Image analysis device and program

Abstract

It helps users to properly determine whether or not there are any complications due to the use of a ventilator. [Solution] The control unit of the console acquires images obtained by taking still or dynamic photographs of the subject at least while the subject is wearing a ventilator or within a specified time after extubation, calculates features related to specified structures based on the acquired images, and generates information regarding the presence or absence of complications related to the subject's ventilator based on the calculated features.

Description

[Technical Field]

[0001] The present invention relates to an image analysis device and a program. [Background technology]

[0002] A technique has been proposed in the past in which the amount of morphological change in a specific structure in the chest is calculated based on a plurality of frame images showing the dynamic state of the chest obtained by radiography of the chest of a subject wearing a ventilator, and the respiratory condition of the subject when the ventilator is attached or when the tube is removed is evaluated based on the calculated amount of morphological change (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-130264 Summary of the Invention [Problem to be solved by the invention]

[0004] By the way, there is a risk of complications occurring when a patient is put on a ventilator, but Patent Document 1 does not mention complications.

[0005] An object of the present invention is to support a user in appropriately determining whether or not complications have occurred due to the use of a ventilator. [Means for solving the problem]

[0006] In order to solve the above problems, the image analysis device of the present invention comprises: an acquisition unit that acquires images obtained by performing still image capture or dynamic image capture of the subject at least while the subject is wearing a ventilator or within a predetermined time after extubation; a generating unit that generates information on the presence or absence of complications related to the artificial respiration of the subject based on the acquired image; Equipped with.

[0007] The program of the present invention is Computer, an acquisition unit that acquires images obtained by performing still image capture or dynamic image capture of the subject at least while the subject is wearing a ventilator or within a predetermined time after extubation; a generating unit that generates information regarding the presence or absence of complications related to the artificial respiration of the subject based on the acquired image; Function as. [Effects of the Invention]

[0008] According to the present invention, it is possible to assist a user in appropriately determining whether or not complications will occur due to the use of a ventilator. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing the overall configuration of a dynamic analysis system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the console of FIG. 1. [Figure 3] FIG. 1 is a diagram schematically showing the movement of the vocal cords in a radiological image of the airway (front). [Figure 4] FIG. 1 is a schematic diagram showing a normal larynx and a larynx with laryngeal edema in a radiological image of the airway (lateral view). [Figure 5] FIG. 1 is a diagram schematically showing the trachea during inspiration and expiration in a radiological image of the airway (front view) of a patient with tracheal stenosis. [Figure 6] 3 is a flowchart showing an airway complication evaluation process executed by the control unit of FIG. 2. [Figure 7] FIG. 10 is a diagram showing an example of calculation of the length of the airway diameter of the larynx. [Figure 8] FIG. 7 is a diagram showing an example of an evaluation screen displayed on the display unit in step S6 of FIG. 6. [Figure 9] FIG. 7 is a diagram showing an example of an evaluation screen displayed on the display unit in step S6 of FIG. 6. [Figure 10]3 is a flowchart showing a pulmonary complication evaluation process executed by the control unit in FIG. 2. [Figure 11] FIG. 11 is a diagram showing an example of an evaluation screen displayed on the display unit in step S26 of FIG. [Figure 12] FIG. 11 is a diagram showing an example of an evaluation screen displayed on the display unit in step S26 of FIG. [Figure 13] 3 is a flowchart showing a cardiac complication evaluation process executed by the control unit in FIG. 2. [Figure 14] FIG. 14 is a diagram showing an example of an evaluation screen displayed on the display unit in step S36 of FIG. 13. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings, but the present invention is not limited to the illustrated examples.

[0011] (Configuration of dynamic analysis system 100) First, the configuration of the embodiment according to the present invention will be described. FIG. 1 shows an example of the overall configuration of a dynamic analysis system 100 according to this embodiment. The dynamic analysis system 100 is a system for performing rounds of radiography on patients who are in an intensive care unit, an operating room, or the like and who have difficulty moving, as subjects. The system includes a radiation generator 1, a console 2, an access point 3, an FPD (Flat Panel Detector) cassette 4, and The radiation generating device 1 has wheels and is configured as a mobile medical cart on which a console 2 and an access point 3 are installed. In the dynamic analysis system 100, the console 2 can be connected to and communicate with the radiation generating device 1 and the FPD cassette 4 via the access point 3.

[0012] As shown in FIG. 1, the dynamic analysis system 100 is brought into an operating room (intensive care unit) Rc or the like, and performs dynamic or still image capture of the subject H by irradiating the FPD cassette 4 from the portable radiation source 11 of the radiation generating device 1 with radiation, for example, inserted between the subject H lying on bed B and the bed B or into an insertion port provided on the opposite side of the bed B (not shown) from the subject H. Dynamic radiography involves irradiating the subject H with pulsed radiation such as X-rays repeatedly at predetermined intervals (pulse irradiation), or irradiating the subject H continuously at a low dose rate ( A series of images obtained by dynamic photography refers to the acquisition of multiple images by using continuous exposure. The images that make up a dynamic image are called frame images. Dynamic photography includes video recording, but does not include taking still images while displaying the video. Dynamic images include video, but do not include images obtained by taking still images while displaying the video.

[0013] Each device constituting the dynamic analysis system 100 will be described below. The radiation generating device 1 includes a radiation source 11 that irradiates radiation, a radiation irradiation control unit 12, an exposure switch 13, and the like.

[0014] The radiation source 11 irradiates the subject H with radiation (X-rays) under the control of the radiation irradiation control unit 12. The radiation irradiation control unit 12 controls the radiation source 11 to perform radiation imaging (dynamic imaging or still image imaging) based on the radiation irradiation conditions transmitted from the console 2. The radiation irradiation conditions input from the console 2 include, for example, the tube current, tube voltage, radiation irradiation time, frame rate (the number of frame images captured per unit time (one second)), total imaging time or total number of imaging frame images per imaging, and type of additional filter. When the exposure switch 13 is pressed, a radiation irradiation instruction signal is input to the console 2 .

[0015] The console 2 outputs radiation irradiation conditions according to the input examination information to the radiation generating device 1 and outputs image reading conditions to the FPD cassette 4 to control the radiation irradiation and radiation image reading operations, and as an image analysis device, analyzes the radiation images (dynamic images or still images) transmitted from the FPD cassette 4 and generates and displays information regarding the presence or absence of complications related to the subject H's ventilator.

[0016] Fig. 2 shows an example of the functional configuration of the console 2. As shown in Fig. 2, the console 2 is configured to include a control unit 21, a storage unit 22, an operation unit 23, a display unit 24, a communication unit 25, a connector 26, etc., and each unit is connected via a bus 27.

[0017] The control unit 21 is composed of a CPU (Central Processing Unit), RAM (Random Access Memory), etc. In response to operations on the operation unit 23, the CPU of the control unit 21 reads out system programs and various processing programs stored in the storage unit 22, loads them into the RAM, and, according to the loaded programs, performs centralized control of the operations of the various units of the console 2 and the operations of the radiation generator 1 and FPD cassette 4. Furthermore, according to the loaded programs, the control unit 21 executes various processes, including an airway complication evaluation process, a pulmonary complication evaluation process, and a cardiac complication evaluation process, which will be described later, and functions as an acquisition unit and a generation unit.

[0018] The storage unit 22 is configured with a nonvolatile semiconductor memory, a hard disk, etc. The storage unit 22 stores various programs executed by the control unit 21, parameters required for executing processes by the programs, data such as processing results, etc. For example, the storage unit 22 stores programs for executing the airway complication evaluation process, pulmonary complication evaluation process, and cardiac complication evaluation process described below. The various programs are stored in the form of readable program code, and the control unit 21 sequentially executes operations in accordance with the program code. The storage unit 22 also stores radiation irradiation conditions and image reading conditions for dynamic radiography. The radiation irradiation conditions and image reading conditions can be set by the user by operating the operation unit 23.

[0019] Furthermore, the memory unit 22 stores the radiological images transmitted from the FPD cassette 4 in association with the patient information (attribute information) of the subject H at the time of imaging, examination information (examination date, examination target area (e.g., chest, airway, etc.), imaging type (dynamic imaging / still image imaging), imaging time (e.g., before / during / after extubation of a ventilator)), evaluation items (e.g., airway complications, pulmonary complications, etc.), calculated features, generated information regarding the presence or absence of complications, etc. The storage unit 22 may also store statistical data of the calculation results obtained by calculating the feature amounts of predetermined structures calculated in the airway complication evaluation process described below from radiographic images of healthy individuals.

[0020] The operation unit 23 is configured with a keyboard having cursor keys, numeric input keys, various function keys, etc., and a pointing device such as a mouse, and outputs instruction signals input by operating the keys on the keyboard or the mouse to the control unit 21. The operation unit 23 may also have a touch panel on the display screen of the display unit 24, and in this case, outputs instruction signals input via the touch panel to the control unit 21.

[0021] The display unit 24 is composed of a monitor such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube), and displays input instructions and data from the operation unit 23 according to instructions of a display signal input from the control unit 21.

[0022] The communication unit 25 includes a wireless LAN adapter or the like, and controls data transmission and reception with external devices such as the radiation generating device 1 and the FPD cassette 4 connected to a communication network such as a wireless LAN via the access point 3.

[0023] The connector 26 is a connector for communication connection with the FPD cassette 4 via a cable (not shown).

[0024] Returning to FIG. 1, the access point 3 relays communications between the radiation generating device 1 and the console 2, communications between the console 2 and the FPD cassette 4, and the like.

[0025] The FPD cassette 4 is a portable radiation detector compatible with dynamic radiography. The FPD cassette 4 is configured by arranging a plurality of radiation detection elements in a matrix (two-dimensionally) at predetermined positions on a substrate such as a glass substrate. The elements detect radiation irradiated from a radiation source 11 and transmitted through at least the subject H according to its intensity, convert the detected radiation into an electrical signal, and store the electrical signal. A switching unit such as a TFT (Thin Film Transistor) is connected to each radiation detection element, and the switching unit controls the storage and reading of the electrical signal in each radiation detection element to obtain image data (frame images). FPDs can be of an indirect conversion type, in which radiation is converted into an electrical signal by a photoelectric conversion element via a scintillator, or a direct conversion type, in which radiation is directly converted into an electrical signal; either type may be used.

[0026] The FPD cassette 4 is equipped with a read control unit that controls the accumulation and reading of electrical signals by the switching unit, and a communication unit for communication connection with the console 2 via the access point 3 (neither is shown). Image reading conditions such as the frame rate, the number of captured frame images per capture, and the image size (matrix size) are set by the console 2 via the communication unit. The read control unit controls the accumulation and reading of electrical signals in each radiation detection element by the switching unit based on the set image reading conditions. The FPD cassette 4 also has a connector, and can be connected for communication with the console 2 via a cable (not shown).

[0027] The FPD cassette 4 may be brought by the person performing the imaging, such as a radiologist, but since the FPD cassette 4 is relatively heavy and may break or malfunction if dropped, it is designed to be transported by being inserted into a cassette pocket 61a provided on the medical cart.

[0028] (Operation of dynamic analysis system 100) Next, the operation of the dynamic analysis system 100 will be described. Complications that may occur when a patient is placed on a ventilator include airway complications, lung complications, and cardiac complications.

[0029] In the console 2 of this embodiment, it is possible to generate information regarding the presence or absence of complications related to the airway, the presence or absence of complications related to the lungs, and the presence or absence of complications related to the heart based on radiological images (dynamic images or still images) obtained by taking dynamic or still images while the patient is attached to a ventilator or after extubation. The process of generating information on the presence or absence of each complication will be described below.

[0030] (Airway Complication Assessment Processing) The airway complication evaluation process is a process for generating information on the presence or absence of airway complications. Airway complications include vocal cord paralysis, laryngeal edema, and tracheal stenosis.

[0031] Vocal cord paralysis is a pathological condition in which the vocal cords remain open and do not close even when a voice is produced. Figure 3 is a diagram that schematically shows the movement of the vocal cords in a radiological image of the airway (front). Reference numeral 51 in Figure 3 indicates the vocal cords. As shown in Figure 3, the vocal cords 51 close when a voice is produced and open when a voice is not produced, but when vocal cord paralysis occurs, the vocal cords remain open.

[0032] Laryngeal edema is a pathological condition in which the mucous membrane inside the larynx swells, impairing breathing. Figure 4 is a diagram showing a normal larynx and a larynx with laryngeal edema (abnormality) in a radiographic image of the airway (lateral view). In Figure 4, reference numeral 52 indicates the larynx, and 521 indicates laryngeal edema. When laryngeal edema occurs, the larynx is compressed and becomes narrower than normal, as shown in Figure 4.

[0033] Tracheal stenosis is a pathological condition in which the diameter of the trachea narrows during inspiration, and the length of the trachea changes between inspiration and expiration. Figure 5 is a diagram showing a schematic representation of the trachea during inspiration and expiration in a radiological image (front view) of the airway of a patient with tracheal stenosis. The reference numeral 53 in Figure 5 indicates the trachea.

[0034] Here, since the airway is kept open by the tube while the patient is on the ventilator, it is difficult to determine any airway-related complications unless the ventilator is removed. Therefore, in this embodiment, an airway complication evaluation process is performed within a predetermined time after extubation from the ventilator, and information regarding airway complications is generated.

[0035] 6 is a flowchart showing the flow of the airway complication evaluation process executed in the console 2. The airway complication evaluation process is executed by cooperation between the control unit 21 and a program stored in the storage unit 22. The airway complication evaluation process will be described below. 6, a case will be described in which dynamic images are acquired by performing dynamic imaging, and information regarding the presence or absence of complications related to the airway is generated based on the acquired dynamic images. In addition, in the dynamic analysis system 100, dynamic images acquired by performing dynamic imaging of the airway of the subject H before the attachment of an artificial respirator are stored in the storage unit 22.

[0036] First, the control unit 21 accepts input of patient information (name, age, sex, disease, etc.) of the subject H and examination information (area to be examined (here, for example, the airway), type of imaging (here, dynamic imaging), time of imaging (here, after extubation), evaluation item (here, airway complications)) via the operation unit 23 (step S1).

[0037] Next, based on the input examination information, the control unit 21 controls the radiation irradiation control unit 12 and the FPD cassette 4 to perform dynamic imaging including the airway of the subject H in response to pressing of the exposure switch 13, and obtains a dynamic image of the airway of the subject H after extubation from the ventilator (step S2).

[0038] Next, the control unit 21 calculates the feature amount of a predetermined structure related to a complication relating to the airway from the acquired dynamic image (step S3).

[0039] For example, control unit 21 calculates the amount of movement of the vocal cords or the amount of change in the width of the glottis as a feature of the vocal cords. For example, control unit 21 recognizes the vocal cords from each frame image of the acquired dynamic image using image processing such as edge detection or machine learning, and tracks point P on the recognized vocal cords (for example, the portion indicated by point P of vocal cord 51 in FIG. 3) from each frame image to calculate the amount of movement (maximum amount of movement) of point P. Alternatively, the width of the glottis may be calculated from each frame image, and the difference between the maximum and minimum values ​​may be calculated as the amount of change in the width of the glottis.

[0040] Furthermore, for example, the control unit 21 calculates the length of the airway diameter of the larynx (indicated by reference numeral 522 in FIG. 7) as a feature amount of the larynx, as shown in FIG. 7. For example, the control unit 21 recognizes the larynx from a predetermined frame image of the acquired dynamic image using image processing such as edge detection or machine learning, and calculates the airway diameter of the recognized larynx. Note that, because the larynx extends in the vertical direction, the maximum diameter and minimum diameter of the larynx may also be calculated. Furthermore, when laryngeal edema occurs, the diameter of the laryngeal airway may narrow in the depth direction, as shown in Fig. 4. In this case, in a radiographic image of the airway captured from the front, the amount of radiation transmitted through the laryngeal edema portion decreases, resulting in a decrease in the signal value (density) of this portion. Therefore, the control unit 21 may calculate the signal value (representative value, for example, the average value or the median value) of the larynx as the feature amount of the larynx.

[0041] Furthermore, for example, the control unit 21 calculates the amount of movement of the tracheal wall or the amount of change in tracheal diameter at a predetermined position in the trachea from the larynx to the bronchi as a feature of the trachea. For example, the control unit 21 recognizes the airway from below the larynx to the bronchi as the trachea from each frame image of the acquired dynamic image using image processing such as edge detection or machine learning, and calculates the amount of movement (maximum amount of movement) of the tracheal wall at a predetermined position (predetermined position in the vertical direction) of the recognized trachea. Alternatively, the control unit 21 may calculate the tracheal diameter at a predetermined position (predetermined position in the vertical direction) of the recognized trachea from each frame image, and calculate the difference between the maximum and minimum values ​​as the amount of change in tracheal diameter. Furthermore, as described above, when tracheal stenosis occurs, the tracheal diameter changes between exhalation and inhalation, and when the diameter in the depth direction in particular changes, the amount of radiation transmitted changes in a radiographic image taken of the airway from the front, resulting in a change in signal value (density). Therefore, the control unit 21 may calculate the amount of change (amount of change in signal value) of the trachea (representative value, for example, average value or median value) as the feature amount of the trachea. Alternatively, the ratio of the upper airway to the lower airway may be determined as the feature amount of the trachea.

[0042] Next, the control unit 21 acquires feature amounts of predetermined structures related to complications relating to the airway in the dynamic image of the airway of the subject H before the attachment of the artificial respirator (step S4). The control unit 21 reads out from the memory unit 22 a dynamic image of the airway of the subject H before the ventilator is attached, and performs processing on the read out dynamic image similar to that described in step S3 to obtain features of specified structures related to airway complications in the dynamic image of the airway of the subject H before the ventilator is attached. In addition, the feature values ​​of specified structures related to airway complications may be calculated in advance from dynamic images of the airway of subject H before the ventilator is attached and stored in memory unit 22, and in step S4, the feature values ​​may be acquired from memory unit 22.

[0043] Next, the control unit 21 generates comparative information on the feature amounts of the predetermined structure before and after the attachment of the ventilator as information on the presence or absence of complications related to the airway (step S5). Then, the control unit 21 causes the display unit 24 to display the evaluation screen 241 on which the generated information on the presence or absence of complications related to the airway is displayed (step S6), and ends the airway complication evaluation process.

[0044] Fig. 8 is a diagram showing an example of evaluation screen 241 displayed on display unit 24 in step S6. As shown in Fig. 8, evaluation screen 241 displays, for example, patient information 241a of the patient to be evaluated (subject H), dynamic image 241b acquired in step S2, vocal cord feature amount (here, vocal cord movement amount) 241c before and after the attachment of an artificial respirator to the patient and after the extubation, and larynx feature amount (here, laryngeal airway diameter) 241d before and after the attachment of an artificial respirator to the patient and after the extubation.

[0045] Fig. 9 is a diagram showing an example of an evaluation screen 242 displayed on the display unit 24 in step S6. As shown in Fig. 9, the evaluation screen 242 displays, for example, patient information 242a of the patient to be evaluated, a frame image 242b of the maximum expiratory position of the dynamic image acquired in step S2, a frame image 242c of the maximum inspiratory position, and a feature amount 242d of the trachea before and after attachment of the artificial respirator (here, the amount of change in tracheal diameter).

[0046] In this way, evaluation screens 241 and 242 display comparative information on the presence or absence of airway complications, such as the characteristic quantities of specified structures related to airway complications (here, vocal cord movement, laryngeal airway diameter, and tracheal diameter change) before and after the attachment of the ventilator, allowing the user to easily grasp the presence or absence of airway complications, such as vocal cord paralysis, laryngeal edema, and tracheal stenosis.

[0047] Note that the dynamic image acquired in step S2 may be displayed as a moving image, or only the representative frame image may be displayed, as the dynamic image 241b on the evaluation screen 241. Furthermore, the dynamic image (or the representative frame image) before and after the attachment of the artificial respirator may be displayed side by side, or the displayed dynamic image (or the representative frame image) may be annotated to indicate the portion where the vocal cord movement amount or the airway diameter was measured.

[0048] In the above airway complication evaluation process, the airway is photographed dynamically, and the obtained dynamic images are analyzed to generate information regarding the presence or absence of complications related to the artificial respirator. However, it is also possible to photograph still images of the airway and analyze the obtained still images to generate information regarding the presence or absence of complications related to the artificial respirator. For example, since laryngeal edema does not involve movement, the laryngeal airway diameter or laryngeal signal value can be calculated from a still image obtained by taking a still image of the airway of subject H after the ventilator is removed, and information regarding the presence or absence of complications related to the ventilator can be generated based on a comparison with the laryngeal airway diameter or laryngeal signal value before subject H was fitted with the ventilator. Furthermore, for example, after extubation of the ventilator, still images of the airway of subject H at the time of exhalation and inhalation are taken, and from these still images obtained at the time of exhalation and the time of inhalation, the amount of change in tracheal diameter, the amount of movement of the tracheal wall, or the amount of change in tracheal signal value can be calculated, and information regarding the presence or absence of complications related to the ventilator (tracheal stenosis) can be generated based on a comparison with the amount of change in tracheal diameter, the amount of movement of the tracheal wall, or the amount of change in tracheal signal value at the time of exhalation and inhalation before the ventilator was attached to subject H.

[0049] Furthermore, since laryngeal edema can be detected in both images of the airway taken from the front (see Figure 7) and from the side (see Figure 5), either one may be used to generate information regarding the presence or absence of complications related to the artificial respirator, or if laryngeal edema is suspected based on the comparison result between one feature and a predetermined threshold, the other image may also be used to generate information regarding the presence or absence of complications related to the artificial respirator (tracheal stenosis).

[0050] Furthermore, in the above-described airway complication evaluation process, comparative information is generated by comparing the feature values ​​after extubation of the ventilator with the feature values ​​of the same patient before the ventilator is attached, as information regarding the presence or absence of complications related to the ventilator. However, without being limited to this, comparative information may be generated by comparing the feature values ​​after extubation of the ventilator with statistical data on healthy subjects (for example, statistical data of the calculation results obtained by calculating the feature values ​​calculated in the airway complication evaluation process from radiological images of healthy subjects) as information regarding the presence or absence of complications related to the ventilator.

[0051] Furthermore, in the above-mentioned airway complication evaluation process, information regarding the presence or absence of complications is generated for all items related to the airway, including vocal cord paralysis, laryngeal edema, and tracheal stenosis, but the configuration may also be such that the user can select which items of information to generate from the operation unit 23.

[0052] In addition, if the difference between the characteristic amount after extubation of the ventilator and the characteristic amount (or statistical data) before the ventilator is attached exceeds a predetermined threshold, an alert may be output (displayed, audio output, etc.).

[0053] (Pulmonary Complication Assessment Processing) The pulmonary complication evaluation process is a process for generating information on the presence or absence of a pulmonary complication. Pulmonary complications include pneumothorax, pneumonia, atelectasis, pulmonary edema, and pleural effusion. These complications primarily occur during mechanical ventilation. Therefore, in this embodiment, a pulmonary complication evaluation process is performed while the patient is on an artificial respirator, and information regarding pulmonary complications is generated.

[0054] 10 is a flowchart showing the flow of pulmonary complication evaluation processing executed in the console 2. The pulmonary complication evaluation processing is executed by cooperation between the control unit 21 and a program stored in the storage unit 22. The pulmonary complication evaluation processing will be described below. 10 will be described as a case where dynamic images are acquired by performing dynamic imaging, and information regarding the presence or absence of pulmonary complications is generated based on the acquired dynamic images. In the dynamic analysis system 100, dynamic images acquired by performing dynamic imaging of the chest of the subject H before the subject H was fitted with an artificial respirator, and dynamic images and feature amounts acquired in a pulmonary complication evaluation process previously performed while the subject H was fitted with an artificial respirator, are stored in the storage unit 22.

[0055] First, the control unit 21 accepts input of patient information (name, age, sex, disease, etc.) of the subject H and examination information (area to be examined (here, for example, chest), type of imaging (here, dynamic imaging), time of imaging (here, while wearing), evaluation item (here, for example, pulmonary complications)) via the operation unit 23 (step S21).

[0056] Next, based on the input examination information, the control unit 21 controls the radiation irradiation control unit 12 and the FPD cassette 4, and in response to pressing of the exposure switch 13, performs dynamic imaging of the chest of the subject H who is wearing a ventilator, and obtains a dynamic image (step S22).

[0057] Next, the control unit 21 calculates the feature amount of a predetermined structure related to a pulmonary complication from the acquired dynamic image (step S23).

[0058] Among the complications that can occur while using a ventilator, pneumonia occurs when pathogens that have entered through the airways multiply in the lungs, causing inflammation. Atelectasis occurs when air is not reaching the lung tissue for some reason, resulting in partial or complete loss of air in the lungs, causing the lungs to collapse. Pulmonary edema occurs when liquid components in the blood leak out and accumulate in the alveoli. Pleural effusion occurs when an abnormal amount of fluid accumulates in the pleural cavity. In radiological images of lung fields with pneumonia, atelectasis, pulmonary edema, or pleural effusion, the signal value (density) within the lung field is lower than normal. Furthermore, when atelectasis or pleural effusion occurs, the lung field area is smaller than normal. Pulmonary edema is often accompanied by cardiomegaly, in which case the cardiothoracic ratio (ratio of the width of the heart to the width of the thorax) is larger than normal.

[0059] Therefore, in step S23, for example, the control unit 21 calculates at least one of the signal values ​​(representative values, for example, average values ​​or median values) of the left and right lung field areas, the lung field area, and the cardiothoracic ratio as feature quantities of a specified structure related to a pulmonary complication. For example, the control unit 21 recognizes the lung field region from each frame image of the acquired dynamic image using known image processing such as edge detection or machine learning, and calculates the signal value (representative value, for example, average or median) and lung field area of ​​each of the left and right lung field regions. Then, for example, the signal value calculated from each frame image and the representative value of the lung field area (for example, maximum value, minimum value, average value, etc.) are used as feature quantities. Furthermore, the control unit 21 recognizes the cardiac region from a predetermined frame image of the acquired dynamic image (for example, a frame image at the maximum inspiration position) using known image processing such as template matching or machine learning, and calculates the cardiothoracic ratio. The control unit 21 associates the calculated feature amount with the patient information, examination information, and dynamic image, and stores them in the storage unit 22.

[0060] On the other hand, in the case of pneumothorax, the lung field shrinks inside the thoracic cavity, so it is necessary to recognize the lung field area inside the thoracic cavity. However, in general lung field recognition, the area inside the outline of the thoracic cavity is recognized as the lung field area. Therefore, the control unit 21 performs frequency enhancement processing to enhance high-frequency components on each frame image of the dynamic image, generates an image from which the ribs have been removed, and recognizes a first lung field region (the region surrounded by the outline of the thoracic cavity) from the generated image by edge detection or the like (see R1 in FIG. 12). The control unit 21 also performs edge detection or the like on the recognized first lung field region to recognize a second lung field region (see R2 in FIG. 12) surrounded by the visceral pleura. Then, information about the size of each of the left and right lung fields or changes therein, for example, the ratio of the area of ​​the second lung field region to the area of ​​the first lung field region (the area within the outline of the thoracic cavity) recognized from the frame image at the maximum expiratory position and the frame image at the maximum inspiratory position (referred to as lung ratio), is calculated for each of the left and right lungs and used as a feature amount.

[0061] Next, the control unit 21 acquires feature quantities of predetermined structures related to lung complications in the dynamic images taken before the ventilator was attached and in the dynamic images taken previously while the ventilator was attached (step S24). The control unit 21 reads out from the memory unit 22 dynamic images taken of the subject H before and while the ventilator was attached, calculates the features related to pneumonia, atelectasis, pulmonary edema, and pleural effusion described in step S23 for the read dynamic images, and obtains the features related to pneumonia, atelectasis, pulmonary edema, and pleural effusion of specified structures related to lung complications in the dynamic images taken before and while the ventilator was attached in the past (past). If feature amounts relating to pneumonia, atelectasis, pulmonary edema, and pleural effusion have already been calculated from past dynamic images and stored in the storage unit 22, the feature amounts are acquired from the storage unit 22 in step S24.

[0062] Next, the control unit 21 generates information on the presence or absence of pulmonary complications based on the feature amounts calculated in steps S23 and S24 (step S25). For example, the control unit 21 generates information indicating changes over time in at least one of the signal value of the lung field region, the lung field area, and the cardiothoracic ratio before and during the use of the ventilator as information regarding the presence or absence of pneumonia, atelectasis, pulmonary edema, and pleural effusion. Images before and during (past) the use of the ventilator and the images (videos or representative frame images) acquired in step S22 may be arranged side by side to generate information regarding the presence or absence of pneumonia, atelectasis, pulmonary edema, and pleural effusion. Furthermore, information on the presence or absence of a pneumothorax is generated by performing frequency emphasis processing on at least the frame images of the maximum expiratory position and the maximum inspiratory position acquired in step S22 and arranging them for comparison, and / or information on the size of the lung field or the amount of change therein.

[0063] Then, the control unit 21 causes the display unit 24 to display the evaluation screen 241 on which the generated information on the presence or absence of a pulmonary complication is displayed (step S26), and ends the pulmonary complication evaluation process.

[0064] 11 is a diagram showing an example of an evaluation screen 243 displayed on the display unit 24 in step S26. Fig. 11 shows an example of the evaluation screen 243 displaying information on the presence or absence of pneumonia, atelectasis, pulmonary edema, and pleural effusion. As shown in Fig. 11, the evaluation screen 243 displays, for example, patient information 243a of the patient to be evaluated, dynamic images 243b (which may be representative frame images or videos) acquired before or during (past) the attachment of an artificial respirator, dynamic images 243c captured at this time, graphs 243d and 243e showing changes over time in signal values ​​of the left and right lung fields, a table 243f showing changes over time in the cardiothoracic ratio, and a table 243g showing changes over time in lung field area.

[0065] In this way, the evaluation screen 243 displays, as information regarding the presence or absence of pulmonary complications, images from before the attachment of the ventilator to the present, and changes over time in the feature quantities of predetermined structures related to pulmonary complications (here, the signal value of the lung field area, the lung field area, and the cardiothoracic ratio), in a comparable manner, so that the user can easily grasp the presence or absence of pulmonary complications, specifically, pneumonia, atelectasis, pulmonary edema, or pleural effusion. Furthermore, if a complication is being treated, the user can easily grasp the effectiveness of the treatment.

[0066] Fig. 12 is a diagram showing an example of an evaluation screen 244 displayed on the display unit 24 in step S26. Fig. 12 shows an example of the evaluation screen 244 displaying information on the presence or absence of a pneumothorax. As shown in Fig. 12, the evaluation screen 244 displays, for example, patient information 244a of the patient to be evaluated, a frequency-enhanced dynamic image 244b generated in step S23, a frame image 244c of the maximum inspiration level thereof, a frame image 244d of the maximum expiration level thereof, and a table 244e of lung proportions at the maximum inspiration level and the maximum expiration level of each of the right and left lungs.

[0067] In this way, the evaluation screen 244 displays frame images of the maximum expiratory position and the maximum inspiratory position while the ventilator is in use, side by side for comparison, as information regarding the presence or absence of pulmonary complications, and also displays the lung proportions of the maximum expiratory position and maximum inspiratory position for each of the right and left lungs, so that the user can easily grasp the presence or absence of pneumothorax as a pulmonary complication.

[0068] In the above pulmonary complication evaluation process, dynamic chest imaging is performed and the obtained dynamic images are analyzed to generate information regarding the presence or absence of pulmonary complications. However, still images of the chest can also be captured and the obtained still images analyzed to generate information regarding the presence or absence of pulmonary complications. For example, still images can be captured at the maximum inspiratory position (when taking a deep breath) or the maximum expiratory position (when fully exhaled) and then analyzed.

[0069] Furthermore, in the above-mentioned pulmonary complication evaluation process, information regarding the presence or absence of complications is generated for all lung complications, including pneumothorax, pneumonia, atelectasis, pulmonary edema, and pleural effusion, but the configuration may also be such that the user can select which item of information to generate from the operation unit 23.

[0070] In addition, an alert may be output (displayed, audio output, etc.) when the difference between the feature calculated before or while the ventilator was previously attached and the feature calculated this time exceeds a predetermined threshold, or when the feature calculated this time exceeds a predetermined threshold.

[0071] Furthermore, information regarding the presence or absence of a pneumothorax may be generated using an image taken within a predetermined time after extubation from the artificial respirator.

[0072] Furthermore, in the above-described pulmonary complication evaluation process, as a preferred example, information indicating the change over time between feature values ​​calculated from images taken before and during the previous use of the ventilator and feature values ​​calculated from the image captured this time is used as the information regarding the presence or absence of a complication. However, information indicating the change over time between feature values ​​calculated from either images taken before or during the previous use of the ventilator and feature values ​​calculated from the image captured this time may also be used as the information regarding the presence or absence of a complication.

[0073] (Cardiac Complication Assessment Processing) The cardiac complication evaluation process is a process for generating information on the presence or absence of cardiac complications. Heart complications include heart failure, which can occur while on a ventilator. Therefore, in this embodiment, a cardiac complication evaluation process is performed while the patient is on an artificial respirator, and information regarding cardiac complications is generated.

[0074] 13 is a flowchart showing the flow of cardiac complication evaluation processing executed on the console 2. The cardiac complication evaluation processing is executed by cooperation between the control unit 21 and a program stored in the storage unit 22. The cardiac complication evaluation processing will be described below. 13 will be described as a case where dynamic images are acquired by performing dynamic imaging, and information regarding the presence or absence of cardiac complications is generated based on the acquired dynamic images. It is also assumed that the dynamic analysis system 100 stores, in the storage unit 22, dynamic images acquired by performing dynamic imaging of the chest of the subject H before the subject H is fitted with an artificial respirator, and dynamic images and feature quantities acquired in a cardiac complication evaluation process previously performed while the subject H was fitted with an artificial respirator.

[0075] First, the control unit 21 accepts input of patient information (name, age, sex, disease, etc.) of the subject H and examination information (area to be examined (here, for example, chest), type of imaging (here, dynamic imaging), time of imaging (here, while wearing), evaluation item (here, for example, cardiac complications)) via the operation unit 23 (step S31).

[0076] Next, based on the input examination information, the control unit 21 controls the radiation irradiation control unit 12 and the FPD cassette 4 to perform dynamic imaging of the chest of the subject H in response to pressing of the exposure switch 13, and acquires dynamic images (step S32). Dynamic chest imaging may be performed in common with the pulmonary complication evaluation process.

[0077] Next, the control unit 21 calculates the feature amount of a predetermined structure related to a cardiac complication from the acquired dynamic image (step S33).

[0078] The heart acts as a pump, sending blood throughout the body, but when this function declines and the body is no longer able to send the necessary blood to the entire body, this is called heart failure. In the case of heart failure, the necessary blood is not sent to the lungs, and areas with a lack of blood flow appear. In addition, in the case of heart failure, the cardiothoracic ratio increases.

[0079] Therefore, in step S33, for example, the control unit 21 performs a blood flow analysis on the acquired dynamic image, and calculates a feature amount related to the blood flow for each small region (each pixel or each set of pixels) of the lung field as a feature amount of a predetermined structure related to a cardiac complication, and calculates the cardiothoracic ratio as a feature amount of a predetermined structure related to a cardiac complication. Either one of them may be generated.

[0080] As a method of blood flow analysis, for example, the difference value (absolute value of the difference value) between the signal value of each small area in the lung field region of each frame image of the dynamic image and the signal value of the corresponding small area in the analysis reference frame image that serves as the reference for the analysis (the frame image with the highest signal value (i.e., the frame image with the least blood flow)) is calculated as a feature indicating the blood flow rate for each small area in the lung field region of each frame image. Alternatively, the difference value between the signal value of each small area in the lung field region of each frame image of the dynamic image and the corresponding small area in the frame image adjacent in the time direction can be calculated as a feature indicating the blood flow rate for each small area in each frame image. Note that when the dynamic images are images taken while breathing, it is preferable to filter the time change in signal value for each corresponding small area between the frame images with a high-pass filter in the time direction (e.g., cutoff frequency 0.7 Hz) before calculating the difference value.

[0081] Alternatively, for example, as described in JP 2012-239796 A, the cardiac region may be recognized from a dynamic image, a signal value waveform of the cardiac region may be generated to serve as a heartbeat signal waveform, and a signal value waveform may be generated for each small region of the lung field region of the dynamic image, and the generated signal value waveform may be shifted by one frame interval (shifted in the time direction) to calculate a cross-correlation coefficient with the heartbeat signal waveform, and the calculated cross-correlation coefficient may be used as a feature related to blood flow for each frame image of each small region.

[0082] The control unit 21 associates the calculated feature amount with the patient information, examination information, and dynamic image, and stores them in the storage unit 22.

[0083] Next, the control unit 21 acquires feature quantities of predetermined structures related to cardiac complications in the dynamic images taken before the ventilator was attached and in the dynamic images taken previously while the ventilator was attached (step S34). The control unit 21 reads out from the memory unit 22 dynamic images taken of the subject H before and while the ventilator was being worn in the past, and performs processing on the read out dynamic images similar to that described in step S33 to obtain features of specified structures related to cardiac complications in the dynamic images taken before and while the ventilator was being worn in the past. It should be noted that if the feature amount of a predetermined structure related to a cardiac complication has already been calculated from a previously acquired dynamic image, the feature amount is acquired from the storage unit 22 .

[0084] Next, the control unit 21 generates information on the presence or absence of pulmonary complications (step S35). For example, for each dynamic image, the maximum values ​​of the blood flow feature values ​​calculated for each frame image are collected into one image, and an analysis result image is generated in which the maximum value is assigned a color. Information is then generated in which the generated analysis result images are arranged over time. Also, a table or graph showing the change in the cardiothoracic ratio over time is generated. Only one of these may be generated.

[0085] Then, the control unit 21 causes the display unit 24 to display the evaluation screen 245 on which the generated information on the presence or absence of cardiac complications is displayed (step S36), and ends the cardiac complication evaluation process.

[0086] Fig. 14 is a diagram showing an example of an evaluation screen 245 displayed on the display unit 24 in step S36. As shown in Fig. 14, the evaluation screen 245 displays, for example, patient information 245a of the patient to be evaluated, analysis result images 245b and 245c generated before and during (past) attachment of the artificial respirator, an analysis result image 245d generated by the current imaging, and a table 245f comparing the feature amount (cardiothoracic ratio) calculated from the dynamic images acquired before and during (past) attachment of the artificial respirator and the feature amount (cardiothoracic ratio) calculated from the dynamic image captured this time.

[0087] As shown in FIG. 14, the evaluation screen 245 displays information regarding the presence or absence of cardiac complications, including images from before the ventilator was attached to the present and changes over time in the features of specific structures related to lung complications (here, features related to blood flow, the cardiothoracic ratio), allowing for comparison. This allows the user to easily understand the presence or absence of cardiac complications, such as heart failure. Furthermore, if a complication is being treated, the user can easily understand whether or not the treatment is effective. For example, in FIG. 14, a blood flow defect (part indicated by A in FIG. 14) is observed in the analysis result image of 9 / 8, but no noticeable blood flow defect is observed in the analysis result image of this time, indicating that the condition has improved with treatment.

[0088] In the cardiac complication evaluation process described above, the chest is dynamically photographed and the obtained dynamic images are analyzed to generate information regarding the presence or absence of cardiac complications. However, the cardiothoracic ratio can also be generated by taking a still image of the chest at the maximum expiratory position (when taking a deep breath) and analyzing the obtained still image.

[0089] In addition, an alert may be output (displayed, audio output, etc.) when the difference between the feature calculated before or while the ventilator is attached and the feature calculated this time exceeds a predetermined threshold, or when the feature calculated this time exceeds a predetermined threshold.

[0090] Furthermore, in the cardiac complication evaluation process, as a preferred example, information indicating the change over time between feature values ​​calculated from images taken before and previously while the ventilator was attached and feature values ​​calculated from the image captured this time is used as information regarding the presence or absence of complications. However, information indicating the change over time between feature values ​​calculated from either images taken before or previously while the ventilator was attached and feature values ​​calculated from the image captured this time may also be used as information regarding the presence or absence of complications.

[0091] Furthermore, it is preferable to perform all of the above-described airway complication evaluation processing, pulmonary complication evaluation processing, and cardiac complication evaluation processing, but it is also possible to perform any one or two of them.

[0092] The embodiment of the present invention has been described above, but the description of the above embodiment is a preferred example of the dynamic analysis system according to the present invention, and the present invention is not limited to this.

[0093] For example, in the above embodiment, the dynamic analysis system was described as a system for rounds, but the present invention can also be applied to a dynamic analysis system that takes images in an imaging room and analyzes the resulting dynamic images.

[0094] In the above description, examples have been disclosed in which a hard disk or a semiconductor nonvolatile memory is used as a computer-readable medium for the program according to the present invention, but the present invention is not limited to these examples. Portable recording media such as CD-ROMs can also be used as other computer-readable media. Furthermore, carrier waves can also be used as a medium for providing data for the program according to the present invention via a communication line.

[0095] In addition, the detailed configuration and operation of each device constituting the dynamic analysis system can be modified as appropriate without departing from the spirit of the invention. [Explanation of symbols]

[0096] 100 Dynamic Analysis System 1. Radiation generator 11 Radiation source 12 Radiation irradiation control unit 13 Exposure switch 2 Console 21 Control section 22 Memory section 23 Control section 24 Display section 25 Communications Department 26 Connector 27 Bus 3. Access Points 4 FPD cassette

Claims

1. an acquisition unit that acquires images obtained by performing still image capture or dynamic image capture of the subject at least while the subject is wearing a ventilator or within a predetermined time after extubation; a generating unit that generates information on the presence or absence of complications related to the artificial respiration of the subject based on the acquired image; An image analysis device comprising:

2. 2. The image analysis device according to claim 1, wherein the generation unit calculates features related to a predetermined structure from the acquired image, and generates information regarding the presence or absence of complications related to the subject's artificial respirator based on the calculated features.

3. The image analysis device according to claim 1 or 2, wherein the complications include at least one of a respiratory tract complication, a lung complication, and a heart complication.

4. The image analysis device according to claim 3 , wherein the airway-related complications include at least one of vocal cord paralysis, airway stenosis, and laryngeal edema.

5. 5. The image analysis device according to claim 4, wherein the generation unit calculates the amount of movement of the vocal cords or the amount of change in the width of the glottis based on dynamic images obtained by performing dynamic imaging of the airway of the subject within a predetermined time after extubation of the ventilator, and generates information regarding the presence or absence of vocal cord paralysis in the subject based on the calculated amount of movement of the vocal cords or the amount of change in the width of the glottis.

6. The image analysis device according to claim 5, wherein the generation unit generates, as information regarding the presence or absence of vocal cord paralysis, comparative information between the amount of vocal cord movement or the amount of change in glottis width calculated based on dynamic images obtained by performing dynamic imaging of the airway of the subject within a predetermined time after extubation of the ventilator, and the amount of vocal cord movement or the amount of change in glottis width calculated based on dynamic images obtained by performing dynamic imaging of the airway of the subject before attachment of the ventilator, or statistical data of the amount of vocal cord movement or the amount of change in glottis width of a healthy subject.

7. The image analysis device according to any one of claims 4 to 6, wherein the generation unit calculates the amount of movement of the tracheal wall, the amount of change in tracheal diameter, or the amount of change in tracheal signal value based on images obtained by taking still images or dynamic images of the airway of the subject within a predetermined time after extubation of the ventilator, and generates information regarding the presence or absence of tracheal stenosis in the subject based on the calculated amount of movement of the tracheal wall, the amount of change in tracheal diameter, or the amount of change in tracheal signal value.

8. 8. The image analysis device according to claim 7, wherein the generation unit generates, as information regarding the presence or absence of tracheal stenosis, comparative information between an amount of movement of the tracheal wall, an amount of change in tracheal diameter, or an amount of change in tracheal signal value calculated based on images obtained by performing still image or dynamic image capture of the airway of the subject within a predetermined time after extubation of the ventilator, and an amount of movement of the tracheal wall, an amount of change in tracheal diameter, or an amount of change in tracheal signal value calculated based on images obtained by performing still image or dynamic image capture of the airway of the subject before attachment of the ventilator, or statistical data of the amount of movement of the tracheal wall, the amount of change in tracheal diameter, or the amount of change in tracheal signal value in a radiological image of a healthy subject.

9. The image analysis device according to any one of claims 4 to 8, wherein the generation unit acquires a laryngeal airway diameter or a signal value of the larynx based on an image obtained by taking still images or dynamic images of the airway of the subject within a predetermined time after extubation of the ventilator, and generates information regarding the presence or absence of laryngeal edema of the subject based on the acquired laryngeal airway diameter or signal value of the larynx.

10. 10. The image analysis device according to claim 9, wherein the generation unit generates, as information regarding the presence or absence of laryngeal edema, comparative information between a laryngeal airway diameter or a signal value of the larynx acquired based on an image obtained by performing still image photography or dynamic image photography of the airway of the subject within a predetermined time after extubation of the ventilator, and a laryngeal airway diameter or a signal value of the larynx acquired based on an image obtained by performing still image photography or dynamic image photography of the subject before attachment of the ventilator, or statistical data of the laryngeal airway diameter of a healthy subject or the signal value of the larynx in a radiological image of a healthy subject.

11. 11. The image analysis device according to claim 3, wherein the lung complications include at least one of pneumothorax, pneumonia, atelectasis, pulmonary edema, and pleural effusion.

12. The image analysis device according to claim 11, wherein the generation unit generates information as information regarding the presence or absence of pneumothorax in the subject by performing frequency emphasis processing on at least an image at a maximum expiratory position and an image at a maximum inspiratory position obtained by taking still images or dynamic images of the subject's chest while the subject is attached to the ventilator or within a predetermined time after extubation, and arranging the images in a comparable manner.

13. 13. The image analysis device according to claim 11 or 12, wherein the generation unit calculates information regarding the sizes of the left and right lung fields based on images obtained by taking still images or dynamic images of the chest of the subject while the subject is attached to the ventilator or within a predetermined time after extubation, and generates the calculated information as information regarding the presence or absence of a pneumothorax in the subject.

14. The image analysis device according to any one of claims 11 to 13, wherein the generation unit calculates at least one piece of information regarding a signal value of a lung field region, a cardiothoracic ratio, and a lung field area from each of images obtained by taking still images or dynamic images of the chest of the subject before and while the ventilator is attached, and generates information indicating a change over time between the calculated information and the information calculated based on images obtained by taking still images or dynamic images of the chest of the subject before or while the ventilator is attached, as information regarding the presence or absence of pneumonia, atelectasis, pulmonary edema, or pleural effusion in the subject.

15. The image analysis device according to any one of claims 3 to 14, wherein the cardiac complication is heart failure.

16. 16. The image analysis device according to claim 15, wherein the generation unit calculates at least one of information regarding blood flow in the lung field region and a cardiothoracic ratio based on images obtained by performing still or dynamic imaging of the chest of the subject while the subject is wearing the ventilator, and generates, as information regarding the presence or absence of heart failure in the subject, information indicating changes over time between the calculated information and the information calculated based on images obtained by performing still or dynamic imaging of the chest of the subject before or while the subject is wearing the ventilator.

17. Computer, an acquisition unit that acquires images obtained by performing still image capture or dynamic image capture of the subject at least while the subject is wearing a ventilator or within a predetermined time after extubation; a generating unit that generates information regarding the presence or absence of complications related to the artificial respiration of the subject based on the acquired image; A program to function as a

Images