JP2018175344A - Diagnosis support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide support to allow for efficient diagnosis with no oversight based on a user-specified attention region.SOLUTION: By means of a controller 31 of a diagnostic console 3, a region specification screen to allow a user to specify an attention region is displayed on a display unit 34, the user using at least one frame image in a dynamic image obtained by radiographing a dynamic state of a subject M or in an analysis result image indicative of a dynamic analysis result for each pixel or for each group of pixels of the dynamic image, and then the size of the attention region specified on the region specification screen is obtained and the image feature amount of the attention region is calculated. Based on the size and image feature amount of the attention region, the controller 31 generates a search condition for a region to be extracted from the dynamic image or analysis result image and extracts a region satisfying the generated search condition from the dynamic image or analysis result image, and then displays the region extracted from the dynamic image or analysis result image in such a manner that the region can be identified.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a diagnosis support system.

Conventionally, there is known a technique for extracting an area to be noted from an image obtained by photographing a subject.
For example, Patent Document 1 is an apparatus that sets an analysis target area by an analysis device in an observation image of a sample, divides the observation image into a plurality of areas, and calculates an image feature amount in each divided area, It is described that the range of the image feature amount of the divided region to be extracted as the analysis target region is determined from the image feature amounts of the plurality of divided regions designated by the user, and the divided region within the range where the image feature amount is determined is extracted. It is done.

Patent No. 5900644

  By the way, in the interpretation of medical images, the size of the observation target is important. However, since the technology described in Patent Document 1 performs area extraction with a plurality of adjacent pixels such as M × N pixels or the like as one divided area, a lesion of a size at which the user pays attention Even if it exists, it can not be extracted and presented to the user so as not to overlook the area. Further, in Patent Document 1, since a still image is an object, it is necessary to present the user with a lesion that can not be expressed at the timing when the image was captured, a lesion that can be captured from time change of pixel signal value, and the like. I can not

  An object of the present invention is to support efficient diagnosis without an oversight based on a user-specified attention area.

In order to solve the above problems, the diagnosis support system of the invention according to claim 1 is
The user pays attention by using at least one frame image in the dynamic image obtained by radiographing the dynamic of the living body or the analysis result of the dynamic analysis of each pixel or block of plural pixels of the dynamic image. Area specification means for specifying an area;
Size acquiring means for acquiring the size of the area of interest specified by the area specifying means;
Feature quantity calculation means for calculating an image feature quantity of the attention area designated by the area designation means;
A search condition of a region to be extracted from the dynamic image or the analysis result image based on the size of the region of interest acquired by the size acquisition unit and the image feature amount of the region of interest calculated by the feature amount calculation unit Search condition generation means for generating
Extracting means for extracting an area corresponding to the search condition generated by the search condition generation means from the dynamic image or the analysis result image;
Display means for identifiably displaying the area extracted by the extraction means in the dynamic image or the analysis result image;
Equipped with

In the invention described in claim 2, in the invention described in claim 1,
The feature amount calculation means calculates an image feature amount based on a temporal change of pixel signal values in the region of interest.

In the invention described in claim 3, in the invention described in claim 1 or 2,
When a region of interest is specified from the dynamic image, a viewpoint specification unit is provided for the user to specify which of a plurality of predetermined viewpoints the user has specified the region of interest.
The feature quantity calculation means calculates an image feature quantity of the attention area designated by the area designation means according to the viewpoint designated by the viewpoint designation means.

In the invention according to claim 4, in the invention according to claim 3,
The movement image is a chest movement image obtained by radiographing movement of the chest of the living body,
The viewpoint specifying means can specify at least one of ventilation, blood flow, and tumor.

In the invention described in claim 5, in the invention described in any one of claims 1 to 4,
A lesion level designation unit for the user to designate a lesion level compared with the target region of the region extracted from the dynamic image or the analysis result image;
The search condition generation unit generates the search condition based on the size of the attention area, the image feature amount of the attention area, and the lesion level designated by the lesion level designation unit.

In the invention according to claim 6, in the invention according to claim 5,
The lesion level designation means is for the user to designate whether the area to be extracted is severe, equal or minor compared to the area of interest.

In the invention according to claim 7, in the invention according to claim 5 or 6,
The area specifying means includes a pointing device
The lesion level designation unit designates the lesion level by the operation of the pointing device when the region designation unit designates the region of interest.

The invention according to claim 8 is the invention according to any one of claims 1 to 7 in which
The area specifying means specifies an area including a partial area of the area specified by the user or an area near the specified area as the noted area specified by the user.

  According to the present invention, it is possible to support an efficient diagnosis without an oversight based on a user-specified attention area.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the whole structure of the kinetic-analysis system in embodiment of this invention. It is a flowchart which shows the imaging | photography control processing performed by the control part of the console for imaging | photography of FIG. It is a flowchart which shows the area | region extraction process A performed by the control part of the console for diagnosis of FIG. 1 in 1st Embodiment. FIG. 7 is a diagram showing user operations in region extraction processing A. It is a figure which shows typically the search in case the image feature-value calculated from the attention area is an image feature-value concerning ventilation or a blood flow. It is a figure which shows an example of the area | region extraction result displayed in FIG.3 S20. It is a figure which shows an example of the area | region extraction result displayed in FIG.3 S20. It is a flowchart which shows the area | region extraction process B performed by the control part of the console for diagnosis of FIG. 1 in 2nd Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the illustrated example.

First Embodiment
[Configuration of Diagnosis Support System 100]
First, the configuration of the first embodiment of the present invention will be described.
FIG. 1 shows the overall configuration of a diagnosis support system 100 in the first embodiment.
As shown in FIG. 1, in the diagnosis support system 100, the imaging device 1 and the imaging console 2 are connected by a communication cable or the like, the imaging console 2 and the diagnostic console 3 are LAN (Local Area Network) etc. Connected via the communication network NT. Each device constituting the diagnosis support system 100 conforms to the Digital Image and Communications in Medicine (DICOM) standard, and communication between the devices is performed according to the DICOM.

[Configuration of Imaging Device 1]
The imaging device 1 is, for example, imaging means for imaging the movement of a living body, such as a change in form of expansion and contraction of the lung accompanying respiratory movement, a pulse of the heart, and the like. With dynamic imaging, radiation such as X-rays is pulsed and repeatedly applied at predetermined time intervals to the subject (pulse irradiation) or continuously applied without interruption at a low dose rate (continuous irradiation) It means to acquire multiple images that show the movement of the subject. A series of images obtained by dynamic imaging are called dynamic images. Further, each of a plurality of images constituting a dynamic image is called a frame image. In the following embodiment, a case of performing dynamic imaging of the chest by pulse irradiation will be described as an example.

The radiation source 11 is disposed at a position facing the radiation detection unit 13 across the subject M (subject), and irradiates the subject M with radiation (X-rays) according to the control of the radiation irradiation control device 12.
The radiation irradiation control apparatus 12 is connected to the imaging console 2 and controls the radiation source 11 based on the radiation irradiation conditions input from the imaging console 2 to perform radiation imaging. The radiation irradiation conditions input from the imaging console 2 include, for example, pulse rate, pulse width, pulse interval, number of imaging frames per imaging, X-ray tube current value, X-ray tube voltage value, additional filter type, etc. It is. The pulse rate is the number of times of radiation irradiation per second, and matches the frame rate described later. The pulse width is the irradiation time per irradiation. The pulse interval is the time from the start of one radiation irradiation to the start of the next radiation irradiation, and matches the frame interval described later.

The radiation detection unit 13 is configured of a semiconductor image sensor such as an FPD (Flat Panel Detector). The FPD has, for example, a glass substrate or the like, detects radiation transmitted from the radiation source 11 at a predetermined position on the substrate and at least transmitted through the object M according to its intensity, and detects the detected radiation as an electric signal A plurality of detection elements (pixels) which convert into and are stored in a matrix. Each pixel is configured to include, for example, a switching unit such as a TFT (Thin Film Transistor). FPDs include an indirect conversion type in which X-rays are converted into an electrical signal by a photoelectric conversion element through a scintillator, and a direct conversion type in which X-rays are directly converted into an electrical signal, any of which may be used.
The radiation detection unit 13 is provided to face the radiation source 11 across the subject M.

  The reading control device 14 is connected to the imaging console 2. The reading control device 14 controls the switching unit of each pixel of the radiation detection unit 13 based on the image reading condition input from the imaging console 2 to switch the reading of the electric signal accumulated in each pixel. Image data is acquired by reading the electrical signal accumulated in the radiation detection unit 13. This image data is a frame image. Then, the reading control device 14 outputs the acquired frame image to the imaging console 2. The image reading conditions are, for example, a frame rate, a frame interval, a pixel size, an image size (matrix size) and the like. The frame rate is the number of frame images acquired per second, which matches the pulse rate. The frame interval is the time from the start of one frame image acquisition operation to the start of the next frame image acquisition operation, which matches the pulse interval.

  Here, the radiation irradiation control device 12 and the reading control device 14 are connected to each other, exchange synchronization signals with each other, and synchronize the radiation irradiation operation and the image reading operation.

[Configuration of imaging console 2]
The imaging console 2 outputs radiation irradiation conditions and image reading conditions to the imaging device 1 to control the radiation imaging and the radiation image reading operation of the imaging device 1 and, at the same time, captures the dynamic image acquired by the imaging device 1 It is displayed for confirmation as to whether or not the image is suitable for the confirmation of the positioning and the diagnosis by the photographer.
As shown in FIG. 1, the imaging console 2 includes a control unit 21, a storage unit 22, an operation unit 23, a display unit 24, and a communication unit 25, and the units are connected by a bus 26.

The control unit 21 includes a central processing unit (CPU) and a random access memory (RAM).
And so on. The CPU of the control unit 21 reads out the system program and various processing programs stored in the storage unit 22 according to the operation of the operation unit 23, develops the program in the RAM, and performs photographing control processing described later according to the developed program. The various processes to be performed are executed to centrally control the operation of each part of the imaging console 2 and the radiation irradiation operation and the reading operation of the imaging device 1.

  The storage unit 22 is configured by a non-volatile semiconductor memory, a hard disk or the like. The storage unit 22 stores data such as parameters necessary for execution of processing by the various programs or programs executed by the control unit 21 or processing results. For example, the storage unit 22 stores a program for executing the photographing control process shown in FIG. Further, the storage unit 22 stores the radiation irradiation condition and the image reading condition in association with the examination target site (here, the chest). The various programs are stored in the form of readable program code, and the control unit 21 sequentially executes operations according to the program code.

  The operation unit 23 includes a keyboard having cursor keys, numeric input keys, various function keys and the like, and a pointing device such as a mouse, and controls a command signal input by key operation on the keyboard or mouse operation. Output to 21 In addition, the operation unit 23 may include a touch panel on the display screen of the display unit 24. In this case, the operation unit 23 outputs an instruction signal input via the touch panel to the control unit 21.

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

  The communication unit 25 includes a LAN adapter, a modem, a TA (Terminal Adapter), and the like, and controls data transmission and reception with each device connected to the communication network NT.

[Configuration of console 3 for diagnosis]
The diagnostic console 3 performs area extraction from the dynamic image in the dynamic image acquired from the imaging console 2 under the search condition based on the size of the attention area designated by the user and the image feature amount, and displays the extracted area Is a device for assisting the diagnosis of a doctor.
As shown in FIG. 1, the diagnostic console 3 includes a control unit 31, a storage unit 32, an operation unit 33, a display unit 34, and a communication unit 35, and the respective units are connected by a bus 36.

  The control unit 31 includes a CPU, a RAM, and the like. The CPU of the control unit 31 reads out the system program stored in the storage unit 32 and various processing programs in response to the operation of the operation unit 33, develops the program in the RAM, and executes the area extraction process A according to the expanded program. And various other processes are performed to centrally control the operation of each part of the diagnostic console 3. The control unit 31 functions as a size acquisition unit, a feature quantity calculation unit, a search condition generation unit, and an extraction unit.

  The storage unit 32 is configured by a non-volatile semiconductor memory, a hard disk or the like. The storage unit 32 stores various programs including a program for executing the difference image display process A in the control unit 31, parameters necessary for executing the process by the program, and data such as processing results. These various programs are stored in the form of readable program code, and the control unit 31 sequentially executes operations according to the program code.

  Also, in the storage unit 32, dynamic images captured in the past are patient information (for example, patient ID, patient's name, height, weight, age, sex, etc.), examination information (for example, examination ID, examination date, It is stored in association with the target site (here, the chest) or the like.

  The operation unit 33 includes a keyboard having cursor keys, numeric input keys, various function keys and the like, and a pointing device such as a mouse, and receives an instruction signal input by a key operation or mouse operation on the keyboard by the user. It is output to the control unit 31. In addition, the operation unit 33 may include a touch panel on the display screen of the display unit 34. In this case, the operation unit 33 outputs an instruction signal input via the touch panel to the control unit 31. The operation unit 33 functions as a region designation unit, a viewpoint designation unit, and a lesion level designation unit.

  The display unit 34 is configured of a monitor such as an LCD or a CRT, and performs various displays in accordance with an instruction of a display signal input from the control unit 31.

  The communication unit 35 includes a LAN adapter, a modem, a TA, and the like, and controls data transmission and reception with each device connected to the communication network NT.

[Operation of Diagnosis Support System 100]
Next, the operation of the diagnosis support system 100 in the present embodiment will be described.

(Operation of photographing device 1, photographing console 2)
First, the photographing operation by the photographing device 1 and the photographing console 2 will be described.
FIG. 2 shows the imaging control process executed by the control unit 21 of the imaging console 2. The photographing control process is executed by the cooperation of the control unit 21 and the program stored in the storage unit 22.

  First, the operator of the imaging console 2 operates the operation unit 23 of the imaging console 2 to input patient information and examination information of a subject (subject M) (step S1).

  Next, radiation irradiation conditions are read from the storage unit 22 and set in the radiation irradiation control device 12, and image reading conditions are read from the storage unit 22 and set in the reading control device 14 (step S2).

  Next, a radiation irradiation instruction by the operation of the operation unit 23 is on standby (step S3). Here, the photographer performs positioning by placing the subject M between the radiation source 11 and the radiation detection unit 13. In addition, it instructs the subject (subject M) a breathing state. When the imaging preparation is completed, the operation unit 23 is operated to input a radiation irradiation instruction.

  When a radiation irradiation instruction is input from the operation unit 23 (step S3; YES), a photographing start instruction is output to the radiation irradiation control device 12 and the reading control device 14, and dynamic imaging is started (step S4). That is, radiation is irradiated by the radiation source 11 at pulse intervals set in the radiation irradiation control device 12, and a frame image is acquired by the radiation detection unit 13.

  When imaging of a predetermined number of frames is completed, the control unit 21 outputs an instruction to finish imaging to the radiation irradiation control device 12 and the reading control device 14, and the imaging operation is stopped. The number of frames to be captured is the number of images that can be captured at least one breathing cycle.

  The frame images acquired by shooting are sequentially input to the shooting console 2 and stored in the storage unit 22 in association with the number (frame number) indicating the shooting order (step S5) and displayed on the display unit 24. (Step S6). The imaging operator confirms positioning and the like based on the displayed dynamic image, and determines whether an image suitable for diagnosis is acquired by imaging (imaging OK) or whether reimaging is necessary (imaging NG). Then, the operation unit 23 is operated to input the determination result.

  When a determination result indicating shooting OK is input by a predetermined operation of the operation unit 23 (step S7; YES), an identification ID for identifying a dynamic image or the like in each of a series of frame images acquired by dynamic shooting or Information such as patient information, examination information, radiation irradiation conditions, image reading conditions, numbers indicating the imaging order (frame numbers) is attached (for example, written in the header area of image data in DICOM format), and the communication unit 25 is It is transmitted to the diagnostic console 3 via the interface (step S8). Then, the process ends. On the other hand, when a determination result indicating shooting NG is input by a predetermined operation of the operation unit 23 (step S7; NO), a series of frame images stored in the storage unit 22 are deleted (step S9). finish. In this case, re-shooting is required.

(Operation of diagnostic console 3)
Next, the operation of the diagnostic console 3 will be described.
In the diagnostic console 3, when a series of frame images of the dynamic image is received from the imaging console 2 via the communication unit 35, an area is generated by cooperation of the control unit 31 and the program stored in the storage unit 32. Extraction processing A is performed.

  FIG. 3 is a flowchart showing the flow of the area extraction process A, and FIG. 4 is a diagram showing user operation in the area extraction process A. The region extraction processing A will be described below with reference to FIGS.

First, the received dynamic image is displayed on the area designation screen of the display unit 34 (step S11).
The area designation screen is a screen for the user to designate the attention area from the dynamic image, and for example, the frame image of the received dynamic image is displayed by the operation unit 33 so as to be sequentially switched and displayed.
The user observes each frame image of the displayed dynamic image, and if there is a focused area suspected of being a lesion, the pointing device of the operation unit 33 designates the position of the focused area on the frame image. For example, the region of interest is surrounded by the pointing device of the operation unit 33. Based on the operation (gesture) of the pointing device of the operation unit 33 when this attention area is specified, which of the lesion level areas more serious than the attention area, the equivalent area, and the slight area is extracted from the dynamic image Can be specified. For example, when the attention area is surrounded from the lower side to the upper side of the attention area, extraction of a more severe area than the attention area can be designated. When the attention area is surrounded from the upper side to the lower side of the attention area, extraction of a smaller area than the attention area can be designated. When the attention area is surrounded from the lateral direction of the attention area, extraction of an area equivalent to the attention area can be designated. That is, designation of a lesion level can be efficiently performed simultaneously with designation of a region of interest.

Next, it is determined by the operation unit 33 whether or not the attention area is designated from at least one frame image of the dynamic image (step S12).
When it is determined that the attention area is designated (step S12; YES), an annotation is attached to the designated area of the frame image displayed on the display unit 34 (step S13).

G1 in FIG. 4 shows an example of a frame image in which the annotation A1 is added to the designated focused area. In G1 of FIG. 4, the case where the designated attention area is surrounded by solid-line circle annotation A1 is shown as an example.
Note that not the area designated by the operation unit 33 itself, but a partial area of the designated area or an area including pixels in the vicinity may be recognized as the designated attention area. For example, when pixel signal values within the range of pixel signal values within a designated area exist in an adjacent area, the area may be included and recognized as an attention area. As a result, it is possible to improve the specification accuracy of the attention area.

Next, the operation of the pointing device of the operation unit 33 at the time of specification of the attention area is analyzed, and based on the operation of the pointing device at the time of specification of the attention area, the lesion level compared with the attention area of the area extracted from the dynamic image is identified. (Step S14).
For example, when the region of interest is surrounded upward from the lower side of the region of interest by the pointing device of the operation unit 33, the lesion level of the region to be extracted is specified more severe than the region of interest. When the attention area is surrounded from the upper side to the lower side of the attention area, the lesion level of the extraction area is specified to be smaller than the attention area. When the region of interest is surrounded in the lateral direction of the region of interest, the lesion level of the region to be extracted is identified as being equal to the region of interest.

  Next, the size (size) of the designated region of interest is measured. For example, the size of the designated focused area is measured based on the number of pixels in the designated focused area (step S15).

  Next, a menu M1 for the user to select from which point of view the area is selected is displayed in the vicinity of the designated area of interest, and designation of the point of view when the area of interest is specified is accepted (step S16) ). As a viewpoint, as shown in the menu M1 of FIG. 4, for example, ventilation, blood flow, and tumor can be designated. Multiple designations are also possible.

Next, an image feature amount according to the designated viewpoint is calculated for the designated attention area (step S17).
Hereinafter, an example of calculation of the image feature amount in each of the cases of ventilation, blood flow, and tumor will be described. Here, with regard to ventilation and blood flow, image feature quantities based on temporal changes in pixel signal values of a designated attention area are calculated. For a tumor, an image feature amount in a designated frame image of a designated region of interest may be calculated (case 1), or an image feature amount based on a temporal change of pixel signal values of the designated region of interest May be calculated (case 2). It is possible to set in advance which image feature amount to calculate according to the user's operation.

(1) When the viewpoint is ventilation First, low-pass filter processing in the time direction is performed on pixel signal values of the dynamic image. Specifically, the temporal change of the pixel signal value is obtained for each pixel of the dynamic image, and filtering is performed with a low pass filter (for example, high frequency cutoff frequency 0.85 Hz) in the time direction. Thereby, the high frequency component by a blood flow etc. can be removed and the signal component of ventilation can be acquired. In addition, the low-pass filter processing is performed after performing the well-known local matching processing and warping processing (refer to JP 2012-5729 A) between the frame images to correct the positional deviation of the lung field between the frame images. It is also good.
Next, the designated regions of interest are associated between the frame images. For example, an area at the same pixel position (coordinates) as the designated area of interest is associated as an area of interest in another frame image.
Then, in the attention area of each frame image, the average of the pixel signal values is calculated, and the average of the pixel signal values in the reference frame image (for example, maximum expiratory position and maximum inspiratory position) and the pixel signal values in each frame image are calculated. A difference value with the average is calculated, and the maximum value (absolute value) of the calculated difference is calculated as an image feature amount of the attention area related to ventilation. This image feature value indicates a large (high) value as the ventilation function works sufficiently. That is, the larger the image feature amount is, the smaller the lesion is, and the smaller the smaller the lesion is.

(2) When the viewpoint is blood flow First, high-pass filter processing in the time direction is performed on pixel signal values of the dynamic image. Specifically, the temporal change of the pixel signal value is obtained for each pixel of the dynamic image, and the filtering is performed with a high pass filter (for example, low cutoff frequency 0.80 Hz) in the time direction. Thereby, the low frequency component by ventilation etc. can be removed and the signal component of a blood flow can be acquired. In addition, as high-pass filter processing is performed after correcting positional deviation of the lung field region between frame images by performing known local matching processing and warping processing (refer to JP 2012-5729 A) between frame images. It is also good.
Next, the designated regions of interest are associated between the frame images. For example, an area at the same pixel position (coordinates) as the designated area of interest is associated as an area of interest in another frame image.
Then, in the attention area of each frame image, the average of pixel signal values is calculated, the difference value of the average of pixel signal values between adjacent frame images is calculated, and the calculated maximum value (absolute value) It calculates as an image feature quantity of the attention field which concerns on. This image feature value indicates a large (high) value as the blood flow function works sufficiently. That is, the larger the image feature amount is, the smaller the lesion is, and the smaller the smaller the lesion is.
Alternatively, in the region of interest of each frame image, the average of pixel signal values is calculated, and the average of pixel signal values in the reference frame image (for example, the phase where the heart expanded most) and the average of pixel signal values in each frame image And the maximum value (absolute value) of the calculated difference is calculated as the image feature amount of the region of interest related to the blood flow. This image feature value indicates a large (high) value as the blood flow function works sufficiently. That is, the larger the image feature amount is, the smaller the lesion is, and the smaller the smaller the lesion is.

(3) When the viewpoint is a tumor (3-1) Case 1
First, an evaluation value indicating a tumor likeness is calculated for each pixel of a designated attention area (an attention area in a designated frame image), and an average of the calculated evaluation values is used as an image feature amount of the designated attention area. calculate. There is no particular limitation on the evaluation value indicating the tumor-likeness, but, for example, a known evaluation value such as the evaluation value described in Japanese Patent No. 2582666 can be used.
(3-2) Case 2
First, the designated regions of interest are associated between the frame images. For example, an area at the same pixel position (coordinates) as the designated area of interest is associated as an area of interest in another frame image. Alternatively, after performing known local matching processing and warping processing (refer to JP 2012-5729A) between frame images to correct the positional deviation of the lung field region between the frame images, the designated attention region An area at the same pixel position may be associated as an attention area in another frame image.
Next, an average of pixel signal values of each pixel in the attention area of the frame image is obtained, and (maximum value-minimum value) of the calculated pixel signal value (average) is calculated as an image feature amount of the attention area in the tumor. Tumors with less temporal change in pixel signal values are more likely to be malignant, such as being harder or adhering to other organs. Conversely, tumors with large temporal changes in pixel signal values are likely to be benign, such as being soft and moving well. That is, the larger the calculated image feature amount, the smaller the lesion is, and the smaller the lesion is.
Alternatively, the variance between frame images of the average of the pixel signal value of each pixel in the focus area of the frame image may be calculated, and the value of the calculated variance may be calculated as the image feature amount of the focus area related to the tumor. . The greater the calculated variance, the more likely it is to move softer and better. The smaller the calculated variance, the harder it is or adhesion to other organs is likely to be malignant. That is, the larger the calculated image feature amount, the smaller the lesion is, and the smaller the lesion is.

Next, a search condition of a region to be extracted from the dynamic image is generated using the designated size of the noted region and the calculated image feature amount (step S18).
For example, a region having a size substantially equal to the size of the region of interest, which is larger (equal to or smaller than) the image feature amount of the region of interest, is generated as a search condition of the region for extracting from the dynamic image. Note that the user can set in advance what percentage up and percentage down sizes are regarded as equal to the size of the attention area. In addition, whether the image feature quantity extracts an area larger than the image feature quantity of the attention area, extracts an equal area, or extracts a smaller area, the lesion level of the area to be extracted identified in step S14 and It is determined by a combination of types of image feature amounts of the region of interest calculated in step S17.

  For example, an average of pixel signal values of a region of interest in a frame image (for example, maximum expiratory position or maximum inspiratory position) in which an image feature value calculated for a region of interest is a reference and an average of pixel signal values of a region of interest in each frame image The image feature is smaller than the image feature of the region of interest, which is the maximum value of the difference value between the two and the size of the region of interest when the designated lesion level is severe. An area is generated as a search condition. If the designated lesion level is equal, a region having a size substantially equal to the size of the region of interest, and in which the image feature amount is equal to the image feature amount of the region of interest is generated as a search condition. When the designated lesion level is minor, a region having a size substantially equal to the size of the region of interest, which is larger than the image feature amount of the region of interest, is generated as the search condition.

  For example, if the image feature value calculated for the region of interest is the maximum value of the average difference value of pixel signal values of the region of interest between adjacent frame images, and the designated lesion level is severe, A region having a size substantially equal to the size and having an image feature smaller than the image feature of the region of interest is generated as a search condition. If the designated lesion level is equal, a region having a size substantially equal to the size of the region of interest, and in which the image feature amount is equal to the image feature amount of the region of interest is generated as a search condition. When the designated lesion level is minor, a region having a size substantially equal to the size of the region of interest, which is larger than the image feature amount of the region of interest, is generated as the search condition.

  For example, when the image feature quantity calculated for the attention area is the image feature quantity of case 1 of the above-mentioned tumor viewpoint, and the designated lesion level is severe, an area of approximately the same size as the size of the attention area That is, a region where the image feature amount is larger than the image feature amount of the region of interest is generated as a search condition. If the designated lesion level is equal, a region having a size substantially equal to the size of the region of interest, and in which the image feature amount is equal to the image feature amount of the region of interest is generated as a search condition. When the designated lesion level is minor, a region having a size substantially equal to the size of the region of interest and in which the image feature amount is smaller than the image feature amount of the region of interest is generated as a search condition.

  For example, if the image feature value calculated for the region of interest is (maximum value-minimum value) in case 2 of the above-mentioned tumor viewpoint, and the designated lesion level is severe, the size of the region of interest is approximately equal. An area having a size that is smaller than the image feature quantity of the attention area is generated as a search condition. If the designated lesion level is equal, a region having a size substantially equal to the size of the region of interest, and in which the image feature amount is equal to the image feature amount of the region of interest is generated as a search condition. When the designated lesion level is minor, a region having a size substantially equal to the size of the region of interest, which is larger than the image feature amount of the region of interest, is generated as the search condition.

  For example, when the image feature value calculated for the region of interest is the variance of Case 2 of the above-mentioned tumor viewpoint, and the designated lesion level is severe, the region is approximately equal in size to the size of the region of interest. Thus, an area where the image feature quantity is smaller than the image feature quantity of the attention area is generated as a search condition. If the designated lesion level is equal, a region having a size substantially equal to the size of the region of interest, and in which the image feature amount is equal to the image feature amount of the region of interest is generated as a search condition. When the designated lesion level is minor, a region having a size substantially equal to the size of the region of interest, which is larger than the image feature amount of the region of interest, is generated as the search condition.

  The regions to be extracted may be defined as a predetermined number of regions among the regions matching the search condition. For example, when an image feature quantity larger than the attention area is searched, areas for a prescribed number are extracted from those having a large image feature quantity, and when an image feature quantity smaller than the attention area is searched, an image feature quantity is small A predetermined number of regions may be extracted from In addition, when the calculated image feature quantity has a trend depending on the region of the lung field (for example, the lower lung is larger than the upper lung, etc.), the trend may be corrected.

Next, an area corresponding to the generated search condition is extracted from the dynamic image (step S19).
For example, as shown in FIG. 5, when the image feature calculated from the attention area is the image feature related to the above-mentioned ventilation or blood flow, the search condition is shifted while the position is shifted by one pixel from the upper left of the dynamic image. A search area of a designated size is set, and for the set search area, the same image feature quantity as the image feature quantity calculated for the attention area is calculated, and the calculated image feature quantity and the value of the image feature quantity of the attention area Extract regions where the magnitude relationship matches the search condition.
For example, when the image feature quantity calculated from the region of interest is the image feature quantity of the above case 1 of a tumor, for example, known abnormal shadow candidate detection processing is performed on each frame image of the dynamic image to Detect a suspected abnormal shadow candidate area. As the abnormal shadow candidate detection process, for example, the method described in Japanese Patent No. 2582666 can be used. Then, for each of the detected abnormal shadow candidate areas, for the area whose size matches the search condition, the same image feature quantity as the attention area is calculated, and the calculated image feature quantity and the size relation of the image characteristic quantity of the attention area Extracts the region that matches the search condition.
For example, if the image feature calculated from the region of interest is the image feature of Case 2 described above pertaining to a tumor, for example, a known abnormal shadow candidate detection process is performed on one frame image of the dynamic image, and the tumor is An abnormal shadow candidate area suspected of being detected. As the abnormal shadow candidate detection process, for example, the method described in Japanese Patent No. 2582666 can be used. Next, among the detected abnormal shadow candidate areas, the image feature quantity that is the same as the attention area is calculated for the area whose size matches the search condition, and the calculated image feature quantity and the image feature quantity of the attention area have a magnitude relationship. Extract the region that matches the search condition.
The region to be searched may be only the lung region.

  Then, the extracted area is displayed on the display unit 34 (step S20), and the area extraction processing A ends.

  6A and 6B show an example of the area extraction result displayed in step S20. FIG. 6A shows a display example in which ventilation, blood flow, and tumor are designated as viewpoints, and an area is extracted from the ventilation viewpoint in the upper left lung and an area is extracted from the blood flow viewpoint in the lower left lung. It shows. FIG. 6B shows a display example in the case where a tumor is designated as a viewpoint and a region is extracted in the right middle lung of a frame image captured at a timing different from that of the frame image designated the region of interest. ing. The pattern (color) of each viewpoint in the menu M1 displayed to select the viewpoint in step S16 corresponds to the pattern (color) of the annotation indicating the search result.

As described above, according to the diagnostic console 3 in the first embodiment, the search condition of the area to be extracted is generated based on the size of the notable area and the image feature amount designated by the user from the frame image of the dynamic image. The area extracted based on the generated search condition is identifiably displayed on the dynamic image displayed on the display unit. Therefore, it is possible to support an efficient diagnosis without an oversight based on a user-designated attention area.
In addition, a menu M1 is displayed for the user to designate which of the ventilation, blood flow, and tumor viewpoints the attention region has been designated, and an image according to the size of the attention region and the designated viewpoint Since the search is performed based on the feature amount, it is possible to present to the user the lesion area of the viewpoint that the user is focusing on.
In addition, since the search is performed based on the user-specified lesion level (whether it is serious, equal to, or less than the region of interest), the region of the lesion level desired by the user is extracted and presented to the user Is possible. Since the lesion level can be designated by the operation of the pointing device when the user designates the region of interest, the lesion level can be designated efficiently.

Second Embodiment
Next, a second embodiment of the present invention will be described.
In the second embodiment, the search condition of the region to be extracted is generated from the analysis result image of the dynamic image based on the size of the region of interest specified by the user and the image feature amount, and the analysis is performed based on the generated search condition. An example of extracting a region to be presented to the user from the result image will be described.

  The configuration in the second embodiment is the same as that described in the first embodiment, except that a program for executing the area extraction process B is stored in the storage unit 32 of the diagnostic console 3. Use the explanation. Further, the operations of the imaging apparatus 1 and the imaging console 2 in the second embodiment are the same as those described in the first embodiment, and therefore, the description will be used. Will be explained.

  FIG. 7 is a flowchart showing an area extraction process B performed by the diagnostic console 3 in the second embodiment. The area extraction processing B is executed by cooperation of the control unit 31 and the program stored in the storage unit 32.

First, analysis processing is performed on the received dynamic image to generate an analysis result image (step S21). The analysis result image is an image showing an analysis result when analysis of the function of ventilation or blood flow is performed for each pixel or for each block of a plurality of pixels with respect to the dynamic image.
In step S21, for example, a menu screen for selecting whether to analyze the ventilation function or the blood flow function is displayed on the display unit 34, and the type of analysis selected by the operation unit 33 is displayed. To be executed.

  For example, when the analysis relating to the ventilation function is selected, first, low-pass filter processing in the time direction is performed in the lung region of the dynamic image in step S21. Specifically, the temporal change of the pixel signal value is obtained for each pixel of the dynamic image, and filtering is performed with a low pass filter (for example, high frequency cutoff frequency 0.85 Hz) in the time direction. Next, pixels or blocks of pixels at the same position (coordinates) are associated with one another among a plurality of frame images in the dynamic image after low-pass filter processing. Then, a reference frame image (for example, a frame image of maximum exhalation position or maximum inspiratory position) of pixel signal values (average value of pixel signal values in the case of blocks) for each pixel or each block of plural pixels in each frame image of dynamic image The difference value (absolute value) with the frame image of 1) is calculated, and an analysis result image in which the pixel signal value of each pixel is the difference value is generated.

Also, for example, when the analysis relating to the blood flow function is selected, in step S21, first, high-pass filter processing in the time direction is performed in the lung field region of the dynamic image. Specifically, the time change of the signal value is obtained for each pixel of the dynamic image, and the filtering is performed with a high pass filter (for example, low cutoff frequency 0.80 Hz) in the time direction. Next, pixels or blocks of pixels at the same position (coordinates) are associated with each other between frame images in the dynamic image after high-pass filter processing. Then, for each pixel of each frame image of each dynamic image or each block of a plurality of pixels, a difference value of pixel signal values (an average value of pixel signal values in the case of a block) of adjacent frame images is calculated. Thereby, an analysis result image concerning the blood flow function is generated.
Low-pass filter processing and high-pass filter processing are performed after performing known local matching processing and warping processing between frame images (refer to JP 2012-5729A) to correct positional deviation of the lung field region between frame images. It is good to do.

Next, the generated analysis result image is displayed on the area designation screen of the display unit 34 (step S22).
The area designation screen is a screen for the user to designate the attention area from the analysis result image, and for example, frame images of the analysis result image are sequentially displayed by the operation unit 33 so as to be switched and displayed.
The user observes each frame image of the displayed analysis result image, and if there is a focused area suspected of being a lesion, the pointing device of the operation unit 33 designates the position of the focused area on the frame image. For example, the region of interest is surrounded by the pointing device of the operation unit 33. At this time, as described in the first embodiment, when specifying an attention area, which lesion level of an area that is more serious than the attention area, an equal area, or a slight area is to be retrieved from the analysis result image It can be designated by the operation (gesture) of the pointing device. That is, designation of a lesion level can be efficiently performed simultaneously with designation of a region of interest.

Next, it is determined by the operation unit 33 whether or not the attention area is designated from at least one frame image of the analysis result image (step S23).
When it is determined that the attention area is designated (step S23; YES), an annotation is attached to the designated attention area (step S24). In step S24, not the area designated by the operation unit 33 but a partial area of the designated area or an area including pixels in the vicinity may be recognized as the designated attention area. For example, when pixel signal values within the range of pixel signal values within a specified area exist in an adjacent area, that area may be recognized as an area specified. As a result, it is possible to improve the specification accuracy of the attention area.

  Next, the operation of the pointing device of the operation unit 33 at the time of specification of the attention area is analyzed, and compared with the attention area of the area to be extracted from the analysis result image based on the operation of the pointing device of the operation unit 33 at the time of specification of the attention area. The lesion level of is identified (step S25). The process of step S25 is the same as that described in step S14 of FIG.

  Next, the size (size) of the designated focused area is calculated (step S26). For example, the size of the designated focused area is calculated based on the number of pixels in the designated focused area.

Next, the image feature amount of the designated attention area is calculated (step S27).
For example, an average of pixel signal values is calculated in a target area of each frame image of the analysis result image (an area having the same pixel position (coordinates) as the specified target area), and the maximum value of the average of the calculated pixel signal values An absolute value is calculated as an image feature amount of the region of interest.

  Next, a search condition of a region to be extracted from the analysis result image is generated using the size of the designated region of interest and the calculated image feature amount (step S28). For example, a region having a size substantially equal to the size of the region of interest, which is larger (equal or smaller) than the image feature amount of the region of interest, is generated as a search condition of the region extracted from the analysis result image . Note that the user can set in advance what percentage up and percentage down sizes are regarded as equal to the size of the attention area. In addition, whether the image feature quantity extracts an area larger than the image feature quantity of the attention area, extracts an equal area, or extracts a smaller area depends on the lesion level of the area to be extracted specified in step S25 and It is determined by a combination of types of image feature amounts of the region of interest calculated in step S27.

Next, an area corresponding to the generated search condition is extracted from the analysis result image (step S29).
For example, while shifting the position one pixel at a time from the upper left of the analysis result image, a search area of approximately the same size as the size of the area of interest is set, and for the set search area, the same image as the image feature quantity calculated for the area of interest A feature quantity is calculated, and an area in which the magnitude relation between the calculated image feature quantity and the image feature quantity of the attention area matches the search condition is extracted.

  Then, the extracted area is displayed on the display unit 34 (step S30), and the area extraction processing B ends.

As described above, according to the diagnostic console 3 in the second embodiment, the search condition of the area to be extracted is generated from the frame image of the analysis result image based on the size of the attention area and the image feature amount designated by the user. Then, the area extracted based on the generated search condition is identifiably displayed on the analysis result image displayed on the display unit 34. Therefore, it is possible to support an efficient diagnosis without an oversight based on a user-designated attention area.
In addition, by performing a search based on the lesion level (severe, equal to or less than the attention area) specified by the user, the area of the lesion level desired by the user is extracted and presented to the user It becomes possible.

  As mentioned above, although the 1st and 2nd embodiment of the present invention was described, the contents of a statement in the above-mentioned embodiment are a suitable example of the present invention, and are not limited to this.

  For example, in the first embodiment, the user's ventilation, the blood flow, and the tumor designate which area the attention area is designated by paying attention to the viewpoint, and calculates the image feature amount according to the designated viewpoint, Although it has been used as a search condition, for example, in a dedicated system that supports the diagnosis of a tumor, designation of a viewpoint by the user is unnecessary, and an image feature value related to a tumor may be automatically calculated. .

  Further, for example, in the first and second embodiments, the user can specify the lesion level of the area to be extracted from the dynamic image or the analysis result image, but without accepting the specification of the lesion level by the user, It is also possible to extract an area of a predetermined lesion level (for example, an area of a lesion that is more severe than the attention area).

  Further, in the above embodiment, it has been described that the lesion level is specified by the operation of the pointing device at the time of specifying the attention area, but for example, a selection menu of lesion levels such as severe, equivalent, and minor is displayed The user may select a desired level using the operation unit 33.

  Further, the image feature amount is not limited to that described above. For example, instead of the maximum value or the variance of the difference values of the pixel signal values (average) between the frames described above, the first derivative or the second derivative of the pixel signal values (average) may be used.

  In the above embodiment, an example in which the present invention is applied to the case where the region extraction is performed from the chest dynamic image or its analysis result image has been described, but the region extraction from the dynamic image obtained by photographing other parts or the analysis result image The present invention may be applied to the case where

  Further, for example, in the above description, although an example using a hard disk, a non-volatile memory of a semiconductor, or the like as a computer readable medium of a program according to the present invention has been disclosed, the present invention is not limited thereto. As another computer readable medium, a portable recording medium such as a CD-ROM can be applied. In addition, carrier wave (carrier wave) is also applied as a medium for providing data of the program according to the present invention through a communication line.

  In addition, the detailed configuration and the detailed operation of each device constituting the diagnosis support system can be appropriately changed without departing from the scope of the present invention.

100 diagnosis support system 1 imaging device 11 radiation source 12 radiation irradiation control device 13 radiation detection unit 14 reading control device 2 imaging console 21 control unit 22 storage unit 23 operation unit 24 display unit 25 communication unit 26 bus 3 diagnostic console 31 control Unit 32 Storage unit 33 Operation unit 34 Display unit 35 Communication unit 36 Bus

Claims (8)

The user pays attention by using at least one frame image in the dynamic image obtained by radiographing the dynamic of the living body or the analysis result of the dynamic analysis of each pixel or block of plural pixels of the dynamic image. Area specification means for specifying an area;
Size acquiring means for acquiring the size of the area of interest specified by the area specifying means;
Feature quantity calculation means for calculating an image feature quantity of the attention area designated by the area designation means;
A search condition of a region to be extracted from the dynamic image or the analysis result image based on the size of the region of interest acquired by the size acquisition unit and the image feature amount of the region of interest calculated by the feature amount calculation unit Search condition generation means for generating
Extracting means for extracting an area corresponding to the search condition generated by the search condition generation means from the dynamic image or the analysis result image;
Display means for identifiably displaying the area extracted by the extraction means in the dynamic image or the analysis result image;
Diagnostic support system comprising:   The diagnosis support system according to claim 1, wherein the feature amount calculation unit calculates an image feature amount based on a temporal change of pixel signal values in the attention area. When a region of interest is specified from the dynamic image, a viewpoint specification unit is provided for the user to specify which of a plurality of predetermined viewpoints the user has specified the region of interest.
The diagnosis support system according to claim 1, wherein the feature amount calculation unit calculates an image feature amount of the attention area designated by the region designation unit according to the viewpoint designated by the viewpoint designation unit. The movement image is a chest movement image obtained by radiographing movement of the chest of the living body,
The diagnosis support system according to claim 3, wherein the viewpoint specifying means can specify at least one of ventilation, blood flow, and tumor. A lesion level designation unit for the user to designate a lesion level compared with the target region of the region extracted from the dynamic image or the analysis result image;
The search condition generation unit generates the search condition based on the size of the region of interest, the image feature amount of the region of interest, and the lesion level designated by the lesion level designation unit. The diagnosis support system according to one item.   6. The diagnosis support system according to claim 5, wherein the lesion level designation means is for the user to designate whether the area to be extracted is severe, equal or minor compared to the attention area. The area specifying means includes a pointing device
The diagnosis support system according to claim 5 or 6, wherein the lesion level designation unit designates the lesion level by an operation of the pointing device when the region designation unit designates the region of interest.   The area specifying means specifies an area including a partial area of the area specified by the user or an area near the specified area as the noted area specified by the user. The diagnosis support system according to one item.

Images