An intelligent image-assisted guidance system for postoperative care of lung cancer

Abstract

The present invention relates to the field of image recognition technology, and particularly relates to an intelligent imaging assisted guidance system for postoperative care of lung cancer. The system obtains the lung CT images at each sampling moment after lung cancer surgery, thereby determining the consolidation information value of the lung clustering clusters, screening out the suspected infected lung clustering clusters, then determining the regularity of the boundary of the lung cluster region, adjusting the consolidation information value according to the regularity, determining the consolidation result of the suspected infected lung clustering clusters, determining the infection rate of lung cancer patients at each sampling moment, thereby obtaining the diffusion attribute of lung cancer patients, and giving different levels of nursing guidance suggestions to lung cancer patients. By analyzing the lung CT images of patients at different times, the present invention obtains the corresponding infection prediction and diffusion results and corresponding nursing guidance suggestions, reduces the risk of postoperative complications, and improves the nursing accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to an intelligent image-assisted guidance system for postoperative nursing of lung cancer. Background Art

[0002] Postoperative nursing guidance for lung cancer can monitor the patient's recovery and provide efficient recovery care plans. Among them, postoperative care mainly includes: postoperative recovery monitoring, image-assisted identification monitoring, lung function recovery assessment, and complication prevention and care. After lung cancer surgery, the patient's recovery process needs to be closely monitored, including the healing of the surgical site and the recovery of lung function. Imaging examinations, such as chest CT, X-rays, and lung function tests, are important means of monitoring the patient's postoperative recovery, and the specific nursing goal is to monitor postoperative complications such as lung infection, pneumothorax, and mediastinal effusion through the analysis of imaging data. The intelligent imaging system can detect postoperative tissue changes, detect abnormalities in a timely manner, and help nurses adjust the nursing plan in a timely manner.

[0003] Existing problems: Postoperative care for lung cancer is particularly important, because after surgery, the patient's immune system is suppressed in many ways, which provides a breeding ground for lung infections. The specific reasons for the suppression are: intraoperative chemotherapy and the immunosuppressive effects of radiotherapy. Lung cancer patients often receive chemotherapy. Chemotherapy drugs will suppress the function of the bone marrow, resulting in a decrease in the number of white blood cells (especially neutrophils), which in turn affects the immune response, greatly reducing the body's ability to resist infections such as bacteria and viruses, and making lung infections more likely to occur. In addition, in order to prevent postoperative complications, some patients will use immunosuppressive drugs (such as glucocorticoids, etc.) for a long time. Such drugs will further suppress the immune system, making patients more susceptible to infection. Therefore, when the analysis of the patient's lung infection based on lung CT images is inaccurate, it will lead to inappropriate auxiliary nursing guidance suggestions for patients, which may reduce the patient's recovery effect after lung cancer surgery. Summary of the invention

[0004] The present invention provides an intelligent image-assisted guidance system for postoperative nursing of lung cancer to solve the existing problems.

[0005] The intelligent image-assisted guidance system for postoperative nursing of lung cancer of the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides an intelligent image-assisted guidance system for postoperative nursing of lung cancer, the system comprising the following modules:

[0007] Lung CT image acquisition module: used to obtain lung CT images of lung cancer patients at each sampling moment after surgery;

[0008] Lung consolidation information analysis module: used to divide lung CT images into several lung clustering clusters, and determine the consolidation information value of the lung clustering clusters according to the number of pixel points and the magnitude of the gray value within the lung clustering clusters;

[0009] Lung consolidation result determination module: used to screen out several suspected infected lung clustering clusters according to the magnitude of the consolidation information value; record the connected region formed by adjacent pixel points within each suspected infected lung clustering cluster as the lung cluster region; determine the regularity of the boundary of the lung cluster region according to the distribution of pixel points on the boundary of the lung cluster region; adjust the consolidation information value of the suspected infected lung clustering clusters with the regularity to determine the consolidation result of the suspected infected lung clustering clusters;

[0010] Nursing guidance advice determination module: used to determine the infection rate of lung cancer patients at each sampling moment according to the magnitude of the consolidation result; determine the diffusion attribute of lung cancer patients according to the difference in the infection rate of lung cancer patients at adjacent sampling moments; give different levels of nursing guidance advice to lung cancer patients according to the magnitude of the diffusion attribute.

[0011] Furthermore, the determination of the consolidation information value of the lung clustering clusters includes:

[0012] Within any lung clustering cluster, obtain the mean value of the gray values of all pixel points, obtain the inverse proportional normalization value of the sum of the absolute values of the differences between the gray values of all pixel points and the mean value, calculate the product of the inverse proportional normalization value and the mean value, and use the normalization value of the sum of the product and the number of pixel points within any lung clustering cluster as the consolidation information value of any lung clustering cluster.

[0013] Furthermore, the screening out of several suspected infected lung clustering clusters includes:

[0014] When the consolidation information value of any lung clustering cluster is greater than the preset infection threshold, record the any lung clustering cluster as a suspected infected lung clustering cluster.

[0015] Furthermore, the determination of the regularity of the boundary of the lung cluster region includes:

[0016] For any lung cluster region, obtain the mean value of the Euclidean distances between the central pixel point of the lung cluster region and all pixel points on the boundary of the lung cluster region, and construct a circular region with the central pixel point of the lung cluster region as the center and the mean value as the radius;

[0017] Determine the regularity of the boundary of the lung cluster region according to the overlapping situation between the boundary of the lung cluster region and the boundary of the circular region, and the Euclidean distance from the central pixel point of the lung cluster region to the boundary of the lung cluster region.

[0018] Further, the rule for determining the regularity of the lung cluster region boundary based on the overlap between the lung cluster region boundary and the circular region boundary, and the Euclidean distance from the central pixel point of the lung cluster region to the lung cluster region boundary includes:

[0019] Obtain the number of overlapping pixel points between the lung cluster region boundary and the circular region boundary, calculate the inverse proportional normalization value of the sum of the absolute values of the differences between the Euclidean distances from the central pixel point of the lung cluster region to all pixel points on the lung cluster region boundary and the mean value, and use the normalization value of the product of the inverse proportional normalization value and the number of overlapping pixel points as the regularity of the lung cluster region boundary.

[0020] Further, the determination of the consolidation result of the suspected infected lung clustering clusters includes:

[0021] Use the mean value of the regularities of all lung cluster region boundaries within any suspected infected lung clustering cluster as the regularity of the suspected infected lung clustering cluster;

[0022] Use the normalization value of the ratio of the consolidation information value to the regularity of the suspected infected lung clustering cluster as the consolidation result of the suspected infected lung clustering cluster.

[0023] Further, the determination of the infection rate of lung cancer patients at each sampling moment includes:

[0024] Use the mean value of the consolidation results of all suspected infected lung clustering clusters in the lung CT image at any sampling moment as the infection rate of lung cancer patients at the sampling moment.

[0025] Further, the determination of the diffusion attribute of lung cancer patients includes:

[0026] Obtain the difference between the infection rates of lung cancer patients at the th sampling moment and the th sampling moment. If , assign the label 0 to the sampling moments from the th sampling moment to the th sampling moment. If , assign the label 1 to the sampling moments from the th sampling moment to the th sampling moment. If , assign the label -1 to the sampling moments from the th sampling moment to the th sampling moment;

[0027] Determine the diffusion attribute of lung cancer patients according to the labels of all adjacent sampling moments.

[0028] Further, determining the diffusion attribute of a lung cancer patient according to the labels at all adjacent sampling moments includes:

[0029] Denote the normalized value of the sum of the labels at all adjacent sampling moments as the diffusion attribute of the lung cancer patient.

[0030] Further, giving different levels of nursing guidance suggestions to lung cancer patients according to the magnitude of the diffusion attribute includes:

[0031] When the diffusion attribute of a lung cancer patient is greater than a preset diffusion threshold, give the patient first-level nursing guidance suggestions; when the diffusion attribute of a lung cancer patient is less than or equal to the preset diffusion threshold, give the patient second-level nursing guidance suggestions.

[0032] The beneficial effects of the technical solution of the present invention are:

[0033] In the embodiments of the present invention, obtain the pulmonary CT images of a lung cancer patient at each sampling moment after surgery, divide them into several pulmonary clustering clusters, determine the consolidation information values of the pulmonary clustering clusters, and use them to screen out several suspected infected pulmonary clustering clusters. Denote the connected region formed by adjacent pixel points within each suspected infected pulmonary clustering cluster as the pulmonary cluster region, determine the regularity of the boundary of the pulmonary cluster region, adjust the consolidation information value according to the regularity, and determine the consolidation result of the suspected infected pulmonary clustering cluster, so as to determine the infection rate of the lung cancer patient at each sampling moment. Thus, by analyzing the CT images of the patient at different times and combining the pulmonary infection characteristics of different regions within the images, such as the local high-density phenomenon caused by consolidation, obtain the infection rate of the lungs, and judge the specific lesion attributes of the patient based on the infection rate, improving the authenticity of the analysis and recognition results. Obtain the diffusion attribute of the lung cancer patient to give different levels of nursing guidance suggestions to the patient. Thus, by analyzing the patient's pulmonary infection results at different stages, obtain the corresponding pulmonary infection diffusion attributes of the patient at multiple stages, and use the diffusion attribute as the factor result of the auxiliary nursing guidance opinion, achieving the nursing purpose of preventing postoperative complications and improving the nursing accuracy and efficiency. Thus, the present invention analyzes the pulmonary CT images of the patient at different times, obtains the corresponding infection prediction and diffusion results and the corresponding nursing guidance suggestions, reduces the risk of postoperative complications, and improves the nursing accuracy. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0035] Figure 1It is the module flowchart of an intelligent image-assisted guidance system for postoperative care of lung cancer according to the present invention;

[0036] Figure 2 It is the flowchart for obtaining nursing guidance suggestions;

[0037] Figure 3 It is the schematic diagram of the lung cluster area and the corresponding circular area. Specific embodiments

[0038] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features and effects of an intelligent image-assisted guidance system for postoperative care of lung cancer proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0040] The following specifically describes the specific solution of an intelligent image-assisted guidance system for postoperative care of lung cancer provided by the present invention in conjunction with the accompanying drawings.

[0041] Please refer to Figure 1 , which shows the module flowchart of an intelligent image-assisted guidance system for postoperative care of lung cancer provided by an embodiment of the present invention. The system includes the following modules:

[0042] Module 101: Lung CT image acquisition module.

[0043] This module is used to obtain the lung CT images of lung cancer patients at each sampling moment after surgery.

[0044] Collect the lung CT images of any lung cancer patient at each sampling moment after surgery.

[0045] It should be noted that: The lung CT image is a grayscale image. The sampling time is selected twice a month for lung cancer patients after surgery until the current time when the patient has not recovered. Taking this as an example, through multiple acquisitions of lung CT images, the dynamic changes of the lungs can be captured, which can be used to evaluate the development process of infections, inflammations or other complications. In this embodiment, the lung CT images have been processed by denoising, smoothing, enhancement and removing the influence of the background, so as to improve the image quality and recognizability. If there is noise in the lung CT image, it will affect the observation and diagnosis of key lesions. Through the denoising algorithm (wavelet transform), the noise in the image is reduced, and the important structural information is retained. Then, through the smoothing process (median filtering), the unnecessary details in the image are reduced, and the boundary of the lesion area is highlighted to make the lesion more clear. Then, through contrast enhancement (Laplacian operator enhancement), the contrast between the lesion and the normal tissue in the image is increased, so that the lesion area is easier to identify. Finally, a segmentation neural network is used to identify and segment the lung CT images and background areas in the complete lung CT images (including part of the background area) obtained by CT (Computed Tomography) scan. Thus, the collected lung CT images are stored in a standardized manner to ensure the traceability of the image sequence, and the lung CT images and related clinical information (such as infection markers and patient symptoms, etc.) at each sampling time are labeled for subsequent analysis and guidance.

[0046] It should be further noted that: Wavelet transform, median filtering, Laplacian operator enhancement and segmentation neural network are all well-known technologies, and the specific methods will not be introduced here. Among them, the relevant content of the segmentation neural network is as follows: The segmentation neural network used in this embodiment is the Mask R-CNN neural network, and the dataset used is the complete lung CT image dataset obtained by CT scan. Among them, Mask R-CNN is a well-known technology, and the specific method will not be introduced here. The Chinese full name of Mask R-CNN is "Mask Region-based Convolutional Neural Network", and the English full name is "Mask Region-based Convolutional Neural Network". The pixel points to be segmented are divided into 2 categories, that is, the training set corresponding label annotation process is: for the single-channel semantic label, the pixel points at the corresponding positions labeled as 0 belong to the lung CT image, and those labeled as 1 belong to the background area. The task of the network is classification, so the loss function used is the cross-entropy loss function. Thus, the lung CT images and background areas in the complete lung CT images are obtained through the segmentation neural network. Thus, through the above processing, the clarity and contrast of the lung CT images are improved, enabling nursing staff to more clearly identify the early signs of lung infections or other complications. Combining the lesion information in the images, the nursing plan (such as body position adjustment, breathing training and anti-infection measures, etc.) is adjusted in a timely manner, thereby effectively reducing the incidence of complications such as postoperative infections.

[0047] Module 102: Pulmonary consolidation information analysis module.

[0048] This module is used to divide the pulmonary CT images into several pulmonary clustering clusters, and determine the consolidation information value of the pulmonary clustering clusters according to the number of pixel points and the magnitude of the gray value within the pulmonary clustering clusters.

[0049] It should be noted that: in this embodiment, by identifying and analyzing the pulmonary CT images at multiple sampling times after lung cancer surgery, the possibility of postoperative infection complications of the patient reflected by the images is obtained, and relevant auxiliary nursing guidance suggestions, etc. are provided based on this possibility. Therefore, it is necessary to first detect and analyze the pulmonary CT images, and extract and analyze indicators such as the infection rate according to the image content.

[0050] Preferably, in an embodiment of the present invention, the method for obtaining the consolidation information value of each pulmonary clustering cluster includes:

[0051] For the pulmonary CT image at any sampling time, taking the absolute value of the difference between the gray values of any two pixel points as the clustering distance between the two pixel points, and using the iterative self-organizing clustering algorithm to perform clustering operations on all pixel points to obtain several pulmonary clustering clusters.

[0052] It should be noted that: the iterative self-organizing clustering algorithm is a well-known technology, and the specific method will not be introduced here. Each obtained pulmonary clustering cluster has the same visual feature information, which is extended to each pulmonary clustering cluster having the same or similar pulmonary health information, because clustering by gray value will take the part with the same gray value or gray distribution information as a pulmonary clustering cluster. For example, after lung cancer surgery, for pneumonia caused by the reduced immunity of the patient, at this time, high-density areas will appear in the image, manifested as consolidation or spots, etc., then such consolidation areas will be used as a pulmonary clustering cluster.

[0053] It should be further noted that: each pulmonary clustering cluster has a consolidation information, which refers to the manifestation characteristics of possible pulmonary inflammation and other complications of the pulmonary clustering cluster. The more obvious the manifestation characteristics, for example, the more severe the pneumonia infection caused by the reduced immunity after lung cancer surgery, the more obvious its corresponding consolidation characteristics are, and the more sufficient the consolidation information is. Specifically, analyze the consolidation amount of each pulmonary clustering cluster, and consolidation refers to the appearance of obvious high-density areas in the lungs, which usually indicates problems such as inflammation, hematoma or tumor in the lung tissue. For pulmonary infections (such as pneumonia), consolidation is usually a manifestation of infection or local inflammation. In pulmonary CT images, consolidation appears as areas with higher density than normal lung tissue, and such areas are signs of pneumonia lesions.

[0054] For the pulmonary CT image at the For a lung clustering cluster, obtain the mean of the gray values of all pixel points within the -th lung clustering cluster. Calculate the absolute value of the difference between the gray value of each pixel point within the -th lung clustering cluster and . Obtain the sum of the absolute values of the differences between the gray values of all pixel points within the -th lung clustering cluster and . Obtain the inverse proportional normalization value of . Calculate the product of the inverse proportional normalization value of this sum and . Divide the product by the sum of the number of pixel points within the -th lung clustering cluster, and use the normalized value as the consolidation information value of the -th lung clustering cluster. It should be noted that in this embodiment, the inverse proportional relationship and normalization process of the sum value are presented by

[0055] . Implementers can set the inverse proportional function and normalization function according to the actual situation. is an exponential function with the natural constant as the base. Use the linear normalization function to normalize the sum value and normalize the data value to the interval. This is used as an example for description. Since the higher the average pixel gray value, the higher the corresponding lesion probability. In the CT images of pneumonia, common patchy or plaque-like images are seen. Especially in pneumonia with a large infection area or untreated for a long time, the CT images will show relatively uniform white patches in the lungs. The distribution, size, and shape of these patches usually show characteristics such as white highlights and irregularities. Therefore, the more pixel points there are in the lung clustering cluster, and the higher their gray value average, the higher the corresponding consolidation information, that is, the higher the probability of pneumonia. Thus, by analyzing the pixel distribution characteristics and pixel quantity within the lung clustering cluster, the density information within the cluster is determined, and then the consolidation information value is obtained. By performing a weighted sum of the pixel quantity information and gray information within the cluster, the density information of the cluster is obtained and used as the consolidation information. When the total number of pixels within the cluster is larger, the corresponding cluster density is higher, and correspondingly, the larger the gray value within the cluster, and the more uniform the gray distribution, that is, is larger, and the smaller the sum value is (using the inverse proportional normalization value of the sum value as the weight of ), the corresponding cluster density is higher. Thus, the consolidation information value of each lung clustering cluster is obtained. The higher this consolidation information value, the higher the corresponding regional consolidation volume, and correspondingly, the higher the infection rate of the patient. is used as ), the corresponding cluster density is higher. Thus, the consolidation information value of each lung clustering cluster is obtained. The higher this consolidation information value, the higher the corresponding regional consolidation volume, and correspondingly, the higher the infection rate of the patient.

[0056] Module 103: Lung consolidation result determination module.

[0057] This module is used to screen out several suspected infected lung clustering clusters according to the magnitude of the consolidation information value; denote the connected region formed by adjacent pixel points within each suspected infected lung clustering cluster as the lung cluster region; determine the regularity of the boundary of the lung cluster region according to the distribution of pixel points on the boundary of the lung cluster region; and adjust the consolidation information value of the suspected infected lung clustering cluster with the regularity to determine the consolidation result of the suspected infected lung clustering cluster.

[0058] It should be noted that: when the consolidation information value is higher, the risk of the patient having pneumonia infection is higher. When the pneumonia infection is more severe, such as lung abscess or gas pneumonia, lung cavities or abscesses will appear in the lung CT image, usually manifested as inflated cavities and irregular edges. Combining with the spot lesion characteristics within the lung clustering cluster, the irregularity of such edges can more completely show the patient's infection risk.

[0059] Preferably, in an embodiment of the present invention, the method for obtaining the consolidation result of each suspected infected lung clustering cluster includes:

[0060] For the lung CT image at any sampling moment, when the consolidation information value of any lung clustering cluster is greater than the preset infection threshold, denote this any lung clustering cluster as a suspected infected lung clustering cluster.

[0061] It should be noted that: in this embodiment, the preset infection threshold is 0.9, and this is used as an example for description. When the consolidation information value is greater than the preset infection threshold, it is considered that the lung clustering cluster has a high possibility of lung infection, and it is necessary to further analyze the shape characteristics of the lung clustering cluster to further determine the corresponding cluster consolidation result.

[0062] At the th sampling moment, in the th suspected infected lung clustering cluster in the lung CT image, denote the connected region formed by adjacent pixel points as the lung cluster region.

[0063] It should be noted that: in this embodiment, the lung clustering cluster is obtained by clustering according to the difference between pixel point gray values, so each lung clustering cluster may be composed of multiple connected regions. For example, if a certain suspected infected lung clustering cluster is composed of 3 lung cluster regions, it means that there may be three lesion spots with relatively consistent gray values or relatively regular tissue parts within this suspected infected lung clustering cluster. The preset area threshold is 10. If the area of the lung cluster region is less than 10, then this lung cluster region is not used as a lung cluster region for subsequent analysis. Taking this as an example for description, the lung cluster region with a small area is probably composed of interference points rather than an infected area, so it is not analyzed.

[0064] For the th lung CT image at the th sampling moment, for the th lung cluster region within the th suspected infected lung cluster, obtain the Euclidean distance between the central pixel point of the th lung cluster region and each pixel point on the boundary of the th lung cluster region, calculate the average value of the Euclidean distances between the central pixel point of the th lung cluster region and all pixel points on the boundary of the , with the central pixel point of the th lung cluster region as the center, and as the radius, construct the circular region corresponding to the th lung cluster region.

[0065] It should be noted that: The schematic diagram of the lung cluster region and the corresponding circular region is shown in Figure 3 . Figure 3 Taking any pixel point on the boundary of the lung cluster region as the sampling point, each dotted line is the distance from the center of the lung cluster region to each sampling point. According to the above-set rules, the regular judgment circle (circular region) of the lung cluster region can be obtained.

[0066] Obtain the number of overlapping pixel points between the boundary of the th lung cluster region and the boundary of the circular region corresponding to the th lung cluster region , calculate the absolute value of the difference between the Euclidean distance between the central pixel point of the th lung cluster region and each pixel point on the boundary of the th lung cluster region and , obtain the sum value of the absolute values of the differences between the Euclidean distances between the central pixel point of the th lung cluster region and all pixel points on the boundary of the th lung cluster region and The inverse proportional normalization value of, and take the product of the inverse proportional normalization value of this sum value and The normalization value of as the regularity of the boundary of the th lung cluster region.

[0067] It should be noted that: In this embodiment, is used to present the inverse proportional relationship and normalization processing of the sum value . The implementer can set the inverse proportional function and normalization function according to the actual situation. is the exponential function with the natural constant as the base, and is the linear normalization function for the product Perform normalization to normalize the data values to within the interval, and describe it by taking this as an example. The above The larger it is, the closer the boundary of the lung cluster area is to a circle and the more regular it is, and the higher the corresponding lung health level is, that is, the lower the possibility of infection. And the Euclidean distance between the central pixel point of the lung cluster area and each pixel point on the boundary of the lung cluster area and The smaller the difference, the more regular the boundary of the lung cluster area is. At this time, it is more likely to be close to the normal tissue part of the patient's lung, so the possibility of the patient being infected at this time is lower.

[0068] At the th sampling moment, take the mean value of the regularity of all the boundaries of the lung cluster areas within the th suspected infected lung clustering cluster in the lung CT image as the regularity of the th suspected infected lung clustering cluster.

[0069] At the th sampling moment, take the ratio of the consolidation information value of the th suspected infected lung clustering cluster to the regularity of the th suspected infected lung clustering cluster The normalized value of is used as the consolidation result of the

[0070] It should be noted that: in this embodiment, taking The linear normalization function comparison value Perform normalization to normalize the data values to within the interval, and describe it by taking this as an example. The ratio The larger it is, the more obvious the corresponding consolidation result is and the higher the infection rate is. When the consolidation results of all suspected infected lung clustering clusters are larger, it indicates that the infection rate of the lung cancer patient is higher.

[0071] Module 104: Nursing guidance suggestion determination module.

[0072] This module is used to determine the infection rate of the lung cancer patient at each sampling moment according to the size of the consolidation result; determine the spread attribute of the lung cancer patient according to the difference in the infection rate of the lung cancer patient at adjacent sampling moments; and give different levels of nursing guidance suggestions to the lung cancer patient according to the size of the spread attribute.

[0073] Preferably, in an embodiment of the present invention, the method for obtaining the spread attribute of the lung cancer patient includes:

[0074] At the th sampling moment, take the mean value of the consolidation results of all suspected infected lung clustering clusters in the lung CT image as the infection rate of the lung cancer patient at the th sampling moment.

[0075] It should be noted that: if there is no lung cluster area in the lung CT image at the th sampling moment, the infection rate of the lung cancer patient at the th sampling moment is set to 0, and this is used as an example for description.

[0076] According to the above method, the infection rate of the lung cancer patient at each sampling moment is obtained.

[0077] It should be noted that: in order to achieve efficient and accurate nursing and prevent complications, it is necessary to analyze the infection rate of the patient at different sampling moments and determine the corresponding diffusion attribute according to the infection rate. When the infection rate shows an increasing trend over time, the higher the diffusion attribute of the patient, that is, after lung cancer surgery, due to the decline of the patient's own immunity, the occurrence of complications such as pneumonia, and at this time, relevant nursing guidance and suggestions need to be given in a timely manner.

[0078] Obtain the difference between the infection rate of the lung cancer patient at the th sampling moment and the infection rate of the lung cancer patient at the th sampling moment , if , then assign the label from the th sampling moment to the th sampling moment as 0, if , then assign the label from the th sampling moment to the th sampling moment as 1, if , then assign the label from the th sampling moment to the th sampling moment as -1, and the normalized value of the sum of the labels of all adjacent sampling moments is recorded as the diffusion attribute of the lung cancer patient.

[0079] It should be noted that: in this embodiment, a linear normalization function is used to normalize the sum value , and the data value is normalized to the interval, and this is used as an example for description. When the patient's infection rate shows an increasing trend, set the label as 1, then the larger the sum of all labels, the higher the diffusion attribute value, and the higher the necessity of corresponding nursing to prevent complications.

[0080] When the diffusion attribute of the lung cancer patient is greater than the preset diffusion threshold, give the lung cancer patient first-level nursing guidance and suggestions. When the diffusion attribute of the lung cancer patient is less than or equal to the preset diffusion threshold, give the lung cancer patient second-level nursing guidance and suggestions.

[0081] It should be noted that: in this embodiment, the preset diffusion threshold is 0.8, and this is taken as an example for description. When the diffusion property is high, it is considered that the patient may have a high diffusion infection. At this time, first-level nursing guidance suggestions are given. When the diffusion property is low, it is considered that the possibility of the patient having a diffusion infection is low. At this time, second-level nursing guidance suggestions are given. Among them, the flowchart for obtaining nursing guidance suggestions is as Figure 2 shown.

[0082] Furthermore, it should be noted that: the first-level nursing guidance suggestions include: respiratory mode adjustment, position management, as well as monitoring and drug use. Among them, the respiratory mode adjustment includes: performing deep breathing training, encouraging the patient to take deep breaths to help expand the alveoli, clear pulmonary secretions, and reduce the risk of lung collapse. Performing effective coughing training, guiding the patient to expel sputum through appropriate coughing techniques to avoid the accumulation of sputum in the lungs and reduce the risk of infection. The position management includes: intermittently encouraging the patient to sit or lie semi-recumbent, which helps the lungs expand, reduces the pressure on the lower lung lobes, and promotes gas exchange. Performing regular position changes, changing the position every hour to avoid certain areas of the lungs being compressed for a long time and reducing the occurrence of static areas in the lungs. Keeping the semi-recumbent or sitting position, for patients with a higher risk of infection, avoiding long-term bed rest, and maintaining a certain angle of sitting or semi-recumbent position helps reduce airway occlusion and pulmonary hydrops. The monitoring and drug use include: regularly monitoring signs (including body temperature, respiratory rate, and blood oxygen saturation, etc.) to detect abnormalities in a timely manner. Performing drug management, using antibiotics or antiviral drugs for preventive treatment at an early stage to reduce the risk of secondary infection. Regularly reviewing images, performing CT examinations regularly to monitor the changes in the lungs and judge whether the pneumonia has worsened.

[0083] The second-level nursing guidance suggestions include: respiratory mode adjustment, position management, as well as routine monitoring and nursing. Among them, the respiratory mode adjustment includes: moderate breathing training, suggesting performing mild breathing training and coughing training to maintain the vitality of the lungs and prevent mucus accumulation. Keeping the normal respiratory rate and depth, encouraging the patient not to take excessive deep breaths, but to maintain the normal respiratory depth and frequency to avoid shallow breathing. The position management includes: normal position changes, encouraging the patient to change positions regularly to avoid maintaining the same posture for a long time, but not adjusting the position too frequently. Avoiding long-term bed rest, the patient can perform activities moderately to keep the body flexible and promote lung function. The routine monitoring and nursing include: mild monitoring, regularly monitoring body temperature and respiratory rate, etc. to ensure that there are no abnormal conditions. Strengthening respiratory tract care, encouraging the patient to drink water to keep the respiratory tract moist and avoid respiratory tract infections caused by dryness.

[0084] So far, the present invention is completed.

[0085] In summary, in the embodiments of the present invention, the pulmonary CT images of lung cancer patients at each sampling time after surgery are obtained, several pulmonary clustering clusters are divided, the consolidation information values of the pulmonary clustering clusters are determined, and several suspected infected pulmonary clustering clusters are screened out. The connected regions formed by adjacent pixel points within each suspected infected pulmonary clustering cluster are denoted as pulmonary cluster regions, the regularity of the boundaries of the pulmonary cluster regions is determined, the consolidation information values are adjusted according to the regularity, the consolidation results of the suspected infected pulmonary clustering clusters are determined, and the infection rates of lung cancer patients at each sampling time are determined, so as to obtain the diffusion attributes of lung cancer patients, and different levels of nursing guidance suggestions are given to lung cancer patients. By analyzing the pulmonary CT images of patients at different times, the present invention obtains the corresponding infection prediction and diffusion results and the corresponding nursing guidance suggestions, reduces the risk of postoperative complications, and improves the nursing accuracy.

[0086] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent image-assisted guidance system for postoperative nursing of lung cancer, characterized in that: The system includes the following modules: Lung CT image acquisition module: used to obtain lung CT images of lung cancer patients at each sampling moment after surgery; Lung consolidation information analysis module: used to divide the lung CT images into several lung clusters, and determine the consolidation information value of the lung cluster according to the number of pixels and the size of the gray value in the lung cluster; Lung consolidation result determination module: used to screen out a number of suspected infected lung clusters according to the size of the consolidation information value; record the connected area formed by adjacent pixels in each suspected infected lung cluster as a lung cluster area; determine the regularity of the lung cluster area boundary according to the distribution of pixels on the lung cluster area boundary; adjust the consolidation information value of the suspected infected lung cluster according to the regularity, and determine the consolidation result of the suspected infected lung cluster; Nursing guidance suggestion determination module: used to determine the infection rate of lung cancer patients at each sampling time according to the size of the consolidation result; determine the diffusion property of lung cancer patients according to the difference in infection rate of lung cancer patients at adjacent sampling times; According to the magnitude of the diffusion attribute, different levels of nursing guidance suggestions are given to lung cancer patients; The regularity of determining the lung cluster region boundaries includes: For any lung cluster region, obtain the mean of the Euclidean distances between the central pixel of the lung cluster region and all the pixel points on the boundary of the lung cluster region, and construct a circular region with the central pixel of the lung cluster region as the dot and the mean as the radius; Determine the regularity of the lung cluster region boundary according to the overlap between the lung cluster region boundary and the circular region boundary and the Euclidean distance from the central pixel point of the lung cluster region to the lung cluster region boundary; The results of the consolidation of suspected infected lung clusters include: Taking the average of the regularities of all lung cluster region boundaries within any suspected infected lung cluster as the regularity of the suspected infected lung cluster; The normalized value of the ratio of the consolidation information value to the regularity of the suspected infected lung cluster is used as the consolidation result of the suspected infected lung cluster.

2. According to claim 1, an intelligent image-assisted guidance system for postoperative nursing of lung cancer is characterized in that: Determining the consolidation information value of the lung cluster includes: In any one lung cluster, the mean of the grayscale values ​​of all pixels is obtained, the inversely proportional normalized value of the sum of the absolute values ​​of the differences between the grayscale values ​​of all pixels and the mean is obtained, the product of the inversely proportional normalized value and the mean is calculated, and the product and the normalized value of the sum of the number of pixels in the any one lung cluster are used as the real change information value of the any one lung cluster.

3. According to claim 1, an intelligent image-assisted guidance system for postoperative nursing of lung cancer is characterized in that: The screening of several suspected lung infection clusters includes: When the consolidation information value of any lung cluster is greater than a preset infection threshold, the any lung cluster is recorded as a suspected infected lung cluster.

4. According to claim 1, an intelligent image-assisted guidance system for postoperative nursing of lung cancer is characterized in that: The determining of the regularity of the lung cluster region boundary according to the overlap between the lung cluster region boundary and the circular region boundary and the Euclidean distance from the central pixel point of the lung cluster region to the lung cluster region boundary includes: The number of overlapping pixels between the boundary of the lung cluster region and the boundary of the circular region is obtained, and an inversely proportional normalized value of the sum of the absolute values ​​of the differences between the Euclidean distances between the central pixel of the lung cluster region and all the pixels on the boundary of the lung cluster region and the mean is calculated; and a normalized value of the product of the inversely proportional normalized value and the number of overlapping pixels is used as the regularity of the boundary of the lung cluster region.

5. According to claim 1, an intelligent image-assisted guidance system for postoperative nursing of lung cancer is characterized in that: Determining the infection rate of lung cancer patients at each sampling time includes: The mean of the consolidation results of all suspected infected lung clusters in the lung CT images at any sampling time is taken as the infection rate of lung cancer patients at the sampling time.

6. According to claim 1, an intelligent image-assisted guidance system for postoperative nursing of lung cancer is characterized in that: Determining the diffusion attribute of the lung cancer patient includes: Get the The sampling time and The difference in infection rates of lung cancer patients at different sampling times ,like , then assign the Sampling time to The label of the sampling moment is 0. , then assign the Sampling time to The label of each sampling moment is 1. , then assign the Sampling time to The label of the sampling moment is -1; Determine the diffusion properties of lung cancer patients based on the labels of all adjacent sampling moments.

7. The intelligent image-assisted guidance system for postoperative nursing care of lung cancer according to claim 6, characterized in that: Determining the diffusion attribute of the lung cancer patient according to the labels of all adjacent sampling moments includes: The normalized value of the sum of the labels at all adjacent sampling moments is recorded as the diffusion attribute of the lung cancer patient.

8. The intelligent image-assisted guidance system for postoperative nursing care of lung cancer according to claim 1, characterized in that: According to the size of the diffusion attribute, the different levels of nursing guidance suggestions for lung cancer patients include: When the diffusion attribute of a lung cancer patient is greater than a preset diffusion threshold, the lung cancer patient is given first-level nursing guidance suggestions; when the diffusion attribute of a lung cancer patient is less than or equal to the preset diffusion threshold, the lung cancer patient is given second-level nursing guidance suggestions.

Images