Liver perfusion regulation and control method and system based on image recognition

Abstract

The invention relates to the field of image processing, in particular to a liver perfusion regulation and control method and system based on image recognition, and the method comprises the steps: recognizing a thermal imaging image of an in-vitro liver during perfusion, obtaining temperature data, and calibrating an activity abnormal region of the in-vitro liver; identifying the change trend of an activity abnormal region of the hepatic artery and the portal vein, and estimating circulation degradation time nodes of the hepatic artery and the portal vein; according to the metabolic data associated with the cycle degradation time node, obtaining a metabolic difference so as to determine a target perfusion parameter; the perfusion operation of the hepatic artery and the portal vein is dynamically adjusted in combination with the real-time perfusion parameters and the target perfusion parameters. The in-vitro liver is subjected to thermal imaging recognition and hepatic artery and portal vein circulation metabolism detection, the metabolism difference between two cycles is determined, the metabolism balance of the two cycles is effectively considered, the preservation life of organs is prolonged, and organ tissue damage is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and particularly to a method and system for regulating liver perfusion based on image recognition. Background Art

[0002] Liver transplantation is an effective means for treating diseases such as liver failure or liver cancer. How to effectively preserve the excised liver until the operation period has a very important impact on the success rate of liver transplantation. Hypothermic preservation and machine perfusion are the two main means for preserving excised livers at present. Hypothermic preservation can extend the lifespan of liver organs to a certain extent by reducing tissue metabolism and oxygen demand. However, with the increasing demand for liver transplantation surgeries, simple hypothermic preservation can no longer meet the needs of preserving large organs. Machine perfusion refers to the use of a rotary pump, temperature control equipment, pressure control equipment, oxygenation equipment, etc. to perform perfusion fluid circulation perfusion on excised organs, and it has been widely used in the preservation of excised kidneys.

[0003] Considering that the liver mainly includes two related metabolic circulations, namely the hepatic artery circulation and the portal vein circulation, which are significantly different from the tissue metabolism of the kidney. During the process of machine perfusion of the excised liver, it is necessary to take into account the tissue metabolism and its differences of the hepatic artery circulation and the portal vein circulation. An abnormality in one circulation during perfusion will inevitably affect the other circulation, which may cause irreversible damage to the excised liver and is not conducive to the normal progress of the transplantation surgery. It can be seen that how to visually monitor and adjust the perfusion preservation of the excised liver in real time is of great significance for increasing the preservation lifespan of the excised liver and reducing organ tissue damage. Summary of the Invention

[0004] In order to synchronously monitor the hepatic artery circulation and the portal vein circulation of the excised liver, ensure that the two circulations maintain stable tissue metabolism, prevent the deterioration of one circulation from affecting the other circulation, achieve real-time and accurate adjustment of the perfusion of the excised liver, increase the preservation lifespan and reduce organ tissue damage, the present invention provides a method for regulating liver perfusion based on image recognition. The method includes the following steps: S1: Identify the thermal imaging image of the excised liver during perfusion to obtain temperature data; according to the temperature data, calibrate the active abnormal area of the excised liver; S2: Identify the change trend of the active abnormal area of the hepatic artery and the portal vein, and estimate the time node of circulation deterioration of the hepatic artery and the portal vein; S3: Determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the circulation deterioration time node; according to the metabolic difference, determine the target perfusion parameters; S4: Dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters.

[0005] Preferably, in S1, the thermal imaging image of the ex vivo liver during perfusion is identified to obtain temperature data; according to the temperature data, the active abnormal area of the ex vivo liver is calibrated, specifically: Identify the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion, determine whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in a stable physiological circulation state; wherein, the state data includes the pressure data of the hepatic artery and the portal vein respectively, and the perfusion fluid component data; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, and thereby calibrate the active abnormal area of the ex vivo liver.

[0006] Preferably, in S2, identify the change trend of the active abnormal area of the hepatic artery and the portal vein, and estimate the circulation deterioration time node of the hepatic artery and the portal vein, specifically: Identify the change trend of the range of the active abnormal area of the hepatic artery and the portal vein respectively, and determine the time series in which the key parts of the hepatic artery and the portal vein are covered by the active abnormal area; Based on the time series, estimate the circulation deterioration time node of the hepatic artery and the portal vein respectively; wherein, the circulation deterioration time node refers to the occurrence time point when the proportion of the number of key parts covered by the active abnormal area under the hepatic artery or the portal vein reaches a preset proportion threshold.

[0007] Preferably, in S3, according to the metabolic data associated with the circulation deterioration time node, determine the metabolic difference between the hepatic artery and the portal vein; according to the metabolic difference, determine the target perfusion parameters, specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively in the corresponding time period before the circulation deterioration time node; identify the blood component change data to determine the metabolic difference between the hepatic artery and the portal vein; wherein, the metabolic difference includes the consumption rate difference of nutrients in the perfusion fluid between the hepatic artery and the portal vein; According to the metabolic difference, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; wherein, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

[0008] Preferably, in S4, according to the real-time perfusion parameters and the target perfusion parameters, dynamically adjust the perfusion operations of the hepatic artery and the portal vein, specifically: Identify the difference value between the real-time perfusion parameters of the ex vivo liver and the target perfusion parameters, and determine the perfusion operation parameter change values for the hepatic artery and the portal vein respectively according to the difference value and the acceptable perfusion change limit values of the hepatic artery and the portal vein; Dynamically adjust the perfusion operation parameters of the hepatic artery and the portal vein according to the perfusion operation parameter change values.

[0009] On the other hand, the present invention provides a liver perfusion regulation system based on image recognition, and the system includes the following modules: A thermal imaging recognition module, configured to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; A calibration module, configured to calibrate the abnormal activity area of the ex vivo liver according to the temperature data; A deterioration estimation module, configured to identify the change trend of the abnormal activity areas of the hepatic artery and the portal vein, and estimate the cyclic deterioration time nodes of the hepatic artery and the portal vein; A difference determination module, configured to determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the cyclic deterioration time nodes; A target parameter determination module, configured to determine the target perfusion parameters according to the metabolic difference; A perfusion adjustment module, configured to dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters.

[0010] Preferably, the thermal imaging recognition module is configured to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; and calibrate the abnormal activity area of the ex vivo liver according to the temperature data, specifically: Recognize the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion, determine whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in the stable physiological circulation state; wherein, the state data includes the pressure data and the perfusion fluid composition data of the hepatic artery and the portal vein respectively; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, and thereby calibrate the abnormal activity area of the ex vivo liver.

[0011] Preferably, the deterioration estimation module is configured to identify the change trend of the abnormal activity areas of the hepatic artery and the portal vein, and estimate the cyclic deterioration time nodes of the hepatic artery and the portal vein, specifically: Identify the change trend of the range of the abnormal activity areas of the hepatic artery and the portal vein respectively, and determine the time series in which the key parts of the hepatic artery and the portal vein are covered by the abnormal activity areas; Based on the time series, estimate the respective circulation degradation time nodes of the hepatic artery and the portal vein; wherein, the circulation degradation time node refers to the occurrence time point when the proportion of the number of key parts covered by the abnormally active area under the hepatic artery or the portal vein reaches a preset proportion threshold.

[0012] Preferably, the difference determination module is used to determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the circulation degradation time node, specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively within the corresponding time interval before the circulation degradation time node; identify the blood component change data to determine the metabolic difference between the hepatic artery and the portal vein; wherein, the metabolic difference includes the consumption rate difference of nutrients in the perfusion fluid between the hepatic artery and the portal vein. The target parameter determination module is used to determine the target perfusion parameters according to the metabolic difference, specifically: According to the metabolic difference, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; wherein, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

[0013] Preferably, the perfusion adjustment module is used to dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters, specifically: Identify the difference value between the real-time perfusion parameters of the ex vivo liver and the target perfusion parameters, and determine the change value of the perfusion operation parameters of the hepatic artery and the portal vein respectively according to the difference value and the respective acceptable perfusion change limit values of the hepatic artery and the portal vein. Dynamically adjust the perfusion operation parameters of the hepatic artery and the portal vein according to the change value of the perfusion operation parameters.

[0014] Compared with the prior art, the present invention has the following beneficial effects: Identify the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; calibrate the abnormally active area of the ex vivo liver according to the temperature data. Through the overall thermal imaging recognition of the ex vivo liver, the temperature data of the global range of the ex vivo liver is obtained, and the temperature situation of the ex vivo liver during the current perfusion period is characterized in the whole range. Then, by comparing the temperatures, the abnormally active area of the ex vivo liver is calibrated, which is convenient for predicting the influence of the abnormally active area of the ex vivo liver on the hepatic artery and the portal vein.

[0015] Identify the changing trends of abnormal active regions of the hepatic artery and the portal vein, and estimate the time nodes of circulatory deterioration of the hepatic artery and the portal vein. Irreversible tissue damage related to hepatic artery circulation and portal vein circulation will occur in the ex vivo liver at the time nodes of circulatory deterioration of the hepatic artery and the portal vein respectively. To avoid the loss of activity of the ex vivo liver, it is necessary to adjust the perfusion operation before the time node of circulatory deterioration to restore the physiological activity of the ex vivo liver. By determining the time nodes of circulatory deterioration of the hepatic artery and the portal vein, measures can be taken in advance to restore the physiological activity of the ex vivo liver.

[0016] Determine the metabolic differences between the hepatic artery and the portal vein according to the metabolic data associated with the time nodes of circulatory deterioration; determine the target perfusion parameters according to the metabolic differences. By determining the target perfusion parameters, it is possible to provide an accurate target for adjusting the perfusion operation to ensure that the hepatic artery circulation and the portal vein circulation reach metabolic balance and maintain the stable physiological metabolism of the whole ex vivo liver.

[0017] Dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters. By dynamically adjusting the perfusion operations of the hepatic artery and the portal vein, a gradual perfusion adjustment of the hepatic artery circulation and the portal vein circulation can be achieved, ensuring that the hepatic artery circulation and the portal vein circulation are gradually changed to match the circulatory metabolic pattern, and avoiding the situation of rupture due to excessive impact on the hepatic artery or the portal vein. Brief Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. 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 be obtained based on these drawings. Among them: Figure 1 is a flowchart of the liver perfusion regulation method based on image recognition provided by the present invention.

[0019] Figure 2 is a graph of the pressure changes of the hepatic artery and the portal vein respectively.

[0020] Figure 3 is a graph of the changes in the perfusion fluid components of the hepatic artery and the portal vein respectively.

[0021] Figure 4 is a thermal imaging image of the ex vivo liver.

[0022] Figure 5 is a schematic diagram of the double-circulation perfusion of the hepatic artery and the portal vein of the ex vivo liver.

[0023] Figure 6 is a structural diagram of the liver perfusion regulation system based on image recognition provided by the present invention. Detailed Description of the Embodiments

[0024] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following will, with reference to the accompanying drawings, provide a detailed description of the specific embodiments of the present invention. It can be understood that the specific embodiments described herein are only for explaining the present invention and not for limiting the present invention. Additionally, it should be noted that for the convenience of description, only the parts related to the present invention rather than all the structures are shown in the drawings. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0025] The terms "comprise" and "have" and any variations thereof in the present invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0026] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0027] Please refer to Figure 1 As shown, the present invention provides a method for regulating liver perfusion based on image recognition, and the method includes the following steps: S1. Identify the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; based on the temperature data, calibrate the abnormally active region of the ex vivo liver.

[0028] Further, in S1, identifying the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; based on the temperature data, calibrating the abnormally active region of the ex vivo liver specifically includes: Identify the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion, determine whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in the stable physiological circulation state; wherein, the state data includes the pressure data of the hepatic artery and the portal vein respectively and the perfusion fluid component data; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, and thereby calibrate the abnormally active region of the ex vivo liver.

[0029] The ex vivo liver temperature is an important parameter characterizing the activity of the ex vivo liver. If during the perfusion of the ex vivo liver, it is not possible to ensure that all regions of the ex vivo liver, especially the marginal regions, obtain continuous and stable nutrient supply and metabolic circulation, the tissue activity in the corresponding regions will decrease, leading to abnormal temperature. In the initial stage of perfusion, since it takes a certain amount of time for the perfusion fluid to be delivered to the entire liver, the perfusion fluid fails to fully supply the entire liver tissue, resulting in the inability of all regions of the liver to truly reflect tissue activity. To avoid errors in thermal imaging recognition of the ex vivo liver, thermal imaging recognition should be performed when the ex vivo liver obtains a stable nutrient supply during perfusion and a continuous metabolic cycle is formed in the hepatic artery and portal vein of the ex vivo liver. For this purpose, pressure sensors pre-set in the hepatic artery and portal vein of the ex vivo liver are used to detect the respective pressures of the hepatic artery and portal vein. Please refer to Figure 2 , where Figure 2 in (a) is the curve of the hepatic artery pressure changing with perfusion time, and (b) is the curve of the portal vein pressure changing with perfusion time. In addition, during the period when the hepatic artery and portal vein of the ex vivo liver receive perfusion fluid supply, a cyclic metabolism will be formed, resulting in changes in the composition of the perfusion fluid as metabolites (such as aspartate aminotransferase AST) are excreted during the cyclic metabolism. When the cyclic metabolism of the hepatic artery and portal vein reaches a stable state, the amount of metabolite excretion also tends to be stable. For this purpose, sensors pre-set in the hepatic artery and portal vein of the ex vivo liver are used to detect the content of aspartate aminotransferase AST in the perfusion fluid corresponding to the hepatic artery circulation and portal vein circulation respectively. Please refer to Figure 3 , where Figure 3 in (a) is the curve of the content of aspartate aminotransferase AST in the perfusion fluid corresponding to the hepatic artery circulation changing with perfusion time, and (b) is the curve of the content of aspartate aminotransferase AST in the perfusion fluid corresponding to the portal vein circulation changing with perfusion time.

[0030] By detecting the respective pressure-time change data of the hepatic artery and portal vein during the perfusion of the ex vivo liver and the AST content-time change data in the perfusion fluid of the hepatic artery circulation and portal vein circulation respectively, and then modeling and analyzing the circulation status of the hepatic artery and portal vein based on the above two change data, it is judged whether the ex vivo liver is in a stable physiological circulation state. Among them, the above circulation status modeling analysis can be realized by an existing neural network model, which will not be introduced in detail here.

[0031] When the ex vivo liver is not in a stable physiological circulation state, it indicates that the perfusion fluid fails to fully supply the entire liver tissue. At this time, it is necessary to continue to wait until the perfusion operation reaches a certain degree before performing thermal imaging; when the ex vivo liver is in a stable physiological circulation state, thermal imaging recognition can be directly performed on the ex vivo liver. Please refer to Figure 4, perform thermal infrared imaging on an isolated liver in a stable physiological circulation state to obtain a thermal imaging image. Identify and analyze the above thermal imaging image, extract the temperature data of the entire global range of the isolated liver, and comprehensively characterize the temperature condition of the isolated liver during the current perfusion period. Then, compare the extracted temperature data with the preset reference temperature data to obtain the temperature difference between the actual temperature value and the preset reference temperature value for each part area of the isolated liver, thereby generating the spatial distribution of the temperature difference of the entire isolated liver; among them, the preset reference temperature data can be obtained by empirically processing the historical multiple perfusion monitoring data of the isolated liver. Also, compare the temperature difference of each part area with the reference temperature difference range. If the temperature difference is within the above reference temperature difference range, the above part area is not designated as an area with abnormal activity of the isolated liver; otherwise, the above part area is designated as an area with abnormal activity of the isolated liver, which is convenient for predicting the impact of the area with abnormal activity of the isolated liver on the hepatic artery and the portal vein in the subsequent process.

[0032] S2. Identify the changing trend of the areas with abnormal activity of the hepatic artery and the portal vein, and estimate the time nodes of circulatory deterioration of the hepatic artery and the portal vein.

[0033] Further, in S2, identifying the changing trend of the areas with abnormal activity of the hepatic artery and the portal vein and estimating the time nodes of circulatory deterioration of the hepatic artery and the portal vein specifically includes: Identify the changing trend of the range of the areas with abnormal activity of the hepatic artery and the portal vein respectively, and determine the time series when the key parts of the hepatic artery and the portal vein are covered by the areas with abnormal activity; Based on the time series, estimate the time nodes of circulatory deterioration of the hepatic artery and the portal vein respectively; among them, the time node of circulatory deterioration refers to the occurrence time point when the proportion of the number of key parts covered by the areas with abnormal activity under the hepatic artery or the portal vein reaches the preset proportion threshold.

[0034] Considering the physiological tissue characteristics of the ex vivo liver, when there are regions with abnormal activity in the ex vivo liver and no repair measures are taken in a timely manner, the liver tissue adjacent to the regions with abnormal activity will also be affected, resulting in a continuous increase in the scope of the regions with abnormal activity. When the scope of the regions with abnormal activity covers key parts such as the bifurcation nodes of the hepatic artery and the portal vein respectively, it will hinder the normal blood circulation of the ex vivo liver and may lead to irreversible damage to the liver tissue. Through the above analysis, it can be seen that the change trend of the scope of the regions with abnormal activity in the hepatic artery and the portal vein directly affects the physiological circulation quality of the hepatic artery and the portal vein. In order to accurately predict the time evolution trend of the circulatory deterioration of the hepatic artery and the portal vein under the influence of the regions with abnormal activity, first identify the change trend of the scope of the regions with abnormal activity in the hepatic artery and the portal vein respectively, and determine the time series of the coverage of the key parts of the hepatic artery and the portal vein by the regions with abnormal activity. The above time series refers to the time series formed by the time points when all the key parts under the hepatic artery or the portal vein are covered by the regions with abnormal activity. Then, extract from the above time series the time points when the proportion of the number of key parts covered by the regions with abnormal activity under the hepatic artery or the portal vein reaches a preset proportion threshold, and obtain the circulatory deterioration time nodes of the hepatic artery and the portal vein respectively. It can be understood that irreversible tissue damage related to the hepatic artery circulation and the portal vein circulation will occur in the ex vivo liver at the circulatory deterioration time nodes of the hepatic artery and the portal vein respectively. In order to prevent the ex vivo liver from losing its activity, it is necessary to adjust the perfusion operation before reaching the circulatory deterioration time node to restore the physiological activity of the ex vivo liver.

[0035] S3. According to the metabolic data associated with the circulatory deterioration time node, determine the metabolic differences between the hepatic artery and the portal vein; according to the metabolic differences, determine the target perfusion parameters Furthermore, in S3, according to the metabolic data associated with the circulatory deterioration time node, determine the metabolic differences between the hepatic artery and the portal vein; according to the metabolic differences, determine the target perfusion parameters, specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively in the corresponding time interval before the circulatory deterioration time node; identify the blood component change data and determine the metabolic differences between the hepatic artery and the portal vein; among them, the metabolic differences include the consumption rate differences of nutrients in the perfusion fluid between the hepatic artery and the portal vein. According to the metabolic differences, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; among them, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

[0036] In order to timely adjust the perfusion operation before the above-mentioned cyclic deterioration time node, improve the hepatic artery circulation and portal vein circulation of the ex vivo liver to restore the overall physiological activity of the ex vivo liver, it is necessary to detect the circulating blood components of the hepatic artery circulation and the portal vein circulation respectively. Specifically, sensors pre-set in the hepatic artery circulation and the portal vein circulation can be used to detect blood component change data such as the blood oxygen concentration and blood glucose concentration corresponding to the above two circulations. Then, according to the above blood component change data, metabolic models of the hepatic artery circulation and the portal vein circulation are constructed respectively, so as to determine the consumption rate difference of nutrients in the perfusion fluid between the hepatic artery and the portal vein.

[0037] The overall physiological metabolism of the ex vivo liver is maintained by the hepatic artery circulation and the portal vein circulation. The respective circulating metabolic states of the hepatic artery circulation and the portal vein circulation directly affect the overall physiological metabolism of the ex vivo liver. In order to ensure that the ex vivo liver maintains a stable and continuous physiological metabolism, according to the above metabolic differences, the target perfusion flow rate (i.e., the target perfusion fluid transmission flow rate) and the target perfusion temperature (i.e., the target perfusion fluid temperature) required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance are determined. When the hepatic artery circulation and the portal vein circulation are perfused at the above-mentioned target perfusion flow rate and the above-mentioned target perfusion temperature, it can ensure that the hepatic artery circulation and the portal vein circulation reach metabolic balance, thereby maintaining the stable physiological metabolism of the overall ex vivo liver.

[0038] S4. Dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters.

[0039] Furthermore, in S4, dynamically adjusting the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters specifically includes: Identifying the difference value between the real-time perfusion parameters and the target perfusion parameters of the ex vivo liver, and determining the change values of the perfusion operation parameters for the hepatic artery and the portal vein respectively according to the difference value and the respective acceptable perfusion change limit values of the hepatic artery and the portal vein; Dynamically adjusting the perfusion operation parameters of the hepatic artery and the portal vein according to the change values of the perfusion operation parameters.

[0040] Please refer to Figure 5 , and two perfusion operation circuits are respectively set for the hepatic artery circulation and the portal vein circulation, so as to independently adjust and control the flowing states of the perfusion fluids of the hepatic artery circulation and the portal vein circulation respectively. Among them Figure 5 in both the hepatic artery circulation and the portal vein circulation, a centrifugal pump is used to drive the perfusion fluid to flow in the circulation circuit, where a flow sensor and a pressure sensor respectively detect the flow rate of the perfusion fluid in the circulation circuit and the pressure of the hepatic artery / portal vein, an oxygenator realizes oxygen-carbon dioxide exchange, and a thrombus filter is used to filter thrombus.

[0041] If the perfusion operation parameters are directly adjusted to the target values in one step during the adjustment of the perfusion operation, it is easy to cause the hepatic artery or portal vein to be impacted too greatly and rupture, resulting in damage to the ex vivo liver tissue. To ensure the safety of the hepatic artery and portal vein tissue structures while gradually improving the physiological circulation performance, first identify the difference values between the real-time perfusion parameters and the target perfusion parameters of the ex vivo liver (such as the perfusion flow difference and the perfusion temperature difference), and combine the acceptable perfusion change limit values of the hepatic artery and portal vein respectively (such as the maximum flow change value and the maximum temperature change value acceptable during each adjustment process), so as to determine the perfusion operation parameter change values of the hepatic artery and portal vein respectively (that is, the actual flow change value and the actual temperature change value during each perfusion operation adjustment process), thereby dynamically adjusting the perfusion flow and perfusion temperature of the hepatic artery and portal vein multiple times, realizing a gradual perfusion adjustment of the hepatic artery circulation and the portal vein circulation, and ensuring that the hepatic artery circulation and the portal vein circulation gradually change to match the circulatory metabolism mode.

[0042] Please refer to Figure 6 As shown, the present invention provides a liver perfusion regulation system based on image recognition, and this system includes the following modules: A thermal imaging recognition module, which is used to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; A calibration module, which is used to calibrate the active abnormal area of the ex vivo liver according to the temperature data; A deterioration estimation module, which is used to recognize the change trend of the active abnormal areas of the hepatic artery and portal vein, and estimate the cyclic deterioration time nodes of the hepatic artery and portal vein; A difference determination module, which is used to determine the metabolic difference between the hepatic artery and portal vein according to the metabolic data associated with the cyclic deterioration time nodes; A target parameter determination module, which is used to determine the target perfusion parameters according to the metabolic difference; A perfusion adjustment module, which is used to dynamically adjust the perfusion operation of the hepatic artery and portal vein according to the real-time perfusion parameters and the target perfusion parameters.

[0043] Furthermore, the thermal imaging recognition module is used to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; and calibrate the active abnormal area of the ex vivo liver according to the temperature data. Specifically: Recognize the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion respectively, judge whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in the stable physiological circulation state; wherein, the state data includes the pressure data of the hepatic artery and portal vein respectively and the perfusion fluid component data; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, so as to calibrate the active abnormal area of the ex vivo liver.

[0044] Further, the degradation estimation module is used to identify the change trend of the active abnormal regions of the hepatic artery and the portal vein, and estimate the circulation degradation time nodes of the hepatic artery and the portal vein. Specifically: Identify the change trend of the range of the active abnormal regions of the hepatic artery and the portal vein respectively, and determine the time series when the key parts of the hepatic artery and the portal vein are covered by the active abnormal regions; Based on the time series, estimate the circulation degradation time nodes of the hepatic artery and the portal vein respectively; wherein, the circulation degradation time node refers to the occurrence time point when the proportion of the number of key parts covered by the active abnormal regions under the hepatic artery or the portal vein reaches a preset proportion threshold.

[0045] Further, the difference determination module is used to determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the circulation degradation time node. Specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively within the corresponding time interval before the circulation degradation time node; identify the blood component change data to determine the metabolic difference between the hepatic artery and the portal vein; wherein, the metabolic difference includes the difference in the consumption rate of nutrients in the perfusion fluid between the hepatic artery and the portal vein; The target parameter determination module is used to determine the target perfusion parameters according to the metabolic difference. Specifically: According to the metabolic difference, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; wherein, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

[0046] Further, the perfusion adjustment module is used to dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters. Specifically: Identify the difference value between the real-time perfusion parameters of the ex vivo liver and the target perfusion parameters, and determine the change values of the perfusion operation parameters for the hepatic artery and the portal vein respectively according to the difference value and the acceptable perfusion change limit values of the hepatic artery and the portal vein; According to the change values of the perfusion operation parameters, dynamically adjust the perfusion operation parameters of the hepatic artery and the portal vein.

[0047] The liver perfusion regulation system based on image recognition of the present invention corresponds to the operation and effect of the above-mentioned liver perfusion regulation method based on image recognition, and the description of the liver perfusion regulation system based on image recognition will not be repeated here.

[0048] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of adding a necessary general hardware platform. Of course, it can also be implemented by a combination of hardware and software. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a computer product. The present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program codes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Other embodiments can also be adopted; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A liver perfusion regulation method based on image recognition, characterized in that The method includes the following steps: S1: Identify the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; based on the temperature data, calibrate the active abnormal area of the ex vivo liver; S2: Identify the change trend of the active abnormal area of the hepatic artery and the portal vein, and estimate the circulation deterioration time nodes of the hepatic artery and the portal vein; S3: Determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the circulation deterioration time nodes; determine the target perfusion parameters according to the metabolic difference; S4: Dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters.

2. The method according to claim 1, wherein in S1, identifying the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; based on the temperature data, calibrating the active abnormal area of the ex vivo liver is specifically: Identify the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion, determine whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in the stable physiological circulation state; wherein, the state data includes the pressure data of the hepatic artery and the portal vein respectively, and the perfusion fluid composition data; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, and thereby calibrate the active abnormal area of the ex vivo liver.

3. The method according to claim 1, wherein in S2, identifying the change trend of the active abnormal area of the hepatic artery and the portal vein, and estimating the circulation deterioration time nodes of the hepatic artery and the portal vein is specifically: Identify the change trend of the range of the active abnormal area of the hepatic artery and the portal vein respectively, and determine the time series of the key parts of the hepatic artery and the portal vein covered by the active abnormal area; Based on the time series, estimate the circulation deterioration time nodes of the hepatic artery and the portal vein respectively; wherein, the circulation deterioration time node refers to the occurrence time point when the proportion of the number of key parts of the hepatic artery or the portal vein covered by the active abnormal area reaches a preset proportion threshold.

4. The method according to claim 1, wherein in S3, determining the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the circulation deterioration time nodes; determining the target perfusion parameters according to the metabolic difference is specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively in the corresponding time interval before the circulation deterioration time node; identify the blood component change data to determine the metabolic difference between the hepatic artery and the portal vein; wherein, the metabolic difference includes the consumption rate difference of nutrients in the perfusion fluid between the hepatic artery and the portal vein; According to the metabolic difference, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; wherein, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

5. The method according to claim 1, wherein: In S4, according to the real-time perfusion parameters and the target perfusion parameters, the perfusion operations of the hepatic artery and the portal vein are dynamically adjusted, specifically: Identify the difference value between the real-time perfusion parameters of the ex vivo liver and the target perfusion parameters, and determine the change values of the perfusion operation parameters for the hepatic artery and the portal vein respectively according to the difference value and the acceptable perfusion change limit values of the hepatic artery and the portal vein; Dynamically adjust the perfusion operation parameters of the hepatic artery and the portal vein according to the change values of the perfusion operation parameters.

6. A liver perfusion regulation system based on image recognition, characterized in that, The system includes the following modules: A thermal imaging recognition module, configured to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; A calibration module, configured to calibrate the active abnormal area of the ex vivo liver according to the temperature data; A deterioration estimation module, configured to recognize the change trend of the active abnormal areas of the hepatic artery and the portal vein, and estimate the cyclic deterioration time nodes of the hepatic artery and the portal vein; A difference determination module, configured to determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the cyclic deterioration time nodes; A target parameter determination module, configured to determine the target perfusion parameters according to the metabolic difference; A perfusion adjustment module, configured to dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters.

7. The system according to claim 6, wherein: The thermal imaging recognition module is configured to recognize the thermal imaging image of the ex vivo liver during perfusion to obtain temperature data; and calibrate the active abnormal area of the ex vivo liver according to the temperature data, specifically: Recognize the state data of the hepatic artery circulation and the portal vein circulation of the ex vivo liver during perfusion, determine whether the ex vivo liver is in a stable physiological circulation state, and collect the thermal imaging image of the ex vivo liver in the stable physiological circulation state; wherein, the state data includes the pressure data and the perfusion fluid composition data of the hepatic artery and the portal vein respectively; Compare the temperature data extracted from the thermal imaging image with the preset reference temperature data to obtain the temperature difference spatial distribution of the ex vivo liver, and thereby calibrate the active abnormal area of the ex vivo liver.

8. The system according to claim 6, wherein: The deterioration estimation module is configured to recognize the change trend of the active abnormal areas of the hepatic artery and the portal vein, and estimate the cyclic deterioration time nodes of the hepatic artery and the portal vein, specifically: Recognize the change trend of the range of the active abnormal areas of the hepatic artery and the portal vein respectively, and determine the time series of the key parts of the hepatic artery and the portal vein covered by the active abnormal areas; Based on the time series, estimate the cyclic deterioration time nodes of the hepatic artery and the portal vein respectively; wherein, the cyclic deterioration time node refers to the occurrence time point when the proportion of the number of key parts of the hepatic artery or the portal vein covered by the active abnormal area reaches a preset proportion threshold.

9. The system according to claim 6, wherein: The difference determination module is configured to determine the metabolic difference between the hepatic artery and the portal vein according to the metabolic data associated with the cyclic degradation time node, specifically: Obtain the blood component change data of the hepatic artery and the portal vein respectively within the corresponding time interval before the cyclic degradation time node; identify the blood component change data to determine the metabolic difference between the hepatic artery and the portal vein; wherein, the metabolic difference includes the difference in the consumption rate of nutrients in the perfusion fluid between the hepatic artery and the portal vein. The target parameter determination module is configured to determine the target perfusion parameter according to the metabolic difference, specifically: According to the metabolic difference, determine the target perfusion parameters required for the hepatic artery circulation and the portal vein circulation of the ex vivo liver to reach metabolic balance respectively; wherein, the target perfusion parameters include the target perfusion flow rate and the target perfusion temperature.

10. The system according to claim 6, wherein The perfusion adjustment module is configured to dynamically adjust the perfusion operations of the hepatic artery and the portal vein according to the real-time perfusion parameters and the target perfusion parameters, specifically: Identify the difference value between the real-time perfusion parameters of the ex vivo liver and the target perfusion parameters, and determine the change values of the perfusion operation parameters for the hepatic artery and the portal vein respectively according to the difference value and the acceptable perfusion change limit values of the hepatic artery and the portal vein respectively; Dynamically adjust the perfusion operation parameters of the hepatic artery and the portal vein according to the change values of the perfusion operation parameters.

Images