JP2001087228A - Image reading support device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image reading support device capable of improving the efficiency of image reading. SOLUTION: A tomogram 12 is displayed at the center in the upper part of a display screen, and a circular marker 14 indicating a candidate position of a lesion as a detected point to be read, is synthesized and displayed in the tomogram 12. By synthesizing and displaying the marker 14 indicating the point to be read in this way, the position of the point to be read can be easily discriminated, so that the efficiency of image reading can be improved.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image interpretation support apparatus, and more particularly to an image interpretation support apparatus for assisting a doctor with a computer when interpreting a lung field image obtained by a CT apparatus or an MR apparatus.

[0002]

2. Description of the Related Art Mass screening for lung cancer is widely performed.
It is said that the rate of missing the lesion is also high. Therefore, as shown in FIG. 8A, the image of (1) such as a film obtained by a CT device or an MR device is read by the first reading doctor (2).
Thereafter, the second doctor interprets the image (3). Thereafter, the results of the interpretation by the two doctors are brought in to make a final conclusion (4).

[0003]

As described above, in the above-mentioned method, since two doctors observe an image in an overlapping manner, the examination efficiency is deteriorated. Therefore, recently, as shown in FIG. 8 (b), the first reading doctor applies an image reading support system instead of reading the image, and one reading doctor corresponding to the second reading doctor alone reads the reading while referring to the points indicated by the system. A procedure to draw conclusions is being considered.

[0004] Such a system is described, for example, in the Transactions of the Computer-Aided Diagnostic Imaging Society, Vol. 2, No. 3, J
uly, l998, "Diagnostic Support System for CT for Lung Cancer Screening (LSCT)", pp. 1-7.

[0005] However, it is important how the position of the lesion is displayed to the doctor, but it has been inconvenient until now.

The present invention has been made in view of such circumstances, and has as its object to provide an image interpretation support apparatus that can improve image interpretation efficiency.

[0007]

In order to achieve the above object, the present invention provides a display means for displaying an original tomographic image, an extracting means for extracting an image reading caution point of the original tomographic image, and an image reading caution point. And a synthesizing means for synthesizing a marker representing the above to the original tomographic image and displaying it on the display means.

According to the present invention, the display means displays the original tomographic image, and the extracting means extracts a portion of the displayed original tomographic image to be read. The synthesizing means synthesizes a marker indicating a cautionary part for interpretation with the original tomographic image and causes the display means to display it. As described above, by combining the marker with the original tomographic image, the position of the image reading caution location can be easily determined, and the image reading efficiency can be improved.

[0009]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing a preferred embodiment of an image interpretation support apparatus according to the present invention.

FIG. 1 is a screen configuration diagram showing a CRT monitor 58 displaying a lung field image.

As shown in FIG. 1, at the left end of the screen of the CRT monitor 58, patient information 10 such as a patient's name, sex, and age is displayed.

A tomographic image 12 is displayed at the upper center of the screen.
On this tomographic image 12, a circular marker 14 representing the position of a lesion candidate point, which is a detected caution point for interpretation, is synthesized and displayed. The size of the marker 14 is about 5 mm or 10 mm in diameter, and is not limited to the circular shape as shown in FIG. 1, but may be any shape such as a square, or may be displayed blinking.

A slice position image 16 in front of the lung field is displayed on the right side of the tomographic image 12, and the lung field area of each tomographic image is indicated by a straight line. On the slice position image having the detected lesion candidate point in the slice position image 16, a marker 18 indicating the position of the lesion candidate point is combined and displayed. This marker 1
8 is clicked with the mouse 60 or the slice position image having the lesion candidate point is clicked, so that the tomographic image 12 including the corresponding lesion candidate point is displayed at the center.
The marker 18 is not limited to the square as shown in FIG. 1 and may have any shape. Although the slice position image 16 from the front of the patient is displayed in FIG. 1, the present invention is not limited to this, and an image from the side of the patient may be displayed.

An original tomographic image 20 is displayed on the lower right side of the screen. When the tomographic image 12 having the detected lesion candidate point is selected and designated, the original tomographic image 20 is displayed as a tomographic image at the same slice position without the marker 18 in conjunction therewith. An image number (50 in FIG. 1) is shown in the upper left corner of the original tomographic image 20, and this image number is assigned, for example, in ascending order of bed coordinates at the time of measurement. An image number indicating section 24 is displayed on the right side of the original tomographic image 20, and the maximum and minimum values of the image number (10 in FIG.
(0, 0) is displayed, and the displayed original tomographic image 20 is displayed at the position of the knob 26. The image number is designated by dragging the knob 26 with the mouse 60 in the vertical direction, and the original tomographic image 20 of the designated image number is displayed.
Note that the original tomographic image 20 may be an enlarged image of the area near the marker display portion of the tomographic image 12 (two points leftward in the figure).

On the left side of the tomographic image 12, a MIP (Maximu
m Intensity Projection (maximum intensity projection) image 28 is displayed. This MIP image 28 is created by performing projection processing on all slice images shown in the slice position image 16, and the projection method when composing the MIP image 28 may be center projection or parallel projection. In the MIP image 28, a marker 30 indicating the detected lesion candidate point position is synthesized and displayed. Boxes 3 for inputting angles α and β and a distance R as parameters constituting the MIP image 28 are provided at the lower left of the screen.
2, 34 and 36 are displayed. As shown in FIG. 2, the angle α is an angle between a line obtained by projecting a straight line connecting the viewpoint and the origin to the ZX plane and the X axis, and the angle β is an angle between the straight line and the ZX plane. , Distance R is the distance from the origin of the viewpoint. By inputting the angles α, β, and the distance R from the keyboard, the viewpoint position and viewing direction of the MIP image 28 can be arbitrarily changed. Although FIG. 2 shows a central projection method, a parallel projection method may be used.

When the viewpoint position and the line-of-sight direction are changed by the above-described method, the MIP image 28 is newly constructed and displayed, and the lesion candidate point position is newly detected, and the marker 30 is recombined with the MIP image 28.

A weighted projection image 38 is displayed in the center of the lower part of the screen, and a marker 40 indicating the position of a lesion candidate point is synthesized and displayed on the weighted projection image 38. The viewpoint position and the line-of-sight direction of the weighted projection image 38 can be arbitrarily changed. When the viewpoint position and the line-of-sight direction are changed, the weighted projection image 38 is newly constructed, and the focus candidate point position is newly detected, and the marker 40 is weighted. The image is recombined with the projection image 38. Japanese Patent Application No. 9-1566 for weighted projection images
89. Desired weighting is performed in association with the pixel value of the tomographic image to form a perspective image. By this weighting process, an observation target site in a tomographic image such as an organ can be emphasized and displayed.

A shaded three-dimensional image 42 is displayed on the lower left side of the screen. The three-dimensional image 42 is composed of an image used for calculating the position of a lesion candidate point.

FIG. 3 is a flowchart showing a calculation procedure for detecting the position of a lesion candidate point in the image interpretation support apparatus.

First, a plurality of original tomographic images for the entire region of the diagnosis target site are sequentially read from the CT or MR device into the memory of the computer (step S30). The data may be read by communication such as Ethernet, DR11, GPIB, or RS2000, or may be read from an MO (optical porcelain disk).

Next, lung fields are extracted from all the read original tomographic images (step S31). As the extraction method, an image may be displayed for each of the original tomographic images, and the lung field may be manually traced and extracted. Extraction ”
MEDICAL IMAGING TECHNOLOG
Y, VOL. 14, No. 2, March, 1997,
The automatic extraction method described on pages 164-173 can also be employed.

Next, lesion candidates are detected for each original tomographic image (step S32). For this purpose, a Quoit Filter as shown in FIGS. 5 and 6 is often used. Q
The uoit Filter includes a disk filter 45 and a ring filter 46 as shown in FIG. The disk filter 45 and the ring filter 46 are configured as software, and their diameters are appropriately set according to the diagnosis target. The amount D when the disk filter 45 is actuated at the high density portion 40 between the blood vessels 41 in FIG. 4 and when the ring filter 46 is actuated is calculated, and when D is larger than a certain value, a lesion candidate is calculated. And

For example, in the region 40, D becomes larger than a certain value, so that it is a lesion candidate. However, in the blood vessel region 41, the disk filter 45 and the ring filter 46 are located at the same position, so that D is as shown in FIG. Is not considered as a lesion candidate. For details, see “CT for Lung Cancer Screening (LS
CT) Diagnosis Support System "Transactions of the Computer-Aided Diagnostic Imaging Society, Vol. 2, No. 3, July, 1999
See pages 8, 1-7.

Next, the feature of the lesion candidate point is extracted from each original tomographic image (step S33). For example, the CT value average and the variance value of the lesion candidate area, the average value of N (= about 5) pixels of the pixel value in the area, the circularity of the area, and the like are checked. For details, see “Reducing False Positive Shadows in a Computer Diagnostic Support System for Chest CT Images”, MEDICAL IMAGING T
ECHNOLOGY, Vol. 17, No. 3, Ma
y, 1999, pp. 217-227.

Thereafter, it is determined whether or not each of the extracted candidate lesion points is to be displayed as an image interpretation caution point (step S).
34).

Normally, since the number of extracted lesion candidate points includes those that are not lesions, a process of narrowing down is required. It is determined whether or not a combination set such as the CT value average, the variance value, the average value of N (= about 5) pixels of the pixel value in the area, the circularity of the area, etc. satisfies a specific condition. If you satisfy
In the next step, it will be displayed as a cautionary part for image interpretation.

Then, the image determined as the image interpretation caution part is displayed on the CRT as shown in FIG. 1 (step S3).
5).

The processing of each step described above is executed using the hardware configuration of the image interpretation support apparatus shown in FIG. This image reading support apparatus records and displays medical image data collected by a medical image diagnostic apparatus 70 such as a CT apparatus or an MR apparatus for a target part of a subject, and indicates a lesion candidate point. Central processing unit (C
PU) 50, a main memory 52 storing a control program of the apparatus and the processing flow program, a magnetic disk 54 storing a plurality of tomographic images and image reconstruction programs, and the like, and displaying reconstructed image data. Memory, a CRT 58 as a display device for displaying image data from the display memory 56, a mouse 60 as a position input device, and a mouse pointer on the CRT 58 by detecting the state of the mouse 60. A mouse controller 62 for outputting signals such as the position of the mouse and the state of the mouse to the CRT 58, and a keyboard 6 for inputting various operation commands and the like.
4, a communication board 72 for reading medical image data from the medical image diagnostic apparatus 70 into the apparatus, an MO 74 for recording medical image data and reading it into the apparatus, and a common bus 76 for connecting the above-described components. Be composed.

In the above description, two-dimensional images have been described for convenience of explanation. However, even images that are three-dimensionally measured, such as MRI and cone beam CT, can be handled as a set of two-dimensional images. Included in the invention.

[0030]

According to the image interpretation support apparatus of the present invention, the position of the image interpretation cautionary point can be easily determined by combining and displaying the marker indicating the image interpretation cautionary point on the original tomographic image, and the image interpretation efficiency can be improved. it can.

[Brief description of the drawings]

FIG. 1 is a screen configuration diagram showing a display screen of an image interpretation support device of the present invention.

FIG. 2 is an explanatory diagram showing a method of setting a line-of-sight direction and a viewpoint position.

FIG. 3 is a flowchart showing a processing procedure of the diagnosis support apparatus.

FIG. 4 is an explanatory diagram showing an original image.

FIG. 5: Quoit Filter for detecting lesion candidates
Explanatory diagram showing

FIG. 6: Quoit Filter for detecting lesion candidates
Explanatory diagram showing

FIG. 7 is a hardware configuration diagram of an image interpretation support apparatus according to the present invention.

FIG. 8 is an explanatory diagram showing a conventional diagnosis support system.

[Explanation of symbols]

12 ... tomographic image, 14, 18, 30, 40 ... marker, 1
6: slice position image, 20: original tomographic image, 24: image number indicating unit, 28: MIP image, 38: weighted projection image,
42 ... three-dimensional image, 50 ... CPU, 52 ... main memory, 5
4 ... Main memory, 58 ... CRT, 60 ... Mouse, 64 ... Keyboard, 70 ... Medical diagnostic imaging device, 74 ... MO

Claims (7)

[Claims] A display unit for displaying an original tomographic image; an extracting unit for extracting a reading caution point of the original tomographic image; a marker representing the cautionary reading point on the original tomographic image; An image interpretation support device, comprising: synthesizing means for displaying. 2. A display means for displaying an MIP image formed on the basis of a three-dimensional original image obtained by stacking a plurality of original tomographic images, a viewpoint position, and a line-of-sight direction; And a synthesizing unit for synthesizing a marker indicating the cautionary part of the image interpretation with the MIP image and displaying it on the display unit. 3. A display means for displaying a weighted projection image formed based on a three-dimensional original image obtained by stacking a plurality of original tomographic images, a viewpoint position, and a line-of-sight direction; And a combining means for combining a marker representing the image reading caution part with the weighted projection image and displaying the combined image on the display means. 4. A display means for displaying a slice position display image indicating a slice position of each original tomographic image of a three-dimensional original image in which a plurality of original tomographic images are stacked, and extraction for extracting a reading caution point of each original tomographic image. And a synthesizing unit for synthesizing a marker representing the image interpretation caution part with the slice position display image and displaying the image on the display unit. 5. A designating means for designating a desired original tomographic image using the slice position display image displayed on the display means of claim 4, and a display means for displaying the original tomographic image designated by the designating means. Extraction means for extracting a cautionary point of interpretation of the original tomographic image designated by the designation means, and combining means for combining a marker representing the cautionary point for interpretation with the original tomographic image and displaying the same on the display means. An image interpretation support apparatus characterized in that: 6. A designating means for designating an image number indicating a desired original tomographic image from a plurality of original tomographic images, extracting an original tomographic image having an image number designated by the designating means, and displaying the original tomographic image. Display means for extracting, an extraction means for extracting a cautionary point of interpretation of the original tomographic image displayed on the display means, and a compositing means for composing a marker representing the cautionary point for interpretation on the original tomographic image and displaying it on the display means An image interpretation support device, comprising: 7. A shadow formed on the basis of at least one of the images synthesized by the synthesizing means of claim 1, 2, 3 and 4, and a three-dimensional original image obtained by stacking a plurality of original tomographic images. And a display means for simultaneously displaying the image and the three-dimensional image.