JP2009061156A - Medical image diagnosis support system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a medical image diagnosis support system capable of easily visualizing an abnormal shadow of early cancer or the like on an X-ray image. <P>SOLUTION: The medical image diagnosis support system comprises a CPU 11 acquiring the position of an abnormal candidate shadow region extracted beforehand on a tomographic image of a subject, converting the position of the acquired abnormal candidate shadow into coordinate or a region on the X-ray image of the subject, and combining pixel information of the abnormal candidate shadow region with the converted coordinates or region on the X-ray image to form a first image, and a display 15 displaying the formed first image. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a medical image diagnosis support system that supports a diagnosis of a doctor using an image displayed on an X-ray image diagnosis apparatus including digital radiography.

Conventionally, when doctors discover abnormal shadows such as lung cancer by interpretation, it is known that tomographic images such as CT are superior to early detection of abnormal shadows than simple X-ray images. For example, in the case of an X-ray image, it is difficult to find it unless the shadow is about 3 cm in size, but in the case of a tomographic image such as a CT, it is possible to find a size of about 5 mm. Therefore, the doctor first interprets the CT image and confirms the abnormal shadow position, and then starts taking a low-exposure X-ray image next time. Then, based on the tomographic image, an abnormal shadow or the like found by CAD or interpretation is used as a specific area, and its coordinates are acquired. When the coordinates of the acquired specific area are converted to the coordinates or area on the X-ray image and the converted coordinates or area can be specified, it may be displayed with a mark on the normal X-ray image. is there. (For example, Patent Document 1)

JP 2006-101975 gazette

  However, in Patent Document 1, the existence area of the abnormal shadow is only clarified, and it is an unresolved problem that the abnormal shadow such as early cancer cannot be found by viewing the abnormal shadow only from the X-ray image. There is.

  An object of the present invention is to provide a medical image diagnosis support system in which abnormal shadows such as early cancer can be easily visually recognized on an X-ray image.

  The medical image diagnosis support system according to the present invention includes a position acquisition unit that acquires a position of an abnormal candidate shadow region extracted in advance on a tomographic image of a subject, and a position of the abnormal candidate shadow acquired by the position acquisition unit. A position converting means for converting the coordinates or area on the X-ray image of the subject, and the pixel information of the abnormal candidate shadow area is combined with the coordinates or area on the X-ray image converted by the position converting means. And an image composition means for generating the first image, and a display means for displaying the first image generated by the image composition means.

  According to the present invention, it is possible to provide a medical image diagnosis support system in which abnormal shadows such as early cancer can be visually recognized on an X-ray image.

  Hereinafter, preferred embodiments of a medical image diagnosis support system according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a hardware configuration diagram showing a configuration of a medical image diagnosis support system 1 according to an embodiment of the invention.

  The medical image diagnosis support system 1 in FIG. 1 stores a medical tomographic imaging apparatus 2 such as an X-ray CT apparatus, an MRI apparatus, an ultrasonic apparatus, and a PET, and a medical image captured by the medical tomographic imaging apparatus 2. An image database 4 and a medical image display device 10 for displaying medical images are provided. The medical tomographic imaging apparatus 2, the image database 4, and the medical image display apparatus 10 are connected to each other via a network such as LAN3.

  In the medical image display device 10, a central processing unit (CPU) 11, a main memory 12, a magnetic disk 13, a display memory 14, a keyboard 16, and a controller 18 are connected to each other via a common bus 19.

  The CPU 11 mainly controls the operation of each component. The main memory 12 stores a control program for the apparatus and serves as a work area when executing the program. The magnetic disk 13 stores an operating system (OS), peripheral device drives, various application software including a program for performing quantitative evaluation of a region of interest from medical images, and the like. The display memory 14 temporarily stores display data used for display on the display 15. The display 15 is connected to the display memory 14 and displays an image based on data from the display memory 14, and there are types such as a CRT monitor and a liquid crystal monitor. The keyboard 16 mainly inputs character information such as a subject ID. The mouse 17 is connected to the controller 18, the mouse cursor is displayed on the display 15, and a soft switch provided on the display 15 and a setting of a region of interest of the display image are input. The controller 18 detects the state of the mouse 17 and outputs signals such as the position of the mouse pointer on the monitor 15 and the state of the mouse 17 to the CPU 11.

  In the present embodiment, the medical image display device 10 reads a medical image from the image database 4 via the LAN 3, but a storage device connected to the medical image display device 10, such as an FDD, a CD-RW drive, an MO drive Medical images may be read from a ZIP drive or the like. Alternatively, a medical image may be acquired directly from the medical tomographic imaging apparatus 2 via the LAN 3.

  FIG. 2 is a diagram showing a main flow executed by the medical image diagnosis support apparatus of FIG. The CPU 11 in FIG. 1 operates according to this main flow. Hereinafter, details of the main flow will be described in the order of steps.

  First, since the subject ID input screen is displayed on the display 14 of the medical image diagnosis support apparatus, the operator inputs the patient ID number. Then, a tomographic image corresponding to the ID number of the patient to be diagnosed is read from the magnetic disk 12 from the tomographic images taken in advance by the medical image modality. When reading is completed, a tomographic image (current image) is displayed.

  FIG. 2 is a flowchart showing an example of an execution program of the medical image display apparatus. 3 to 5 are diagrams showing an example of image display in the medical image display apparatus of FIG.

[Step S20]
The CPU 11 acquires the coordinates of the abnormal shadow on the tomographic image such as a CT image. The acquisition method may be extracted manually by an operator using a mouse or the like, or automatically using CAD (Computer-Aided Detection) processing as disclosed in JP-A-2002-325761. The position of the abnormal candidate shadow may be extracted.

[Step S21]
The CPU 11 converts the coordinates of the abnormal candidate shadow acquired in step S20 into coordinates on the X-ray image photographed by the X-ray image diagnostic apparatus. If a conversion formula is determined between the CT apparatus and the X-ray diagnostic imaging apparatus, that formula is used. If the formula is not determined, for example, a pseudo X-ray image is first generated by calculation from the CT image, and the size of the X-ray image and the entire pseudo X-ray image taken by the X-ray image diagnostic apparatus, or an organ (e.g., A coordinate conversion formula may be obtained by calculating alignment of anatomical information (such as lungs) based on similarity such as shape.

[Step S22]
In step S21, the CPU 11 obtains a position where the abnormal candidate shadow on the CT image corresponds to the photographed X-ray image. The CPU 11 combines the pixel information of the abnormal candidate shadow area with the coordinates or area on the X-ray image to generate a first image. Further, the corresponding part on the X-ray image may be emphasized. This enhancement processing method may be n times the pixel value. Moreover, you may emphasize by the maximum value of the vicinity pixel.

[Step S23]
The CPU 11 writes the first image generated in step S22 into the display memory 14. The first image written in the display memory 14 is displayed on the display 15 as shown in FIGS.

  In FIG. 3, an X-ray image 31 photographed in parallel by DR (digital radiography) or the like and a first image 32 of the present invention are displayed in parallel in a display area 30 in the display image. Further, as shown in FIG. 4, the first image 32 may be displayed alone.

  Further, in FIG. 5, a second image obtained by performing the same treatment as the first image on an image photographed in the past of the same subject and an X-ray image 33 photographed on that day are displayed. This makes it possible to easily observe the progress on the X-ray image.

  6 is a flowchart showing another embodiment of FIG. 2, and FIG. 7 is a diagram showing an example of image display in the medical image display apparatus of FIG.

[Step S60]
As in step S20, the CPU 11 acquires the coordinates of the abnormal shadow on the tomographic image.

[Step S61]
When the CPU 11 acquires the position of the abnormal shadow on the tomographic image manually in the acquisition process, the CPU 11 calculates a feature amount such as the size of the abnormal shadow candidate and the position in the whole.

[Step S62]
As in step S21, the CPU 11 converts the coordinates of the abnormal shadow candidate into coordinates on the X-ray image.

[Step S63]
The CPU 11 enhances the shadow on the X-ray image by a shadow enhancement method according to the characteristics (size, existing position and shadow type) of the abnormal shadow candidate. Here, the shadow type is classified as a solid shadow, a ground glass-like shadow, or a solid and ground glass mixture.

[Step S64]
The CPU 11 writes the X-ray image in which the abnormal candidate shadow portion is emphasized in the display memory 14 in step S63. The emphasized X-ray image written in the display memory 14 is displayed on the display 15 as shown in FIG.

  FIG. 8 is a flowchart showing an example of another execution program of the medical image display device, and FIG. 9 is a diagram showing an example of image display in the medical image display device of FIG.

[Step S80]
As in step S20, the CPU 11 acquires the coordinates of the abnormal candidate shadow on the tomographic image.

[Step S81]
As in step S21, the CPU 11 converts the coordinates of the abnormal candidate shadow into coordinates on the X-ray image.

[Step S82]
As in step S22, the CPU 11 emphasizes the abnormal candidate shadow portion on the X-ray image. The emphasis method is the same as described above.

[Step S83]
The CPU 11 acquires the same part as the coordinates of the abnormal candidate shadow acquired in step S80 in the CT image (past image) taken in the past of the same subject.

[Step S84]
The CPU 11 performs a region analysis process on the abnormal candidate shadow portion in the past image acquired in step S83.

[Step S85]
Similar to step S81, the CPU 11 converts the coordinates of the abnormal candidate shadow in the past image into coordinates on the X-ray image. Further, alignment processing is performed so that the converted image is aligned with the image captured on that day. The conversion method is the same as described above.

[Step S86]
As in step S82, the CPU 11 emphasizes the abnormal candidate shadow portion on the X-ray image. The emphasis method is the same as described above.

[Step S87]
The CPU 11 writes the X-ray image emphasized in step S82 and slap S86 into the display memory 14. The emphasized X-ray image written in the display memory 14 is displayed on the display 15 as shown in FIG.

  FIG. 10 is a diagram schematically showing a processing flow of the medical image display method and apparatus shown in FIGS. As shown in FIG. 10, when an abnormal candidate shadow is detected from a tomographic image such as a CT image by a CAD process or an interpretation doctor, the abnormal candidate shadow is acquired as coordinates on the tomographic image. CPU11 creates a pseudo X-ray image by interpolation and reconstruction based on the CT image, aligns the actual X-ray image with the entire size, inclination, etc., and landmarks in the body (eg, ribs) Align at the position. When this alignment is completed, the CPU 11 emphasizes and displays the corresponding abnormal candidate shadow region on the X-ray image. This makes it possible to capture shadows that are difficult to capture with an X-ray image, as well as the overall shape of the region of interest.

  FIG. 11 shows an example of image display in the medical image display method and apparatus. Since the site requiring attention is clarified by the present invention, the image interpretation doctor can easily confirm by displaying in parallel with the CT image.

1 is an overall configuration diagram of an image diagnostic system according to an embodiment of the present invention. The flowchart which shows an example of the process of the execution program of the medical image display method and apparatus which concerns on this invention. FIG. 3 is a diagram showing an example of image display in the medical image display method and apparatus of FIG. FIG. 3 is a diagram showing an example of image display in the medical image display method and apparatus of FIG. FIG. 3 is a diagram showing an example of image display in the medical image display method and apparatus of FIG. The flowchart which shows an example of a process of another execution program of the medical image display method and apparatus which concerns on this invention. FIG. 7 is a diagram showing an example of image display in the medical image display method and apparatus of FIG. The flowchart which shows an example of a process of another execution program of the medical image display method and apparatus which concerns on this invention. FIG. 9 is a diagram showing an example of image display in the medical image display method and apparatus of FIG. FIG. 7 is a diagram schematically showing a processing flow of the medical image display method and apparatus of FIGS. 2 and 6. The figure which shows an example of the image display in the medical image display method and apparatus which concerns on this invention.

Explanation of symbols

  1 Medical image display system, 2 Medical tomography system, 3 LAN, 4 Image database, 10 Medical image display device, 11 CPU, 12 Main memory, 13 Magnetic disk, 14 Display memory, 15 Monitor, 16 Keyboard, 17 Mouse, 18 controller, 19 common bus

Claims (4)

Position acquisition means for acquiring the position of the abnormal candidate shadow region extracted in advance on the tomographic image of the subject;
Position conversion means for converting the position of the abnormal candidate shadow acquired by the position acquisition means into coordinates or a region on the X-ray image of the subject;
Image synthesizing means for synthesizing the pixel information of the abnormal candidate shadow area with the coordinates or area on the X-ray image converted by the position converting means, and generating a first image;
A medical image diagnosis support system comprising: display means for displaying the first image generated by the image composition means.   The medical image diagnosis support system according to claim 1, wherein the position acquisition unit acquires the position of a shadow as an abnormal candidate shadow extracted by CAD processing or interpretation based on the tomographic image. When the abnormal candidate shadow is extracted by interpretation, feature amount calculating means for calculating a feature amount of the extracted abnormal candidate shadow;
An emphasis degree change setting means for changing and setting the emphasis method and the emphasis degree of the abnormal shadow region according to the shadow feature quantity calculated by the shadow feature quantity calculating means,
The image synthesizing means may include coordinates on the X-ray image of the subject converted by the position converting means or pixel information of the abnormal candidate shadow region of the emphasis method and the emphasis degree changed and set by the emphasis degree change setting means. The medical image diagnosis support system according to claim 1, wherein the first image is generated by combining with a region. Position search means for searching for a position equivalent to the position of the abnormal candidate shadow obtained by the position acquisition means from tomographic images taken in the past of the subject;
Area analysis means for analyzing the similarity with the abnormal shadow area from the area near the position searched by the position search means;
The image synthesizing unit synthesizes pixel information that takes into account the similarity of the abnormal candidate shadow region analyzed by the region analyzing unit with coordinates or regions on the X-ray image of the subject converted by the position converting unit. Generate a second image,
The medical image diagnosis support system according to any one of claims 1 to 3, wherein the display unit displays the first image and the second image side by side.

Images