JP2005261839A - Photographic image generation system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a photographic image generation system capable of processing a breast image speedily. <P>SOLUTION: In the photographic image generation system 1, when a photographic image generated by readers 30a and 30b is the breast image, a controller 20m obtains a plurality of breast images of the same patient, sorts the group of the breast images to a plurality of image processing means to be distributed to image processors 40x and 40y, and instructs various kinds of image processing such as detection processing, gradation processing of an abnormal shadow candidate. Then, the controller 20m composites respective breast images image-processed by the image processors 40x and 40y to prepare a composite image for reading shadows. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a captured image generation system that generates a captured image of a patient, performs image processing on the captured image, and generates a processed image.

  At present, digitization of medical images obtained by examination imaging and the like has been realized, and a computer radiographic imaging apparatus (hereinafter referred to as CR; Computed Radiography) and a nuclear magnetic resonance imaging apparatus (hereinafter referred to as MRI; Magnetic Resonance Imaging). When a digital image data is obtained by a tomographic imaging apparatus (hereinafter referred to as CT; Computed Tomography) or the like, a captured image generation system is used that distributes it to an image management apparatus or a display apparatus via a communication network (for example, patents). Reference 1).

  In a conventional captured image generation system, a photographing reading device that captures the CR or the like and reads the photographed image as digital data, or when a photograph is taken using a cassette, reads the photographed image recorded in the cassette. A cassette-dedicated reading device and a control device that manages data of the captured image obtained by the imaging reading device and the reading device are connected via a communication network. The captured image generation system is connected to a system for managing information in the radiology department (hereinafter referred to as RIS; Radiology Information System).

  In the radiographic image generation system configured as described above, radiographing order information (instruction information for instructing radiographing target patient, radiographing site, radiographing method, etc.) is first issued in response to a request from a doctor at the RIS and transmitted to the control device. Is done. Shooting order information is displayed on the control device, and the shooting engineer performs shooting on the shooting device in accordance with the displayed shooting order information. After shooting, a shooting reading device such as a CR generates shot image data and transmits it to the control device. On the other hand, when photographing is performed using the cassette, the photographing engineer attaches the cassette to the reading device and causes the data to be read. In the reading device, the data of the photographed image is read from the attached cassette and transmitted to the control device. In the control device, various image processes are performed on the received captured image so that it can be confirmed whether or not an image suitable for interpretation is captured, and the captured image subjected to the image processing is displayed on the monitor.

In general, when a breast image (this is called mammography) is taken, since the breast image requires high image quality, a higher-definition reading process is performed than in the case of other imaging parts, and further referred to as phase contrast imaging. It is predicted that shooting with the shooting method will increase. As a result, in the case of a breast image, the data capacity becomes large. For example, a captured image of another part (this is referred to as a general image) is an 18 × 24 inch (six-cut size) cassette and has a read pixel size of 87.5 μm, whereas in the case of a breast image, 43. 75 μm. That is, the breast image has a data capacity about four times that of a general image. In addition, when shooting is performed using the phase contrast imaging method, the size of the cassette used for the shooting is twice that of normal shooting, and the read pixel size is halved. It is about 16 times the image.
Japanese Patent Laid-Open No. 2000-276587

  As described above, since the breast image has a very large data capacity of 4 times or 16 times as compared with the captured images of other imaging regions, a considerable time is required for the image processing. Therefore, when a breast image is taken and the image processing is performed by the control device, other processing cannot be performed by the control device during the image processing, and other processing in the control device is delayed. This delays the processing in the system as a whole. In addition, if the photographed image is confirmed, the subject may be re-photographed because the position of the subject is bad or blurred, so the patient must wait until the photographed image is confirmed. The longer the time, the longer the patient's waiting time, which puts a burden.

  Furthermore, in the case of a breast image, the right and left breasts can be imaged in different imaging directions, such as the vertical direction and the oblique direction, for a single patient, and a comprehensive diagnosis can be performed from these multiple breast images. Many. In recent years, it has begun to arrange a plurality of breast images taken for the same patient side by side and output them on the same film. For example, a breast image obtained by photographing the left breast vertically and a right breast photographed vertically The breast image is output to the same film, and the breast image obtained by photographing the left breast in the oblique direction and the breast image obtained by photographing the right breast in the oblique direction are output to the same film, and the two films are used. There are many interpretation styles such as interpretation of four images at once.

  However, even when a plurality of images of the same patient are output together on a single film as described above, the control device must individually perform image processing on the breast image to be output. Time is taken up. In addition, when imaging is performed using a cassette, the reading process for breast images is high-definition as described above, so that not only does it take time to read one image, but also a plurality of images for one patient. It takes a considerable amount of time to read all breast images with the same reading device.

  The subject of this invention is providing the picked-up image generation system which can process a breast image rapidly.

The invention according to claim 1 is a captured image generation system,
Image generation means for generating a captured image of the patient;
A plurality of image processing means for performing image processing on the captured image;
Of the captured images generated by the image generating means, a plurality of breast images for one patient are acquired, the acquired plurality of breast images are classified for each related image, and a group of classified breast images is obtained. Control means for distributing the image processing to the plurality of image processing means;
It is characterized by providing.

The invention according to claim 2 is a captured image generation system,
Reading means for reading the captured image from the cassette in which the captured image of the patient is recorded;
A plurality of image processing means for performing image processing on the captured image;
A plurality of breast images for one patient read by the reading unit are acquired, the acquired plurality of breast images are classified for each related image, and the classified breast image group is classified into the plurality of image processing units. A control means for distributing the images into image processing,
It is characterized by providing.

The invention described in claim 3 is the captured image generation system according to claim 1 or 2,
The control means classifies a plurality of breast images for one patient for each imaging region of the left breast and the right breast, and a group of breast images classified as the left breast is classified as a right breast by one image processing means. The breast image group is distributed to other image processing means.

The invention according to claim 4 is the captured image generation system according to claim 1 or 2,
The control means classifies a plurality of breast images for one patient for each imaging direction, and distributes the classified breast image groups to different image processing means.

The invention according to claim 5 is a captured image generation system,
A plurality of reading means for reading the captured image from a cassette in which a breast image of the patient is recorded;
A plurality of image processing means for performing image processing on the breast image;
Control means for acquiring a plurality of breast images of the same patient obtained by controlling the plurality of reading means, and distributing the acquired plurality of breast images to the plurality of image processing means;
It is characterized by providing.

The invention according to claim 6 is the captured image generation system according to any one of claims 1 to 5,
The control means distributes designation information of image processing conditions together with the breast image when sorting the breast image.

The invention according to claim 7 is the captured image generation system according to any one of claims 1 to 6,
The control means acquires each breast image subjected to image processing by the plurality of image processing means and synthesizes each breast image subjected to the image processing to create a composite image.

The invention according to claim 8 is a captured image generation system,
Image generation means for generating a captured image of the patient;
Image processing means for performing image processing on the captured image;
Control means for determining a photographed image to be subjected to image processing by the image processing means from among the photographed images generated by the image generating means, delivering the determined photographed image to the image processing means, and performing image processing; ,
It is characterized by providing.

The invention according to claim 9 is the captured image generation system according to claim 8,
A plurality of the image processing means;
The control means divides a captured image determined to be subjected to image processing by the image processing means into a plurality of regions, and distributes the divided images to the plurality of image processing means for image processing. It is characterized by that.

The invention described in claim 10 is the captured image generation system according to claim 9,
The control means acquires each divided image subjected to image processing in the plurality of image processing means, and combines the divided images subjected to the image processing to restore the original captured image.

The invention according to claim 11 is the captured image generation system according to claim 9 or 10,
The control means distributes image processing condition designation information together with the divided image when the divided image is distributed.

The invention according to claim 12 is the captured image generation system according to any one of claims 8 to 11,
The photographed image to be image-processed by the image processing means is a breast image obtained by photographing a patient's breast.

  According to the first aspect of the present invention, since a breast image that generally has a large data capacity and requires time for image processing is distributed to a plurality of image processing means for image processing, the burden of image processing on the breast image is reduced. It can be distributed and can be processed quickly. In the case of a breast image, since the left and right breasts are photographed for one patient, at least two breast images are obtained. The breast images for one patient are classified, and the classified breast image group is subjected to a plurality of image processing. Since it is distributed to the means, it is possible to efficiently perform image processing of a breast image having a large number of images.

  According to the second aspect of the present invention, since a breast image, which generally has a large data capacity and requires time for image processing, is distributed to a plurality of image processing means for image processing, the burden of image processing on the breast image is reduced. It can be distributed and can be processed quickly. In the case of a breast image, since the left and right breasts are photographed for one patient, at least two breast images are obtained. The breast images for one patient are classified, and the classified breast image group is subjected to a plurality of image processing. Since it is distributed to the means, it is possible to efficiently perform image processing of a breast image having a large number of images.

  According to the invention described in claim 3, since a plurality of breast images for one patient are classified for each imaging part of the left breast and the right breast and are distributed to each image processing means, the same image processing means for each imaging part Image processing.

  According to the invention described in claim 4, since a plurality of breast images for one patient are classified for each imaging direction and distributed to each image processing means, it is possible to perform image processing by the same image processing means for each imaging direction. it can.

  According to the fifth aspect of the present invention, since a plurality of breast images of the same patient are acquired by controlling a plurality of reading means, it is possible to read images almost simultaneously by the plurality of reading means, and generally the data capacity is large. In the case of a large breast image in which a plurality of images are taken for one patient, the reading time of a breast image for one patient is shortened by putting cassettes already photographed for one patient into a plurality of reading means almost simultaneously. be able to. In addition, since a plurality of breast images obtained by reading are distributed to a plurality of image processing means, it is possible to disperse the image processing burden of a breast image having a large amount of data and a large number of images to be taken, and the breast image can be quickly obtained. Can be processed.

  According to the sixth aspect of the invention, since the designation information of the image processing conditions is distributed together with the breast image, the image processing conditions in each image processing means can be unified, and any image processing means can perform image processing. Even if they are combined, it is possible to obtain a breast image that has undergone image processing under the same conditions.

  According to the seventh aspect of the present invention, a synthesized image is created by synthesizing breast images that have been distributed to a plurality of image processing means and subjected to image processing. During diagnosis, multiple breast images for one patient are often combined, arranged, and observed, so even when creating a composite image in this way, image processing for each breast image should be distributed and processed. And a composite image can be created quickly.

  According to the eighth aspect of the present invention, among the generated photographed images, the photographed image to be subjected to image processing by the image processing means is distributed to the image processing means for image processing. For breast images with a large number of images taken, image processing is performed by the image processing means, so that the burden of image processing can be dispersed and breast image processing can be performed quickly. Further, since the control means can execute other processing without taking time for image processing of the breast image, it is possible to improve the overall processing efficiency in the captured image generation system.

  According to the ninth aspect of the present invention, since the captured image is divided into a plurality of regions and each divided image is distributed to a plurality of image processing means, in the case of a breast image or the like having a large data capacity and requiring time for image processing, The burden of processing can be distributed and processing can be performed more quickly.

  According to the tenth aspect of the present invention, since the original images are restored by synthesizing the divided images that have been distributed to the image processing means and subjected to the image processing, one captured image that has undergone image processing as a whole is obtained. be able to.

  According to the eleventh aspect of the invention, since the designation information of the image processing conditions is distributed together with the divided images, the image processing conditions in each image processing unit can be unified, and one captured image is restored from the divided images. In this case, it is possible to obtain a captured image that has been subjected to image processing under the same conditions as a whole.

  According to the twelfth aspect of the present invention, a breast image having a large data capacity and a large number of images taken for one patient requires time for image reading and image processing. By performing image processing in a distributed manner by a plurality of image processing means, breast image processing can be performed quickly.

<First Embodiment>
In the first embodiment, when the captured image is a breast image, a plurality of breast images of the same patient are acquired, and these breast image groups are distributed to a plurality of image processing means to detect abnormal shadow candidates and perform gradation processing. An example will be described in which various image processes such as these are performed, and each breast image processed by these image processing means is combined to create a combined image for interpretation.

First, the configuration will be described.
FIG. 1 shows a system configuration of a captured image generation system 1 in the first embodiment.
As shown in FIG. 1, the captured image generation system 1 includes a job manager 10, control devices 20m and 20n, reading devices 30a to 30c, and image processing devices 40x and 40y. Are connected so that data can be sent and received.

  Although FIG. 1 illustrates an example in which two control devices 20m and 20n, three reading devices 30a to 30c, and two image processing devices 40x and 40y are connected, the number of installed devices is limited to this. do not do.

  The captured image generation system 1 is connected to the RIS 2 via the communication network N. The RIS 2 accepts a request from a doctor and issues imaging order information, and the issued imaging order information identifies identification information (hereinafter referred to as order ID) for identifying the imaging order information from other imaging order information. ). Instead of RIS2, a system for managing information in the hospital (hereinafter referred to as HIS; Hospital Information System) and a reception terminal for issuing and receiving imaging order information may be connected.

Hereinafter, each device of the captured image generation system 1 will be described.
The job manager 10 registers the cassette c in the captured image read from the cassette c, regardless of which reading device 30a to 30c reads the cassette c registered by any of the control devices 20m and 20n. It is a computer that controls to be returned to the control devices 20m and 20n. The job manager 10 stores an image generation management table 11 as shown in FIG. 2, and determines a transmission destination of captured images read by the reading devices 30 a to 30 c based on the image generation management table 11. .

  As shown in FIG. 2, the image generation management table 11 is associated with a captured image number issued to individually identify captured images generated by reading from the cassette c in each of the reading devices 30 a to 30 c. Identification information (hereinafter referred to as a control device ID) of a control device that is a transmission destination of the captured image, and identification information of a cassette registered as a cassette c for recording the captured image in the control device (hereinafter referred to as a cassette ID) , A reading condition for reading a photographed image from the cassette, and a reading end flag indicating whether or not reading of the photographed image from the cassette c has been completed (for example, a flag of “ON” in the case of reading completion) Each item information of “OFF” flag is stored when not completed).

  For example, the job manager 10 reads the cassette ID “1010101” of the registered cassette c from the control device 20m with the control device ID “M10” and the reading pixel size “43.75 μm” as a reading condition when reading a photographed image from the cassette. Is received, information on the control device ID, cassette ID and reading conditions received in association with the photographed image number is stored in the image generation management table 11 and read. Set the end flag to OFF. Then, in any one of the reading devices 30a to 30c, when the photographed image is read from the cassette c having the cassette ID “1010101” and the inquiry of the photographing image reading condition and the transmission destination is received based on the cassette ID, the cassette ID Information on the control device ID “M10” corresponding to “1010101” and the read pixel size “43.75 μm” that is the read condition is read from the image generation management table 11 and returned to the reading devices 30a to 30c that made the inquiry, The reading conditions for the cassette reading process are specified, and an instruction is given to transmit the captured image to the control device 20m with the control device ID “M10”. Thereafter, the reading end flag corresponding to the cassette ID “1010101” inquired is set to “ON”.

Next, the control devices 20m and 20n will be described.
The control devices 20m and 20n acquire the data of the captured images read by the respective reading devices 30a to 30c by controlling the reading operation of the captured images by the reading devices 30a to 30c according to the imaging order information distributed from the RIS 2. Image management is performed by associating the acquired captured image with the managed imaging order information.

Hereinafter, the internal configuration of the control devices 20m and 20n will be described. Since the control devices 20m and 20n have substantially the same configuration, the control device 20m will be described as a representative here.
FIG. 3 shows an internal configuration of the control device 20m.
As illustrated in FIG. 3, the control device 20 m includes a control unit 21, an input unit 22, a display unit 23, a communication unit 24, a RAM (Random Access Memory) 25, and a storage unit 26.

  The control unit 21 includes a CPU (Central Processing Unit) and the like, expands various control programs stored in the storage unit 26 in the RAM 25, and controls each unit according to the expanded control program.

  The control unit 21 stores, as pre-shooting processing, each piece of shooting order information stored in the storage unit 26 in association with the cassette ID of the cassette c used for shooting the shooting order information. This is called cassette registration. When cassette registration is performed, it is determined whether the captured image is a breast image based on the imaging order information registered in the cassette, and reading at the time of cassette reading processing after imaging is performed according to the determination result. Determine the conditions. For example, if it is determined that the image is a captured image other than a breast image (this is referred to as a general image), the read pixel size is determined to be “87.50 μm”, and if it is determined to be a breast image, the read pixel is determined. The size is determined to be a high-definition condition of “43.75 μm”. Then, the registered cassette ID and the determined reading condition information are transmitted to the job manager 10 by the communication unit 24 together with the information of the own control device ID.

Further, after photographing, an image acquisition process (see FIG. 5) and a first image display process (see FIG. 6) according to the present invention are executed.
In the image acquisition process, the reading operation of each of the reading devices 30a to 30c is controlled to acquire the captured image and the cassette ID information of the cassette c in which the captured image is recorded, and the captured image acquired based on the cassette ID. Correlate images with shooting order information. This is called image registration. Specifically, when the captured image is stored in the image DB 262, the order ID of the imaging order information is attached to the captured image as incidental information. Further, when the cassette c is simultaneously inserted in each of the reading devices 30a to 30c and reading is started substantially simultaneously, a captured image read first from any one of the reading devices is acquired, and as soon as the acquisition is finished, Captured images read by other reading devices are acquired, and the reading devices 30a to 30c are controlled in parallel.

  In the first image display process, when displaying a captured image, it is determined whether the captured image is a breast image based on the imaging order information associated with the captured image. If it is another imaging region, various image processes are performed on the captured image and the image is displayed on the display unit 23. On the other hand, if it is a breast image, another breast image of the same patient is acquired from the image DB 262 based on the imaging order information, and distributed to the image processing devices 40x and 40y to instruct image processing. At this time, image processing parameters of the breast image are determined, and information on the determined image processing parameters is distributed together with the breast image so that the image processing conditions in the image processing apparatuses 40x and 40y are unified. When a breast image subjected to image processing is received from each of the image processing devices 40x and 40y, the received breast images are combined to create a combined image, and the combined image is displayed on the display unit 23. That is, the control device 20m is a control unit in the captured image generation system 1.

  The input unit 22 includes a keyboard including numeric keys, character keys, and various function keys, a touch panel configured integrally with the display unit 23, a mouse, and the like, and sends operation signals according to these operations to the control unit 21. Output to. That is, the cassette ID of the cassette c for which cassette registration is performed can be input by the input unit 22. The cassette ID may be converted into a barcode and provided in the cassette c, and the cassette ID may be read and input by providing a barcode reader.

  The display unit 23 includes an LCD (Liquid Crystal Display) or the like, and displays various operation screens such as a shooting order information list screen, a cassette registration screen, and an image confirmation screen, and processing results by the control unit 21.

  The communication unit 24 includes a NIC (Network Interface Card), a modem, and the like, and transmits / receives information to / from an external device. For example, photographing order information is received from the RIS 2 before photographing, and photographed images and cassette IDs are received from the readers 30a to 30c after photographing.

  The RAM 25 forms a work area that temporarily stores various control programs executed by the control unit 21 and data related to these control programs.

  The storage unit 26 is configured by a magnetic or optical recording medium or a semiconductor memory, and stores various control programs such as an image acquisition processing program and an image display processing program, data processed by these control programs, and the like.

  The storage unit 26 includes an order file 261 that stores imaging order information in an updatable manner. In the order file 261, as shown in FIG. 4, shooting order information is stored for each piece of identification information (hereinafter referred to as order ID) for individually identifying shooting order information. The imaging order information includes information about the patient such as the patient ID and name of the patient to be imaged (hereinafter referred to as patient information), information related to imaging such as the imaging region, imaging direction, and imaging date (hereinafter referred to as imaging information). Etc. are included. Each photographing order information is associated with the cassette ID of the cassette c registered in the cassette.

  The storage unit 26 also includes an image DB 262. The captured image (original image) acquired from the reading devices 30a to 30c, a processed image subjected to image processing, a synthesized image created by synthesis, and the like are stored in the image DB 262. The various image data are stored.

Next, the reading devices 30a to 30c will be described.
The reading devices 30a to 30c are reading means that read a captured image recorded in the cassette c and generate digital data thereof, and are image generating means. The reading devices 30a to 30c are configured to include a communication unit (not shown) such as a NIC or a modem, read a captured image and a cassette ID from the cassette c, and associate the cassette ID with the read captured image. Then, the job manager 10 is inquired about the transmission destination of the photographed image, and the photographed image and the cassette ID are transmitted to the control device 20m or the control device 20n that is the designated transmission destination.

  In the present embodiment, the reading devices 30a and 30b are reading devices that can handle both a breast image and a general image. In addition to reading at a normal reading pixel size applied to a general image, the reading device 30a, 30b It is assumed that the image can be read with a pixel size, and the reading device 30c is a reading device dedicated to general images that can be read only with a normal reading pixel size. When all of the reading devices 30a to 30c are compatible with both a breast image and a general image, the reading processing of the breast image uses the reading devices 30a and 30b from the viewpoint of processing efficiency in the entire system. In addition, it is advisable to make arrangements in advance with the imaging technician so that the reading device 30c is dedicated to general images.

  Note that, as another image generation unit, a photographing reading device that performs photographing and data reading of the photographed image, such as CR, CT, and MRI, may be connected to the photographed image generation system 1.

  The image processing devices 40x and 40y are image processing units that perform various types of image processing on captured images input from the control devices 20m and 20n. The image processing devices 40x and 40y are computer devices loaded with an image processing program, and store a CPU and RAM for executing image processing, a communication unit for communicating with external devices on the communication network N, and an image data group. And a program memory for storing an image processing program and the like.

  Various types of image processing include gradation processing to adjust contrast, frequency processing to adjust image sharpness, and dynamic range compression to keep an image with a wide dynamic range within an easy-to-view density range without reducing the contrast of details of the subject. In the case of a breast image that includes processing, etc., the density gradation of the low density area of the mammary gland or tumor that tends to have low contrast is expanded, and conversely the density of the fat area where there is little possibility of the presence of microcalcification clusters Contrast correction processing is performed to perform correction so as to compress the gradation.

Hereinafter, each image processing will be described.
The gradation process is a process of converting the gradation of the original image data to a desired gradation using a gradation conversion curve indicating the correspondence between the original image data and the processed image data after the gradation process. As a method for creating a gradation conversion curve, for example, the methods disclosed in Japanese Patent Application Laid-Open Nos. 55-116340 and 2-272529 can be applied.

As frequency processing, for example, unsharp mask processing disclosed in Japanese Patent Publication No. 62-62373 and multi-resolution analysis disclosed in Japanese Patent Laid-Open No. 9-44645 can be applied. In the frequency processing, a specific sharpness component of a certain mask size included in the original image data is multiplied by the enhancement coefficient α to perform the calculation represented by the following formula (1), and the desired sharpness is obtained from the original image data. Get the processed image data.
S = So + α (So-Sus) (1)
S: frequency processed image signal
So: Original image signal
Sus: Unsharp image signal
α: Emphasis coefficient

As the dynamic range processing, for example, a technique disclosed in Japanese Patent No. 250950 can be applied. In the dynamic range compression processing, the density of the low density region is corrected by multiplying the image signal in the low density region from a certain signal value A by the correction coefficient β by performing the calculation represented by the following equation (2). Compress gradation.
S = So + β (A−Sus) (2)
However, β = βL (Sus ≦ A) βL is a positive value
β = βH (Sus> A) βH = 0
S: Dynamic range compression processed image signal
So: Original image signal
Sus: Unsharp image signal
β: Correction coefficient
A: Constant (threshold value)

  The contrast correction process is a process for converting the original image data using a contrast correction curve for correcting the contrast of a shadow area existing over a wide area to the same level, and is performed as a pre-process for detecting an abnormal shadow candidate. . As a method for creating the contrast correction curve, the method described in pages 665 to 679 of MEDICAL IMAGING TECHNOLOGY Vol.14 No.6 November 1996 can be applied.

  In contrast correction processing, by converting the medical image using the above contrast correction curve, the density of the low density region of the mammary gland or tumor that tends to be low in contrast is enlarged, and conversely there is an image of a microcalcification cluster. Correction is performed so as to compress the density gradation of the fat mass region that is less likely. This contrast correction process not only contributes to improving the detection accuracy of abnormal shadow candidates, but is also very effective as a pre-process for abnormal shadow candidate detection in that it facilitates visual observation in the mammary gland tissue. Image processing.

  In addition, when the input captured image is a breast image, the image processing apparatuses 40x and 40y execute processing for detecting candidates for abnormal shadows such as microcalcification clusters and tumors that are findings of breast cancer from the breast image. . Detection of abnormal shadow candidates is performed for each lesion type using a detection algorithm corresponding to the lesion type of the abnormal shadow to be detected.

  The mass shadow has a shape close to a circle, and appears as a low-density shadow having a Gaussian distribution-like density change on the breast image. When detecting a shadow of a mass based on such characteristic density characteristics, for example, as disclosed in Japanese Patent Application Laid-Open No. 08-263642, an iris filter is used to mask the size of the mask around the pixel of interest. Is set, and the intensity component and direction component of the density gradient from the periphery to the target pixel are calculated as feature amounts in this mask size, and candidate regions are specified based on the feature amounts.

  When a candidate area is specified, various feature quantities such as contrast, standard deviation, density average value, curvature, fractal dimension, circularity, and area in the candidate area are calculated. Is compared with the set threshold value for detecting the tumor shadow, and it is determined whether or not the identified candidate area is a true positive abnormal shadow. If it is determined that the shadow is a true positive abnormal shadow, this candidate area is output as a detection result of a final tumor shadow candidate.

  In addition, the microcalcification cluster shadow appears on the breast image as a shadow in which low-density microcalcification portions having a substantially conical density change are gathered (clustered). Based on such characteristic density characteristics, as a filter for detecting a microcalcification portion, three ring filters in which the intensity component and the direction component of the density gradient when the density change shows an ideal cone shape are determined in advance. An image region having a density change close to a conical shape is specified as a candidate region for a microcalcification portion.

  Once the candidate area is characterized, as in the case of a tumor shadow, various feature quantities in the candidate area are calculated, and the feature quantity and a minute calcified cluster shadow set in advance for each feature quantity are detected. And a region in which a plurality of candidate regions of microcalcification portions determined to be true positive abnormal shadows are collected and output as a final microcalcification cluster shadow detection result.

  The image processing described above is an example, and other image processing, such as irradiation field detection processing, rotation / reversal processing, blackening processing (processing to paint a predetermined area black), overlay (composition of characters, etc.) Processing) and the like.

  The image processing devices 40x and 40y transmit the captured image that has been subjected to image processing (this is referred to as a processed image) to the control device 20m or the control device 20n that is the transmission source of the captured image. When an abnormal shadow candidate is detected, information on the detection result is transmitted to the control device 20m or the control device 20n in association with the processed image.

Next, the operation of the captured image generation system 1 in the first embodiment will be described.
In the captured image generation system 1, first, imaging order information is distributed from the RIS 2 to the control devices 20m and 20n. In the control devices 20m and 20n, the received photographing order information is stored in the order file 261, and the photographing order information is registered. Then, cassette registration is performed in the control devices 20m and 20n as pre-shooting processing. After the photographing, the photographed images read by the reading devices 30a to 30c are transmitted to the control devices 20m and 20n that have performed cassette registration. Therefore, although the processing described below is possible in any of the control devices 20m and 20n, in consideration of combining general imaging and mammography, one control device is a control device that combines both mammogram and general image processing. Since it is preferable from the viewpoint of processing efficiency of the entire system that the other control device is dedicated to general imaging, an example in which the following processing is performed assuming that the control device 20m is a control device for both general imaging and mammography is performed. explain.

  At the time of cassette registration, a list of imaging order information registered in the control device 20m is displayed. The imaging engineer selects imaging order information to be imaged from the imaging order information displayed in a list, and inputs the cassette ID of the cassette c used for the imaging via the input unit 22. In the control device 20m, the cassette ID input in association with the selected photographing order information is written in the order file 261, and cassette registration is performed. Here, when taking a breast image, the left breast and the right breast are each in the vertical direction (hereinafter referred to as the CC direction), the oblique direction (hereinafter referred to as the MLO direction), or the inner and outer direction (hereinafter referred to as the M direction). In general, photographing is performed in one or a plurality of photographing directions. That is, when imaging a breast image, at least two pieces of imaging order information are issued to one patient. Therefore, in the case of a breast image, cassette registration for one patient, that is, a plurality of photographings is performed at a time.

  Information on the registered cassette ID is transmitted to the job manager 10 together with the control device ID of the control device 20m for which the cassette registration has been performed. When the cassette ID and the control device ID are received, the job manager 10 issues a new photographic image number, and stores the cassette ID and the control device ID in association with the newly issued photographic image number in the image generation management table 11. Is done.

  When the cassette registration is completed, the photographing engineer moves to the photographing apparatus with the cassette c registered in the cassette, and corresponds to the cassette c corresponding to the photographing order information to be photographed, that is, the cassette registered for the photographing order information. c is attached to the imaging apparatus, and after the imaging part and the imaging direction designated by the imaging order information are adjusted, imaging is instructed. In the photographing apparatus, the patient is irradiated with radiation and photographing is performed, and the photographed image is recorded in the cassette c. In the case of a breast image, imaging is repeated while replacing the cassette c until all of the imaging for one patient is completed.

  When the photographing is completed, the photographing engineer moves toward the reading devices 30a to 30c. When a general image is taken, it can be read by any of the reading devices 30a to 30c, but it is preferably put into the reading device 30c corresponding to only the general image. When a breast image is taken, the cassette c in which the breast image is recorded in the reading devices 30a and 30b corresponding to the breast image is put into the reading devices 30a and 30b almost simultaneously. In the case of a breast image, since there are a plurality of cassettes c that have been photographed, one of them is loaded into the reading device 30a and the other is loaded into the reading device 30b. When reading is completed in each reading device 30a, 30b, the remaining one is loaded into the reading device 30a and the other is loaded into the reading device 30b. The cassette c is sequentially inserted into the reading devices 30a and 30b until the operation is completed. In addition, even if it is not a breast image, in the case where a plurality of continuous imaging is performed for one patient, the captured cassettes c may be sequentially inserted into the reading devices 30a and 30b.

Hereinafter, an image acquisition process executed in the captured image generation system 1 will be described assuming that a cassette c that has already been captured is inserted into the reading devices 30a and 30b.
FIG. 5 shows image acquisition processing executed in the reading devices 30a and 30b and the control devices 20m and 20n at the time of image reading. Here, a case will be described in which four cassettes c are loaded into the reading devices 30a and 30b approximately two at a time. For convenience of explanation, the reading device 30a is referred to as a reading device A, and the reading device 30b is referred to as a reading device B.

  First, when a cassette c that has been photographed is input in each of the reading device A and the reading device B (steps S1a and S1b), the cassette ID is read from the input cassette c in each reading device A and B (steps S2a and S1b). S2b). Next, in each of the reading devices A and B, the information of the read cassette ID is transmitted to the job manager 10 and an inquiry about the reading condition of the photographed image corresponding to the cassette ID and the destination of the photographed image is performed (step S2a). , S2b). In the job manager 10, a captured image reading condition and a control device ID corresponding to the cassette ID for which an inquiry has been made are read from the image generation management table 11. Referring to the example of FIG. 2, for example, when an inquiry about the cassette ID “1010102” is made, the reading pixel size “43.75 μm” and the control device ID “M10” are read as the reading conditions corresponding to the cassette ID.

  The job manager 10 generates response information for instructing to transmit the photographed image to the control device 20m having the control device ID “M10” along with the information of the read size “43.75” which is the read reading condition. Is sent to each of the reading devices A and B. Then, the reading end flag corresponding to the cassette ID for which the inquiry has been made is set to ON.

  In the reading device A and the reading device B, based on the response information received from the job manager 10, reading of the captured image is started under the specified reading condition, and the captured image and cassette read by the designated control device 20m are started. The ID is transferred (steps S3a and S3b).

  In the control device 20m, a captured image and a cassette ID are acquired from one of the reading devices A and B that have started reading operations substantially simultaneously (step S4), and the acquired captured image is stored in the image DB 262. Then, image registration of the photographed image is performed (step S5). At the time of image registration, first, shooting order information corresponding to the cassette ID associated with the acquired shot image is read from the order file 261. The captured image acquired in association with the order ID of the read imaging order information is stored in the image DB 262. Thus, as soon as a captured image is acquired from one reading device A or reading device B, a captured image and a cassette ID are acquired from the other reading device A or reading device B (step S6), and similarly to the cassette ID. Based on this, image registration of the photographed image is performed (step S7).

  On the other hand, in the reading device A and the reading device B that have finished the reading operation, when the cassette c is input again (steps S8a and S8b), the cassette ID is read from the input cassette c, and the reading devices A and B are read. Then, an inquiry about the read condition of the captured image and the transmission destination is made to the job manager 10 (steps S9a and S9b). Then, based on the response information from the job manager 10, reading of the photographed image is started under the designated reading condition, and the photographed image and the cassette ID are transferred to the designated transmission destination control device 20m ( Steps S10a, 10b).

  In the control device 20m, a captured image associated with a cassette ID is acquired from either one of the reading devices A and B that have started reading operations substantially simultaneously (step S11), and image registration of the acquired captured image is performed. (Step S12), the captured image and cassette ID are immediately acquired from the other (step S13), and the image registration of the captured image is performed (step S14), and this process ends.

  Next, a first image display process executed by the control devices 20m and 20n and the image processing devices 40x and 40y after the image registration of the captured image will be described with reference to FIG. The first image display process is a process of performing image processing on a captured image and displaying it so that a photographing engineer can confirm a captured image obtained by photographing. Here, an example of the operation by the control device 20m will be described, but the same processing is possible in the case of the control device 20n. For convenience of explanation, the image processing device 40x is referred to as an image processing device X, and the image processing device 40y is referred to as an image processing device Y.

  In the first image display process shown in FIG. 6, first, in the control device 20m, shooting order information corresponding to an order ID associated with a captured image registered as an image is read from the order file 261, and the shooting order information is read out. Based on this, the imaging part and the imaging direction of the captured image are recognized (step S21). Next, it is determined whether or not the photographed image is a breast image from the recognized photographed part (step S22). When it is determined that the imaging region is a chest or abdomen and the captured image is not a breast image (step S22; N), the control device 20m performs gradation processing, frequency processing, dynamic range compression processing, and the like on the captured image. Various image processing is performed (step S23). Next, the processed image that has been subjected to the image processing is displayed on the display unit 23 of the control device 20m (step S24), and this processing ends.

  On the other hand, when it is determined that the imaging region is the breast and the imaging image is a breast image (step S22; Y), based on the imaging order information stored in the order file 262, the breast of the same patient as the breast image is stored. An image is read from the image DB 262. As described above, since the breast image is taken at least once for the right breast and the left breast, at least two breast images are taken for one patient. In the example shown in FIG. 4, two imaging directions are designated for each of the left and right breasts for the patient with the patient ID “1001”, and a total of four imaging order information is registered, which corresponds to the acquired imaging image. If the attached imaging order information is, for example, order ID “0002”, the imaging site is the same patient ID “1001” based on the patient ID “1001” included in the imaging order information of this order ID “0002”. Imaging order information that is a breast is retrieved. Next, the breast image associated with the retrieved order ID of the imaging order information or the breast image associated with the cassette ID registered in the retrieved imaging order information is read from the image DB 262.

  Thus, when a plurality of breast images for the same patient are acquired, the breast image group is distributed to the image processing apparatus X and the image processing apparatus Y. Here, since there are two transmission destinations, the image processing apparatus X and the image processing apparatus Y, the image is divided into two for each imaging region of the left breast and the right breast, or for each imaging direction in the CC direction, the M direction, and the MLO direction. The image is classified into two for each related image group such as bisection. It is assumed that it is possible to appropriately set whether the classification condition is an imaging region or an imaging direction. In this embodiment, since two image processing apparatuses X and Y are installed, the breast image group is divided into two for each related image, but the number of classifications is the number of image processing apparatuses to be distributed. What is necessary is just to determine suitably according to.

  Next, one of the divided breast image groups is transmitted to the image processing apparatus X, the other breast image group is transmitted to the image processing apparatus Y, and the breast image group is distributed (step S25). At this time, the image processing parameter for the breast image is determined in the control device 20m, and information on the determined image processing parameter is transmitted to each of the image processing devices X and Y together with the breast image group to instruct image processing. That is, the image processing conditions are unified by the control device 20m. The image processing parameters referred to here are, for example, an enhancement coefficient α in frequency processing, a correction coefficient β in dynamic range compression processing, a threshold value when an abnormal shadow candidate is detected, and the like.

  In the image processing apparatuses X and Y that have received the breast image group, first, abnormal shadow candidate detection processing is performed on each of the breast image groups (steps S26a and S26b). When the abnormal shadow candidate detection processing is performed, next, various image processing such as gradation processing, contrast correction processing, frequency processing, dynamic range compression processing, and the like are performed using the image processing parameters designated by the control device 20m. (Steps S27a and S27b). The processed image subjected to the image processing is transmitted to the control device 20m together with the detection result of the abnormal shadow candidate (steps S28a and S28b).

In the control device 20m, when all processed images are received from the image processing devices X and Y, the processed images are combined to generate a combined image (step S29), and the generated combined image is displayed on the display unit. If displayed on the screen 23 (step S24), the process is terminated.
For example, when a total of four processed images captured in the two imaging directions of the left and right breasts in the vertical direction and the oblique direction are received, as shown in FIGS. Two composite images are created. In the composite image shown in FIG. 7A, a processed image G1 in which the imaging part is the left breast and the imaging direction is the CC direction and a processed image G2 in which the imaging part is the right breast and the imaging direction is also the CC direction are arranged in parallel. Is synthesized. Also, the composite image shown in FIG. 7B is composed of a processed image G3 in which the imaging region is the left breast and the imaging direction is the MLO direction, and a processed image G4 in which the imaging region is the right breast and the imaging direction is the same MLO direction. It has been done.

  A detection result of abnormal shadow candidates is generated on the sub-image by generating a sub-image obtained by reducing each of the processed images G1 to G4 and overlaying marker information indicating the position of the detected abnormal shadow candidate on the sub-image. For example, as shown in FIG. 8, the sub-images g3 and g4 on which the detection results of the abnormal shadow candidates are superimposed may be combined on the processed images G3 and G4.

  The radiographer looks at the composite image displayed on the display unit 23, confirms the image quality such as the position, density, and sharpness of the subject region for a plurality of breast images taken for one patient, and the composite image If it is OK, the imaging of the patient is terminated, and the next patient imaging is started.

  As described above, since it is possible to read an image from the cassette c that is input almost simultaneously in the plurality of reading devices 30a and 30b, the time required to read all the plurality of images can be shortened. As a result, the time from reading to display of the captured image is shortened, and the time for the patient to be released from the photographing is shortened, so that the burden on the patient's photographing can be reduced. In particular, in the case of a breast image in which a plurality of images are taken for one patient, the number of cassettes c to be read is large, and the data capacity of one image is large and requires a great amount of reading time. It is particularly effective to apply the present invention in which reading is performed by 30b.

  In addition, when the captured images read by the reading devices 30a and 30b are breast images, the control devices 20m and 20n do not perform image processing, and the breast images are separately provided for image processing. Since the image processing is performed by transmitting to 40x and 40y, a breast image having a large data capacity and requiring a long time for image processing can be quickly processed. While the image processing of the breast image is being performed in each of the image processing devices 40x and 40y, the control devices 20m and 20n execute other processing such as image registration of other captured images and image processing. Therefore, the flow of processing in the captured image generation system 1 becomes smooth, and the processing efficiency can be improved in the entire system.

  Furthermore, when performing image processing, a plurality of breast images belonging to the same patient are acquired and distributed to each of the image processing devices 40x and 40y for each related image, and image processing is performed by specifying image processing parameters. Since the image processing is performed, it is possible to disperse the image processing of the breast image having a large data capacity of one image and a large number of images for one patient, and the image processing time can be shortened. Also, when combining and displaying a plurality of breast images for one patient for interpretation, the control devices 20m and 20n receive and combine the processed images processed by the image processing devices X and Y. The processing time for creating the composite image can be shortened.

Second Embodiment
In the second embodiment, when the captured image is a breast image, the one breast image is divided into a plurality of regions, the divided image is distributed to a plurality of image processing means, and abnormal shadow candidate detection processing is performed by each image processing means. Next, an example will be described in which various image processing such as gradation processing is performed and a breast image restored by combining the image-processed divided images is displayed.

  Since the system configuration of the captured image generation system in the second embodiment is the same as that of the captured image generation system 1 described in the first embodiment, the same reference numerals are given to the respective components, and the illustration thereof is omitted. Different functional parts will be described. That is, the captured image generation system 1 includes a job manager 10, control devices 20m and 20n as control means, reading means, reading devices 30a to 30c as image generation means, and image processing devices 40x and 40y as image processing means. Consists of Of the reading devices 30a to 30c, the reading devices 30a and 30b are reading devices that can read breast images and general images, and the reading device 30c is a reading device that can read only general images. This is the same as the embodiment.

The control unit 21 of the control device 20m (20n) executes the second image display process (see FIG. 9) characteristic of the second embodiment in accordance with the second image display processing program stored in the storage unit 26. .
In the second image display process, when displaying a captured image, it is determined whether or not the captured image is a breast image based on the imaging order information associated with the captured image. If it is an imaging part, various image processings are performed on the captured image and displayed on the display unit 23. On the other hand, if it is a breast image, the breast image (one image) is divided into a plurality of regions, and one of the divided divided images is transmitted to the image processing device 40x and the other is transmitted to the image processing device 40y via the communication unit 24. . At this time, image processing parameters of the breast image are determined, and information on the determined image processing parameters is distributed together with the breast image so that the image processing conditions in the image processing apparatuses 40x and 40y are unified. When the processed images subjected to the image processing are received from the image processing apparatuses 40x and 40y, the processed images are combined to restore the original breast image and displayed on the display unit 23.

Next, the operation of the captured image generation system 1 in the second embodiment will be described.
In the captured image generation system 1 in the second embodiment, cassette registration is first performed as in the first embodiment. Since the cassette registration method is as described above, the description thereof is omitted here. Next, imaging for one patient is performed using the cassette c registered in the cassette, and the cassette c on which the captured image is recorded is put into one of the reading devices 30a to 30c by the imaging technician. When a plurality of mammograms are performed for one patient and there are a plurality of cassettes c, two of them can be loaded almost simultaneously into each of the reading devices 30a and 30b.

  When the photographed cassette c is inserted into each of the reading devices 30a and 30b, the photographed image generation system 1 performs image acquisition processing. Since this image acquisition process is the same as the process described with reference to FIG. 5 in the first embodiment, the description thereof is omitted here. That is, the captured image and the cassette ID are read from the cassettes c inserted almost simultaneously in the reading devices 30a and 30b, and the captured images associated with the cassette IDs are transmitted to the control devices 20m and 20n. Image registration is performed at 20m and 20n.

When the image registration is completed, a second image display process that is a characteristic process of the second embodiment is executed.
The second image display process will be described with reference to FIG. In addition, although the example of operation | movement by the control apparatus 20m is demonstrated here, the same process is also possible in the control apparatus 20n. Similarly to the first image display process, the image processing device 40x is referred to as an image processing device X, and the image processing device 40y is referred to as an image processing device Y.

  In the second image display process shown in FIG. 9, first, shooting order information corresponding to an order ID associated with a captured image registered as an image is read from the order file 261, and shooting is performed based on the shooting order information. The imaging part and the imaging direction of the image are recognized (step S101). Next, it is determined whether or not the captured image is a breast image from the recognized captured region (step S102). When it is determined that the imaging region is the chest or abdomen and the captured image is not a breast image (step S102; N), the control device 20m performs gradation processing, frequency processing, dynamic range compression processing, etc. on the captured image. Various image processing is performed (step S13). Next, the processed image on which the image processing has been performed is displayed on the display unit 23 of the control device 20m (step S104), and this processing is terminated.

  On the other hand, when it is determined that the imaging region is a breast and the captured image is a breast image (step S102; Y), the breast image (one image) is divided into two regions (step S105). Each of the divided images is referred to as a divided image. For example, the breast image F1 is vertically divided into two as shown in FIG. 10A, and divided images F11 and F12 are generated as shown in FIG. In this embodiment, since two image processing apparatuses X and Y are installed, an example in which one image is divided into two and each divided image is distributed to the image processing apparatuses X and Y will be described. The number may be appropriately determined according to the number of image processing apparatuses.

  Next, one of the two divided images is transmitted to the image processing apparatus X and the other is transmitted to the image processing apparatus Y, and each divided image is distributed and distributed (step S106). At this time, the control device 20m determines an image processing parameter for each divided image, and transmits information on the determined image processing parameter to each of the image processing devices X and Y together with the divided image to instruct image processing. That is, the image processing conditions are unified by the control device 20m.

  In the image processing apparatuses X and Y, first, abnormal shadow candidate detection processing is performed on the received divided images (steps S107a and S107b). When the abnormal shadow candidate detection processing is performed, next, various image processing such as gradation processing, contrast correction processing, frequency processing, dynamic range compression processing, and the like are performed using the image processing parameters specified by the control device 20m. (Steps S108a and S108b). The processed image subjected to the image processing is transmitted to the control device 20m together with the detection result of the abnormal shadow candidate (steps S109a and S109b).

  In the control device 20m, when the processed image of each divided image is received from each of the image processing devices X and Y, the processed image is synthesized and the original breast image before the division is restored (step S110). . In the case of processing an image divided into a plurality of parts, it is preferable to overlap each divided image area boundary with each other so that a compositing process that does not cause a problem such as a loss of an image at the boundary portion at the time of image compositing is possible. . Next, the restored breast image is displayed on the display unit 23 (step S104), and this process ends.

A sub-image is generated by reducing the restored breast image, and the detection result of the abnormal shadow candidate is superimposed on the sub-image, and the sub-image on which the detection result of the abnormal shadow candidate is superimposed is displayed on the breast image. A synthesized composite image may be created and displayed.
Further, the image processing as described above is repeated for a plurality of breast images for one patient to obtain a processed image, and a composite image for interpretation as shown in FIGS. 7A, 7B, and 8 is created. It is good.

  The radiographer looks at the breast image displayed on the display unit 23 and confirms the image quality, such as the position, density, and sharpness of the subject area. Transition to patient imaging.

  As described above, since it is possible to read an image from the cassette c that is input almost simultaneously in the plurality of reading devices 30a and 30b, the time required to read all the plurality of images can be shortened. As a result, the time from reading to display of the captured image is shortened, and the time for the patient to be released from the photographing is shortened, so that the burden on the patient's photographing can be reduced. In particular, in the case of a breast image in which a plurality of images are taken for one patient, the number of cassettes c to be read is large, and the data capacity of one image is large and requires a great amount of reading time. It is particularly effective to apply the present invention in which reading is performed by 30b.

  In addition, when the captured images read by the reading devices 30a and 30b are breast images, the control devices 20m and 20n do not perform image processing, and the breast images are separately provided for image processing. Since the image processing is performed by transmitting to 40x and 40y, a breast image having a large data capacity and requiring a long time for image processing can be quickly processed. While the image processing of the breast image is being performed in each of the image processing devices 40x and 40y, the control devices 20m and 20n execute other processing such as image registration of other captured images and image processing. Therefore, the flow of processing in the captured image generation system 1 becomes smooth, and the processing efficiency can be improved in the entire system.

  Further, when performing image processing, one breast image is divided into two, one of the divided images is transmitted to the image processing device 40x, and the other divided image is transmitted to the image processing device 40y to perform image processing. Since each divided image that has undergone image processing is acquired from each image processing device 40x, 40y and synthesized, and the original one image is restored and displayed, quick processing can be achieved by performing image processing on one image in a distributed manner Is possible. In particular, in the case of a breast image, since the data capacity of one image is very large, it is effective. Furthermore, since a plurality of breast images are taken for one patient, it is possible to reduce the image processing time in this way. This is particularly effective in terms of overall processing efficiency.

  The description content in the first and second embodiments is a preferred example of the captured image generation system 1 to which the present invention is applied, and is not limited to this.

  For example, in the captured image generation system 1 described above, an example in which imaging is performed using the cassette c has been described. However, imaging and reading may be performed using another radiation detector without using the cassette c.

  As other radiation detectors, image generation means such as a flat panel detector (hereinafter referred to as FPD; Flat Panel Detector) can be applied. The FPD is a two-dimensional array of radiation detection elements that generate charges according to the intensity of irradiated radiation, and capacitors that store the charges generated by the radiation detection elements. The FPD is installed in a photographing apparatus, and image data is generated based on an image signal obtained by the FPD in the photographing apparatus at the time of photographing.

  As described above, when the photographic device is configured to obtain the photographic image as digital data, the transmission destination of the photographic image generated by photographing is fixed to either the control device 20m or 20n, and the fixed control device 20m is fixed. , 20n, the photographed image obtained for each photographing is associated with the photographing order information. That is, when shooting order information to be shot is selected by the control devices 20m and 20n and shooting is performed according to the selected shooting order information, the shot image obtained by shooting is associated with the selected shooting order information.

  In addition, as supplementary information of image data acquired by image generation means such as FPD, additional information related to imaging order information such as left and right information indicating the captured breast and imaging direction and patient information is added. If possible, each time an image is taken, the left and right information, information on the photographing direction, patient information, etc., automatically discriminated on the image generating apparatus side or input by a photographing engineer, are attached to the image data as supplementary information. When the image data and the accompanying information are transmitted to the control device, the control device receives the left and right information included in the accompanying information when transmitting the breast image for one patient to the image processing device. Based on the imaging direction information, for example, the same imaging unit, for example, transmitting the breast image in the CC direction at the right breast and the breast image in the MLO direction at the right breast as a set to the image processing apparatus Or it may transmit the same imaging direction of the breast image as one set.

  In the above description, the case of processing a breast image has been described. However, the present invention is not limited to this, and it is necessary to perform image processing that requires a processing time such as a large data capacity or abnormal shadow candidate detection processing. The present invention may be applied when processing a photographed image that requires processing time.

  In addition, the detailed configuration and detailed operation of the captured image generation system 1 in the first and second embodiments can be changed as appropriate without departing from the spirit of the present invention.

It is a figure which shows the system configuration | structure of the picked-up image generation system 1 in 1st Embodiment. It is a figure which shows the data structure of the image generation management table 11 with which the job manager 10 is provided. It is a figure which shows the internal structure of the control apparatus 20m. 4 is a diagram showing a data configuration of an order file 261 in the storage unit 26. FIG. 4 is a flowchart for describing image acquisition processing executed in the captured image generation system 1. 4 is a flowchart for explaining a first image display process executed in the captured image generation system 1. (A), (b) is a figure which shows the example of a synthesized image produced by synthesize | combining each breast image by which the image process was carried out. It is a figure which shows the example of a synthesized image produced by synthesize | combining the subimage which shows the detection result of an abnormal shadow candidate on the breast image by which the image process was carried out. It is a flowchart explaining the 2nd image display process performed in 2nd Embodiment. (A) is a figure which shows the example of a division | segmentation of a breast image, (b) is a figure which shows each divided | segmented image.

Explanation of symbols

1 Captured image generation system 2 RIS
DESCRIPTION OF SYMBOLS 10 Job manager 11 Image generation management table 20m, 20n Control apparatus 21 Control part 22 Input part 23 Display part 24 Communication part 25 RAM
26 storage unit 261 order file 262 image DB
30a, 30b Reading device 40x, 40y Image processing device

Claims (12)

Image generation means for generating a captured image of the patient;
A plurality of image processing means for performing image processing on the captured image;
Of the captured images generated by the image generating means, a plurality of breast images for one patient are acquired, the acquired plurality of breast images are classified for each related image, and a group of classified breast images is obtained. Control means for distributing the image processing to the plurality of image processing means;
A photographed image generation system comprising: Reading means for reading the captured image from the cassette in which the captured image of the patient is recorded;
A plurality of image processing means for performing image processing on the captured image;
A plurality of breast images for one patient read by the reading unit are acquired, the acquired plurality of breast images are classified for each related image, and the classified breast image group is classified into the plurality of image processing units. A control means for distributing the images into image processing,
A photographed image generation system comprising:   The control means classifies a plurality of breast images for one patient for each imaging region of the left breast and the right breast, and a group of breast images classified as the left breast is classified as a right breast by one image processing means. 3. The captured image generation system according to claim 1, wherein the breast image group is distributed to other image processing means.   The said control means classify | categorizes the several breast image with respect to one patient for every imaging | photography direction, and distributes each classified said breast image group to another image processing means, respectively. Taken image generation system. A plurality of reading means for reading the captured image from a cassette in which a breast image of the patient is recorded;
A plurality of image processing means for performing image processing on the breast image;
Control means for acquiring a plurality of breast images of the same patient obtained by controlling the plurality of reading means, and distributing the acquired plurality of breast images to the plurality of image processing means;
A photographed image generation system comprising:   The photographed image generation system according to any one of claims 1 to 5, wherein when the breast image is sorted, the control unit distributes designation information of an image processing condition together with the breast image.   The said control means acquires each breast image image-processed in these image processing means, and synthesize | combines each said breast image image-processed, and produces a synthesized image. The captured image generation system described in 1. Image generation means for generating a captured image of the patient;
Image processing means for performing image processing on the captured image;
Control means for determining a photographed image to be subjected to image processing by the image processing means from among the photographed images generated by the image generating means, delivering the determined photographed image to the image processing means, and performing image processing; ,
A photographed image generation system comprising: A plurality of the image processing means;
The control means divides a captured image determined to be subjected to image processing by the image processing means into a plurality of regions, and distributes the divided images to the plurality of image processing means for image processing. The photographed image generation system according to claim 8.   The said control means acquires each divided image image-processed in the said several image processing means, synthesize | combines each said divided image processed image, and restore | restores the original picked-up image. The captured image generation system described in 1.   The photographed image generation system according to claim 9 or 10, wherein when the divided image is distributed, the control means distributes designation information of an image processing condition together with the divided image.   The captured image generation system according to any one of claims 8 to 11, wherein the captured image to be subjected to image processing by the image processing means is a breast image obtained by capturing a breast of a patient.

Images