based on the preprocessed chest image through an inflammation evaluation algorithm, setting an inflammation severity threshold value, and judging whether the cut is abnormal or not. The technical problems that the prior method is difficult to accurately process tiny and frequent displacement, causes the loss of edge information, cannot fully combine space and time information, and easily ignores the development trend of inflammation are solved.
Description
Technical Field
The invention relates to the field of image processing, in particular to an extracardiac operation monitoring system and method based on image processing.
Background
Along with the progress of medical technology, the success rate of modern cardiac surgery is obviously improved, but complications and risks after the surgery are still important points of strict monitoring required by medical staff, the traditional extracardiac surgery monitoring mode depends on monitoring of various physiological indexes, such as electrocardiogram, blood pressure, blood oxygen saturation, respiratory rate and the like, real-time physiological information can be provided, but the change of external visual characteristics cannot be directly reflected, high-frequency observation and recording are required, and particularly for severe patients, the medical staff is required to frequently check vital signs and physical conditions, so that a large amount of manpower resources are consumed, and the problem of incapacity or negligence of monitoring is easy to occur.
Along with the rapid development of image processing technology, artificial intelligence and computer vision, an extracardiac operation monitoring system and method based on image processing gradually become an important technical trend, and the image processing technology can capture physical characterization information of a patient in real time through a camera and identify potential risk factors through algorithm analysis, so that finer and comprehensive support is provided for extracardiac operation monitoring.
However, the existing extracardiac operation monitoring method has the following technical problems that tiny and frequent displacement such as image blurring caused by breathing or slight shaking is difficult to accurately process, details are easy to blur while noise is removed, edge information is lost, dynamic change in a healing process cannot be captured by means of single time point information of an image, inflammation red and swelling areas are difficult to distinguish in an RGB color space, detection accuracy is low, spatial and time information cannot be fully combined, and development trend of inflammation is easy to ignore.
Disclosure of Invention
The invention provides an extracardiac operation monitoring system and method based on image processing, which are used for solving the technical problems that the existing system is difficult to accurately process tiny and frequent displacement, such as image blurring caused by breathing or slight shaking, the details are easy to be caused to blur while noise is removed, edge information is lost, dynamic change in a healing process cannot be captured by means of single time point information of an image, inflammation red and swelling areas are difficult to distinguish in an RGB color space, detection accuracy is low, space and time information cannot be fully combined, and development trend of inflammation is easy to be ignored.
The invention discloses an extracardiac operation monitoring system and method based on image processing, which concretely comprises the following technical scheme:
an extracardiac operation monitoring method based on image processing comprises the following steps:
s1, acquiring a chest image of a patient, and preprocessing the chest image of the patient through an improved image preprocessing algorithm to obtain a preprocessed chest image;
S2, calculating to obtain an estimated value of the healing progress of the incision based on the preprocessed thoracic cavity image by using a healing progress estimation algorithm, setting an incision healing speed threshold value and a standard progress value of the healing progress of the incision, and judging whether the healing progress of the incision is abnormal or not;
And S3, calculating an inflammation severity assessment value by using an inflammation assessment algorithm based on the preprocessed chest image when the healing progress of the incision is abnormal, setting a inflammation severity threshold value, and judging whether the incision is abnormal or not.
Preferably, the S1 specifically includes:
The improved image preprocessing algorithm comprises a motion compensation part and a noise removal and edge preservation part, wherein the motion compensation part calculates the displacement of each pixel point in the thoracic image by analyzing the pixel position difference between adjacent frames, and carries out position correction on the pixels in the thoracic image.
Preferably, the S1 specifically includes:
The noise removing and edge retaining part calculates noise distribution according to the local noise characteristic of each pixel in the chest image, and adopts filtering operation with different intensities for the areas with different noise distribution, and introduces a nonlinear diffusion model, selectively diffuses according to the characteristics of the area where the pixel is positioned, and obtains the pixel intensity of the preprocessed chest image by calculating the gradient of the pixel point in the chest image, wherein the calculation formula is as follows:
,
Wherein, Is shown inTime space coordinates areIs used for preprocessing the chest image pixel intensity; Is shown in Time space coordinates arePixel intensities of a patient's thoracic image; And Representing displacement compensation parameters caused by small movements of the patient during imaging,Compensating atThe movement in the direction of the movement is,Compensating atMovement in a direction; Representing a first adjustment factor; Representing chest image in position AndNoise distribution at time instant; representing a second adjustment factor; Representing the second order rate of change of the chest image portion; Representing chest images at Direction and directionFirst derivative in direction.
Preferably, the S2 specifically includes:
in the implementation process of the healing progress evaluation algorithm, the incision edge is detected by calculating the transverse gradient and the longitudinal gradient of the preprocessed chest image, and noise interference is restrained by combining the local topological interference quantity, so that the edge strength of the preprocessed chest image is obtained, wherein the specific calculation formula is as follows:
,
Wherein, Is shown inTime space coordinates areIs used for preprocessing the chest image edge intensity; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction; Representing a square root operation; And Representing a square term; Representing an exponential function; The adjustment parameters for controlling the influence of the local topological disturbance quantity on the gradient calculation result are represented; representing the amount of local topological disturbance.
Preferably, the S2 specifically includes:
in the implementation process of the healing progress evaluation algorithm, the edge intensity of the preprocessed chest image is compared with the set incision area detection threshold by setting the incision area detection threshold, pixel points meeting the conditions are extracted, and the complete incision outline is constructed.
Preferably, the S2 specifically includes:
In the implementation process of the healing progress evaluation algorithm, after the incision area is detected, an adaptive weighting coefficient is introduced to adjust the weight value of the pixel point, the healing progress of the incision is evaluated by calculating the change rate of the incision edge along with time, and the second derivative of the incision edge along with time is calculated to obtain an estimated value of the healing progress of the incision.
Preferably, the S3 specifically includes:
In the implementation process of the inflammation evaluation algorithm, the red channel value of the pixel points in the chest image after color separation is obtained through color conversion of the preprocessed chest image, after the color separation treatment, the inflammation area is detected through the extracted red channel value, the inflammation area detection threshold value is set, the red channel value is compared with the set inflammation area detection threshold value, the pixel points meeting the conditions are extracted, and the pixel point set of the inflammation area is formed.
Preferably, the S3 specifically includes:
In the implementation process of the inflammation evaluation algorithm, a spatial derivative adjusting parameter and a time derivative adjusting parameter are introduced, and the inflammation area is analyzed in the spatial and time dimensions to obtain an inflammation severity evaluation value.
An extracardiac postoperative monitoring system based on image processing, comprising the following parts:
The device comprises an image acquisition module, an image preprocessing module, a healing progress evaluation module, an inflammation detection and evaluation module and a monitoring and early warning module;
the image acquisition module is used for acquiring a thoracic image of a patient and outputting the thoracic image of the patient to the image preprocessing module;
the image preprocessing module is used for preprocessing the chest image of the patient through an improved image preprocessing algorithm based on the chest image of the patient of the image acquisition module to obtain a preprocessed chest image, and outputting the preprocessed chest image to the healing progress evaluation module and the inflammation detection and evaluation module;
The healing progress evaluation module is used for calculating to obtain an estimated value of the healing progress of the incision based on the preprocessed thoracic cavity image of the image preprocessing module, setting a healing speed threshold value and a standard progress value of the healing progress of the incision, judging whether the healing abnormality of the incision exists or not, and outputting a healing abnormality judgment result to the monitoring and early warning module;
The inflammation detection and evaluation module is used for calculating an inflammation severity evaluation value by using an inflammation evaluation algorithm based on the preprocessed chest image of the image preprocessing module and the healing abnormality judgment result of the monitoring and early warning module, setting a inflammation severity threshold value, judging whether inflammation abnormality exists in the incision or not, and outputting the inflammation abnormality judgment result to the monitoring and early warning module;
And the monitoring early warning module is used for receiving the healing abnormality judgment result from the healing progress evaluation module, notifying the medical staff to process and outputting the healing abnormality judgment result to the inflammation detection and evaluation module, and receiving the inflammation abnormality judgment result from the inflammation detection and evaluation module.
The technical scheme of the invention has the beneficial effects that:
1. By analyzing the pixel position difference between adjacent frames, the displacement of each pixel point in the thoracic image of the patient is calculated, accurate compensation is carried out in the horizontal and vertical directions, the image distortion caused by the non-autonomous action of respiration and slight vibration is corrected, the problem of thoracic image blurring caused by slight movement of the patient is effectively eliminated, the thoracic image is kept at high resolution and consistency, and the influence of thoracic image distortion on subsequent judgment is avoided.
2. According to local noise distribution of pixels, dynamic filtering operation is used for removing noise, the nonlinear diffusion model is used for enhancing diffusion in a flat area to remove noise, diffusion is weakened in an edge area to keep details, and the Laplacian operator is combined for enhancing edge information, so that the problem of detail blurring in the denoising process is avoided.
3. The edge pixels of the incision are identified by detecting brightness changes of the pixels, a complete incision outline is constructed based on local topological disturbance quantity, a self-adaptive weighting coefficient is further introduced, the incision healing state is estimated according to the smoothness degree of the pixel changes, a second derivative is used for capturing acceleration or deceleration trend of the incision healing progress, whether the incision healing progress is abnormal or not is judged through the incision healing speed threshold value and the standard progress value of the incision healing progress, the incision healing progress is accurately estimated, feedback is timely carried out, manual intervention is reduced, and the postoperative monitoring efficiency is improved.
4. The method comprises the steps of converting a chest image from an RGB color space to an HSV color space, separating red channel information, highlighting the characteristics of an inflammation area, easily identifying the inflammation area, reducing misjudgment, setting an inflammation area detection threshold, extracting pixels meeting the conditions, constructing a pixel point set of the inflammation area, timely capturing signals of worsening or relieving the illness state by analyzing the spatial texture and time change trend of the inflammation area, and controlling the precision of an evaluation process by the spatial derivative adjustment parameter and the time derivative adjustment parameter.
Drawings
FIG. 1 is a block diagram of an extracardiac monitoring system based on image processing according to the present invention;
Fig. 2 is a flowchart of an extracardiac operation monitoring method based on image processing according to the present invention.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of 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 apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of an extracardiac operation monitoring system and method based on image processing.
Referring to fig. 1, there is shown a structural diagram of an extracardiac monitoring system based on image processing according to an embodiment of the present invention, the system includes the following parts:
The device comprises an image acquisition module, an image preprocessing module, a healing progress evaluation module, an inflammation detection and evaluation module and a monitoring and early warning module;
The image acquisition module is used for acquiring a thoracic image of a patient by using the camera equipment and outputting the thoracic image of the patient to the image preprocessing module;
the image preprocessing module is used for preprocessing the chest image of the patient through an improved image preprocessing algorithm based on the chest image of the patient of the image acquisition module to obtain a preprocessed chest image, and outputting the preprocessed chest image to the healing progress evaluation module and the inflammation detection and evaluation module;
The healing progress evaluation module is used for calculating to obtain an estimated value of the healing progress of the incision based on the preprocessed thoracic cavity image of the image preprocessing module, setting a healing speed threshold value and a standard progress value of the healing progress of the incision to judge whether the healing abnormality of the incision exists or not, and outputting a healing abnormality judgment result to the monitoring and early warning module;
The inflammation detection and evaluation module is used for calculating an inflammation severity evaluation value by using an inflammation evaluation algorithm based on the preprocessed chest image of the image preprocessing module and the healing abnormality judgment result of the monitoring and early warning module, setting an inflammation severity threshold value for judging whether inflammation abnormality exists in the incision or not, and outputting the inflammation abnormality judgment result to the monitoring and early warning module;
And the monitoring early warning module is used for receiving the healing abnormality judgment result from the healing progress evaluation module, notifying the medical staff to process and outputting the healing abnormality judgment result to the inflammation detection and evaluation module, further evaluating whether the inflammation abnormality exists in the incision, receiving the inflammation abnormality judgment result from the inflammation detection and evaluation module and notifying the medical staff to process.
Referring to fig. 2, a flowchart of an extracardiac monitoring method based on image processing according to an embodiment of the present invention is shown, the method includes the following steps:
s1, acquiring a chest image of a patient, and preprocessing the chest image of the patient through an improved image preprocessing algorithm to obtain a preprocessed chest image;
acquiring a chest image of a patient by using an image pickup device, and preprocessing the chest image of the patient by using an improved image preprocessing algorithm to obtain a preprocessed chest image;
the improved image preprocessing algorithm includes a motion compensation portion and a noise removal and edge preservation portion for removing noise and compensating for image blurring due to small movements of the patient while preserving image details and edge information;
The motion compensation part calculates the displacement of each pixel point in the thoracic image by analyzing the pixel position difference between adjacent frames, the displacement is respectively the displacement in the horizontal direction and the vertical direction, and after the displacement is determined, each pixel in the thoracic image is subjected to position correction, namely the thoracic image is corrected, the thoracic image distortion caused by the tiny motion of a patient during postoperative monitoring is corrected, the problem of blurring of the thoracic image can be avoided, and the continuity of thoracic image information can be ensured;
The noise removing and edge preserving part calculates the noise distribution according to the local noise characteristic of each pixel in the chest image, and adopts filtering operation with different intensities for areas with different noise distributions, meanwhile, a nonlinear diffusion model is introduced to ensure that the noise can be removed while the edge information is preserved, the noise is removed by gradually smoothing the pixels in the chest image, but the same smoothing treatment is not carried out on all the pixels, but the selective diffusion is carried out according to the characteristics of the area where the pixels are positioned, the gradient of each pixel point in the chest image, namely the change condition of the pixel value along with the spatial position, can strengthen the diffusion in the area with extremely small gradient, namely the flat area (such as the area with the same color in a large area) of the chest image, so that the noise is effectively removed, and the diffusion can be weakened in the area with extremely large gradient, namely the area with abundant details, so that the details can not be blurred due to the denoising;
The calculation formula of the pixel intensity of the preprocessed thoracic image is as follows:
,
Wherein, Is shown inTime space coordinates areIs used for preprocessing the chest image pixel intensity; Is shown in Time space coordinates arePixel intensities of a patient's thoracic image; And Representing displacement compensation parameters caused by minute movements of a patient during imaging for reducing image blur due to involuntary movements of the patient (e.g. breathing, slight tremors), helping image correction to recover a clear thoracic image, whereinCompensating atThe movement in the direction of the movement is,Compensating atMovement in a direction; Representing a first adjustment factor for weighing And a nonlinear diffusion termThe influence on the preprocessing of the thoracic image determines the balance degree between noise elimination and detail retention; Representing chest image in position AndThe noise distribution at the moment is used for helping to remove the influence of random noise on the details of the chest image; representing a second adjustment factor for controlling the effect of image gradients in the process, balancing the weights of edge enhancement and detail preservation, preventing excessive smoothing from causing edge blurring; The second-order change rate of the chest image part is represented, namely, the Laplacian is used for strengthening details and edges, and remarkable image details and edge structures are reserved, so that edge information can be kept from being lost particularly in the noise removal process; Representing chest images at Direction and directionThe first derivative in direction, the image gradient, describes the rate of change of pixel intensity in the chest image, which is used to identify contours and detail parts in the image; Representing normalization processing of image gradients and controlling gradient influence of the images;
S2, calculating to obtain an incision healing progress evaluation value by using a healing progress evaluation algorithm based on the preprocessed chest image, setting an incision healing speed threshold value and a standard progress value of the incision healing progress, and judging whether the incision healing progress is abnormal or not;
Based on the preprocessed chest image, calculating to obtain an incision healing progress evaluation value by using a healing progress evaluation algorithm;
The method comprises the steps of calculating the transverse gradient and the longitudinal gradient of the preprocessed thoracic image to detect the incision edge, inhibiting noise interference by combining local topological disturbance quantity, ensuring the accuracy of edge detection, realizing the comprehensive evaluation of the incision healing progress by analyzing the incision edge variation in different time periods, calculating to obtain the incision healing progress evaluation value, considering the edge information in the space direction and combining time analysis, ensuring the comprehensiveness and the accuracy of the evaluation, judging the edge point of the incision by checking the brightness variation condition of each pixel point along the horizontal direction and the vertical direction, and judging the brightness of the pixel if the brightness of the pixel is in the range of Direction and directionThe pixel points are possible edge points of the notch, and a calculation method based on local topological disturbance quantity is further introduced, wherein the local topological disturbance quantity is used for measuring brightness difference between the pixel points and surrounding neighborhood pixels, and the contour and the boundary of the notch are gradually detected by continuously comparing difference values of the pixel points and the surrounding pixels;
The calculation formula of the edge intensity of the preprocessed thoracic image is as follows:
,
Wherein, Is shown inTime space coordinates areThe edge intensity of the pretreated chest image reflects the edge change and is used for detecting the contour of the incision; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction reflecting lateral edge information; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction reflecting longitudinal edge information; representing square root operation, guaranteeing positive values of gradients; And The square term is expressed and used for eliminating positive and negative differences of gradient directions, so that the measurement of the edge intensity of the preprocessed chest image only reflects the gradient magnitude and is not influenced by the directions; expressing an exponential function, weighting gradient values by adjusting local topological disturbance quantity, and inhibiting insignificant edge change, so as to avoid noise disturbance or false detection of a non-target area; representing adjustment parameters for controlling the influence of local topological disturbance quantity on the gradient calculation result; representing local topological disturbance quantity for measuring target pixel At the position ofThe brightness difference between the time point and the neighborhood pixels reflects the obvious change of the local area, and is used for identifying the edge of the notch, and the calculation formula of the local topological disturbance quantity is as follows:
,
Wherein, Representing target pixelsThe surrounding neighborhood pixel set can be specifically set according to the specific implementation scene, and is not limited herein; Representing pixel sets in a neighborhood Pixel coordinates of (a); representing pairs of neighborhood pixel sets The brightness differences of all pixels in the target pixel area are accumulated to capture the integral change of the target pixel area; representing absolute value symbols, eliminating positive and negative differences, and ensuring that the calculated brightness difference reflects the change of the notch edge; Is shown in Time space coordinates areIs used for preprocessing the chest image pixel intensity;
By setting the incision area detection threshold, comparing the preprocessed chest image edge intensity with the set incision area detection threshold, extracting all pixel points meeting the conditions, and further constructing a complete incision outline, wherein the formula is as follows:
,
Wherein, Is shown inAll pixel point sets meeting the conditions at the moment, namely the detected notch area; Is shown in The threshold value for detecting the incision area at the moment can be specifically set according to the specific implementation scene, and is not limited herein; Indicating that all conditions are satisfied A set of pixels;
After detecting the incision area, in order to further accurately reflect the recovery condition of the incision, introducing an adaptive weighting coefficient for adjusting the weight value of each pixel point, if the brightness change of the pixel point becomes smooth, the pixel point is in a healing state, and the pixel point is given an extremely low weight;
In order to capture the change of the speed in the incision healing process, the change condition of the incision boundary along with time is further analyzed, and whether the incision healing progress is accelerated or decelerated is evaluated by calculating the change rate of the incision edge along with time, so that the overall progress of incision healing can be tracked, and whether the incision healing speed is normal within a certain time period can be judged;
the calculation formula of the incision healing progress evaluation value is as follows:
,
Wherein, Is shown inA time incision healing progress evaluation value; Representing summing all pixels belonging to the cutout region; representing self-adaptive weighting coefficients, and adjusting the influence of different incision areas on the healing progress; Representing balance parameters for adjusting the local smoothness of the pixel intensity of the preprocessed thoracic image; The Laplacian which represents the pixel intensity of the preprocessed chest image reflects the local change degree around the pixel point; representing the pixel intensity of the preprocessed thoracic image; representing the second derivative of the edge intensity of the pretreated chest image with respect to time, wherein the second derivative is used for representing the acceleration of the incision healing process and reflecting the change trend of the incision healing progress; Is shown in Time space coordinates areThe edge intensity of the chest image after pretreatment reflects the edge change;
if the change of the progress of the incision healing is slow and is lower than the standard progress value of the progress of the incision healing, prompting that the incision healing is abnormal, otherwise, the incision healing is normal;
the specific implementation formula is as follows:
,
Wherein, The first derivative of the estimated value of the progress of the incision healing with respect to time is represented, reflecting the rate of change of the progress of the incision healing, for judging the speed of the healing of the incision; the threshold value of the incision healing speed can be specifically set according to specific implementation situations, and is not limited herein; a standard progress value representing progress of healing of the incision;
When the progress of incision healing is abnormal, medical staff needs to be informed to process and evaluate whether inflammation abnormality exists;
S3, when the healing progress of the incision is abnormal, calculating to obtain an inflammation severity assessment value by using an inflammation assessment algorithm based on the preprocessed chest image, setting an inflammation severity threshold value, and judging whether the incision is abnormal or not;
Based on the pretreated chest image, calculating to obtain an inflammation severity assessment value by using an inflammation assessment algorithm;
the inflammation evaluation algorithm realizes rapid positioning of the inflammation region and judgment of the severity thereof through color space conversion separation, inflammation region detection and inflammation severity evaluation based on space and time derivatives;
Converting the input preprocessed chest image from an RGB (red, green, blue) color space, which is a conventional color representation, to an HSV (hue, saturation, brightness) color space, wherein different combinations of colors are difficult to clearly distinguish red features of an inflammation area, and the HSV color space is suitable for analyzing the features of colors, particularly red, by separating the brightness of the colors from the saturation, and mapping data of each pixel point from the RGB color space to the HSV color space by a standard color conversion process so as to highlight information of a red channel;
The color conversion process formula is as follows:
,
Wherein, Representing pixel points in chest image after color separationAt the position ofThe red channel value at the moment is obtained by converting the preprocessed chest image into an HSV color space through an RGB color space and is used for detecting an inflammation area;
after the color separation treatment, detecting an inflammation area through the extracted red channel, setting an inflammation area detection threshold value, and obtaining pixel points in the chest image after the color separation At the position ofComparing the red channel value at the moment with a set detection threshold value of the inflammation area, extracting all pixel points meeting the condition, and forming a pixel point set of the inflammation area, wherein the formula is as follows:
,
Wherein, Is shown inAll pixel point sets meeting the conditions at the moment, namely the detected inflammation area; Is shown in The threshold value for detecting the inflammation area at the moment can be specifically set according to the specific implementation scene, and is not limited herein; Indicating that all conditions are satisfied A set of pixels;
To evaluate the severity of inflammation, all pixels detected are traversed, texture changes and temporal changes are calculated, the aim is to analyze the development of inflammation through two dimensions, namely, the change in the spatial dimension (namely, the red swelling or local exudation of the adjacent area) and the change in the temporal dimension (namely, whether the inflammation is expanding or reducing with the passage of time), the detection of the change in the spatial dimension reveals the intense fluctuation of texture, such as a sudden red swelling area, by calculating the local change intensity between the pixels, and simultaneously, in order to avoid the misjudgment caused by the local detail change, a spatial derivative adjustment parameter is designed for controlling the weight of the spatial change in the evaluation process, and the detection of the change in the temporal dimension is used for analyzing the trend of each pixel in the temporal sequence, so as to ensure that the rapid expansion or alleviation of the inflammation can be captured;
The calculation formula of the inflammation severity evaluation value is as follows:
,
Wherein, Is shown inA time of day inflammation severity assessment for quantifying the severity of the detected inflammation area; representing the summation of all pixels belonging to the inflammatory region; representing a spatial derivative adjusting parameter, which is used for controlling the weight of the second spatial derivative, adjusting the influence of spatial variation on an evaluation result, and avoiding erroneous judgment caused by local detail variation; representing pixel points For detecting the intensity of local texture changes, reflecting texture changes such as redness or oozing; representing a time derivative adjustment parameter for controlling the weight of the time varying derivative, ensuring that a change in the rate of inflammation development can be detected; representing pixel points Reflecting the rate of change of the inflammatory region over time;
If the inflammation severity evaluation value exceeds the inflammation severity threshold, prompting that inflammation abnormality exists, otherwise, the inflammation abnormality is normal;
,
Wherein, The threshold value for representing the severity of inflammation can be specifically set according to the specific implementation scenario, and is not limited herein;
accurate inflammation abnormality alerts are convenient to prompt the physician to take further intervention.
In summary, an extracardiac operation monitoring system and method based on image processing are completed.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing embodiments are merely for illustrating the technical solution of the present invention, but not for limiting the same, and although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solution described in the foregoing embodiments may be modified or substituted for some of the technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solution of the embodiments of the present invention and are intended to be included in the scope of the present invention.
Claims (4)
1. An extracardiac operation monitoring method based on image processing is characterized by comprising the following steps:
S1, acquiring a chest image of a patient, and preprocessing the chest image of the patient through an improved image preprocessing algorithm to obtain a preprocessed chest image, wherein the improved image preprocessing algorithm comprises a motion compensation part and a noise removal and edge preservation part, and the motion compensation part calculates the displacement of each pixel point in the chest image and corrects the position of the pixel in the chest image by analyzing the pixel position difference between adjacent frames;
The noise removing and edge retaining part calculates noise distribution according to the local noise characteristic of each pixel in the chest image, and adopts filtering operation with different intensities for the areas with different noise distribution, and introduces a nonlinear diffusion model, selectively diffuses according to the characteristics of the area where the pixel is positioned, and obtains the pixel intensity of the preprocessed chest image by calculating the gradient of the pixel point in the chest image, wherein the calculation formula is as follows:
,
Wherein, Is shown inTime space coordinates areIs used for preprocessing the chest image pixel intensity; Is shown in Time space coordinates arePixel intensities of a patient's thoracic image; And Representing displacement compensation parameters caused by small movements of the patient during imaging,Compensating atThe movement in the direction of the movement is,Compensating atMovement in a direction; Representing a first adjustment factor; Representing chest image in position AndNoise distribution at time instant; representing a second adjustment factor; Representing the second order rate of change of the chest image portion; Representing chest images at Direction and directionFirst derivative in direction;
S2, calculating to obtain an incision healing progress evaluation value by using a healing progress evaluation algorithm based on the preprocessed chest image, detecting incision edges by calculating transverse gradients and longitudinal gradients of the preprocessed chest image in the implementation process of the healing progress evaluation algorithm, and inhibiting noise interference by combining local topological interference amount to obtain the edge strength of the preprocessed chest image, wherein the specific calculation formula is as follows:
,
Wherein, Is shown inTime space coordinates areIs used for preprocessing the chest image edge intensity; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction; representing the intensity of the preprocessed thoracic image pixels at A gradient of direction; Representing a square root operation; And Representing a square term; Representing an exponential function; The adjustment parameters for controlling the influence of the local topological disturbance quantity on the gradient calculation result are represented; Representing the local topological disturbance quantity;
Comparing the edge intensity of the preprocessed chest image with the set incision area detection threshold value by setting the incision area detection threshold value, extracting pixel points meeting the condition, and constructing a complete incision outline;
after the incision area is detected, introducing a self-adaptive weighting coefficient, adjusting the weight value of the pixel point, evaluating the incision healing progress by calculating the change rate of the incision edge along with time, and obtaining an incision healing progress evaluation value by calculating the second derivative of the incision edge along with time;
Setting a threshold value of the healing speed of the incision and a standard progress value of the healing progress of the incision, and judging whether the healing progress of the incision is abnormal or not;
And S3, calculating an inflammation severity assessment value by using an inflammation assessment algorithm based on the preprocessed chest image when the healing progress of the incision is abnormal, setting a inflammation severity threshold value, and judging whether the incision is abnormal or not.
2. The method for monitoring the extracardiac operation based on the image processing according to claim 1, wherein the step S3 specifically comprises:
In the implementation process of the inflammation evaluation algorithm, the red channel value of the pixel points in the chest image after color separation is obtained through color conversion of the preprocessed chest image, after the color separation treatment, the inflammation area is detected through the extracted red channel value, the inflammation area detection threshold value is set, the red channel value is compared with the set inflammation area detection threshold value, the pixel points meeting the conditions are extracted, and the pixel point set of the inflammation area is formed.
3. The method for monitoring the extracardiac operation based on the image processing according to claim 2, wherein the step S3 specifically comprises:
in the implementation process of the inflammation evaluation algorithm, introducing a space derivative adjusting parameter and a time derivative adjusting parameter, and analyzing an inflammation area in space and time dimensions to obtain an inflammation severity evaluation value, wherein a specific calculation formula is as follows:
,
Wherein, Is shown inA time of day inflammation severity assessment; representing the summation of all pixels belonging to the inflammatory region; representing a spatial derivative adjustment parameter; representing pixel points Is a spatial second derivative of (2); Representing a time derivative adjustment parameter; representing pixel points Is a time derivative of (a).
4. An extracardiac operation monitoring system based on image processing, which is applied to the extracardiac operation monitoring method based on image processing as claimed in claim 1, and is characterized by comprising the following parts:
The device comprises an image acquisition module, an image preprocessing module, a healing progress evaluation module, an inflammation detection and evaluation module and a monitoring and early warning module;
the image acquisition module is used for acquiring a thoracic image of a patient and outputting the thoracic image of the patient to the image preprocessing module;
the image preprocessing module is used for preprocessing the chest image of the patient through an improved image preprocessing algorithm based on the chest image of the patient of the image acquisition module to obtain a preprocessed chest image, and outputting the preprocessed chest image to the healing progress evaluation module and the inflammation detection and evaluation module;
The healing progress evaluation module is used for calculating to obtain an estimated value of the healing progress of the incision based on the preprocessed thoracic cavity image of the image preprocessing module, setting a healing speed threshold value and a standard progress value of the healing progress of the incision, judging whether the healing abnormality of the incision exists or not, and outputting a healing abnormality judgment result to the monitoring and early warning module;
The inflammation detection and evaluation module is used for calculating an inflammation severity evaluation value by using an inflammation evaluation algorithm based on the preprocessed chest image of the image preprocessing module and the healing abnormality judgment result of the monitoring and early warning module, setting a inflammation severity threshold value, judging whether inflammation abnormality exists in the incision or not, and outputting the inflammation abnormality judgment result to the monitoring and early warning module;
And the monitoring early warning module is used for receiving the healing abnormality judgment result from the healing progress evaluation module, notifying the medical staff to process and outputting the healing abnormality judgment result to the inflammation detection and evaluation module, and receiving the inflammation abnormality judgment result from the inflammation detection and evaluation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411648175.3A CN119151934B (en) | 2024-11-19 | 2024-11-19 | Extracardiac operation monitoring system and method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411648175.3A CN119151934B (en) | 2024-11-19 | 2024-11-19 | Extracardiac operation monitoring system and method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119151934A CN119151934A (en) | 2024-12-17 |
| CN119151934B true CN119151934B (en) | 2025-01-28 |
Family
ID=93802234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411648175.3A Active CN119151934B (en) | 2024-11-19 | 2024-11-19 | Extracardiac operation monitoring system and method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119151934B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118969277A (en) * | 2024-08-01 | 2024-11-15 | 陕西省结核病防治院(陕西省第五人民医院) | A method and system for postoperative rehabilitation nursing of thoracic surgery |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8165383B2 (en) * | 2008-03-24 | 2012-04-24 | Applied Materials Israel, Ltd. | Method, system and computer program product for edge detection |
| EP2599055A2 (en) * | 2010-07-30 | 2013-06-05 | Fundação D. Anna Sommer Champalimaud E Dr. Carlos Montez Champalimaud | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| GB2523253B (en) * | 2015-01-23 | 2017-04-12 | Visidon Oy | Image processing method |
| CN114007535A (en) * | 2019-04-18 | 2022-02-01 | 盖乐世公司 | Devices, systems and methods for treating abnormal tissue |
| CN113989138B (en) * | 2021-10-21 | 2024-07-16 | 武汉博视电子有限公司 | Method for extracting facial skin image inflammation and forming red area spectrum |
| CN117459793B (en) * | 2023-12-25 | 2024-04-09 | 沈阳视达广电网络传输有限责任公司 | Video noise optimization processing method |
| CN118552793B (en) * | 2024-07-25 | 2024-09-24 | 吉林大学 | A postoperative incision healing status recognition system based on artificial intelligence |
| CN118552533B (en) * | 2024-07-29 | 2024-10-29 | 南通市肿瘤医院（南通市第五人民医院） | Cancerous wound monitoring data analysis processing method, device and storage medium |
| CN118570099B (en) * | 2024-08-02 | 2024-10-11 | 中国人民解放军海军青岛特勤疗养中心 | Postoperative rehabilitation effect monitoring system based on image enhancement |
| CN118800458B (en) * | 2024-09-14 | 2024-11-15 | 吉林大学 | Method and system for predicting complications after cardiothoracic surgery |
-
2024
- 2024-11-19 CN CN202411648175.3A patent/CN119151934B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118969277A (en) * | 2024-08-01 | 2024-11-15 | 陕西省结核病防治院(陕西省第五人民医院) | A method and system for postoperative rehabilitation nursing of thoracic surgery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119151934A (en) | 2024-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107451998B (en) | Fundus image quality control method | |
| CN111340789A (en) | Method, device, equipment and storage medium for identifying and quantifying eye fundus retinal blood vessels | |
| CN103702014B (en) | Non-contact physiological parameter detection method, system and device | |
| CN117876971B (en) | Building construction safety monitoring and early warning method based on machine vision | |
| CN105791709A (en) | Automatic exposure processing method and apparatus with back-light compensation | |
| CN117764864B (en) | Nuclear magnetic resonance tumor visual detection method based on image denoising | |
| CN107292835B (en) | Method and device for automatically vectorizing retinal blood vessels of fundus image | |
| RAJA et al. | Screening diabetic retinopathy in developing countries using retinal images | |
| CN117372284B (en) | Fundus image processing method and fundus image processing system | |
| CN107358612A (en) | A kind of retinal vessel segmenting system combined based on fractal dimension with gaussian filtering and method | |
| CN118101924A (en) | Method for analyzing kitchen picture quality | |
| CN116363021A (en) | Intelligent collection system for nursing and evaluating wound patients | |
| CN116757972A (en) | Fabric defect detection method capable of resisting influence of shadow noise | |
| CN119151934B (en) | Extracardiac operation monitoring system and method based on image processing | |
| CN109632811A (en) | Structural steel pattern segregation fault detection based on machine vision quantifies ranking method | |
| CN116843582B (en) | Denoising enhancement system and method of 2CMOS camera based on deep learning | |
| CN118247277B (en) | Self-adaptive enhancement method for lung CT image | |
| CN114972084A (en) | Image focusing accuracy evaluation method and system | |
| CN118823292A (en) | An urban surveillance image recognition system | |
| CN111192280A (en) | Method for detecting optic disc edge based on local feature | |
| CN114598849B (en) | Building construction safety monitoring system based on thing networking | |
| CN112950479B (en) | Image gray level region stretching algorithm | |
| CN117616453A (en) | Cell image analysis method | |
| CN118247494B (en) | Flight training safety management system based on vision technology | |
| Martins | Automatic microaneurysm detection and characterization through digital color fundus images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |