Medical information processing apparatus, medical information processing method, and program

Abstract

To minutely and accurately evaluate a risk of a lung injury.SOLUTION: A medical operation device of an embodiment comprises an image acquisition part, an inner pressure acquisition part, a generation part, an estimation part, and a display control part. The image acquisition part acquires a CT image of the chest of an analyte. The inner pressure acquisition part acquires an esophageal pressure and an airway pressure of the analyte. The generation part generates a risk information map in the lung field of the analyte based on the CT image, the esophageal pressure and the airway pressure. The estimation part estimates risk information at the lung field of the analyte based on the risk information map. The display control part causes the risk information map and the risk information to be displayed on a display part.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing device, a medical information processing method, and a program. [Background technology]

[0002] In the artificial respiratory management of patients with acute respiratory distress syndrome (ARDS), a lung-protective ventilation strategy based on limiting tidal volume is recommended to prevent ventilator-associated lung injury due to alveolar hyperstretching. Transpulmonary pressure, a determining factor of ventilator-associated lung injury, is measured by transpulmonary pressure measurement using an esophageal balloon or other device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-178936 A Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional lung protective ventilation strategies, uniform artificial ventilation management is performed with the same tidal volume (6ml / kg) for all patients. As a result, the mortality rate of patients remains extremely high. For this reason, a method is required to establish an individualized lung protective ventilation strategy for each patient according to the degree of risk of ventilator-associated lung injury. In order to establish an individualized lung protective ventilation strategy, it is necessary to accurately grasp the transpulmonary pressure, which is a determining factor of ventilator-associated lung injury that differs from patient to patient. However, conventional transpulmonary pressure measurement methods using esophageal balloons, etc., are a measurement method that reflects the transpulmonary pressure in a specific local lung region, and cannot grasp the accurate transpulmonary pressure in the entire lung. As a result, it was not possible to appropriately evaluate the risk of ventilator-associated lung injury.

[0005] The problem to be solved by the embodiments disclosed in this specification and the drawings is to enable detailed and accurate evaluation of the risk of lung injury. However, the problem to be solved by the embodiments disclosed in this specification and the drawings is not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0006] The medical operation device of the embodiment has an image acquisition unit, an internal pressure acquisition unit, a generation unit, an estimation unit, and a display control unit. The image acquisition unit acquires a CT image of a subject's chest. The internal pressure acquisition unit acquires the subject's esophageal pressure and airway pressure. The generation unit generates a risk information map of the subject's lung field based on the CT image, the esophageal pressure, and the airway pressure. The estimation unit estimates risk information of the subject's lung field based on the risk information map. The display control unit causes the risk information map and risk information to be displayed on the display unit. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a functional block diagram showing an example of a medical information processing apparatus 100 according to an embodiment. [Diagram 2] 4 is a flowchart showing an example of processing by the medical information processing apparatus 100 according to the embodiment. [Diagram 3] 4A to 4C are views for explaining how a lung region and an esophageal pressure measurement position are determined in a CT image IMG1 according to the embodiment. [Figure 4] 13A to 13C are diagrams for explaining calculation of transpulmonary pressure for each unit region in a CT image IMG1 according to the embodiment. [Diagram 5] FIG. 4 is a diagram showing an example of a transpulmonary pressure map according to the embodiment. [Figure 6] FIG. 13 is a diagram showing another example of a transpulmonary pressure map according to the embodiment. [Figure 7A] 4A to 4C are diagrams illustrating an example of input and output of a risk estimation model M according to the embodiment. [Figure 7B] 11A to 11C are diagrams for explaining another example of input and output of the risk estimation model M according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, a medical information processing device, a medical information processing method, and a program according to an embodiment will be described with reference to the drawings. The medical information processing device according to the embodiment generates a risk information map showing a lung injury risk in a lung field of a patient based on a CT image, an esophageal pressure, and an airway pressure of a subject (patient), estimates the risk information in the lung field of the patient, and displays the risk information map and the risk information on a display unit, thereby enabling a detailed and accurate evaluation of the risk of lung injury.

[0009] <Configuration of medical information processing device 100> FIG. 1 is a functional block diagram showing an example of a medical information processing device 100 according to an embodiment. The medical information processing device 100 is operated by a user, such as a doctor or technician who examines and treats a patient. The medical information processing device 100 is, for example, a computer device (terminal device such as a personal computer or tablet) used in a CT examination room, an operating room, a hospital room, etc. The medical information processing device 100 is communicably connected to external devices (medical devices, modalities, etc.) such as an X-ray CT device D1, an artificial ventilator D2, and an esophageal pressure measuring device D3 via a communication network NW. The medical information processing device 100 may be a server device and may be connected to terminal devices used by doctors via a network.

[0010] The medical information processing device 100 includes, for example, a communication interface 110, an input interface 120, a display 130, a processing circuit 140, and a memory 150. The communication interface 110 communicates with an external device via a communication network NW. The communication network NW may mean a general information communication network using electric communication technology. For example, the communication network NW includes a wireless / wired LAN such as a hospital backbone LAN (Local Area Network) and the Internet network, as well as a telephone communication line network, an optical fiber communication network, a cable communication network, and a satellite communication network. The communication interface 110 includes, for example, a NIC (Network Interface Card) and an antenna for wireless communication.

[0011] The input interface 120 accepts various input operations from a user (operator), converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing circuit 140. For example, the input interface 120 includes a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch panel, and the like. The input interface 120 may be, for example, a user interface that accepts audio input from a microphone or the like. When the input interface 120 is a touch panel, the input interface 120 may also have the display function of the display 130.

[0012] In this specification, the input interface 120 is not limited to an interface having physical operation parts such as a mouse, a keyboard, etc. For example, an example of the input interface 120 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to a control circuit.

[0013] The display 130 provides various information to the user. For example, the display 130 displays a CT image and various measurement values ​​acquired from an external device, a risk information map generated by the processing circuit 140, a GUI (Graphical User Interface) image for receiving various input operations by the user, and the like. The display 130 is, for example, a liquid crystal display. The display 130 may be provided separately from the medical information processing device 100. The display 130 is an example of a "display unit".

[0014] The processing circuitry 140 controls the overall operation of the medical information processing device 100. The processing circuitry 140 has, for example, an acquisition function 141, a determination function 142, a calculation function 143, a generation function 144, an estimation function 145, and a display control function 146. The processing circuitry 140 realizes these functions by, for example, a hardware processor executing a program stored in a storage device (storage circuit).

[0015] The hardware processor refers to a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD) or a complex programmable logic device (CPLD), or a field programmable gate array (FPGA). Instead of storing a program in a storage device, the program may be directly built into the circuit of the hardware processor. In this case, the hardware processor realizes a function by reading and executing the program built into the circuit. The hardware processor is not limited to being configured as a single circuit, and may be configured as one hardware processor by combining multiple independent circuits to realize each function. The storage device may be a non-transitory (hardware) storage medium. Furthermore, multiple components may be integrated into one hardware processor to realize each function.

[0016] The acquisition function 141 acquires various types of medical information from external devices via the communication network NW. The acquisition function 141 has, for example, an image acquisition function 141-1 and an internal pressure acquisition function 141-2.

[0017] The image acquisition function 141-1 acquires a CT image of the chest of the patient P from the X-ray CT device D1. This CT image includes, for example, a plurality of cross-sectional images of the patient P sliced ​​in the XY plane (A-A' cross section in FIG. 1) in a range of the chest (for example, more than two-thirds of the lower thoracic esophagus) in the body axis direction (Z direction) of the patient P placed on the bed device BD of the X-ray CT device D1. The body axis direction of the patient P is defined as the Z axis direction (longitudinal direction of the top board of the bed device BD), the axis perpendicular to the Z axis direction and horizontal to the floor surface is defined as the X axis direction, and the direction perpendicular to the Z axis direction and perpendicular to the floor surface is defined as the Y axis direction. The image acquisition function 141-1 may acquire a CT image from a database in which captured CT images are stored (e.g., a Picture Archiving and Communication System (PACS)). The image acquisition function 141-1 may acquire one CT image of the patient P from the X-ray CT device D1. The image acquisition function 141-1 is an example of an "image acquisition unit."

[0018] The internal pressure acquisition function 141-2 acquires information indicating the airway pressure and esophageal pressure of the patient P. The information on the airway pressure is acquired, for example, from an artificial ventilator D2 connected to the lungs of the patient P via the mouth, throat, etc. The information on the esophageal pressure is acquired, for example, from an esophageal pressure measurement device D3. For example, an esophageal pressure tube or an esophageal pressure balloon kit for measuring esophageal pressure is used as the esophageal pressure measurement device D3. For example, before or after CT imaging, an esophageal pressure balloon kit is placed in the esophagus of the patient P via the mouth, etc. of the patient P. Thereafter, the esophageal balloon placed in the esophagus of the patient P is filled with an appropriate amount of air, and the presence of a cardiac waveform and the appropriate placement position of the esophageal balloon are confirmed by the Baydur occlusion method, etc., and then the esophageal pressure is measured. The esophageal pressure measured in this way is used as a substitute for the pleural pressure. The internal pressure acquisition function 141-2 is an example of an "internal pressure acquisition unit".

[0019] The determination function 142 performs image analysis on the acquired CT image to determine the characteristics of the chest on the CT image. For example, any method such as segmentation using machine learning technology can be used as the image analysis. The determination function 142 has, for example, a lung region determination function 142-1 and an esophageal pressure measurement position determination function 142-2. The lung region determination function 142-1 determines the lung region indicating the region in which the lungs are imaged in the CT image. The esophageal pressure measurement position determination function 142-2 determines the esophageal pressure measurement position indicating the position where the esophageal balloon is placed in the esophagus and the esophageal pressure is measured in the CT image. The determination function 142 may determine or correct the lung region and the esophageal pressure measurement position based on information manually input by the user via the input interface 120. In particular, patients with ARDS often have bilateral infiltrative shadows in the dorsal region. Depending on the method for automatically determining the lung region, the infiltrative shadow may not be correctly recognized as being within the lung region. Therefore, the user can manually correct the information via the input interface 120.

[0020] The calculation function 143 calculates the transpulmonary pressure for each unit area included in the area determined to be a lung area in the CT image. The calculation function 143 calculates the transpulmonary pressure for each unit area based on the relative positional relationship of the unit area of ​​the transpulmonary pressure calculation target with respect to the esophageal pressure measurement position, the CT value of the unit area in the CT image, and the actual measurement values ​​of the airway pressure and the esophageal pressure. The unit area may correspond to each pixel of the CT image, or may be composed of a plurality of pixels. The processing of the calculation function 143 will be described in detail later. The calculation function 143 is an example of a "calculation unit." The calculation function 143 calculates the ratio of unit areas having a transpulmonary pressure equal to or higher than a threshold based on the transpulmonary pressure for each unit area.

[0021] The generating function 144 generates a risk information map (Lang stress map) indicating the transpulmonary pressure for each unit area based on the calculated transpulmonary pressure value for each unit area. The risk information map divides the lung area of ​​the patient P into small areas (unit areas) and visualizes the amount, location, and pattern of risk areas of lung injury based on the transpulmonary pressure value. The processing of the generating function 144 will be described in detail later. The generating function 144 is an example of a "generating section." That is, the generating function 144 generates a risk information map of the lung field of the subject based on the CT image, the esophageal pressure, and the airway pressure.

[0022] The estimation function 145 estimates risk information in the lung region of the patient P based on the risk information map. The risk information includes, for example, information indicating a high-risk region where the risk of lung injury is particularly high. The estimation function 145 estimates the risk information using, for example, a machine learning function by AI (Artificial Intelligence). The estimation function 145 may be realized by, for example, a deep neural network. Alternatively, the estimation function 145 may be implemented using other machine learning models such as a support vector machine, a decision tree, a random forest, and a logistics regression instead of a neural network. The details of the processing of the estimation function 145 will be described later. The estimation function 145 is an example of an "estimation unit." The estimation function 145 estimates the risk information using a risk estimation model that has been trained to output information indicating risk information when information based on the risk information map or a combination of information based on the risk information map and information on the subject is input.

[0023] The display control function 146 causes the display 130 to display, for example, a CT image and various measurement values ​​acquired from an external device, a risk information map generated by the processing circuit 140, risk information, and a GUI image for accepting various input operations by a user. The display control function 146 is an example of a "display control unit." The display control function 146 causes the display unit to display the risk information map superimposed on the CT image. The display control function 146 causes the display unit to display the ratio of unit areas having a transpulmonary pressure equal to or greater than a threshold value.

[0024] The memory 150 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, or the like. The memory 150 stores, for example, a risk estimation model M used in the estimation process in the estimation function 145. In addition, the memory 150 stores CT images and various measurement values ​​acquired from an external device, a risk information map generated by the processing circuit 140, and the like. These data may be stored in an external memory with which the medical information processing device 100 can communicate, instead of the memory 150 (or in addition to the memory 150). The external memory is controlled by a cloud server that manages the external memory, for example, by the cloud server accepting a read / write request.

[0025] <Processing flow> Next, a flow of processing by the medical information processing device 100 will be described. Fig. 2 is a flowchart showing an example of processing by the medical information processing device 100 according to the embodiment. In the following, it is assumed that processing is started in a state where a patient P is placed on the bed device BD of the X-ray CT device D1. The processing of the flowchart shown in Fig. 2 is started, for example, when a user issues an instruction to start a risk assessment process via the input interface 120.

[0026] First, the image acquisition function 141-1 acquires a CT image of the patient P from the X-ray CT device D1 (step S101). This CT image includes, for example, a plurality of cross-sectional images of the patient P sliced ​​in the XY plane in the range of the chest in the body axis direction (Z direction) of the patient P placed on the bed device BD.

[0027] Next, the internal pressure acquisition function 141-2 acquires information indicating the airway pressure and esophageal pressure of the patient P (step S103). The airway pressure information is acquired from the artificial ventilator D2. The esophageal pressure information is acquired, for example, from an esophageal pressure measuring device D3 using an esophageal balloon. Note that, regarding the inspiratory pressure and positive end-expiratory pressure (PEEP), the airway pressure measured with the same ventilator settings as during CT imaging may be acquired.

[0028] Next, the determination function 142 identifies one CT image at a slice position to be processed from among the acquired CT images (step S105). Then, the lung region determination function 142-1 performs image analysis on the extracted CT image to determine the lung region (step S107). Furthermore, the esophageal pressure measurement position determination function 142-2 performs image analysis on the extracted CT image to determine the esophageal pressure measurement position (step S109).

[0029] Fig. 3 is a diagram for explaining how lung regions and esophageal pressure measurement positions are determined in a CT image IMG1 according to the embodiment. In the example of Fig. 3, a lung region AR1 corresponding to the right lung and a lung region AR2 corresponding to the left lung are determined as the lung regions, and an esophageal pressure measurement position ES indicating the position of the esophagus is determined as the esophageal pressure measurement position. When the slice position of the extracted CT image corresponds to the placement position of the esophageal balloon, the esophageal balloon is located at the esophageal pressure measurement position ES.

[0030] 2, next, the calculation function 143 calculates the transpulmonary pressure (also called "local transpulmonary pressure") for each unit region in the region determined to be a lung region in the extracted CT image (step S111). The calculation function 143 calculates the transpulmonary pressure for each unit region based on the relative position of the unit region with respect to the esophageal pressure measurement position ES, the CT value of the unit region, and the actual measurement values ​​of the airway pressure and esophageal pressure.

[0031] FIG. 4 is a diagram for explaining how the transpulmonary pressure is calculated for each unit region in a CT image IMG1 according to an embodiment. As shown in FIG. 4, small regions (unit regions PG) having a predetermined area are set on lung regions AR1 and AR2. The unit region PG may correspond to one pixel of the CT image, or may be composed of multiple pixels. Here, for example, the position in the Y-axis direction of the esophageal pressure measurement position ES is set as the height reference position Pb (height 0), and a case will be described in which the transpulmonary pressure (local transpulmonary pressure) is calculated for unit region PG1 corresponding to a position h [cm] higher in the Y-axis direction than height reference position Pb. The average CT value of the part corresponding to height h for unit region PG1 is H Avg The airway pressure acquired in step S103 is P Airway [cmH2O], and the esophageal pressure obtained in step S103 is P Esophagus [cmH2O], the local transpulmonary pressure P Transpulmonary [cmH2O] is calculated using the following formula (1).

[0032] P Transpulmonary =P Airway -[P Esophagus -h*{1-(H Avg / -1000)}]...Equation (1)

[0033] The average CT value H of the part corresponding to the height h Avg is obtained by setting a rectangular region of interest (ROI) vertically downward from the unit region PG1, which is the calculation point of the local transpulmonary pressure, to the height reference position Pb, which is the height of the measurement position of the esophageal pressure, and averaging the CT values ​​of all pixels present in the region of interest (ROI). Since the CT value is also a value that indicates the density of the target region, the CT value information can be used to calculate the transpulmonary pressure. The width of the region of interest (ROI) can be one pixel, or it can have a width of multiple pixels centered on the unit region PG1. This makes it possible to reduce noise caused by local deviations (errors) in the CT value.

[0034] When the calculation point of the local transpulmonary pressure is near the edge of the lung, such as unit areas PG2 and PG3, the region of interest ROI for calculating the average CT value may include pixels outside the lung region. In this case, the average CT value H Avg You may ask for the following.

[0035] When the calculation point of the local transpulmonary pressure is lower than the reference height position Pb, which is the measurement position of the esophageal pressure, as in the unit area PG4, the value of h in the above formula (1) is calculated as a negative value.

[0036] By repeating the calculation of the local transpulmonary pressure with each unit region PG (each pixel or pixel group) in the lung region as a calculation point of the local transpulmonary pressure, the transpulmonary pressure value can be calculated over the entire lung region.

[0037] 2, the processing circuitry 140 determines whether the calculation process of the transpulmonary pressure has been completed for all the acquired CT images (step S113). If it is determined that the calculation process of the transpulmonary pressure has not been completed for all the CT images (step S113; NO), the processing circuitry 140 returns to step 105 and executes the same process for unprocessed CT images.

[0038] On the other hand, when it is determined that the calculation process of the transpulmonary pressure is completed for all CT images (step S113; YES), the generating function 144 generates a transpulmonary pressure map (risk information map) based on the value of the transpulmonary pressure for each unit region PG calculated for each CT image (step S115). Here, a transpulmonary pressure map is obtained for a plurality of tomographic images (CT images) in the range of the chest in the body axis direction of the patient P, and as a result, a three-dimensional 3D transpulmonary pressure map is generated. That is, the generating function 144 generates a three-dimensional risk information map along the body axis direction of the subject based on a CT image including a plurality of tomographic images of the chest captured along the body axis direction of the subject.

[0039] 5 is a diagram showing an example of a transpulmonary pressure map LSM1 in which the transpulmonary pressure values ​​calculated for each unit region according to the embodiment are superimposed on a CT image. As shown in FIG. 5, a user such as a doctor can grasp the detailed and accurate risk of lung injury of a patient P by checking such a transpulmonary pressure map LSM1.

[0040] Furthermore, by preparing a lookup table in advance that associates the transpulmonary pressure value with a display color or grayscale, the generating function 144 can generate the transpulmonary pressure map as a color map image or grayscale image. The high and low distribution of the transpulmonary pressure in the lung region and its degree can be intuitively grasped as a color or grayscale. FIG. 6 is a diagram showing an example of a transpulmonary pressure map LSM2 displayed as a grayscale image according to the embodiment. By checking the transpulmonary pressure map LSM2 displayed as such a grayscale image (or color image), users such as doctors can intuitively and easily grasp the risk status of lung injury of the patient P.

[0041] Returning to FIG. 2, next, the estimation function 145 estimates risk information in the lung region of the patient P based on the transpulmonary pressure map (step S117). For example, the estimation function 145 estimates a high-risk region where the risk of lung injury is particularly high. The estimation function 145 estimates the risk information using, for example, a risk estimation model M stored in advance in the memory 150.

[0042] 7A and 7B are diagrams for explaining input and output of a risk estimation model M according to an embodiment. The risk estimation model M shown in FIG. 7A is a model trained to output risk information when a transpulmonary pressure map LSM (risk information map) or information based on the transpulmonary pressure map LSM (e.g., numerical information on transpulmonary pressure, information on the ratio of the area of ​​the region where the transpulmonary pressure is equal to or greater than a threshold value to the total area of ​​the lung region, etc.) is input. The risk information includes, for example, information indicating a high-risk region and information indicating a prognosis prediction (mortality rate, treatment method, etc.). The risk estimation model M shown in FIG. 7B is a model trained to output risk information when a transpulmonary pressure map LSM (risk information map) or information based on the transpulmonary pressure map LSM (e.g., numerical information on transpulmonary pressure, etc.) and patient information are input. The patient information includes, for example, information included in a chart (medical history, smoking status, etc.), clinical information, etc. In such a risk estimation model M, risk information can be estimated in detail by determining the distribution pattern of the transpulmonary pressure in addition to the ratio of the area of ​​the region where the transpulmonary pressure is equal to or greater than the threshold to the area of ​​the entire lung region. Even if the ratio of the area of ​​the region where the transpulmonary pressure is equal to or greater than the threshold to the area of ​​the entire lung region is the same, the treatment method can be changed by grasping the level of risk according to the distribution pattern. For example, when the transpulmonary pressure on the ventral side is higher than that on the dorsal side, the risk can be reduced by changing the position to prone. In recent years, there is a method of monitoring the state of the lungs in real time during artificial ventilation management using EIT (Electrical Impedance Tomography). The transpulmonary pressure map LSM is the initial value of the state of the lungs, and the EIT is the state of the lungs at time t during artificial ventilation management. The transpulmonary pressure map LSM at time t may be estimated by a model that inputs the transpulmonary pressure map LSM and EIT. In addition, the risk of developing ventilator-associated lung injury during artificial ventilation management may be predicted by a model that inputs the transpulmonary pressure map LSM and EIT.

[0043] Returning to Fig. 2, next, the display control function 146 causes the generated transpulmonary pressure map LSM and the estimated risk information to be displayed on the display 130 (step S119). By checking such transpulmonary pressure map LSM and risk information, users such as doctors can perform a detailed and accurate risk assessment of lung injury for the patient P. With this, the processing of this flowchart ends.

[0044] In the above, the case where the transpulmonary pressure is calculated for each unit region PG (pixel by pixel) has been described as an example. However, when displaying, a grid may be formed with a predetermined size, and a representative value such as the average value of the transpulmonary pressure in each grid may be used to generate and display a transpulmonary pressure map. Areas where the transpulmonary pressure is equal to or greater than a threshold value may be highlighted. Areas where the transpulmonary pressure is equal to or greater than a predetermined threshold value may be regarded as areas at high risk of ventilator-associated lung injury or areas at high risk of complications related to the ventilator (e.g., pneumothorax, pneumomediastinum, pneumatocele, etc.), and the relevant areas may be highlighted. For example, a display method such as encircling the relevant area on the CT image with a contour or overlaying the relevant area may be adopted.

[0045] Alternatively, the lung region may be divided into a number of sections, and the statistics of the transpulmonary pressure may be calculated for each section, and the statistics may be displayed, or may be displayed as a color map image or a grayscale image according to a look-up table. For example, the lung region may be divided into four sections by dividing the left and right lungs in the left-right direction and the ventral and dorsal sides in the up-down direction. As statistics, the mean, median, maximum, minimum, variance, etc. may be used. Such a display makes it possible to visualize the distribution of the risk of ventilator-associated lung injury. Furthermore, the bias in the risk level, such as the left-right ratio or the up-down ratio, may be quantified or verbalized and displayed.

[0046] The above-mentioned partitioning method may be based on the CT value range of the CT image. For example, the partitioning method includes partitioning into hyperinflated lungs of -1,000 to -900 HU, normal lungs of -900 to -500 HU, poorly aerated lungs of -500 to -200, and atelectasis of -200 to +100. Transpulmonary pressure or h*{1-(H Avg The distribution range (maximum value to minimum value, etc.) and distribution pattern of the air distribution in the lungs may be displayed. Such a display makes it possible to quantify and visualize the uniformity and non-uniformity of the air distribution in the lungs. In addition, an alert may be issued to the user depending on the risk of ventilator-associated lung injury (alert display).

[0047] Also, the transpulmonary pressure map LSM may be generated using values ​​different from the airway pressure and esophageal pressure acquired in step S103. For example, if the transpulmonary pressure map LSM is generated using a value higher than the airway pressure acquired in step S103, it is possible to obtain a transpulmonary pressure map LSM assuming that the settings of the artificial ventilator are changed so that the airway pressure is higher. By comparing with the transpulmonary pressure map LSM generated using the airway pressure acquired in step S103, it is possible to determine whether the settings of the artificial ventilator can be changed safely.

[0048] According to the medical information processing device 100 of the embodiment described above, it becomes possible to perform detailed and accurate assessment of lung injury risk for the entire lungs, taking into account the lung condition of each patient. In addition, not only does it enable artificial respiration management tailored to the patient's condition, but it also makes it possible to prevent lung injury from worsening by visualizing the risk at an early stage, which is expected to improve the patient's prognosis.

[0049] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0050] 100... medical information processing device 100, 110... communication interface, 120... input interface, 130... display, 140... processing circuit, 141... acquisition function, 141-1... image acquisition function, 141-2... internal pressure acquisition function, 142... determination function, 142-1... lung area determination function, 142-2... esophageal pressure measurement position determination function, 143... calculation function, 144... generation function, 145 estimation function, 146... display control function, 150... memory, D1... X-ray CT device, D2... artificial ventilator, D3... esophageal pressure measuring device, NW... communication network, BD... bed device

Claims

1. an image acquisition unit for acquiring a CT image of a subject's chest; an internal pressure acquiring unit for acquiring an internal esophageal pressure and an internal airway pressure of the subject; A generating unit that generates a risk information map of a lung field of the subject based on the CT image, the esophageal pressure, and the airway pressure; an estimation unit that estimates risk information in the lung field of the subject based on the risk information map; A display control unit that displays the risk information map and the risk information on a display unit; A medical information processing device comprising:

2. The display control unit causes the risk information map to be superimposed on the CT image and displayed on the display unit. The medical information processing device according to claim 1 .

3. The estimation unit estimates the risk information using a risk estimation model that has been trained to output the risk information when information based on the risk information map is input. The medical information processing device according to claim 1 .

4. The estimation unit estimates the risk information using a risk estimation model that has been trained to output information indicating the risk information when information based on the risk information map and information about the subject are input. The medical information processing device according to claim 1 .

5. a calculation unit that calculates a transpulmonary pressure for each unit region of a lung field in the CT image based on a CT value in the CT image, the esophageal pressure, and the airway pressure; The generating unit generates the risk information map indicating the transpulmonary pressure for each unit area. The medical information processing device according to claim 1 .

6. the calculation unit further calculates the transpulmonary pressure for each unit region based on a relative positional relationship between a measurement position of the esophageal pressure in the CT image and the unit region for calculating the transpulmonary pressure. The medical information processing device according to claim 5 .

7. The calculation unit further calculates a ratio of the unit areas having a transpulmonary pressure equal to or greater than a threshold value based on the calculated transpulmonary pressure for each unit area; The display control unit causes the display unit to display the ratio of the unit regions having a transpulmonary pressure equal to or greater than the threshold value. The medical information processing device according to claim 5 .

8. The generating unit generates the three-dimensional risk information map along the body axis direction of the subject based on the CT image including a plurality of tomographic images of the chest taken along the body axis direction of the subject. The medical information processing device according to claim 1 .

9. The computer obtaining a CT image of the subject's chest; acquiring esophageal and airway pressures of the subject; generating a risk information map for a lung field of the subject based on the CT image, the esophageal pressure, and the airway pressure; Estimating risk information in the lung field of the subject based on the risk information map; Displaying the risk information map and the risk information on a display unit; Medical information processing method.

10. On the computer, obtaining a CT image of the subject's chest; acquiring esophageal and airway pressures of the subject; generating a risk information map for a lung field of the subject based on the CT image, the esophageal pressure, and the airway pressure; estimating risk information in a lung field of the subject based on the risk information map; Displaying the risk information map and the risk information on a display unit; program.

Images