JP2005137640A - Breast region detecting method, apparatus, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve performance in detecting a breast region from a breast image. <P>SOLUTION: A binary image is produced by using a value, which is a boundary between a pixel value (a first pixel value) of the pixel for a direct X ray radiation part 103 and a pixel value (a second pixel value) of the pixel for non-direct X ray radiation parts (101, 102, 104, 105) in the breast image 100 captured by radiography, as a threshold value. A plurality of regions (101, 102, 104, 105) in which the pixels with the second pixel value continue are extracted among the binary image. Rectangular areas (101, 102, 104) are distinguished from a non-rectangular area (105) in the extracted regions, and the area with the largest dimensions among the non-rectangular areas is detected as the breast region (105). <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to region extraction processing, and more particularly to a region extraction method and apparatus suitable for automatic detection of a breast region in a digital breast image, and a program therefor.

  The part necessary for interpreting an image obtained by X-ray imaging is not the entire image obtained by imaging, but an area where the subject in the image is captured. However, areas other than the subject where the marker attached to identify the subject is photographed, and the field outside the field that appears when the subject field is photographed so as not to irradiate the subject with unnecessary X-rays A region (a portion that appears as a low-density region in an X-ray image due to X-ray blocking) may adversely affect the discrimination ability of an observer. In particular, since the irradiation field area appears as a high-luminance area, there is a large luminance difference from the surrounding area, which greatly affects the discrimination ability.

  Therefore, conventionally, in order to remove the influence from the surrounding area other than the subject, only the region where the subject is photographed is extracted instead of the entire image, and the contrast resolution or the like is made so that the subject can be easily read. To make it easy to interpret.

  Therefore, it is determined that the subject region and the region other than the subject are discriminated from the X-ray image, and the pixel value of the subject region and the pixel value of the region other than the subject appearing in the image change greatly with the contour of the subject as a boundary. The center point that is the center of the subject is recognized, contour points are obtained from the pixel values of the pixels on the line extending radially from the center point, and the region surrounded by these contour points is determined by the subject. There is what is recognized as a certain thing (for example, patent document 1).

Also, there is a big difference between the pixel value of the subject part and the direct X-ray irradiation part directly irradiated with X-rays, and the pixel value intermediate between the pixel value appearing in the subject part and the pixel value appearing in the direct X-ray irradiation part is used as a threshold value. In some cases, the subject portion and the direct X-ray irradiation portion are binarized to extract the subject portion (for example, Patent Document 2).
JP-A-4-13764 JP 2001-145614 A

  However, in the method of Patent Document 1, the center point is calculated by regarding a pixel having a certain pixel value or more as a subject, but there may be a marker other than the subject in the medical image. Since the value has a value close to that of the subject, the center point is calculated assuming that the marker is also the subject, so that the center point may be at a position that protrudes from the subject. For this reason, when recognizing the subject, there is a case where the recognition of the outline is not properly performed.

  Further, even in the method of Patent Document 2, since the marker appears at a contrast close to the subject when binarizing, it is impossible to determine whether the marker is a subject region or a marker.

  In view of the circumstances described above, an object of the present invention is to provide a region detection method and apparatus capable of improving the detection performance of a breast region from a breast image, and a program therefor.

The breast region detection method of the present invention includes a region extraction step of extracting one or more breast region candidate regions from a breast image obtained by X-ray imaging,
A rectangularity calculating step for calculating the rectangularity of each extracted region;
Based on the calculated rectangularity, the extracted region is distinguished into a rectangular region and a non-rectangular non-rectangular region, and a region having the largest area among the non-rectangular regions is detected as a breast region. is there.

Further, the breast region detection apparatus of the present invention includes a region extraction unit that extracts one or more breast region candidate regions from a breast image obtained by X-ray imaging,
Rectangularity calculating means for calculating the rectangularity of each extracted region;
Breast region detection means for distinguishing the extracted region into a rectangular region and a non-rectangular non-rectangular region based on the calculated rectangularity, and detecting a region having the largest area among the non-rectangular regions as a breast region. It is characterized by that.

Further, the program of the present invention includes a region extraction step of extracting a region that is one or more breast region candidates from a breast image obtained by X-ray imaging,
A rectangularity calculating step for calculating the rectangularity of each extracted region;
A breast region detection step of distinguishing the extracted region into a rectangular region and a non-rectangular non-rectangular region based on the calculated rectangularity, and detecting a region having the largest area among the non-rectangular regions as a breast region; It is characterized by that.

  A “rectangular area” is an area having a rectangular shape. For example, a marker attached to identify a subject appearing on the breast image, an area outside the irradiation field, or the like.

  A “non-rectangular region” is a region that is not a rectangular shape. For example, a breast region that appears on a breast image.

  The “rectangularity” is an index indicating whether or not the shape is rectangular.

In the region extraction step, a value that is a boundary between a pixel value of a pixel of the direct X-ray irradiation unit in the breast image and a pixel value of a pixel of the non-direct X-ray irradiation unit excluding the direct X-ray irradiation unit is obtained. Using as a threshold value, the pixel value of the pixel of the direct X-ray irradiation unit of the breast image is replaced with a first pixel value, and the pixel value of the pixel of the non-direct X-ray irradiation unit is replaced with a second pixel value. A binarization step for generating a digitized image;
In the binarized image, a region that is a candidate for the breast region may be extracted with a pixel group in which pixels having the second pixel value are connected as a group.

  The “direct X-ray irradiation unit” is a part where a recording medium such as a stimulable phosphor sheet is directly irradiated with X-rays without passing through a subject or the like.

  The “non-direct X-ray irradiation part” is a part where the recording medium is not directly irradiated with X-rays on a storage phosphor sheet or the like such as an area that has passed through the subject, an irradiation field area, or a scattered radiation area.

  The “pixel group in which pixels having the second pixel value are connected” is a continuous region in which adjacent pixels have the same second pixel value. Specifically, “extracting a pixel group in which pixels having a second pixel value are connected as a group area” extracts a region in which pixels having the same pixel value are connected using a labeling process or the like.

  The rectangularity calculating step includes a straight line having an orientation in the Y-axis direction passing through a pixel having a maximum coordinate value in the X-axis direction among pixels included in the extracted region, and a pixel included in the region. Among these, a straight line having a direction in the Y-axis direction passing through a pixel having a minimum coordinate value in the X-axis direction, and an X-axis direction passing through a pixel having a maximum coordinate value in the Y-axis direction among pixels included in the region. An area of a rectangle surrounded by a straight line having an orientation of X and a straight line having an orientation in the X-axis direction passing through a pixel having a minimum coordinate value in the Y-axis direction among the pixels included in the region, What calculates the rectangularity of the extracted area | region from the area of a rectangle and the area of the extracted area | region can be used.

  The “X axis” is an axis in the direction along one side of the rectangular image as an X axis, and the “Y axis” is an Y axis that is orthogonal to the X axis.

  The “area of the extracted region” can be obtained, for example, by counting the number of pixels included in each extracted region.

  The “rectangular area” is a rectangular area surrounding an “extracted area” having sides parallel to the X axis and the Y axis. The “rectangular area” may be represented by the number of pixels included in the rectangle.

  According to the breast region detection method, apparatus, and program of the present invention, an irradiation field stop is detected by detecting a breast region from the rectangularity of each region that is a candidate for a breast region in a breast image obtained by X-ray imaging. It is possible to extract a breast region excluding a rectangular region in an image such as an irradiation field region or a marker that appears when an image is captured using. In addition, by setting the region having the largest area among the non-rectangular regions as the breast region, the breast region and the marker can be accurately distinguished even when the marker is attached with an inclination.

  In addition, a binarized image is generated by binarizing a direct X-ray irradiator and a non-direct X-ray irradiator for a region that is a candidate for a breast region, and the same from the binarized image using a labeling process or the like. By extracting as a region where pixels having pixel values are connected, it is possible to extract a region not directly irradiated with X-rays as a candidate for a breast region.

  Further, the rectangularity calculation calculates the rectangularity of the extracted region based on the area of the rectangle formed by straight lines parallel to the X axis and the Y axis surrounding the extracted region, and the area of the extracted region, Based on whether or not the extracted region is a rectangle composed of straight lines parallel to the X-axis and the Y-axis, it is possible to discriminate between the marker, the X-ray scattering region, and the breast region.

  DESCRIPTION OF EMBODIMENTS Hereinafter, an embodiment of a breast region detection apparatus that performs a breast region detection method of the present invention will be described with reference to the drawings.

  As shown in FIG. 1, the breast region detection apparatus 1 includes a region extraction unit 3 that extracts one or more breast region candidate regions from a breast image 100 obtained by X-ray imaging, and each extracted region. Based on the calculated rectangularity, the rectangularity calculating means 4 extracts a non-rectangular area that is not rectangular from the extracted area, and among the extracted non-rectangular areas, the area having the largest area is the breast area. And a breast region detecting means 5 for detecting as follows.

  The region extraction unit 3 uses a threshold value as a boundary between the pixel value of the pixel of the direct X-ray irradiation unit in the breast image 100 and the pixel value of the pixel of the non-direct X-ray irradiation unit excluding the direct X-ray irradiation unit. And a binarizing unit 2 for generating a binarized image, and extracting a region that is a candidate for a breast region from a binarized image using a group of pixels having pixels having the same pixel value as a group. .

  A breast image 100 is an image of a breast taken using an irradiation field stop. As shown in FIG. 3, the region 101 of the stop, the scattered radiation region 102, and the direct X-ray irradiation unit where X-rays are blocked by the irradiation field stop. 103, a marker area 104, and a breast area 105 obtained by photographing the subject appear.

  Therefore, description will be made according to a flowchart showing the procedure of breast region detection shown in FIG.

  First, a breast image 100 is taken, and automatic sensitivity correction (EDR) is performed so as to have an appropriate density and contrast so that the breast image 100 becomes an X-ray photograph having high diagnostic ability, and an EDR reduced image is obtained (S100). ).

  When a histogram representing the pixel values of the pixels included in the breast image 100 and the appearance frequency thereof is obtained from the breast image 100, three large peaks as shown in FIG. 4 appear in the histogram (S101). First, the rightmost peak is the direct X-ray irradiation unit 103, the middle peak is the breast region 105, the scattered radiation region 102, and the marker region 104, and the leftmost peak is the aperture region 101.

  Therefore, the binarizing means 2 detects the lowest position (Q portion in FIG. 4) of the valley appearing between the first peak and the second peak, and uses the pixel value at this position as a threshold (S102). ) Perform binarization processing. When performing binarization processing, the portion of the direct X-ray irradiation unit is replaced with the first pixel value, and the portion other than the direct X-ray irradiation unit (breast region, scattering region, marker and aperture region) is set to the second pixel value. The replaced binary image 110 is formed (S103).

  Next, the area extraction unit 3 scans the binarized image and performs a labeling process in which adjacent pixels have the same pixel value and assign the same label (S104). For example, in the case of the binarized image 110 as shown in FIG. 5, a label is assigned to each pixel as shown in FIG. 6, and the direct X-ray irradiation region 103 (A), breast region 105 (B), marker Four regions can be extracted: region 104 (C), aperture region 101 + scattering region 102 (D) (S105). Of these four regions, the region assigned with the A label which is the direct X-ray irradiation region 103 has the first pixel value and can be distinguished from other regions. The area to which the label is assigned has the second pixel value, and it cannot be distinguished from the pixel value which area is the breast area 105.

  The breast region 105 has a shape close to a semicircle or an ellipse, but the marker region 104 (C) and the aperture region 101 + scattering region 102 (D) have a rectangular shape. Therefore, it is determined whether or not each extracted region is a rectangle, and it is determined which of the regions to which the labels B, C, and D are assigned is the breast region 105.

  Since the rectangles of the contours of the marker region 104 (C) and the aperture region 101 + the scattering region 102 (D) are rectangular shapes with each side extending along the X direction or the Y direction, the rectangularity calculation means 4 is used by using this rectangle. Thus, the rectangularity r of each of the regions B, C, and D is obtained, and it is determined whether or not the extracted region is a rectangle.

Here, a method of obtaining the rectangularity r will be described using the region B as an example. As shown in FIG. 7, among the pixels included in the region B, the pixel P1 = (P1x, P1y) having the maximum X-axis coordinate value and the pixel P2 = (P2x, P2x, having the minimum X-axis coordinate value). P2y). Next, a pixel P3 = (P3x, P3y) having the maximum Y-axis coordinate value and a pixel P4 = (P4x, P4y) having the minimum Y-axis coordinate value are obtained. Therefore, a straight line l ₁ having a Y direction passing through the pixel P1, a straight line l ₂ having a Y direction passing through the pixel P2, a straight line l ₃ having a X direction passing through the pixel P3, and the pixel P4. a rectangular area E1 surrounded by the straight line l ₄ with X orientation through,
E1 = (P1x−P2x) × (P3y−P4y) (1)
Ask for. This area may be obtained by the number of pixels included in the rectangle. For example, when the rectangle surrounding the breast region in FIG. 7 is (P1x−P2x) = 80 pixels and (P3y−P4y) = 40 pixels, the area included in E1 is 3200 pixels.

  On the other hand, the area E2 of each region can be obtained by, for example, counting the number of pixels included in the region (specifically, counting pixels with the same label).

Therefore, the rectangularity r is
r = E2 / E1 (2)
Asking. The other areas C and D are similarly determined (S106).

  As described above, the marker region 104 (C) and the aperture region 101 + scattering region 102 (D) each have a rectangular shape whose sides are parallel to the X direction or the Y direction (see FIGS. 6 and 7). Therefore, in a rectangular area such as the marker area 104 (C) or the aperture area 101 + the scattering area 102 (D), the pixel P1 having the maximum X-axis coordinate value, the pixel P2 having the minimum X-axis coordinate value, The pixel P3 having the maximum Y-axis coordinate value and the pixel P4 having the minimum Y-axis coordinate value are located as shown in FIG. 7 and the rectangularity r is a value close to approximately 1. On the other hand, a non-rectangular area such as the breast area 105 (B) has a value smaller than 1.

  From these facts, the breast region detecting means 5 distinguishes whether the region labeled B, C, D from the rectangularity r is a rectangular region or a non-rectangular region, and determines from the non-rectangular region. The thing corresponding to the breast region is detected.

Specifically, the range value of the rectangularity r of the breast region is considered. For example, if the shape of the breast is a semicircle with a radius R,
E1 = R × 2R = 2R ²
E2 = (1/2) × π × R ²
When this result is applied to Equation (2), the rectangularity is about 0.785. From this, it can be said that the rectangularity r of the breast region 105 is highly likely to be about 0.9 or less, and a region having the rectangularity r of 0.9 or less is set as a non-rectangular region and is a candidate for the breast region 105. be able to. In addition, when the rectangularity r is extremely small, the difference between the area of the extracted region enclosed by the rectangle and the area of the extracted region is quite large, and the breast region 105 cannot be considered from the shape of the breast. . Therefore, a breast region 105 having a rectangularity r between 0.2 and 0.9 is detected (S107).

  Further, in the marker region 104 (C), the rectangle may be inclined with respect to the X axis (or Y axis) as shown in FIG. 8 depending on how the marker is attached. The rectangularity r may be a value close to the rectangularity of the breast region 105, and it is impossible to distinguish whether the rectangular region is the breast region 105 or the marker region. However, the marker area 104 has a very small area compared to the breast area 105. Therefore, a region having a rectangularity r between 0.2 and 0.9 and having the largest area is detected as the breast region 105 (S108).

  Alternatively, it is possible to obtain an axis of inertia moment of each region and obtain whether or not it is a rectangle along this axis, thereby increasing the accuracy of the rectangularity.

  In the above description, the breast region is discriminated by paying attention only to the rectangularity. However, it may be discriminated based on whether or not the breast region has a shape similar to a circle like the breast region by taking in the circularity or the like.

  In the above description, the case where the breast region is imaged using the irradiation field stop has been described. However, even in the case of a breast image captured without using the irradiation field stop, the breast region and the marker region are distinguished from each other. It is possible to extract only the region.

  As described above, the region extracting unit 3 has described the case where the binarization process is performed to form the binarized image and then the binarized image is subjected to the labeling process to extract the region. And a closed curve composed of the detected edge points, or a closed curve composed of the detected edge points and the edges of the breast image 100 is obtained, and the density of the pixel values in the closed region surrounded by the closed curve is determined. A region that is a candidate for a breast region can be extracted from a low region (low irradiation X-ray dose). Specifically, the average value of the pixel values in the closed region is a region that is a candidate for a breast region on the basis of the boundary between the direct X-ray irradiation portion and the portion other than the direct X-ray irradiation portion and the pixel value. It is determined whether or not.

  As described above in detail, it is possible to detect a breast region from a breast image.

Schematic configuration diagram of breast area detection device The figure which shows the flowchart showing the procedure of a breast area | region detection Illustration of a breast image using an irradiation field stop for breast imaging Histogram of pixel values appearing in breast image Example of binarized image Diagram for explaining the labeling process Diagram for explaining the calculation of the rectangularity An example of a breast image taken with the marker tilted

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Breast area detection apparatus 2 Binarization means 3 Area extraction means 4 Rectangularity calculation means 5 Breast area detection means 100 Breast image 101 Aperture area 102 Scatter area 103 Direct X-ray irradiation area 104 Marker area 105 Breast area 110 Binary image

Claims (5)

A region extraction step of extracting regions that are candidates for one or more breast regions from a breast image obtained by X-ray imaging;
A rectangularity calculating step for calculating the rectangularity of each extracted region;
A breast region characterized by distinguishing the extracted region into a rectangular region and a non-rectangular non-rectangular region based on the calculated rectangularity, and detecting a region having the largest area among the non-rectangular regions as a breast region Detection method. The region extraction step includes:
Using the value that is a boundary between the pixel value of the pixel of the direct X-ray irradiation unit in the breast image and the pixel value of the pixel of the non-direct X-ray irradiation unit excluding the direct X-ray irradiation unit as a threshold value, the breast image The binarization for generating a binarized image by replacing the pixel value of the pixel of the direct X-ray irradiation unit with a first pixel value and replacing the pixel value of the pixel of the non-direct X-ray irradiation unit with a second pixel value With steps,
2. A region as a candidate for the breast region is extracted from the binarized image by using a group of pixels in which pixels having the second pixel value are connected as a group of regions. Breast area detection method.   In the rectangularity calculation step, a straight line having a direction in the Y-axis direction passing through a pixel having a maximum coordinate value in the X-axis direction among the pixels included in the extracted region, and X among the pixels included in the region A straight line having a direction in the Y-axis direction passing through a pixel having a minimum coordinate value in the axial direction, and a direction in the X-axis direction passing through a pixel having a maximum coordinate value in the Y-axis direction among pixels included in the region And an area of a rectangle surrounded by a straight line having an orientation in the X-axis direction passing through a pixel having a minimum coordinate value in the Y-axis direction among the pixels included in the region, 3. The breast region detection method according to claim 1, wherein the rectangularity of the extracted region is calculated from the area and the area of the extracted region. Region extracting means for extracting one or more candidate breast regions from a breast image obtained by X-ray imaging;
Rectangularity calculating means for calculating the rectangularity of each extracted region;
Breast region detection means for distinguishing the extracted region into a rectangular region and a non-rectangular non-rectangular region based on the calculated rectangularity, and detecting a region having the largest area among the non-rectangular regions as a breast region. A breast region detection apparatus characterized by the above. A region extraction step of extracting regions that are candidates for one or more breast regions from a breast image obtained by X-ray imaging;
A rectangularity calculating step for calculating the rectangularity of each extracted region;
A breast region detection step of distinguishing the extracted region into a rectangular region and a non-rectangular non-rectangular region based on the calculated rectangularity, and detecting a region having the largest area among the non-rectangular regions as a breast region. A program to make it run.

Images