An automatic organ trauma recognition and control system

Abstract

The present invention relates to the technical field of trauma recognition, and in particular to an automatic organ trauma recognition control system. The system includes a data acquisition module for collecting organ trauma image data of a user and historical organ trauma image data of the user, an image segmentation module for determining whether to segment the organ trauma image according to the uniformity of the organ trauma in the organ trauma image data, a trauma recognition module for determining the type of organ trauma according to the organ trauma image data, a control module for determining to upload the organ trauma image to different databases according to the type of organ trauma and the change value of the organ trauma degree under the third type within a preset time, and an adjustment module for determining whether to adjust the parameters of the automatic organ trauma recognition control process according to the accuracy of the automatic organ trauma recognition control result. The present invention improves the accuracy of organ trauma type recognition by accurately analyzing the organ trauma image data.

Description

Technical Field

[0001] The present invention relates to the technical field of trauma recognition, and particularly to an automatic organ trauma recognition control system. Background Art

[0002] With the continuous development of medical imaging technology and the popularization of advanced algorithms, the technology of external organ trauma recognition control system has become a research direction attracting much attention in the medical field. This technology combines computer vision, deep learning, and medical image processing technology, aiming to achieve rapid, accurate recognition and quantitative evaluation of external organ trauma, providing important diagnostic support and treatment guidance for medical staff. However, the traditional external organ trauma recognition control technology not only has a slow processing speed but also is difficult to capture the changes of trauma in a timely manner, affecting the decision-making and treatment process of medical staff.

[0003] Chinese Patent Application Publication No.: CN117409002A discloses a visual recognition detection system for trauma and its detection method. The system includes an image acquisition module, an image preprocessing module, a visual neural network module, a trauma analysis module, a data storage and management module, and a result display module. This invention can perform automated trauma detection, reduce the error of subjective judgment, and improve the efficiency and accuracy of trauma recognition and measurement, playing a positive role in assisting medical decision-making.

[0004] It can be seen that the existing technology has the problem that the inaccurate analysis of organ trauma image data leads to inaccurate determination of organ trauma types, resulting in the failure to timely detect potentially dangerous organ traumas. Summary of the Invention

[0005] Therefore, the present invention provides an automatic organ trauma recognition control system to overcome the problem in the existing technology that the inaccurate analysis of organ trauma image data leads to inaccurate determination of organ trauma types, resulting in the failure to timely detect potentially dangerous organ traumas.

[0006] To achieve the above object, the present invention provides an automatic organ trauma recognition control system, including:

[0007] A data acquisition module, which is used to collect the organ trauma image data of the user and the historical organ trauma image data of the user, and preprocess the organ trauma image data;

[0008] An image segmentation module, which is connected to the data acquisition module and is used to determine whether to segment the organ trauma image according to the uniformity of the trauma in the organ trauma image data;

[0009] A trauma recognition module, which is connected to the image segmentation module and is used to determine the type of organ trauma according to the trauma degree of the organ in the organ trauma image data, the malignancy rate of the organ trauma, and whether there is a historical trauma of the organ. Among them, the types of organ trauma include the first type, the second type, and the third type;

[0010] A control module, which is connected to the trauma recognition module and is used to determine whether to upload the organ trauma image to different databases according to the type of organ trauma and the change value of the organ trauma degree under the third type within a preset time;

[0011] An adjustment module, which is connected to the control module and is used to determine whether to adjust the parameters of the automatic recognition control process of organ trauma according to the comparison result between the accuracy of the automatic recognition control result of organ trauma and the preset accuracy;

[0012] Among them, the control module determines whether to upload the organ trauma image to the first database, the second database, and the third database according to the comparison result between the type of organ trauma and the change value of the organ trauma degree under the third type within a preset time and the preset change value. The preset change value includes the first preset change value and the second preset change value.

[0013] Further, the image segmentation module determines whether to segment the organ trauma image according to the comparison result that the uniformity degree of the organ trauma in the organ trauma image data is greater than or equal to the preset uniformity degree.

[0014] Further, the types of organ trauma determined by the trauma recognition module include:

[0015] The trauma recognition module determines that the type of organ trauma is the first type according to the comparison result that the trauma degree of the organ is greater than or equal to the preset trauma degree;

[0016] The trauma recognition module determines to detect the malignancy rate of the organ trauma according to the comparison result that the trauma degree of the organ is less than the preset trauma degree.

[0017] Further, under the condition that the trauma recognition module determines to detect the malignancy rate of the organ trauma, it determines the type of organ trauma according to the comparison result between the malignancy rate of the organ trauma and the preset malignancy rate. Among them,

[0018] The trauma recognition module determines that the type of organ trauma is the first type according to the comparison result that the malignancy rate of the organ trauma is greater than or equal to the preset malignancy rate;

[0019] The trauma recognition module determines to detect whether there is a historical trauma of the organ according to the comparison result that the malignancy rate of the organ trauma is less than the preset malignancy rate.

[0020] Further, when the trauma recognition module determines the condition for detecting whether there is a historical trauma in the organ, it determines the type of the organ trauma according to whether there is a historical trauma in the organ, where

[0021] the trauma recognition module determines that the type of the organ trauma is the second type according to the existence of a historical trauma in the organ;

[0022] the trauma recognition module determines that the type of the organ trauma is the third type according to the non - existence of a historical trauma in the organ.

[0023] Further, the control module determines to upload the organ trauma image to different databases according to the comparison result between the change value of the trauma degree of the organ and the preset change value, where

[0024] the control module determines to upload the organ trauma image to the first database according to the comparison result that the change value of the trauma degree of the organ within the preset time is less than the first preset change value;

[0025] the control module determines to upload the organ trauma image to the second database according to the comparison result that the change value of the trauma degree of the organ within the preset time is greater than or equal to the first preset change value and less than the second preset change value;

[0026] the control module determines to upload the organ trauma image to the third database according to the comparison result that the change value of the organ trauma within the preset time is greater than or equal to the second preset change value.

[0027] Further, the preset change value of the organ trauma is determined according to the preset trauma degree.

[0028] Further, the adjustment module determines to adjust the parameters of the automatic recognition control process of the organ trauma according to the comparison result that the accuracy of the automatic recognition control result of the organ trauma is less than the preset accuracy, where the parameters of the automatic recognition control process of the organ trauma include the preset uniformity and the preset malignancy rate.

[0029] Further, the adjustment amount of the preset uniformity is negatively correlated with the fluctuation degree of the error types when uploading the organ trauma image to different databases during the automatic recognition control process of the organ trauma in several preset cycles, and the adjustment amount of the preset malignancy rate is positively correlated with the fluctuation degree of the error types when uploading the organ trauma image to different databases during the automatic recognition control process of the organ trauma in several preset cycles.

[0030] Further, the value of the preset fluctuation degree is the average value of the fluctuation degree of the error types when uploading the organ trauma image to different databases during the automatic recognition control process of the organ trauma in several preset cycles.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows. The present invention determines whether to segment an organ trauma image based on the uniformity of the organ trauma in the organ trauma image data. If the trauma in the organ trauma image data is relatively uniform, the organ trauma image is not segmented to improve the accuracy of subsequent trauma analysis. If the trauma in the organ trauma image data is non-uniform, by segmenting the organ trauma image, the location and scope of the trauma can be determined more accurately, which helps to improve the accuracy of subsequent trauma analysis, including the type and severity of the trauma, etc. Segmenting the organ trauma can make the quantitative assessment of the trauma more convenient. Through segmentation, parameters such as the size and shape of the trauma area can be calculated, thereby providing more quantitative data for analysis. Segmenting the organ trauma image can help doctors better understand the trauma situation of patients, so as to formulate more personalized treatment plans. Traumas of different sizes and locations may require different treatment strategies. The segmented organ trauma image can provide a clearer visualization effect, which helps doctors and researchers better understand the characteristics of the trauma and discover details that may be overlooked. The segmented organ trauma image can be more easily integrated with other medical data, such as clinical data, biomarkers, etc., so as to achieve comprehensive trauma analysis and prediction.

[0032] Furthermore, the present invention determines the type of organ trauma through the trauma recognition module according to the degree of organ trauma and the preset trauma degree. If the degree of trauma is greater than or equal to the preset trauma degree, it indicates that the organ trauma is the first type that requires emergency treatment. If the degree of trauma is less than the preset trauma degree, the type of the organ trauma is re-determined by detecting the malignancy rate of the organ trauma. Through the above method, the accuracy of the analysis of the organ trauma image data is improved, and thus the accuracy of the determination of the organ trauma type is improved to timely discover organ traumas with potential risks.

[0033] Furthermore, the present invention determines the type of organ trauma through the trauma recognition module according to the comparison result between the malignancy rate of the organ trauma and the preset malignancy rate. If the malignancy rate is greater than or equal to the preset malignancy rate, it indicates that the organ trauma is the first type that is prone to malignancy and requires emergency treatment. If the malignancy rate is less than the preset malignancy rate, the type of the organ trauma is determined by detecting whether there is a historical trauma in the organ. Through the above method, the accuracy of the analysis of the organ trauma image data is improved, and thus the accuracy of the determination of the organ trauma type is improved to timely discover organ traumas with potential risks.

[0034] Furthermore, the present invention uses a trauma recognition module to further determine the type of organ trauma based on whether there is a historical trauma to the organ. If there is a historical trauma to the organ, it indicates that there may be potential risks associated with this organ trauma. The trauma recognition module determines that the type of this organ trauma is the second type with potential risks. If there is no historical trauma to the organ, it indicates that the type of this organ trauma is the third type that does not require emergency treatment by a doctor. By the above method, the accuracy of data analysis of organ trauma images is improved, thereby improving the accuracy of organ trauma type determination and timely detecting organ traumas with potential risks.

[0035] Furthermore, the present invention uploads the organ trauma images of the first type and the second type that require a doctor to determine whether treatment is needed to the first database through a control module. The control module determines to upload the images of the organ trauma of the third type to different databases according to the change situation of the organ trauma within a preset time. If the change value of the organ trauma degree within the preset time is greater than or equal to the second preset change value, it indicates that the organ trauma has deteriorated due to bacterial infection or other external factors. At this time, the organ trauma image is uploaded to the second database. If the change value of the organ trauma degree within the preset time is greater than or equal to the first preset change value and less than the second preset change value, the display clarity of the organ trauma image is enhanced to more accurately judge the change situation of the organ trauma. If the change value of the organ trauma degree within the preset time is less than the first preset change value, it indicates that this organ trauma does not require treatment by a doctor and can recover naturally. At this time, the organ trauma image is uploaded to the first database. By the above method, the accuracy of data analysis of organ trauma images is improved, thereby improving the accuracy of organ trauma type determination and timely detecting organ traumas with potential risks.

[0036] Furthermore, the present invention determines the accuracy of the organ trauma automatic recognition control result according to the accuracy of uploading the organ trauma images to different databases by the control module, and determines whether to adjust the process parameters of the organ trauma automatic recognition control based on the comparison result of the accuracy with the preset accuracy. By the above method, the accuracy of data analysis of organ trauma images is improved, thereby improving the accuracy of organ trauma type determination and timely detecting organ traumas with potential risks.

[0037] Further, according to the present invention, the adjustment module determines the adjustment method for the automatic recognition control process of organ trauma based on the fluctuation degree of the errors in uploading organ trauma to different databases by the control module. If the fluctuation degree is less than the preset fluctuation degree, it indicates that during the automatic recognition control process of organ trauma, due to the existence of regions with a minimal trauma degree greater than the preset trauma degree during the image segmentation process of organ trauma, organ traumas that do not require emergency treatment are misjudged as the first type, resulting in a low accuracy of the automatic recognition control result of organ trauma. At this time, the preset uniformity degree is increased with the first adjustment coefficient. If the fluctuation degree is greater than or equal to the preset fluctuation degree, it indicates that there are many misjudgments of the third type of organ trauma. At this time, the preset malignancy rate is reduced with the second adjustment coefficient, thereby reducing the number of the third type of organ trauma, and further reducing the number of misjudgments of the third type of organ trauma. Through the above method, the accuracy of data analysis of organ trauma images is improved, and thus the accuracy of organ trauma type determination is improved to timely detect organ traumas with potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic structural diagram of the automatic recognition control system for organ trauma according to an embodiment of the present invention;

[0039] Figure 2 It is a flowchart of the operation of the image segmentation module in the automatic recognition control system for organ trauma according to an embodiment of the present invention;

[0040] Figure 3 It is a flowchart of the operation of the adjustment module in the automatic recognition control system for organ trauma according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0043] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention.

[0044] In addition, it should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] Please refer to Figures 1 - 3 as shown in Figure 1 the structural schematic diagram of the organ trauma automatic recognition control system according to the embodiment of the present invention; Figure 2 the working flowchart of the image segmentation module in the organ trauma automatic recognition control system according to the embodiment of the present invention; Figure 3 the working flowchart of the adjustment module in the organ trauma automatic recognition control system according to the embodiment of the present invention.

[0046] The organ trauma automatic recognition control system according to the embodiment of the present invention includes:

[0047] a data acquisition module, which is used to acquire the organ trauma image data of the user and the historical organ trauma image data of the user, and preprocess the organ trauma image data;

[0048] an image segmentation module, which is connected to the data acquisition module and is used to determine whether to segment the organ trauma image according to the uniformity of the trauma in the organ trauma image data;

[0049] a trauma recognition module, which is connected to the image segmentation module and is used to determine the type of organ trauma according to the degree of organ trauma, the malignancy rate of organ trauma, and whether there is historical trauma in the organ trauma image data, wherein the types of organ trauma include the first type, the second type, and the third type;

[0050] a control module, which is connected to the trauma recognition module and is used to determine to upload the organ trauma image to different databases according to the type of organ trauma and the change value of the degree of organ trauma of the third type within a preset time;

[0051] an adjustment module, which is connected to the control module and is used to determine whether to adjust the parameters of the organ trauma automatic recognition control process according to the comparison result between the accuracy of the organ trauma automatic recognition control result and the preset accuracy.

[0052] The preset change value of the degree of organ trauma in the embodiment of the present invention includes a first preset change value and a second preset change value.

[0053] Specifically, the image segmentation module determines whether to segment the organ trauma image based on the comparison result between the uniformity degree S of the organ trauma in the organ trauma image data and the preset uniformity degree S0.

[0054] If S≥S0, the image segmentation module determines to segment the organ trauma image.

[0055] If S<S0, the image segmentation module determines not to segment the organ trauma image.

[0056] Among them, the value range of the preset uniformity degree S0 is set to 0 - 0.3, and the value of the preset uniformity degree S0 is preferably 0.2. However, the above values are not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0057] Specifically, the uniformity degree S of the organ trauma in the organ trauma image data is calculated by the following formula. Let:

[0058]

[0059] Among them, M represents the difference between the maximum value and the minimum value of the organ trauma density, M0 represents the average value of the organ trauma density, α represents the influence coefficient of the organ trauma density on the trauma uniformity degree, and its value is preferably 0.56. D represents the maximum chromaticity value of the organ trauma, D0 represents the average chromaticity value of the organ trauma, and β represents the influence coefficient of the chromaticity value of the organ trauma on the trauma uniformity degree, and its value is set to 0.44.

[0060] In the embodiment of the present invention, the organ trauma density can be determined according to the gray value in the organ trauma image.

[0061] The present invention determines whether to segment an organ trauma image based on the uniformity of the organ trauma in the organ trauma image data. If the trauma in the organ trauma image data is relatively uniform, the organ trauma image is not segmented to improve the accuracy of subsequent trauma analysis. If the trauma in the organ trauma image data is non-uniform, segmenting the organ trauma image can more accurately determine the location and scope of the trauma, which helps to improve the accuracy of subsequent trauma analysis, including the type and severity of the trauma, etc. Segmenting the organ trauma can make the quantitative assessment of the trauma more convenient. Through segmentation, parameters such as the size and shape of the trauma area can be calculated, thus providing more quantitative data for analysis. Segmenting the organ trauma image can help doctors better understand the patient's trauma situation, so as to develop a more personalized treatment plan. Traumas of different sizes and locations may require different treatment strategies. The segmented organ trauma image can provide a clearer visualization effect, which helps doctors and researchers better understand the characteristics of the trauma and discover details that may be overlooked. The segmented organ trauma image can be more easily integrated with other medical data, such as clinical data, biomarkers, etc., so as to achieve comprehensive trauma analysis and prediction.

[0062] Specifically, under the condition that the trauma recognition module determines the type of organ trauma, the trauma recognition module determines the type of the organ trauma according to the comparison result between the trauma degree Y of the organ and the preset trauma degree Y0;

[0063] If Y≥Y0, the trauma recognition module determines that the type of the organ trauma is the first type;

[0064] If Y<Y0, the trauma recognition module determines the malignancy rate of the detected organ trauma;

[0065] Among them, the value range of the preset trauma degree Y0 is set to 9-20, and the preferred value of the preset trauma degree Y0 is 15, but the above values are not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0066] In the embodiment of the present invention, the trauma degree can be determined according to the Injury Severity Score (ISS).

[0067] The present invention determines the type of organ trauma through the trauma recognition module according to the trauma degree of the organ and the preset trauma degree. If the trauma degree is greater than or equal to the preset trauma degree, it indicates that the organ trauma is the first type that requires emergency treatment. If the trauma degree is less than the preset trauma degree, the malignancy rate of the organ trauma is detected to perform a secondary determination on the type of the organ trauma. Through the above method, the accuracy of the data analysis of the organ trauma image is improved, and further the accuracy of the determination of the organ trauma type is improved to timely discover the organ traumas with potential risks.

[0068] Specifically, under the condition of determining to detect the malignancy rate of the trauma of the organ, the trauma recognition module determines the type of the organ trauma according to the comparison result between the malignancy rate A of the organ trauma and the preset malignancy rate A0;

[0069] If A≥A0, the trauma recognition module determines that the type of the organ trauma is the first type;

[0070] If A<A0, the trauma recognition module determines whether there is a historical trauma to the organ;

[0071] Among them, the value range of the preset malignancy rate A0 is set to 0.5 - 1, and the value of the preset malignancy rate is preferably 0.7, but the above values are not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0072] In the present invention, the malignancy rate is the ratio of the number of organ traumas that have become malignant to the total number of organ traumas of several patients with the same degree of trauma as the organ trauma, and the occurrence of malignancy requires emergency treatment by a doctor.

[0073] The present invention determines the type of organ trauma through the trauma recognition module according to the comparison result between the malignancy rate of the organ trauma and the preset malignancy rate. If the malignancy rate is greater than or equal to the preset malignancy rate, it indicates that the organ trauma is the first type that is prone to malignancy and requires emergency treatment. If the malignancy rate is less than the preset malignancy rate, the type of organ trauma is determined by detecting whether there is a historical trauma to the organ. Through the above method, the accuracy of data analysis of organ trauma images is improved, and then the accuracy of determining the type of organ trauma is improved to timely discover organ traumas with potential risks.

[0074] Specifically, under the condition of determining to detect whether there is a historical trauma to the organ, the trauma recognition module determines the type of the organ trauma according to whether there is a historical trauma to the organ;

[0075] If the organ has a historical trauma, the trauma recognition module determines that the type of the organ trauma is the second type;

[0076] If the organ has no historical trauma, the trauma recognition module determines that the type of the organ trauma is the third type.

[0077] In the present invention, the trauma recognition module further determines the type of organ trauma based on whether there is a historical trauma to the organ. If there is a historical trauma to the organ, it indicates that there may be potential danger hidden in this organ trauma. The trauma recognition module determines that the type of this organ trauma is the second type with potential danger. If there is no historical trauma to the organ, it indicates that the type of this organ trauma is the third type that does not require emergency treatment by a doctor. By the above method, the accuracy of data analysis of organ trauma images is improved, and further the accuracy of determination of organ trauma types is improved to timely discover organ traumas with potential danger.

[0078] Specifically, the control module uploads the organ trauma image to different databases according to the type of organ trauma;

[0079] The control module determines to upload the organ trauma image to the third database according to the types of the organ trauma being the first type and the second type;

[0080] The control module determines to conduct a secondary determination on uploading the organ trauma image to different databases according to the type of the organ trauma being the third type.

[0081] Specifically, under the condition that the control module determines to conduct a secondary determination on uploading the organ trauma image to different databases, the control module determines to upload the organ trauma image to different databases according to the comparison result between the change value B of the organ trauma within a preset time and the preset change value Bi;

[0082] If B < B0, the control module determines to upload the organ trauma image to the first database;

[0083] If B0 ≤ B < B1, the control module determines to upload the organ trauma image to the second database;

[0084] If B ≥ B1, the control module determines to upload the organ trauma image to the third database;

[0085] Wherein, i = 0, 1; the value of the first preset change value B0 is preferably -3, and the value of the second preset change value B1 is preferably 0, but the above values are not limited to this, and those skilled in the art can also adjust the values according to actual needs.

[0086] In the embodiment of the present invention, the preset time is set to one twentieth of the time for the complete recovery of this organ trauma, but the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0087] In the embodiment of the present invention, the organ trauma image data stored in the first database are organ trauma images that require doctors to confirm whether emergency treatment is needed. The organ trauma images stored in the second database are organ trauma images that require enhancing the display clarity of the organ trauma images. The organ trauma images stored in the third database serve as the historical organ trauma images of the user.

[0088] In the present invention, the control module uploads organ trauma images of the first type and the second type that require doctors to determine whether treatment is needed to the first database. The control module determines to upload the images of organ trauma of the third type to different databases according to the change situation of the organ trauma within a preset time. If the change value of the organ trauma degree within the preset time is greater than or equal to the second preset change value, it indicates that the organ trauma has deteriorated due to bacterial infection or other external factors. At this time, the organ trauma image is uploaded to the second database. If the change value of the organ trauma degree within the preset time is greater than or equal to the first preset change value and less than the second preset change value, the display clarity of the organ trauma image is enhanced to more accurately judge the change situation of the organ trauma. If the change value of the organ trauma degree within the preset time is less than the first preset change value, it indicates that the organ trauma does not require doctor treatment and can recover naturally. At this time, the organ trauma image is uploaded to the first database. Through the above method, the accuracy of the organ trauma image data analysis is improved, thereby improving the accuracy of the organ trauma type determination and timely discovering organ traumas with potential risks.

[0089] Specifically, under the condition that the adjustment module determines whether to adjust the process parameters of the automatic recognition control of organ trauma, the adjustment module determines whether to adjust the process parameters of the automatic recognition control of organ trauma according to the comparison result between the accuracy degree P of the automatic recognition control result of organ trauma and the preset accuracy degree P0.

[0090] If P < P0, the adjustment module determines that it is necessary to adjust the process parameters of the automatic recognition control of organ trauma.

[0091] If P ≥ P0, the adjustment module determines that there is no need to adjust the process parameters of the automatic recognition control of organ trauma.

[0092] Among them, the value range of the preset accuracy degree P0 is set to 0.7 - 1, and the value of the preset accuracy degree is preferably 0.82. However, the above values are not limited to this, and those skilled in the art can also adjust this value according to actual needs.

[0093] In the embodiment of the present invention, the accuracy of the automatic recognition control result of organ trauma is one-third of the sum of the accuracies of uploading organ trauma images to different databases. The accuracy of uploading organ trauma images to the third database is the ratio of the number of organ trauma images that require medical treatment in the third database to the total number of organ trauma images in the third database. The accuracy of uploading organ trauma images to the second database is the ratio of the number of organ trauma images in the second database that are uploaded to the first database or the third database when uploaded to the database next time to the total number of organ trauma images in the second database. The accuracy of uploading organ trauma images to the third database is the ratio of the number of organ trauma images that do not require emergency treatment during subsequent spot checks in the third database to the total number of organ trauma images in the third database.

[0094] The present invention determines the accuracy of the automatic recognition control result of organ trauma according to the accuracy of uploading organ trauma images to different databases by the control module, and determines whether to adjust the parameters of the automatic recognition control process of organ trauma based on the comparison result between the accuracy and the preset accuracy. Through the above method, the accuracy of data analysis of organ trauma images is improved, thereby improving the accuracy of organ trauma type determination and timely discovering organ traumas with potential risks.

[0095] Specifically, under the condition that the adjustment module determines that the parameters of the automatic recognition control process of organ trauma need to be adjusted, the adjustment module determines the adjustment method according to the comparison result between the fluctuation degree R of the error types of uploading organ trauma images to different databases by the control module within a preset period and the preset fluctuation degree R0;

[0096] If R < R0, the adjustment module determines to adjust the preset uniformity degree with the first adjustment coefficient K1;

[0097] If R ≥ R0, the adjustment module determines to adjust the preset malignancy rate with the second adjustment coefficient K2;

[0098] Among them, the value of the preset fluctuation degree R0 is the average value of the fluctuation degrees of the error types of uploading organ trauma images to different databases during the automatic recognition control process of organ trauma within several preset periods, but the above value is not limited to this, and those skilled in the art can also adjust this value according to actual needs.

[0099] In the embodiment of the present invention, the preset period can be set to 3 days. The fluctuation degree of the error types of uploading organ trauma images to different databases within the preset period can be calculated according to the change frequency of the error types within the preset period. For example, if the number of changes in the error types of uploading organ trauma images to different databases within the preset period is 35 times, and the number of errors in uploading organ trauma images to different databases within the preset period is 50 times, then the fluctuation degree is 0.7.

[0100] Specifically, the first adjustment coefficient K1 is calculated by the following formula. Let:

[0101]

[0102] The second adjustment coefficient K2 is calculated by the following formula. Let:

[0103]

[0104] Set the adjusted preset uniformity degree S0' as S0' = K1 × S0;

[0105] Set the adjusted preset malignancy rate A0' as A0' = K2 × A0.

[0106] In the embodiment of the present invention, the error types of uploading organ trauma images to different databases include the first error type corresponding to uploading organ trauma images incorrectly to the first database, the second error type corresponding to uploading organ trauma images incorrectly to the second database, and the third error type corresponding to uploading organ trauma images incorrectly to the third database.

[0107] The present invention determines the adjustment method for the automatic recognition control process of organ trauma through the adjustment module according to the fluctuation degree of the error types of uploading organ trauma to different databases by the control module. If the fluctuation degree is less than the preset fluctuation degree, it indicates that in the automatic recognition control process of organ trauma, due to the existence of regions with a minimum trauma degree greater than the preset trauma degree during the segmentation of organ trauma images, organ traumas that do not require emergency treatment are misjudged as the first type, resulting in a low accuracy of the automatic recognition control result of organ trauma. At this time, the preset uniformity degree is increased by the first adjustment coefficient. If the fluctuation degree is greater than or equal to the preset fluctuation degree, it indicates that there are many misjudgments of the third type of organ trauma. At this time, the preset malignancy rate is reduced by the second adjustment coefficient to reduce the number of the third type of organ trauma, and thus reduce the number of misjudgments of the third type of organ trauma. Through the above method, the accuracy of data analysis of organ trauma images is improved, and thus the accuracy of organ trauma type determination is improved to timely discover organ traumas with potential risks.

[0108] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easily understood by those skilled in the art that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0109] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An automatic organ injury identification and control system, characterized in that: include: A data acquisition module, which is used to acquire the user's organ trauma image data and the user's historical organ trauma image data, and pre-process the organ trauma image data; An image segmentation module, which is connected to the data acquisition module and is used to determine whether to segment the organ trauma image according to the uniformity of the trauma in the organ trauma image data; The image segmentation module determines whether to segment the organ trauma image according to a comparison result of the uniformity of the organ trauma in the organ trauma image data and a preset uniformity; If the uniformity of the organ trauma in the organ trauma image data is greater than or equal to the preset uniformity, the image segmentation module determines to segment the organ trauma image; If the uniformity of the organ trauma in the organ trauma image data is less than the preset uniformity, the image segmentation module determines not to segment the organ trauma image; The uniformity of organ trauma in the organ trauma image data is calculated by the following formula, set: Wherein, S represents the uniformity of the organ trauma in the organ trauma image data, M represents the difference between the maximum and minimum values ​​of the organ trauma density, M0 represents the average value of the organ trauma density, α represents the influence coefficient of the organ trauma density on the uniformity of the trauma, and its value is preferably 0.56, D represents the maximum chromaticity value of the organ trauma, D0 represents the average chromaticity value of the organ trauma, and β represents the influence coefficient of the chromaticity value of the organ trauma on the uniformity of the trauma, and its value is set to 0.44; a trauma identification module, which is connected to the image segmentation module and is used to determine the type of organ trauma according to the degree of organ trauma in the organ trauma image data, the malignant transformation rate of the organ trauma, and whether the organ has historical trauma, wherein the types of organ trauma include a first type, a second type, and a third type; A control module connected to the trauma identification module, for determining whether to upload the organ trauma image to different databases according to the type of organ trauma and the change value of the degree of organ trauma under the third type within a preset time; An adjustment module, connected to the control module, for determining whether to adjust the parameters of the organ injury automatic identification control process according to a comparison result of the accuracy of the organ injury automatic identification control result and a preset accuracy; Among them, the control module determines to upload the organ trauma image to the first database, the second database and the third database by comparing the type of organ trauma and the change value of the degree of organ trauma under the third type within the preset time with the preset change value, and the preset change value includes a first preset change value and a second preset change value.

2. The organ injury automatic identification and control system according to claim 1, characterized in that: The trauma identification module determines the type of organ trauma by: The trauma identification module determines that the type of the organ trauma is the first type according to the comparison result that the degree of trauma of the organ is greater than or equal to the preset degree of trauma; The trauma recognition module determines the malignant transformation rate of the organ trauma according to the comparison result that the trauma degree of the organ is less than the preset trauma degree.

3. The organ injury automatic identification and control system according to claim 2, characterized in that: The trauma identification module determines the type of the organ trauma according to the comparison result of the malignant transformation rate of the organ trauma and the preset malignant transformation rate under the condition of determining the malignant transformation rate of the organ trauma, wherein: The trauma identification module determines that the type of the organ trauma is the first type according to the malignant transformation rate of the organ trauma being greater than or equal to the preset malignant transformation rate; The trauma identification module determines whether the organ has a historical trauma according to the malignant transformation rate of the organ trauma being less than a preset malignant transformation rate.

4. The organ injury automatic identification and control system according to claim 3, characterized in that: The trauma identification module determines the type of the organ trauma according to whether the organ has a historical trauma, under the condition of determining whether the organ has a historical trauma. The trauma identification module determines that the type of the organ trauma is the second type according to the existence of historical trauma to the organ; The trauma identification module determines that the type of the organ trauma is the third type based on the absence of historical trauma to the organ.

5. The organ injury automatic identification and control system according to claim 4, characterized in that: The control module determines to upload the organ trauma image to different databases according to the comparison result between the change value of the organ trauma degree and the preset change value, wherein: The control module determines to upload the organ trauma image to the first database according to a comparison result that the change value of the organ trauma degree within the preset time is less than the first preset change value; The control module determines to upload the organ trauma image to the second database according to a comparison result that the change value of the organ trauma degree within the preset time is greater than or equal to the first preset change value and less than the second preset change value; The control module determines to upload the organ trauma image to the third database according to the comparison result that the change value of the organ trauma within the preset time is greater than or equal to the second preset change value.

6. The organ injury automatic identification and control system according to claim 5, characterized in that: The preset change value of the organ trauma is determined according to a preset trauma degree.

7. The organ injury automatic identification and control system according to claim 6, characterized in that: The adjustment module determines the adjustment of the parameters of the automatic organ trauma identification control process according to the comparison result that the accuracy of the automatic organ trauma identification control result is less than the preset accuracy, wherein the parameters of the automatic organ trauma identification control process include a preset uniformity and a preset malignancy rate.

8. The organ injury automatic identification and control system according to claim 7, characterized in that: The adjustment amount of the preset uniformity is negatively correlated with the fluctuation degree of the error types of uploading organ trauma images to different databases during the automatic identification and control process of organ trauma within several preset cycles, and the adjustment amount of the preset malignancy rate is positively correlated with the fluctuation degree of the error types of uploading organ trauma images to different databases during the automatic identification and control process of organ trauma within several preset cycles.

9. The organ injury automatic identification and control system according to claim 8, characterized in that: The value of the preset fluctuation degree is the average value of the fluctuation degrees of the error types in uploading the organ trauma images to different databases during the organ trauma automatic recognition control process within a plurality of preset cycles.

Images