JP2005103053A - Medical image processing system and medical image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an inexpensive medical image processing system capable of enabling a physician to easily and quickly refer to and utilize diagnosis support information in image interpretation and thus improving the diagnosis performance and work efficiency of the physician without changing the conventional flow of work inside a hospital. <P>SOLUTION: An image processor 2 applies image processing suitable for diagnosis to inputted image data and prepares images for diagnosis. The image processor 2 also prepares diagnosis support information relating to the image data inputted from an image input means 11, applies the image processing suitable for referring to the image data, adds an annotation indicating the diagnosis support information, and prepares images for diagnosis support. Then, the images for diagnosis support are outputted from an output channel corresponding to an image recorder 3c, and the images for diagnosis are outputted from an output channel corresponding to an image recorder 3a or 3b selected in accordance with a photographed part, image generator information and an output image size included in auxiliary information. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a medical image processing system that performs image processing on a medical image to improve the efficiency of doctor's interpretation diagnosis and outputs it as a hard copy from an image recording apparatus.

  Conventionally, as a medical image used by a doctor for diagnosis, an analog image such as an intensifying screen / film used for radiography or an image obtained from a digital image input system using a stimulable phosphor is used as a hardware image such as a silver salt film. Some of the images are output as copies, and doctors generally interpret these medical images using an image observation apparatus such as Schaukasten in each clinic.

On the other hand, in recent years, diagnostic support information such as abnormal shadow candidate detection results is added to a medical image for interpretation by an image diagnosis support device (for example, see Patent Document 1), and the result is applied to a CRT (Cathode Ray Tube) monitor, a liquid crystal monitor, or the like. A system for outputting and supporting doctor's diagnosis has been proposed. When a medical image is output to a monitor for interpretation, the brightness and contrast of the monitor are changed by the adjustment means attached to the monitor at the time of interpretation, and image processing conditions such as gradation processing and frequency processing are changed in real time by image display software. It is possible to change. Further, the image can be enlarged / reduced or moved by image display software. As described above, when the medical image is read by the monitor, the display format can be changed in real time, and the degree of freedom is high.
JP 2000-342559 A

  However, when a medical image is displayed on a monitor, in order to provide an image suitable for interpretation, the monitor is required to have high performance, is expensive, requires a space for placement, and consumes power and heat. large. Therefore, except for some hospitals such as large hospitals, it has been practically difficult to install monitors for displaying medical images in all of the radiology department's interpretation rooms and clinics.

  Also, in order to introduce a display monitor in a hospital, doctors need to get used to the operation of the monitor system, and the flow of in-hospital work from radiography to image interpretation changes greatly. Major issues such as adjustment occur.

  On the other hand, in a method of outputting and interpreting a medical image as a hard copy of a silver halide film or the like, if a graphic indicating diagnosis support information such as an abnormal shadow candidate detection result is added to a medical image for interpretation, a part of the image information is There is a problem that it is missing and interferes with interpretation.

  An object of the present invention is an inexpensive system that allows a doctor to easily and quickly refer to and utilize diagnosis support information in interpretation without changing the flow of conventional hospital work, thereby enabling the diagnosis performance of the doctor and To provide a medical image processing system and a medical image processing method capable of improving work efficiency.

In order to solve the above-mentioned problem, the invention described in claim 1
In a medical image processing system comprising an image processing device that performs image processing on a medical image, and a plurality of image recording devices that record and output the medical image output from the image processing device,
The image processing apparatus includes:
Diagnostic image creation means for creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
A diagnostic support information generating means for generating diagnostic support information related to the medical image by analyzing the medical image;
Diagnostic support image creating means for creating a diagnostic support image using the diagnostic support information generated by the diagnostic support information generating means;
Identification information adding means for adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
Image output means for outputting the diagnostic image and the diagnostic support image to each of different image recording devices;
It is characterized by having.

The invention according to claim 2 is the invention according to claim 1,
The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and are characterized by different recording characteristics.

The invention according to claim 3 is the invention according to claim 1 or 2,
The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and outputs images having different image quality characteristics.

The invention according to claim 4 is the invention according to any one of claims 1 to 3,
The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and are characterized in that the quality of the recording media used is different.

The invention according to claim 5 is the invention according to any one of claims 1 to 4,
The image output means of the image processing device has a plurality of output channels corresponding to the plurality of image recording devices, and outputs the diagnosis image and the diagnosis support image to any of the plurality of output channels. The present invention is characterized in that output channel selection means for selecting each of them independently is provided.

The invention according to claim 6 is the invention according to any one of claims 1 to 5,
The image processing device includes image recording device information storage means for storing image recording device information corresponding to the plurality of image recording devices,
The diagnostic image creation means and the diagnostic support image creation means of the image processing device are configured to create the diagnostic image and the diagnostic support image based on the image recording device information stored in the image recording device information storage means. The condition is determined.

The invention according to claim 7 is an image processing apparatus that performs image processing on a medical image and an apparatus that records and outputs the medical image output from the image processing apparatus, and includes a plurality of types having different recording characteristics. In a medical image processing system comprising an image recording apparatus provided with a recording medium,
The image processing apparatus includes:
Diagnostic image creation means for creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
A diagnostic support information generating means for generating diagnostic support information related to the medical image by analyzing the medical image;
Diagnostic support image creating means for creating a diagnostic support image using the diagnostic support information generated by the diagnostic support information generating means;
Identification information adding means for adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
A different recording medium type is selected for each of the diagnostic image and the diagnostic support image from the plurality of types of recording media, and the diagnostic image, the diagnostic support image, and the selected recording are selected. Image output means for outputting medium type information to the image recording device;
It is characterized by having.

The invention according to claim 8 is the invention according to claim 7,
The image output means of the image processing apparatus has a plurality of output channels corresponding to the plurality of types of recording media, and outputs the diagnosis image and the diagnosis support image to any of the plurality of output channels. The present invention is characterized in that output channel selection means for selecting each of them independently is provided.

The invention according to claim 9 is the invention according to claim 7 or 8,
The image processing apparatus includes a recording medium information storage unit that stores recording medium information corresponding to the plurality of types of recording media,
The diagnostic image creation means and the diagnostic support image creation means of the image processing device are configured to create the diagnostic image and the diagnostic support image creation based on recording medium information stored in the recording medium storage means. It is characterized by determining.

The invention according to claim 10 is the invention according to any one of claims 1 to 9,
The image processing apparatus includes output enable / disable selecting means for independently selecting whether or not to output the diagnostic image and the diagnostic support image to any of the plurality of image recording apparatuses. It is said.

The invention according to claim 11 is the invention according to any one of claims 1 to 10,
The image processing device adds information indicating whether one of the diagnostic image and the diagnostic support image is output to any one of the plurality of image recording devices to the other image. An output information adding means is provided.

The invention according to claim 12 is the invention according to any one of claims 1 to 11,
The image processing apparatus includes:
Diagnostic support image storage means for storing the diagnostic support image;
An output instruction means for inputting an output instruction of the diagnostic support image;
The image output means of the image processing apparatus reads the diagnosis support image from the diagnosis support image storage means and outputs it to the image recording apparatus based on input information from the output instruction means. .

The invention according to claim 13 is the invention according to any one of claims 1 to 11,
The image processing apparatus includes:
Diagnostic support information storage means for storing the diagnostic support information;
An output instruction means for inputting an output instruction of the diagnostic support image;
The diagnostic support image creation means of the image processing device reads the diagnostic support information from the diagnostic support information storage means based on the input information from the output instruction means, creates a diagnostic support image,
The image output means of the image processing device outputs the created diagnosis support image to the image recording device.

The invention according to claim 14 is the invention according to any one of claims 1 to 13,
The diagnostic image creating means of the image processing apparatus determines an image processing condition by analyzing the medical image, and performs image processing including at least gradation processing on the medical image using the determined image processing condition. To create a diagnostic image,
The diagnostic support image creating means of the image processing apparatus performs image processing on the medical image using an image processing condition different from that used in the diagnostic image creating means, and the image subjected to the image processing. The diagnostic support image is created by adding the diagnostic support information generated by the diagnostic support information generating means to the image.

The invention according to claim 15 is the invention according to any one of claims 1 to 13,
The diagnostic support image creating means of the image processing apparatus creates a schema image corresponding to the medical image, and adds diagnostic support information generated by the diagnostic support information generating means to the schema image, thereby providing diagnostic support. It is characterized by creating an image.

The invention according to claim 16 is the invention according to any one of claims 1 to 15,
The diagnostic support information generation means of the image processing apparatus is characterized by detecting an abnormal shadow candidate by analyzing the medical image and generating diagnostic support information related to the detected abnormal shadow candidate.

The invention according to claim 17 is the invention according to any one of claims 1 to 15,
The diagnosis support information generating means performs image measurement by analyzing the medical image and generates the diagnosis support information related to a measurement result.

The invention described in claim 18
In a medical image processing method in a medical image processing system comprising an image processing device that performs image processing on a medical image and a plurality of image recording devices that record and output the medical image output from the image processing device.
Creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
Generating diagnostic support information related to the medical image by analyzing the medical image;
Creating a diagnostic support image using the generated diagnostic support information;
Adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
Outputting the diagnostic image and the diagnostic support image to each of different image recording devices;
It is characterized by including.

The invention according to claim 19 is an image processing apparatus that performs image processing on a medical image, and an apparatus that records and outputs the medical image output from the image processing apparatus, and includes a plurality of types having different recording characteristics. In a medical image processing method in a medical image processing system comprising an image recording apparatus provided with a recording medium,
The image processing apparatus includes:
Creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
Generating diagnostic support information related to the medical image by analyzing the medical image;
Creating a diagnostic support image using the generated diagnostic support information;
Adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
A different recording medium type is selected for each of the diagnostic image and the diagnostic support image from the plurality of types of recording media, and the diagnostic image, the diagnostic support image, and the selected recording are selected. Outputting medium type information to the image recording device;
It is characterized by including.

  According to the invention described in claims 1 and 18, a diagnostic image is created by performing image processing including at least gradation processing on the medical image, and diagnostic support information related to the medical image is obtained by analyzing the medical image. Generating a diagnostic support image using the generated diagnostic support information, adding identification information for associating the generated diagnostic image and the diagnostic support image to each image, Are output to each of the different image recording apparatuses. Therefore, even when a diagnostic image output to a hard copy such as a silver halide film is read using an image observation device such as Saucusten, information on a part of the diagnostic image is obtained by superimposing diagnostic support information on the diagnostic image. The diagnosis support information can be referred to and used easily and quickly.

  According to the second aspect of the present invention, the plurality of image recording apparatuses include the image recording apparatus that outputs the diagnostic support image and the image recording apparatus that outputs the diagnostic image, and have different recording characteristics. Therefore, the diagnostic image and the diagnostic support image can be output by an image recording apparatus having recording characteristics suitable for each observation.

  According to a third aspect of the present invention, the plurality of image recording devices include an image recording device that outputs a diagnostic support image and an image recording device that outputs a diagnostic image, and outputs images having different image quality characteristics. To do. Therefore, the diagnostic image and the diagnostic support image can be output by an image recording apparatus having image quality characteristics suitable for each observation.

  According to the fourth aspect of the present invention, the plurality of image recording apparatuses include an image recording apparatus that outputs an image for diagnosis support and an image recording apparatus that outputs an image for diagnosis. Different. Accordingly, the diagnostic image and the diagnostic support image can be output by an image recording apparatus using a recording medium suitable for each observation.

  According to the fifth aspect of the present invention, each of the plurality of output channels includes a plurality of output channels corresponding to the plurality of image recording apparatuses, and the diagnosis image and the diagnosis support image are output to each of the plurality of output channels. Can be selected independently.

  According to the sixth aspect of the present invention, the image processing apparatus includes the image recording apparatus information storage unit that stores the image recording apparatus information corresponding to the plurality of image recording apparatuses, and the image processing apparatus information storage unit stores the image recording apparatus information. Based on the recorded image recording apparatus information, conditions for creating diagnostic images and diagnostic support images are determined. Accordingly, it is possible to create a diagnostic image and a diagnostic support image under the creation conditions according to the characteristics of the image recording apparatus.

  According to the seventh and nineteenth aspects of the present invention, a diagnostic image is created by performing image processing including at least gradation processing on a medical image, and the medical image is analyzed, whereby diagnostic support information related to the medical image is obtained. And generating diagnostic support images using the generated diagnostic support information, adding identification information for associating the generated diagnostic images and diagnostic support images to the respective images, A recording medium to be used is selected from a plurality of types of recording media having different recording characteristics provided in the recording apparatus, and a diagnostic image, a diagnosis support image, and the type of the selected recording medium are output to the image recording apparatus. . Therefore, even when a diagnostic image output to a hard copy such as a silver halide film is read using an image observation device such as Saucusten, information on a part of the diagnostic image is obtained by superimposing diagnostic support information on the diagnostic image. Since the information is recorded using a recording medium having recording characteristics suitable for each image, the diagnosis support information can be referred to and used easily and quickly.

  According to the eighth aspect of the present invention, each of the plurality of output channels has a plurality of output channels corresponding to a plurality of types of recording media, and the diagnosis image and the diagnosis support image are output to each of the plurality of output channels. Can be selected independently.

  According to the ninth aspect of the present invention, the image processing apparatus includes recording medium information storage means for storing recording medium information corresponding to a plurality of types of recording media included in the image recording apparatus. Based on the recording medium information stored in the means, conditions for creating diagnostic images and diagnostic support images are determined. Therefore, it is possible to create a diagnostic image and a diagnostic support image under the creation conditions according to the characteristics of the recording medium to be used.

  According to the invention described in claim 10, the image processing apparatus independently selects whether or not to output the diagnostic image and the diagnostic support image to any one of the plurality of image recording apparatuses. Therefore, only necessary images can be output.

  According to the invention described in claim 11, the image processing apparatus is information indicating whether one of the diagnostic image and the diagnostic support image is output to any one of the plurality of image recording apparatuses. Is added to the other image. Therefore, it is possible to easily recognize whether a diagnostic support image for the diagnostic image is output, or whether a diagnostic image for the diagnostic support image is output, and management of the image is facilitated.

  According to the twelfth aspect of the present invention, the diagnostic support image can be read out from the diagnostic support information storage means storing the diagnostic support image and output to the image recording apparatus based on the output instruction input. The image for diagnosis support can be easily output from the image recording apparatus when necessary.

According to the invention described in claim 13, based on the output instruction input, the diagnostic support information is read from the diagnostic support information storage means in which the diagnostic support image is stored, and the diagnostic support image is created.
Since the created diagnostic support image is output to the image recording apparatus, the diagnostic support image can be output from the image recording apparatus when necessary.

  According to the invention of claim 14, by determining an image processing condition by analyzing a medical image, and performing image processing including at least gradation processing on the medical image using the determined image processing condition. Creating a diagnostic image, performing image processing on the medical image using image processing conditions different from those used in creating the diagnostic image, and adding diagnostic support information to the image subjected to the image processing A diagnostic support image is created by the above. Accordingly, a diagnostic image for the purpose of diagnosis and a diagnostic support image for the purpose of reference can be created by performing image processing suitable for each purpose.

  According to the fifteenth aspect of the present invention, a schema image corresponding to a medical image is created, and diagnostic support information is created by adding diagnostic support information to the schema image. Therefore, in referring to the diagnosis support information, the boundary between the subject and the background can be displayed in an easy-to-understand manner.

  According to the sixteenth aspect of the present invention, the abnormal shadow candidate is detected by analyzing the medical image, and the diagnostic support information related to the detected abnormal shadow candidate is generated. By outputting the image, it is possible to reduce oversight of the lesion by the doctor and reduce the burden of interpretation by the doctor.

  According to the invention described in claim 17, since the image measurement is performed by analyzing the medical image and the diagnosis support information related to the measurement result is generated, the diagnosis support image to which the diagnosis support information is added is output. Thus, the accuracy of image measurement by a doctor can be improved and the burden of interpretation can be reduced.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
First, the configuration will be described.
FIG. 1 is a conceptual diagram showing the overall configuration of a medical image processing system 100 in the present embodiment. As shown in FIG. 1, a medical image processing system 100 is connected so that image generation apparatuses 1a to 1c, an image processing apparatus 2, image recording apparatuses 3a to 3c, and the like can exchange data with each other via a network N. ing.

  As the network N, various line forms such as a LAN (Local Area Network), a WAN (Wide Area Network), and the Internet can be applied. Note that wireless communication or infrared communication may be used as long as it is permitted within a medical institution such as a hospital. However, since important patient information is included, it is preferable to encrypt information to be transmitted and received. Moreover, as a communication system in a hospital, the DICOM (Digital Image and Communications in Medicine) standard is generally used, and in the communication between each device on the network N described above, DICOM MWM (Modality Worklist Management). Or DICOM MPPS (Modality Performed Procedure Step).

  The image generation apparatuses 1a to 1c are composed of, for example, a CR (Computed Radiography), an FPD (Flat Panel Detector), a CT (Computed Tomography), an MRI (Magnetic Resonance Imaging), a mammography apparatus (mammography), an ultrasonic diagnostic apparatus, and the like. In this apparatus, a subject is photographed, and the photographed image is digitally converted to generate a medical image. In the present embodiment, an example will be described in which the image generation device 1a is a standing CR, the image generation device 1b is a CT, and the image generation device 1c is a mammography device.

  The image generation apparatuses 1a to 1c are apparatuses conforming to the above-described DICOM standard, and can input DICOM image supplementary information (hereinafter referred to as supplementary information) or automatically generate it. The image generation apparatuses 1a to 1c output the accompanying information together with the generated medical images to the image processing apparatus 2 via the network N. If the image generation apparatuses 1a to 1c are not compliant with the DICOM standard, a DICOM conversion apparatus (not shown) is used. Attached information can be input.

  The image processing apparatus 2 performs image processing on the medical image image data input from the image generation apparatuses 1a to 1c to create a diagnostic image, and analyzes the image data to detect abnormal shadow candidates, image measurement, and the like. And generating diagnostic support information using the diagnostic support information, and generating image data of the diagnostic image and the diagnostic support image that are different from the image recording devices 3a to 3c. It is a device that outputs each to the recording device. The internal configuration of the image processing apparatus 2 will be described later.

  The image recording devices 3a to 3c output hard copies obtained by reproducing the image data input from the image processing device 2 as visible images. The image recording devices 3a to 3c are image recording devices having different recording characteristics.

  For example, the image recording device 3a records a latent image by laser exposure on a transmission type recording medium (film) based on image data input from the image processing device 2, and visualizes the latent image by thermal phenomenon processing. This is a photothermal silver salt image recording apparatus. The image recording apparatus 3a includes two trays T1 and T2. For example, a film having a size of 6 is stored in the tray T1, and a film having a size of 4 is stored in the tray T2. It shall be. The maximum recording density Dmax of the film loaded in the trays T1 and T2 is 4.0.

  The image recording device 3b is, for example, an image recording device that records image data input from the image processing device 2 on a transmissive recording medium (film) by a photothermal silver salt method or a thermal method. The image recording apparatus 3b includes two trays T3 and T4. For example, the tray T3 stores a film having a size of four or more, and the tray T4 stores a film of a size that is half-cut. Shall. The maximum recording density Dmax of the film loaded in the trays T3 and T4 is 3.0.

  The image recording device 3c is, for example, an image recording device that records image data input from the image processing device 2 on a reflective recording medium (paper medium, sticker, or the like) by an inkjet method or a laser method. For example, the image recording device 3c records an image on a B5 size paper medium.

In addition, the image recording apparatuses 3a, 3b, and 3c have, for example, the following differences in recording characteristics.
The number of recording pixels of the image recording device 3b is relatively small compared to the number of recording pixels of the image recording device 3a. Further, the number of recording pixels of the image recording device 3c is relatively smaller than the number of recording pixels of the image recording device 3b.
The resolution of the image recording device 3b is relatively lower than the resolution of the image recording device 3a. The resolution of the image recording device 3c is relatively lower than the resolution of the image recording device 3b.
The density resolution of the image recording device 3b is relatively lower than the density resolution of the image recording device 3a. Further, the density resolution of the image recording device 3c is relatively lower than the density resolution of the image recording device 3b.
The maximum recording density of the image recording device 3b is relatively lower than the maximum recording density of the image recording device 3a. Further, the maximum recording density of the image recording apparatus 3c is relatively lower than the maximum recording density of the image recording apparatus 3b.
The number of gradations of the image recording device 3b is relatively small compared to the number of gradations of the image recording device 3a. Further, the number of gradations of the image recording device 3c is relatively smaller than the number of gradations of the image recording device 3b.

  For this reason, the images output from the image recording apparatuses 3a, 3b, and 3c have different image quality characteristics. The image quality characteristics of the image recording device 3a are relatively higher than those of the image recording devices 3b and 3c. The image quality characteristics of the image recording device 3b are relatively higher than those of the image recording device 3c.

Next, the internal configuration of the image processing apparatus 2 will be described.
FIG. 2 is a diagram illustrating a configuration of a main part inside the image processing apparatus 2 according to the present embodiment. 2, the image processing apparatus 2 includes an image input unit 11, an image data storage unit 12, a diagnosis support information generation unit 13, a diagnosis support information storage unit 14, a diagnostic image generation unit 15, a diagnosis support image generation unit 16, It comprises a diagnostic support image storage means 17, an image recording device information storage means 18, an operation display means 19, an image output means 20, and the like.

  The image input unit 11 acquires image data (referred to as image data D) of a digitally converted medical image from the image generation apparatuses 1 a to 1 c via the network N. Further, the image input means 11 may be configured to read the image data D from various storage media such as a CD-ROM or floppy (registered trademark) on which the photographed image data D is recorded. The image input means 11 includes an interface for connecting to an image generation apparatus such as a CR, CT, mammography apparatus, FPD, MRI, ultrasonic diagnostic apparatus, etc. via a cable or the like, and is generated by these apparatuses. The image data D may be acquired.

  When obtaining a digital medical image with the various configurations described above, the effective pixel size of the image is 200 μm or less, for example, for a mammogram (breast radiation image), depending on the imaging region and the diagnostic purpose. It is preferable that the thickness is 100 μm or less. In order to maximize the performance of the image processing apparatus 2 of the present invention, a configuration using image data D input with an effective pixel size of about 50 μm, for example, is preferable.

  The image input means 11 inputs image data D and incidental information related to the image data D, for example, patient information related to the patient such as the name, patient ID, age, and sex of the patient, image generation device information, and imaging Input image data information such as date, imaging ID, imaging site, imaging conditions (position, imaging direction, etc.), imaging information such as imaging apparatus, number of pixels of image data D, sampling pitch, number of bits, designated output size, When the image data D is output to the image data storage unit 12, the supplementary information is output in association with the image data D.

  The image data storage unit 12 stores the image data D input by the image input unit 11 by performing data compression as necessary. Here, as a data compression method, reversible compression or irreversible compression using a known method such as JPEG, DPCM (Differential Pulse Code Modulation), wavelet compression or the like is used, but there is no loss of diagnostic information due to data compression. Compression is preferred.

  In a small-scale diagnosis, the amount of data input from the image input means 11 is not so large, so that the image data D can be stored on the magnetic disk without being compressed. In this case, the image data D can be stored and read out at a very high speed as compared with the magneto-optical disk. Since a high-speed cycle time is required at the time of image interpretation, necessary image data D is also stored in the semiconductor memory.

  The diagnosis support information generation unit 13 includes an abnormal shadow candidate information generation unit 13a and a measurement information generation unit 13b.

  The abnormal shadow candidate information generation unit 13a reads out the image data D from the image data storage unit 12 and performs image analysis, so that abnormal shadows such as microcalcification clusters and tumor shadows in the mammogram and nodular shadows in the chest image are considered. The candidate is detected, and diagnostic support information including position information in the image of the abnormal shadow candidate is generated. An example of a microcalcification cluster is shown to Fig.3 (a). When microcalcifications are gathered (clustered), they are likely to be early cancers, which is an important finding for finding early breast cancer. On the mammogram, it appears as a whitish round shadow with a substantially conical structure. Further, the mass shadow shown in FIG. 3B is seen as a whitish and round shadow close to a Gaussian distribution on a lump or mammogram having a certain size.

A known detection method described in the following paper can be used for the method for detecting a shadow of a tumor.
(1) Mass shadow ・ Detection method by comparing left and right breasts (Med.Phys., Vol.21.No.3, pp.445-452)
・ Detection method using iris filter (Science theory (D-11), Vol.J75-D-11, no.3, pp.663-670,1992)
・ Detection method using Quiot filter (Science theory (D-11), Vol.J76-D-11, no.3, pp.279-287,1993)
・ Detection method by binarization based on histogram of pixel values of divided breast regions (JAMIT Frontier Proceedings, pp.84-85,1995)
・ Minimum direction difference filter that takes the minimum output of many directional Laplacian filters)
(Science Theory (D-11), Vol.J76-D-11, no.2, pp.241-249, 1993)
・ Method of distinguishing benign and malignant masses using fractal dimension (Medical Imaging Technology17 (5), pp.577-584,1999)

In addition, as a method for detecting an abnormal shadow candidate for a microcalcification cluster, a known detection method described in the following paper can be used.
(2) Microcalcification cluster ・ Method to localize the area suspected of calcification from the breast area and remove false positive candidates from the standard deviation value of the optical density difference and boundary density difference of the shadow image (IEEE Trance Biomed Eng BME-26 (4): 213-219,1979)
・ Detection method using images subjected to Laplacian filter processing (Science Theory (D-11), Vol.J71-D-11, no.10, pp.1994-2001,1988)
・ Detection method using morphologically analyzed image to suppress the influence of background pattern of mammary gland etc. (Science Theory (D-11), Vol.J71-D-11, no.7, pp.1170-1176,1992 )

Further, as other abnormal shadow candidate detection methods, for example, the following known detection methods can be used.
(3) Detection of nodular shadow in chest image-JP-A-6-121792 (4) Detection of interstitial disease shadow in chest image-JP-A-2-185240

  The measurement information generation unit 13b reads the image data D from the image data storage unit 12, performs image measurement, and generates diagnosis support information including position information in the image related to the measurement result. Image measurement includes, for example, measurement of cardiothoracic ratio used for diagnosis of cardiac hypertrophy in chest images, measurement of bone length of lower limbs used for surgical planning in lower limb images, and Cobb used for diagnosis of scoliosis in spine images. Measure corners. The measurement may be configured to be performed by automatic processing (for example, Medical Physics, Vol17, No.3, pp.342-350, 1990, Japanese Patent Laid-Open No. 7-381), or the operator can display the operation display unit 19. A configuration (for example, Japanese Patent Application Laid-Open No. 8-256993) calculated based on information input using a pointing device such as a touch pen or a mouse while observing an image displayed on the screen may be employed.

  The diagnosis support information storage unit 14 stores the diagnosis support information generated by the abnormal shadow candidate information generation unit 13a in association with the image data D and the diagnosis support information generated by the measurement information generation unit 13b. Is stored in correspondence with the image data D.

  As shown in FIG. 4A, the abnormal shadow candidate file 141 includes a shooting ID area 141a, an abnormality type area 141b, a position information area 141c, a size area 141d, and the like, and is specified by the shooting ID. The abnormality type, position information, and size, which are diagnostic support information generated by the abnormal shadow candidate information generation unit 13a with respect to the image data D, are stored in association with each other, and stored in the image data storage unit 12 by the photographing ID. The image data D and the diagnosis support information in the abnormal shadow candidate file 141 are associated with each other.

  The abnormality type area 141b stores data indicating the types of detected abnormal shadow candidates (for example, mass shadow, microcalcification, nodular shadow,...) As “abnormality type”. The position information area 141c is data indicating the coordinate value of the position of the center of gravity of the abnormal shadow candidate (for example, (x, y) = (100, 1200), (300, 700), (400, 500),...)). Is stored as “position information”. The position information is not limited to this, and may be a coordinate value indicating an abnormal shadow candidate image area, for example. It may also be indicated by the distance to the characteristic normal tissue.For example, when the imaging part is the chest, the position is determined by the distance between the centroid of the abnormal shadow candidate and the centroid of the lung field region that is the characteristic normal tissue. It may be shown. The characteristic normal tissue is a biological tissue with little positional change such as an organ or bone such as the heart, lungs, and vertebrae, and is preferably a tissue that can serve as an index of the temporal change in the position of the abnormal shadow candidate. The size information area 141d stores data indicating the area occupied by the image area of the abnormal shadow candidate (for example, 225 mm 2, 300 mm 2, 310 mm 2,...) As “size”. The size information may be indicated by an average distance or a longest distance (for example, 15 mm) from the center of gravity of the abnormal shadow candidate to the edge.

  As shown in FIG. 4B, the measurement information file 142 includes a shooting ID area 142a, a measurement target area 142b, a position information area 142c, a measurement result area 142d, and the like, and image data specified by the shooting ID. The measurement object, position information, and measurement result, which are diagnostic support information generated by the measurement information generation unit 14b with respect to D, are stored in association with each other, and the image data D stored in the image data storage unit 12 by the photographing ID And the diagnostic support information in the measurement information file 142 are associated with each other.

  The measurement target region 142b includes data indicating the measurement target (for example, chest-cardiothoracic ratio (%), lower limb bone-bone length (cm), spinal scissors-Cobb angle (degree),...) “Measurement target. ". The position information area 142c includes data (for example, {(200, 1200), (700, 1200), (1340, 1200), (1800, 1200)}) represented by coordinate values on the image of the point used for measurement, { (300, 1200), (300, 100)}, {(900, 500), (1000, 770), (1000, 1000)},...) Are stored as “position information”. The measurement result area 142d stores numerical data indicating the measurement result (for example, 40, 75, 20,...) As “measurement result”. The unit of the measurement result is set in advance for each measurement target.

  Note that the manner of saving each diagnosis support information is not limited to this, and for example, it may be saved in the header information of the image data D in the image data storage means 12.

  The diagnostic image creation means 15 performs image processing on the image data D (original image) input from the image data storage means 12 to create diagnostic image data for interpretation by a doctor, and sends it to the image output means 20. Output. The diagnostic image creating means 15 includes an image processing unit 15a and an output formatting unit 15b.

  The image processing unit 15 a performs image processing suitable for interpretation of a lesion shadow on the image data D input from the image data storage unit 12. Image processing includes gradation processing to adjust the contrast of the image, frequency enhancement processing to adjust the 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 the details of the subject. Processing etc. are included.

In the gradation processing, gradation processing conditions for giving sufficient contrast for interpretation of a lesion shadow are determined, and gradation processing is performed on the image data D under the determined image processing conditions. Two examples of gradation processing condition determination methods for generating diagnostic images are shown.
・ Method 1
First, the image data D is analyzed, and the lung field region extraction method in the chest image disclosed in Japanese Patent Laid-Open No. Hei 3-218578 and the Journal of Japanese Breast Cancer Screening Society, Vol.17, No.1, pp87-102,1998 are shown. An image region corresponding to a desired portion of the subject is set by using a thick mammary region extraction method or the like in mammography. Next, as shown in FIG. 5 (a), histogram analysis within the region is performed using the method disclosed in Japanese Patent Laid-Open No. 63-262141 and Japanese Patent Laid-Open No. 8-62751, and signal regions important for diagnosis are obtained. The corresponding area a is determined. After the region a is determined, a cumulative histogram in the region a is calculated, signal values S1 and S2 corresponding to predetermined cumulative histogram values (for example, 5% and 95%) are obtained, and these S1 and S2 are used as reference signal values. decide.

Next, as shown in Japanese Patent Application Laid-Open No. 59-83149, a reference gradation curve selected from several kinds of reference gradation curves prepared in advance is modified to show in FIG. 5B. In the input signal value Sin, a gradation conversion curve corresponding to a function F (Sin) is determined that converts the previously obtained reference signal values S1 and S2 into S1 ′ and S2 ′ in the output signal value Sout, respectively.
<Formula 1> Sout = F (Sin)
Here, S1 ′ and S2 ′ are values corresponding to predetermined reference output densities D1 and D2, respectively, and the relationship between the output signal value Sout and the density D is an image recording that is an output destination for outputting an image. It is determined by the characteristics of the devices 3a to 3c. The characteristics of the image recording apparatuses 3a to 3c are: image recording apparatus information (model, output image size (film size / number of vertical and horizontal pixels)), maximum and minimum recording densities, and densities stored in an image recording apparatus information storage unit 18 described later. Resolution, gradation characteristics, frequency characteristics, etc.). The diagnostic image is output to either the image recording device 3a or 3b based on the imaging region or the image generation device information included in the incidental information of the image data D. Specifically, if the imaging region is a breast, it is output to the image recording device 3a, and if the imaging region is other than the breast, it is output to the image recording device 3b.

・ Method 2
First, the reference signal values S1 and S2 are obtained by the same method as the method 1 described above. Next, as shown in FIG. 5C, a reference gradation curve G (Sstd) selected from the reference gradation curves prepared in advance is prepared. Then, a standardized straight line represented by a linear function L (Sin) is determined for the input signal value Sin so that the reference signal values S1 and S2 are converted into predetermined standardized signal values Sstd1 and Sstd2, respectively.
<Formula 2> Sstd = L (Sin)
Here, the normalized signal values Sstd1 and Sstd2 output output signal values S1 ′ and S2 ′ corresponding to the reference output densities D1 and D2 respectively determined when converted using the reference gradation curve Gstd. It is defined as a signal value.

  When the relationship between input and output in gradation processing is expressed by a curve graph with the horizontal axis representing the logarithm of the X-ray dose and the vertical axis representing the output density, the output density at two predetermined points (for example, 0.25 and 2.0) The average slope of the curve in between is called the average gradient.

  As gradation processing conditions for diagnostic images, it is required to have a high average gradient in order to observe lesion shadows and the like in detail. Specifically, it is 2.0 or more for mammography, and at imaging sites other than mammography. It is preferably 1.5 or more, more preferably 2.5 or more in mammography, and 2.0 or more in imaging regions other than mammography.

  Prior to gradation processing, if irradiation field recognition processing is performed to detect the radiation field area, it is necessary for diagnosis by setting various image processing conditions based on the image data in the recognized irradiation field area. This is preferable because image processing of the image portion can be appropriately performed. As a method for this irradiation field recognition processing, for example, means disclosed in JP-A-63-259538, JP-A-5-7579, and JP-A-7-181609 can be used.

  In the frequency processing, for example, a non-sharp mask process disclosed in Japanese Patent Publication No. 62-62373 and Japanese Patent Publication No. 62-62376, or a multi-resolution method disclosed in Japanese Patent Application Laid-Open No. 9-44645 is used. Control the sharpness.

  In addition, the low spatial frequency component of the image is controlled by the dynamic range compression process, and the entire image having a wide dynamic range is included in the easy-to-view density range. As a method of the dynamic range compression processing, for example, means disclosed in Japanese Patent No. 266318 can be used.

  Here, the image processing conditions for the frequency processing and the dynamic range compression processing are determined by the characteristics of the image recording apparatuses 3a and 3b serving as output destinations for outputting an image together with the analysis result of the image data D. The characteristics of the image recording apparatuses 3a and 3b are the same image recording apparatus information as described in the section of gradation processing.

The output formatting unit 15b performs rotation processing and inversion processing for correcting the diagnostic image that has been subjected to image processing such as gradation processing and frequency processing by the image processing unit 15a to a direction and size suitable for diagnosis. Then, trimming processing is performed.
In addition, when the imaging region is the breast, the output formatting unit 15b performs a synthesis process for composing the diagnostic images of the left and right breasts in the same imaging direction so as to be combined into one piece of diagnostic image data. Here, an alignment process (Japanese Patent Laid-Open No. 2000-287957) for aligning the left and right breasts based on the analysis of the image data D may be performed.

  Further, the output formatting unit 15b obtains the patient ID from the incidental information of the image data D as identification information adding means and uses this as identification information, and applies it to a predetermined area of the diagnostic image created by the image processing unit 15a. Add identification information. The identification information is not limited to the patient ID. For example, dedicated identification information (for example, imaging date + examination number of the day + serial number during the same examination) is automatically issued and added to a predetermined area of the diagnostic image. You may make it do.

  Further, the output formatting unit 15b serves as output information adding means that indicates whether or not there is a diagnostic support image for this diagnostic image (the output of the diagnostic support image for this diagnostic image is output from the operation display means 19). “Yes” when instructed and “No” when not instructed) are added to a predetermined area of the diagnostic image. Note that whether or not information indicating whether there is identification information and diagnosis support information is added to the diagnostic image can be switched based on an input from the operation display means 19.

  Further, the output formatting unit 15b acquires patient information such as a patient ID, a patient name, an imaging date, an imaging site / position from the incidental information of the image data D, and adds the patient information to a predetermined region of the diagnostic image. The combined diagnostic image data for output is output to the image output means 20.

  The diagnostic image data created by the diagnostic image creation means 15 or the image processing conditions applied to the image data D for creating the diagnostic image is associated with identification information in an HDD (Hard Disk Drive), It is desirable to store in a non-volatile memory such as a semiconductor. Further, the diagnostic image data and the image processing conditions are stored in a nonvolatile memory such as an HDD (Hard Disk Drive) or a semiconductor in association with the image data D stored in the image data storage unit 12 and the imaging ID. Is desirable. This eliminates the need to perform calculations for creating a diagnostic image again at the time of re-output. Also, by storing the image data D and the image processing conditions for creating the diagnostic image in association with each other, it is possible to keep a record of what conditions the doctor has determined based on the image created. it can.

  Further, information regarding whether or not there is a diagnostic support image for the diagnostic image is also stored in association with the identification information and the image data D, and the information is updated when the diagnostic support image is output later. It is preferable to continue. In this way, even when the diagnostic image is re-output, the presence / absence of the diagnostic support image at that time can be accurately displayed.

  The diagnostic support image creating unit 16 performs image processing on the image data D input from the image data storage unit 12 to create diagnostic support image data for referring to the diagnostic support information, and sends the image data to the image output unit 20. Output. The diagnostic image creating means 16 includes an image processing unit 16a, a diagnostic support information adding unit 16b, and an output formatting unit 16c.

  The image processing unit 16 a performs image processing suitable for referring to the diagnosis support information on the image data D input from the image data storage unit 12. The image processing unit 16a performs gradation processing, frequency processing, dynamic compression processing, and the like under image processing conditions different from those of the image processing unit 15a, and creates a diagnosis support image suitable for referring to diagnosis support information. Alternatively, the diagnosis support image may be created by creating a schema image from the image data D (first mode) (second mode).

(First aspect)
In the gradation processing, the image processing unit 16a determines a gradation processing condition for expressing the positional relationship of the annotation in an easy-to-understand manner within a density range where the entire image can be easily seen, and the image data is determined under the determined gradation processing condition. A gradation process is applied to D.
When the gradation processing condition for generating the diagnostic image is determined by using the method 1 described above in the image processing unit 15a, after determining the gradation conversion curve F (Sin) of the diagnostic image, The gradation conversion curve of the diagnosis support image is determined based on As a method for determining the gradation conversion curve of the diagnosis support image, the gradation conversion curve Fsub (sin) of the diagnosis support image is created by multiplying F (Sin) by a predetermined coefficient α (α <1.0). (See FIG. 5 (b)).
When the gradation processing condition for generating the diagnostic image is determined using the method 2 described above in the image processing unit 15a, the standardized straight line L (Sin) of the diagnostic image is determined, and then L ( By multiplying Sin) by a predetermined coefficient α (α <1.0), a standardized straight line Lsub (Sin) of the diagnosis support image is created (see FIG. 5C).
Alternatively, as the reference output densities Dsub1 and Dsub2 of the diagnostic support image, values smaller than the reference output densities D1 and D2 of the diagnostic image are set in advance, and the above-described gradation processing of the diagnostic image using Dsub1 and Dsub2 A method of determining the gradation processing condition of the diagnosis support image by including the same procedure as the condition determination method 1 or 2 may be used. Here, Dsub1 and Dsub2 are set so that the value of (Dsub2-Dsub1) is smaller than (D2-D1).

  As the diagnosis support image, a relatively low average gradient gradation processing condition is set in order to express the entire subject to the background in a density range that is easy to see. Specifically, it is preferably 3.5 or less for mammography, 3.0 or less for imaging parts other than mammography, more preferably 3.0 or less for mammography, and 2.5 or less for imaging parts other than mammography. . Furthermore, the average gradient of the diagnostic support image is preferably 80% or less of the average gradient of the diagnostic image.

  In this way, the gradation conversion curves F (Sin), Fsub (Sin), or standardized straight line L (so that the average gradient of the diagnostic support image becomes relatively smaller than the average gradient (slope) of the diagnostic image. Sin) and Lsub (Sin) are determined to give sufficient contrast to the interpretation of the lesion shadow in the diagnostic image for the purpose of diagnosis, and at the same time, the entire image is used for the diagnosis support image for the purpose of reference. It is possible to express the positional relationship between annotations in an easy-to-understand density range.

Further, the gradation processing conditions of the diagnosis support image may be determined as follows.
The tone conversion curve F (Sin) of the diagnostic image or the standardized straight line L (Sin) of the diagnostic image is inverted in the vertical axis direction.
The gradation conversion curve Fsub (Sin) or the normalized straight line Lsub (Sin) created so that the average gradient is lower than that of the diagnostic image by the method described above is inverted in the vertical axis direction.

  Thus, with respect to the average gradient of the gradation conversion curve or standardized straight line of the diagnostic image, or with respect to the average gradient of the gradation conversion curve or standardized straight line created so that the average gradient is lower than that of the diagnostic image. Thus, the gradation conversion curve or the normalization line of the diagnosis support image is determined so that the average gradient of the diagnosis support image has the value of the opposite sign. This provides sufficient contrast for the interpretation of lesion shadows in diagnostic images intended for diagnosis, and at the same time, in the diagnostic support images intended for reference, the black and white of the image is reversed to provide a boundary between the subject and the background. It is possible to express the positional relationship between the subject and the annotation in an easy-to-understand manner. This processing is particularly effective in mammography.

  The method for determining the gradation processing conditions of the diagnostic support image data can be selected and instructed by the user through the operation display means 19.

  In the frequency processing, for example, a non-sharp mask process disclosed in Japanese Patent Publication No. 62-62373 and Japanese Patent Publication No. 62-62376, or a multi-resolution method disclosed in Japanese Patent Application Laid-Open No. 9-44645 is used. Control the sharpness. At this time, the frequency processing condition is determined so that the low frequency component of the diagnostic support image is relatively attenuated compared to the low frequency component of the diagnostic image. This provides sufficient contrast for the interpretation of lesion shadows in diagnostic images for diagnostic purposes, and at the same time, in the diagnostic support images for reference purposes, the entire image is within an easy-to-view density range, The positional relationship can be expressed in an easy-to-understand manner. Further, as another aspect for relatively reducing the low frequency component of the diagnosis support image, in the dynamic range compression process, the low frequency component of the diagnosis support image is compressed compared to the diagnosis image. The dynamic range compression processing conditions may be determined so as to increase the degree.

(Second aspect)
The image processing unit 16a analyzes the image data D input from the image data storage unit 12 to perform contour extraction and generate a schema. As a contour extraction method, for example, as shown in Japanese Patent Laid-Open No. 63-240832, attention is paid to one row or column in the image data D, and the values of the preceding and succeeding data values in the one-dimensional density data sequence are ascertained. A specific pattern having a predetermined relationship (for example, a point having a minimum value, a point having the maximum inclination, a point having the minimum inclination, etc.) is used as a contour point in the row or column, and a row or column in a necessary range. A contour point is obtained for and a line connecting these points is defined as a contour line. Alternatively, other known contour extraction methods (for example, in mammography, medical electronics and biotechnology, Vol. 39, No. 4, pp 297-304, 2001) may be used.

  Note that the operation display means 19 can be used to select and instruct the image processing method for the diagnostic support image.

  The diagnosis support information adding unit 16b reads the diagnosis support information corresponding to the image data D from the abnormal shadow candidate file 141 or the measurement information file 142, and displays the annotation (diagnosis support information as symbols, characters, markers, etc.) corresponding thereto. Is created and added to the diagnostic support image data. At this time, an optimum annotation shape, size, color, and the like are determined based on the image recording device information stored in the image recording device information storage unit 18. Note that the shape, size, color, and the like of the annotation may be selected by the user from the operation display unit 19.

  The output formatting unit 16c performs a reduction process so that the diagnosis support image has a smaller size than the diagnosis image. Also, image rotation and inversion processing are performed.

The diagnosis support image may be an image representing the entire subject area represented by the diagnosis image, but is a portion obtained by cutting out a partial area of the image (for example, a partial area including an abnormal shadow candidate) based on the diagnosis support information It may be an image.
In addition, for the purpose of easily recognizing the position and size of the structure in the diagnosis support image, a scale (scale) is added to the diagnosis support image, or a grid pattern of equal intervals is superimposed on the diagnosis support image. It may be shown.
In addition to the annotation, information indicating abnormal shadow candidates or information on measurement information as character information or the like may be added outside the image area of the diagnosis support image.

  In addition, when the imaging region is the breast, the output formatting unit 16 performs a synthesis process in which the diagnostic support images of the left and right breasts in the same imaging direction are opposed to each other and combined into one diagnostic support image. Here, an alignment process (Japanese Patent Laid-Open No. 2000-287957) for aligning the left and right breasts based on the analysis of the image data D may be performed. In addition, a diagnostic support image is fitted into a predetermined area of a preset output format, and diagnostic support image data for output is created.

  Further, the output formatting unit 16c adds the same identification information as the output formatting unit 15b to a predetermined area of the output format as identification information adding means. Whether or not the identification information is added can be switched based on an input from the operation display means 19.

  Further, the output formatting unit 16c adds patient information such as a patient ID, a patient name, an imaging date, and an imaging site / position included in the incidental information of the image data D to a predetermined area of the output format. The synthesized output image data for diagnosis support is output to the image output means 20.

  For example, when a plurality of pieces of diagnosis support information (for example, a tumor and a microcalcification cluster) exist for one image data D, a diagnosis support image is created for each piece of diagnosis support information. Alternatively, a single diagnosis support image may be created by collecting all the diagnosis support information.

  The diagnostic support image data for output created in this way is stored in the diagnostic support image storage means 17.

  The diagnosis support image storage unit 17 stores the data of the diagnosis support image created by the diagnosis support image creation unit 16 in association with the identification information. In this way, when only the diagnosis support image is output later according to an instruction from the operation display means 19, the image output means 20 may read out and output the stored diagnosis support image, thereby reducing the processing load. Can be made. Further, it is desirable that the diagnosis support image data and the identification information are stored in association with the image data D stored in the image data storage unit 12. Specifically, the image data D, the diagnosis support image, and the identification information are associated with each other by a shooting ID for specifying the image data D. Or you may make it preserve | save a diagnostic support image and identification information in the header information of the image data D of the image data storage means 12. FIG.

  The image recording device information storage unit 18 is connected to the image processing device 2 via the network N, and stores information of each image recording device that can be output from the image processing device 2 in association with an output channel. FIG. 6 shows an example of the image recording device information storage unit 18. As shown in FIG. 6, the image recording device information storage unit 18 associates the output channel with the model of the image recording device, the tray, the output target image, the output target photographing part, and the output image size (film size / number of vertical and horizontal pixels). ), Maximum and minimum recording densities, density resolution, gradation characteristics, frequency characteristics, output target image generation apparatus, etc.) are stored.

  The operation display means 19 is composed of an LCD (Liquid Crystal Display), displays various operation buttons and device status on the display screen, a diagnostic image output to the image recording devices 3a to 3c, a preview display of a diagnostic support image, and the like. I do. The LCD display screen is covered with a pressure-sensitive (resistive film pressure) touch panel configured with transparent electrodes arranged in a grid, and the XY coordinates of the force point pressed with a finger or a touch pen are expressed as voltage values. The detected position signal is output as an operation signal. The display device and the input device may be separated. As the display device, a CRT, a liquid crystal display, a plasma display, or the like can be used. As the input device, a keyboard provided with function keys corresponding to various functions such as a cursor key, a numeric input key, and a determination key, and a pointing device such as a mouse can be used.

  In addition, the operation display means 19 is an input instruction means for inputting diagnosis support information and / or an instruction to output a diagnosis support image by the user. For example, the operation display unit 19 displays a screen for inquiring whether or not to output a diagnostic image and / or a diagnostic support image when creating a diagnostic image, and the image is displayed when an output instruction is input from the user. This output instruction is output to the output means 20. When the user inputs identification information and a diagnosis support image output instruction after the diagnosis image is output, the diagnosis support image output instruction corresponding to the input identification information is output to the image output means 20. .

  The image output means 20 serves as an output enable / disable selection means based on whether an instruction to output a diagnostic image and a diagnostic support image is input from the operation display means 19. Whether or not to output the diagnostic image data is independently selected, and the diagnostic image data output from the diagnostic image creation means 15 is output to the image recording apparatus. Further, the diagnostic support image data is read from the diagnostic support image storage means 17 and output to the image recording apparatus.

  Here, the image output means 20 has a plurality of output channels corresponding to a plurality of image recording apparatuses and their respective trays. Further, it has an output channel selection means 20a for independently selecting which of the plurality of output channels to output the diagnostic image and the diagnostic support image, and corresponds from the output channel selected by this output channel. Image data for diagnosis or image data for diagnosis support is output to the image recording apparatus. Information of the image recording device (or each tray thereof) corresponding to each output channel is stored in the image recording device information storage unit 18.

  The output channel selection means 20a automatically selects the optimum output channel based on the incidental information of the output target image and whether the output target image is a diagnostic image or a diagnostic support image. For example, when the imaging part included in the supplementary information of the image to be output is the breast, or the image generation device information is information indicating the image generation device 1c, the designated output size is six cuts, and the output target image is a diagnostic image, The output channel selection unit 20a refers to the image recording device information storage unit 18 and selects an output channel corresponding to the tray T1 of the image recording device 3a. When the imaging region included in the incidental information of the image to be output is information indicating the chest, or the image generation device information is the information indicating the image generation device 1a, the output designation size is large, and the output target image is a diagnostic image. The output channel selection unit 20a refers to the image recording device information storage unit 18 and selects an output channel corresponding to the tray T3 of the image recording device 3b. Regardless of the incidental information of the image to be output, when the output target image is a diagnosis support image, the output channel selection means 20a selects an output channel corresponding to the image recording device 3c. Alternatively, the output channel selection unit 20 a may select an output channel based on the input from the operation display unit 19.

  Alternatively, in the image generation devices 1a to 1c, an image recording device that should output a diagnostic image or a diagnosis support image is determined in advance, and the determined image recording device name is transmitted to the image processing device 2 as image supplementary information. The image processing apparatus 2 may be configured to select an output channel corresponding to the image recording apparatus name designated based on the image supplementary information.

  Although the image processing apparatus 2 has been described above, the diagnostic support information generating unit 13, the diagnostic image creating unit 15, the diagnostic support image creating unit 16, and the image output unit 20 are a CPU (Central Processing Unit) and a ROM (Read Only). It may be realized by software processing in cooperation with a program stored in (Memory), or may be configured by dedicated hardware. The image data storage unit 12, the diagnosis support information storage unit 14, the diagnosis support image storage unit 17, and the image recording apparatus information storage unit 18 may be stored in the same recording apparatus and recording medium.

  Examples of diagnostic images and diagnostic support images output by the medical image processing system 100 are shown below.

  FIG. 7A shows an example of a hard copy 300 of a diagnostic image that has been subjected to image processing by the image processing apparatus 2 and output from the image recording apparatus 3a. This hard copy 300 is an example when the operation display means 19 is set not to display identification information. As shown in FIG. 7A, in the hard copy 300, two diagnostic images of a right breast mammogram and a left breast mammogram are printed on one film. In FIG. 7A, 300a is a diagnostic image of a mammogram of the right breast, and 300b is a diagnostic image of a mammogram of the left breast. In the upper left of the hard copy, patient information 300c such as a patient ID and a patient name is displayed.

  FIG. 7B shows an example of a hard copy 301 of an image for diagnosis support that has been subjected to image processing by the image processing apparatus 2 and output from the image recording apparatus 3c. The hard copy 301 is a diagnostic support image for the hard copy 300 of the diagnostic image in FIG. 7A and is printed on a paper medium. As shown in FIG. 7B, the hard copy 301 displays a diagnosis support image 301a for the diagnosis image shown in FIG. 7A and patient information 301b such as a patient ID and a patient name. Abnormal shadow candidates are displayed as annotations in the diagnosis support image 301a. “M” in the diagnosis support image indicates a tumor candidate, and “C” indicates a microcalcification cluster.

  FIG. 8A shows an example of a hard copy 302 of a diagnostic image that has been subjected to image processing by the image processing apparatus 2 and output from the image recording apparatus 3a. As shown in FIG. 8A, in the hard copy 302, two diagnostic images of a right breast mammogram and a left breast mammogram are printed on one film. In FIG. 8A, 302a is a diagnostic image of a mammogram of the right breast, and 302b is a diagnostic image of a mammogram of the left breast. On the upper left of the hard copy, patient information 302c such as a patient ID and a patient name is displayed. In the lower part of the hard copy, identification information for associating the diagnostic image with the diagnostic support image and information 302d indicating whether or not the diagnostic support image is output are displayed. When there are a plurality of diagnosis support information, for example, when a tumor and a microcalcification cluster are created as separate diagnosis support images, the presence / absence of each diagnosis support information image is displayed together with the information. You may do it.

  FIG. 8B shows an example of a hard copy 303 of a diagnosis support image that has been subjected to image processing by the image processing device 2 and output from the image recording device 3c. The hard copy 303 is a diagnostic support image for the hard copy 303 of the diagnostic image shown in FIG. 8A, and is printed on a paper medium. As shown in FIG. 8B, on the left side of the hard copy 303 is a patient such as an identification number 303a, a diagnosis support image 303b, a patient ID, and a patient name for associating the diagnosis image with the diagnosis support image. Information 303c is displayed. The diagnosis support image of the hard copy 303 is a schema image, and abnormal shadow candidates are displayed as annotations on the schema image. A portion indicated by a triangle on the schema image indicates a tumor candidate, and a portion surrounded by a circle indicates a microcalcification cluster. Also, an interpretation result entry field 303d is provided on the right side of the hard copy so that a doctor can enter the interpretation result.

  FIG. 9A shows an example of a hard copy 304 of a diagnostic image that has been subjected to image processing by the image processing apparatus 2 and output from the image recording apparatus 3b. As shown in FIG. 9A, the hard copy 304 has a diagnostic image 304a on the front of the chest printed on a film. On the upper left of the hard copy, patient information 304b such as a patient ID and a patient name is displayed. In the lower part of the hard copy, identification information for associating the diagnostic image with the diagnostic support image and information 304c indicating the presence or absence of the diagnostic support information are displayed.

  FIG. 9B shows an example of a hard copy 305 of a diagnostic support image that has been subjected to image processing by the image processing device 2 and output from the image recording device 3c. This hard copy 305 is a diagnostic support image for the hard copy 305 of the diagnostic image in FIG. 9A, and is printed on a paper medium. As shown in FIG. 9B, the hard copy 305 includes patient information 305c such as an identification number 305a, a diagnosis support image 305b, a patient ID, and a patient name for associating the diagnosis image with the diagnosis support image. It is displayed. In the diagnosis support image 305b, a measurement result “40%” of the cardiothoracic ratio measured from the chest front image and an annotation indicating the measured position are displayed.

  The output format of the diagnostic image and the diagnostic support image shown in FIGS. 7 to 9 is preferably selected by the user from the operation display unit 19.

  A hard copy of the diagnostic support image output by the medical image processing system 100 may be stored together in a film bag for storing the hard copy of the diagnostic image, or stored in a pocket provided in the film bag, It can be stored and used by being affixed to a film bag or affixed to a medical chart.

  As a method of using the diagnosis support image, when the diagnosis support image is output to a reflective recording medium such as paper, the diagnosis support image can be placed on a desk and referred to when the diagnosis image is read on the Schaukasten.

  In addition, the diagnosis support image may be output to a transmissive recording medium such as a film. In this case, when the diagnostic image is read on the shaucus ten, it can be set and referred to on the shaucus ten. .

  The diagnosis support image may be output on a sheet with an adhesive such as a sticker.

  The diagnosis support image can be output at any time by inputting the identification information on the operation display means 19 and instructing the output, so that the diagnosis support image can be output according to the hospital workflow or the doctor's usage. is there. The identification number may be directly input by the user, or a list of identification numbers is displayed on the operation display means 19, and by selecting identification information from this list, a corresponding diagnostic support image is output. Also good.

  As described above, in the image processing apparatus 2 described above, image processing suitable for diagnosis is performed on the image data D input from the image input unit 11 to create a diagnostic image. In addition, diagnostic support information related to the image data D input from the image input unit 11 is created, image processing suitable for reference is performed on the image data D, an annotation indicating the diagnostic support information is added, and an image for diagnosis support is added. Create The diagnostic support image is selected from the output channel corresponding to the image recording device 3c, and the diagnostic image is selected according to the imaging region, the image generation device information, and the output image size included in the supplementary information. Output from the output channels corresponding to 3a or 3b, respectively.

  Therefore, even when a hard copy such as a silver halide film is read using a conventional image observation apparatus such as Saucusten, diagnosis support information can be easily and quickly obtained without loss of diagnostic image information. It becomes possible to refer to and utilize, and the diagnostic performance and work efficiency of a doctor can be improved without changing the flow of hospital work. In addition, since the diagnostic support image is output from a general-purpose image recording device that is not as high-performance as the diagnostic image that is required to have a high image quality for interpretation, the cost of outputting the diagnostic support image is suppressed. can do.

In addition, the description content in the said embodiment is a suitable example of the medical image processing system 100, and is not limited to this.
For example, in the above embodiment, a diagnostic support image is also created at the time of creating the diagnostic image, and if there is no instruction to output the diagnostic support image, it is stored in the diagnostic support image storage means 17, When the output of the diagnostic support image is instructed, the image output unit 20 reads out and outputs the diagnostic support image from the diagnostic support image storage unit 17. However, when the diagnostic image is created, the output of the diagnostic support image is not instructed. In this case, the processing by the diagnostic support image creation unit 16 is omitted, and when the output instruction is input again, the diagnostic support image generation unit 16 reads the data from the image data storage unit 12 and the diagnostic support information storage unit 14. Thus, a configuration may be adopted in which a diagnostic support image of the instructed image data D is created and output by the image output means 20.

  Even if an instruction to output a diagnosis support image is input, if the number of detected cases is 0 as a result of the abnormal shadow candidate, only the display indicating that it is 0 is displayed on the operation display means 19, and output is performed. It may not be performed.

  In the above embodiment, information indicating whether or not the diagnosis support image is output to the image recording apparatus (information indicating whether or not there is diagnosis support information) is added to the diagnosis image and output. However, similarly, in the output formatting unit 16c, as output information adding means, information indicating whether or not the diagnostic image is output to the image recording apparatus is added to the diagnostic support image and output. Also good.

  In the above embodiment, the image processing means 20 for outputting the diagnostic image and the diagnostic support image to the image recording apparatus suitable for each image is configured to be provided inside the medical image processing apparatus 2. The processing means 20 may be an independent device connected to the network N.

  In the above embodiment, the medical image processing system 100 includes a plurality of image recording devices 3a to 3c, and each of the diagnostic image and the diagnostic support image created by the image processing device 2 is different from each other. However, one image recording device (referred to as image recording device 3d) is provided with a plurality of trays, and recording media having different recording characteristics (for example, maximum recording density) are placed for each tray. The image output means 20 of the image processing device 2 uses different recording media for each of the diagnostic image and the diagnostic support image from the types of recording media placed on each tray of the image recording device 3d. The type may be selected, and a diagnostic image, a diagnostic support image, and information on the type of the selected recording medium may be output to the image recording apparatus 3d. For example, when the image recording apparatus 3d includes two trays on which recording media having a maximum recording density of 4.0 and a maximum recording density of 3.0 are mounted, the maximum recording density of the diagnostic image is 4.0. The recording medium having the maximum recording density of 3.0 is selected for the diagnosis support image. In the image recording apparatus 3d, the recording medium is conveyed from the tray loaded with the recording medium selected for each image based on the information on the type of the recording medium output from the image processing apparatus 2, and recorded.

  As a result, the diagnostic image and the diagnostic support image can be output separately. Therefore, even when a hard copy such as a silver salt film is read using a conventional image observation apparatus such as Saucusten. Diagnostic information can be referred to and used easily and quickly without missing diagnostic image information, and the diagnostic performance and work efficiency of doctors can be improved without changing the flow of hospital work. it can. In addition, diagnostic support images are recorded on a general-purpose recording medium that is not as high-performance as diagnostic images that are required to have high image quality for interpretation, thus reducing the cost of diagnostic support image output. can do.

  At this time, the image processing apparatus 2 obtains information (for example, maximum recording density, size, output target image, output target imaging part, output target image generation apparatus, etc.) corresponding to the type of recording medium that can be used in the image recording apparatus. If the recording medium information storage unit is provided, the image output unit 20 can easily select the recording medium with reference to the recording medium information storage unit. Further, in the diagnostic image creation means 15 and the diagnosis support image creation means 16, conditions for creating a diagnostic image and a diagnostic support image (for example, based on the recording medium information stored in the recording medium information storage means (for example, If gradation processing conditions, annotation colors, etc.) are determined, an image corresponding to the type of recording medium can be created.

  In addition, the detailed configuration and detailed operation of the medical image processing system 100 can be changed as appropriate without departing from the spirit of the present invention.

1 is a diagram showing an overall configuration of a medical image processing system 100 according to the present invention. It is a block diagram which shows the functional structure of the image processing apparatus 2 of FIG. (A) is a figure which shows an example of a microcalcification cluster, (b) is a figure which shows an example of a tumor shadow. It is a figure which shows the data storage example of the abnormal shadow candidate file 141 and the measurement information file 142 which the diagnostic assistance information storage means 14 of FIG. 2 preserve | saves. (A) is a figure which shows an example of a histogram analysis, (b) is a figure which shows an example of the determination method of a gradation conversion curve, (c) is a figure which shows the determination method of a normalization line. It is a figure which shows the example of data storage of the image recording apparatus information preservation | save means 18 of FIG. FIG. 3 is a diagram illustrating an example of a hard copy 300 that is image-processed by the image processing apparatus 2 of FIG. 1 and output from the image recording apparatus 3a and a hard copy 301 that is output from the image recording apparatus 3c. FIG. 3 is a diagram illustrating an example of a hard copy 302 that is image-processed by the image processing apparatus 2 of FIG. 1 and that is output from the image recording apparatus 3a and a hard copy 303 that is output from the image recording apparatus 3c. FIG. 2 is a diagram illustrating an example of a hard copy 304 that is processed by the image processing apparatus 2 of FIG. 1 and output from the image recording apparatus 3b, and a hard copy 305 that is output from the image recording apparatus 3c.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Medical image processing system 1a-1c Image generation apparatus 2 Image processing apparatus 3a-3c Image recording apparatus 11 Image input means 12 Image data storage means 13 Diagnosis support information generation means 13a Abnormal shadow candidate information generation part 13b Measurement information generation part 14 Diagnosis Support information storage means 15 Diagnosis image creation means 15a Image processing section 15b Output formatting section 16 Diagnosis support image creation means 16a Image processing section 16b Diagnosis support information addition section 16c Output formatting section 17 Diagnosis support image storage means 18 Image Recording device information storage means 19 Operation display means 20 Image output means 20a Output channel selection means

Claims (19)

In a medical image processing system comprising an image processing device that performs image processing on a medical image, and a plurality of image recording devices that record and output the medical image output from the image processing device,
The image processing apparatus includes:
Diagnostic image creation means for creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
A diagnostic support information generating means for generating diagnostic support information related to the medical image by analyzing the medical image;
Diagnostic support image creating means for creating a diagnostic support image using the diagnostic support information generated by the diagnostic support information generating means;
Identification information adding means for adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
Image output means for outputting the diagnostic image and the diagnostic support image to each of different image recording devices;
A medical image processing system comprising:   The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and the recording characteristics are different from each other. Medical image processing system.   The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and outputs images having different image quality characteristics. The medical image processing system according to 1 or 2.   The plurality of image recording apparatuses include an image recording apparatus that outputs the diagnostic support image and an image recording apparatus that outputs the diagnostic image, and the quality of recording media used for each of them is different. The medical image processing system according to any one of 1 to 3.   The image output means of the image processing device has a plurality of output channels corresponding to the plurality of image recording devices, and outputs the diagnosis image and the diagnosis support image to any of the plurality of output channels. The medical image processing system according to any one of claims 1 to 4, further comprising output channel selection means for independently selecting whether or not to perform. The image processing device includes image recording device information storage means for storing image recording device information corresponding to the plurality of image recording devices,
The diagnostic image creation means and the diagnostic support image creation means of the image processing device are configured to create the diagnostic image and the diagnostic support image based on the image recording device information stored in the image recording device information storage means. The medical image processing system according to claim 1, wherein the condition is determined. An image processing apparatus for performing image processing on a medical image, and an apparatus for recording and outputting the medical image output from the image processing apparatus, the image recording apparatus including a plurality of types of recording media having different recording characteristics In a medical image processing system consisting of
The image processing apparatus includes:
Diagnostic image creation means for creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
A diagnostic support information generating means for generating diagnostic support information related to the medical image by analyzing the medical image;
Diagnostic support image creating means for creating a diagnostic support image using the diagnostic support information generated by the diagnostic support information generating means;
Identification information adding means for adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
A different recording medium type is selected for each of the diagnostic image and the diagnostic support image from the plurality of types of recording media, and the diagnostic image, the diagnostic support image, and the selected recording are selected. Image output means for outputting medium type information to the image recording device;
A medical image processing system comprising:   The image output means of the image processing apparatus has a plurality of output channels corresponding to the plurality of types of recording media, and outputs the diagnosis image and the diagnosis support image to any of the plurality of output channels. 8. The medical image processing system according to claim 7, further comprising output channel selection means for independently selecting whether or not to perform. The image processing apparatus includes a recording medium information storage unit that stores recording medium information corresponding to the plurality of types of recording media,
The diagnostic image creation means and the diagnostic support image creation means of the image processing device are configured to create the diagnostic image and the diagnostic support image creation based on recording medium information stored in the recording medium storage means. The medical image processing system according to claim 7, wherein the medical image processing system is determined.   The image processing apparatus includes output enable / disable selecting means for independently selecting whether or not to output the diagnostic image and the diagnostic support image to any of the plurality of image recording apparatuses. The medical image processing system according to any one of claims 1 to 9.   The image processing device adds information indicating whether one of the diagnostic image and the diagnostic support image is output to any one of the plurality of image recording devices to the other image. The medical image processing system according to claim 1, further comprising output information adding means. The image processing apparatus includes:
Diagnostic support image storage means for storing the diagnostic support image;
An output instruction means for inputting an output instruction of the diagnostic support image;
The image output means of the image processing apparatus reads the diagnosis support image from the diagnosis support image storage means and outputs it to the image recording apparatus based on input information from the output instruction means. The medical image processing system according to any one of claims 1 to 11. The image processing apparatus includes:
Diagnostic support information storage means for storing the diagnostic support information;
An output instruction means for inputting an output instruction of the diagnostic support image;
The diagnostic support image creation means of the image processing device reads the diagnostic support information from the diagnostic support information storage means based on the input information from the output instruction means, creates a diagnostic support image,
The medical image processing system according to claim 1, wherein the image output unit of the image processing apparatus outputs the created diagnostic support image to the image recording apparatus. The diagnostic image creating means of the image processing apparatus determines an image processing condition by analyzing the medical image, and performs image processing including at least gradation processing on the medical image using the determined image processing condition. To create a diagnostic image,
The diagnostic support image creating means of the image processing apparatus performs image processing on the medical image using an image processing condition different from that used in the diagnostic image creating means, and the image subjected to the image processing. The medical image processing system according to any one of claims 1 to 13, wherein a diagnostic support image is created by adding diagnostic support information generated by the diagnostic support information generating means to the image.   The diagnostic support image creating means of the image processing apparatus creates a schema image corresponding to the medical image, and adds diagnostic support information generated by the diagnostic support information generating means to the schema image, thereby providing diagnostic support. The medical image processing system according to claim 1, wherein a medical image is created.   16. The diagnostic support information generation means of the image processing apparatus detects an abnormal shadow candidate by analyzing the medical image, and generates diagnostic support information related to the detected abnormal shadow candidate. The medical image processing system according to any one of the above.   The medical support information according to any one of claims 1 to 15, wherein the diagnosis support information generation unit performs image measurement by analyzing the medical image and generates the diagnosis support information related to a measurement result. Image processing system. In a medical image processing method in a medical image processing system comprising an image processing device that performs image processing on a medical image and a plurality of image recording devices that record and output the medical image output from the image processing device.
Creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
Generating diagnostic support information related to the medical image by analyzing the medical image;
Creating a diagnostic support image using the generated diagnostic support information;
Adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
Outputting the diagnostic image and the diagnostic support image to each of different image recording devices;
A medical image processing method comprising: An image processing apparatus for performing image processing on a medical image, and an apparatus for recording and outputting the medical image output from the image processing apparatus, the image recording apparatus including a plurality of types of recording media having different recording characteristics In the medical image processing method in the medical image processing system comprising:
Creating a diagnostic image by performing image processing including at least gradation processing on the medical image;
Generating diagnostic support information related to the medical image by analyzing the medical image;
Creating a diagnostic support image using the generated diagnostic support information;
Adding identification information that associates the diagnostic image created from the same medical image with the diagnostic support image to the created image;
A different recording medium type is selected for each of the diagnostic image and the diagnostic support image from the plurality of types of recording media, and the diagnostic image, the diagnostic support image, and the selected recording are selected. Outputting medium type information to the image recording device;
A medical image processing method comprising:

Images