JP7270917B2 - computer program and image processing device - Google Patents

Description

The present invention relates to image processing technology.

PET (Positron Emission Tomography) examination in brain tumor examination utilizes the property that tumor cells accelerate sugar metabolism and amino acid metabolism. Evaluating tumor tissue metabolism. In this way, the position, size (area), and activity of the tumor are evaluated.

PET examination is also useful for determining the efficacy of cancer therapeutic drugs. Since cancer cells are characteristic in that their metabolism declines before they die, it is possible to evaluate drug efficacy at an early stage by observing metabolic changes in PET examinations.

However, for highly malignant abnormalities, it is necessary to appropriately evaluate the condition of the abnormal site. Easy to get out.

SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to appropriately evaluate the state of an abnormal site independently of an operator.

A computer program according to one aspect of the present invention is a computer program for an image processing apparatus having storage means for storing image data of a first image and a second image obtained by imaging the same part of the same subject, extracting an abnormal site area as a first characteristic area based on the image and the second image; and extracting an abnormal site area different from the first characteristic area based on the first image and the second image. The image processing apparatus is caused to execute a step of extracting as two characteristic regions, and a step of calculating an index regarding the state of the abnormal site based on the first characteristic region and the second characteristic region.

Further, for pixels of the first image, calculating a first pixel ratio between each pixel value and a pixel value of a candidate pixel of normal tissue; calculating a second pixel ratio between the pixel value of the candidate pixel and a plurality of pixels that are candidates for the abnormal site as first candidate pixels based on the calculated first pixel ratio and the second pixel ratio and extracting, as second candidate pixels, a plurality of pixels that are candidates for an abnormal site based on the calculated first pixel ratio and second pixel ratio. and extracting the first characteristic region based on the first candidate pixels, and extracting the second characteristic region based on the second candidate pixels.

The first image and the second image may be images with different modalities, or images with the same modality but obtained with different drugs.

Also, accepting designation of one pixel among the plurality of first candidate pixels;
receiving the designation of one pixel among the plurality of second candidate pixels; It may be extracted as the first characteristic region, and a region of pixels contiguous to the designated pixel among the plurality of second candidate pixels may be extracted as the second characteristic region.

Further, the index is the volume or surface area of the difference area between the first characteristic area and the second characteristic area, the ratio of the volume or surface area of the difference area and the second characteristic area, or the first characteristic area. and the second characteristic region.

Further, the first characteristic region may be a tumor site region, the second characteristic region may be a core region of the tumor site, and the index regarding the state of the abnormal site may be an index regarding invasion of the tumor site. .

The first image is a PET image taken by administering 18F-FDG (fluorodeoxyglucose) to the subject, and the second image is a PET image taken by administering 11C-methionine to the subject. There may be.

Further, an image processing apparatus according to another aspect of the present invention is an image processing apparatus having storage means for storing image data of a first image and a second image obtained by imaging the same part of the same subject, wherein the first image and a first feature region extraction unit for extracting an abnormal site region as a first feature region based on the second image, and an abnormality different from the first feature region based on the first image and the second image A second characteristic region extracting section for extracting a part region as a second characteristic region, and an index calculating section for calculating an index relating to the state of the abnormal region based on the first characteristic region and the second characteristic region.

According to the embodiment of the present invention, it is possible to appropriately evaluate the state of the abnormal site without depending on the operator.

1 is an overall configuration diagram of an image processing apparatus according to an embodiment of the present invention; FIG. FIG. 4 is an explanatory diagram of index calculation according to the present embodiment; It is an example of a histogram of pixel values of pixels. FIG. 3 is a diagram showing the relationship between the FDG/N value and the MET/N value and the tumor (invasion) area, tumor (core) area, edema area, and normal area.

An image processing apparatus according to an embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is an overall configuration diagram of an image processing apparatus 1 according to this embodiment.

An input device 2 , an output device 3 and an input/output device 4 are connected to the image processing device 1 .

The image processing apparatus 1 is configured by, for example, a general-purpose computer system having a processor and memory, and individual components or functions within the image processing apparatus 1 described below are realized, for example, by executing a computer program. be done. The computer program is storable on a computer-readable recording medium. The input device 2 may be, for example, a keyboard, pointing device, or the like. The output device 3 may be, for example, a display device, a printer, or the like. The input/output device 4 may be, for example, a mass storage device or a network interface device.

The image processing apparatus 1 includes an FDG-PET image data storage unit 31, a MET-PET image data storage unit 32, an alignment processing unit 11, a first area extraction unit 12, an MET representative value identification unit 13, a 2-area extraction unit 14, FDG representative value identification unit 15, FDG pixel ratio calculation unit 16, MET pixel ratio calculation unit 17, mask processing unit 18, first candidate pixel extraction unit 19, and second candidate pixel It includes an extractor 20 , a first feature region extractor 21 , a second feature region extractor 22 , and an index calculator 23 .

The image processing apparatus 1 uses two types of images obtained by imaging the same part (organ) of a common subject, and performs processing for calculating the representative value of each image. In this embodiment, a PET image (hereinafter referred to as FDG-PET image (first image)) taken by administering 18F-FDG (fluorodeoxyglucose) to the same subject and an image taken by administering 11C-methionine are shown. A PET image (hereinafter referred to as a MET-PET image (second image)) is used. Thus, in this embodiment, the first image and the second image are images obtained from different drugs with the same modality. That is, images obtained by different accumulation mechanisms.

The image data of the FDG-PET image and the MET-PET image are both three-dimensional voxel data, and in this embodiment, they are three-dimensional images obtained by imaging the brain (head) of the same subject. The FDG-PET image and the MET-PET image may each consist of multiple slice images. Pixel values (voxel values) of the FDG-PET image and the MET-PET image may both be normalized to SUV (Standardized Uptake Value).

The FDG-PET image data storage unit 31 stores image data of FDG-PET images. Image data of an FDG-PET image generated by a predetermined imaging device is captured by the image processing device 1 by interface means (not shown) and stored in the FDG-PET image data storage unit 31 .

The MET-PET image data storage unit 32 stores image data of MET-PET images. The image data of the MET-PET image generated by a predetermined imaging device is captured by the image processing device 1 and stored in the MET-PET image data storage unit 32 by interface means (not shown).

The alignment processing unit 11 aligns the FDG-PET image stored in the FDG-PET image data storage unit 31 and the MET-PET image stored in the MET-PET image data storage unit 32 . Alignment is performed by, for example, a well-known algorithm so that the positions of the images reflected in the two images are aligned (the same locations have the same coordinates). This alignment may be performed three-dimensionally or may be performed for each corresponding slice image. Also, the images that are moved for alignment may undergo linear or non-linear transformation. The images after alignment are stored in the FDG-PET image data storage unit 31 and the MET-PET image data storage unit 32, respectively. The following processing is performed using the FDG-PET image and the MET-PET image that are aligned with each other.

A first area extraction unit 12 extracts an area having a predetermined characteristic from the FDG-PET image as a first area. For example, the first area extraction unit 12 extracts an area composed of pixels having a pixel value equal to or greater than a predetermined threshold in the FDG-PET image (first image) as the first area. The first area extraction unit 12 specifies coordinates of pixels included in the extracted first area.

This threshold is, for example, 1.0 times, 1.5 times, 2.0 times, 3.0 times the average value of pixel values of all pixels in the brain region (whole brain) in the FDG-PET image. value is fine. The brain region may be, for example, an area having a value equal to or greater than ⅛ of the average pixel value of all pixels in the FDG-PET image including the background. This threshold may be set for each slice image, or one threshold may be set for all slice images (whole brain).

The first area may be set for a specific slice image, or may be set for all slice images (whole brain).

Due to the properties of the FDG-PET image, which is a drug that is physiologically accumulated in normal tissues, the first area is considered to include normal gray matter areas and tumor areas where FDG accumulates above a certain level. That is, the first area extraction unit 12 extracts a first area that is a candidate area for a normal gray matter area (normal tissue). Here, the presence of physiological accumulation in normal tissues means the presence of physiological accumulation in normal tissues among organs to be diagnosed.

The MET representative value identifying unit 13 identifies the representative value of the MET-PET image based on the processing result of the first area extracting unit 12 . For example, the MET representative value specifying unit 13 specifies a representative value (hereinafter referred to as MET representative value) 51 of the MET-PET image based on the pixel values of the pixels belonging to the first area in the MET-PET image (second image). do.

The MET representative value identifying unit 13, for example, acquires the coordinates of the pixels included in the first area from the first area extracting unit 12, and identifies the MET representative value 51 from the pixel values of those coordinates in the MET-PET image. . The MET representative value 51 may be, for example, a value (statistical value) obtained by applying a statistical algorithm such as the mode, average, or median of the pixel values of the target pixels.

For example, the MET representative value specifying unit 13 creates a histogram of pixel values of pixels included in the first area. FIG. 3 is a diagram showing an example of a histogram. The pixel values of the normal gray matter region included in the first area are considered to follow a substantially normal distribution, forming one peak P1. Due to the nature of the MET-PET image, which is a drug that does not accumulate physiologically in normal tissue, if the first area includes a tumor region, a region with a higher pixel value than the normal region will have a peak smaller than P1. A peak P2 is formed. At this time, the mode is the value V1 of the peak P1. The average value is V2, which is slightly larger than the mode V1. Here, the absence of physiological accumulation in normal tissues means that there is no physiological accumulation in normal tissues among the organs to be diagnosed, or, even if there is, the accumulation is limited to an extent that does not affect the identification of the diseased area. do.

The MET representative value 51 specified here is considered to be a value representative of the normal gray matter region in the MET-PET image.

The second area extraction unit 14 extracts an area including pixels having a pixel value of MET representative value 51 in the MET-PET image (second image) as a second area. At this time, the second area extracting unit 14 may set only the pixels having the MET representative value 51 as the second area, or may determine a certain range of values including the MET representative value 51 and enter the range of these values. A pixel having a pixel value may be the second area. The second area extraction unit 14 specifies coordinates of pixels included in the extracted second area.

This second area is believed to contain only normal gray matter regions.

The first area and/or the second area may be set only in the left hemisphere or right hemisphere of the brain. For example, when an operator such as a doctor designates either the left or right hemisphere, the first area extraction unit 12 may set the first area only for the designated hemisphere. Similarly, when the operator designates either the left or right hemisphere, the second area extraction unit 14 may set the second area only for the designated hemisphere. This makes it possible to set the first area and/or the second area in the hemisphere opposite to the tumor hemisphere.

The FDG representative value identifying section 15 identifies the representative value of the FDG-PET image based on the processing result of the second area extracting section 14 . For example, the FDG representative value specifying unit 15 determines a representative value (hereinafter referred to as FDG representative value) 52 of the FDG-PET image based on the pixel values of the pixels belonging to the second area in the FDG-PET image (first image). Identify.

The FDG representative value specifying unit 15, for example, acquires the coordinates of the pixels included in the second area from the second area extracting unit 14, and specifies the FDG representative value 52 from the pixel values of those coordinates in the FDG-PET image. . The FDG representative value 52 may be, for example, a value (statistical value) obtained by applying a statistical algorithm such as the mode, average, or median of the pixel values of the target pixels. A specific method of specifying the FDG representative value 52 may be the same as the process performed by the MET representative value specifying unit 13 to specify the MET representative value 51 .

The FDG representative value 52 specified here is considered to be a value representing the normal gray matter region in the FDG-PET image.

As described above, in the present embodiment, in order to specify the representative value of an area having a specific property in an image, the area is defined in an image of a different type from that image. In particular, in this embodiment, two types of images of the same modality are used.

The FDG pixel ratio calculator 16 calculates the ratio between the pixel value and the FDG representative value 52 for a plurality of pixels of the FDG-PET image.

For example, the FDG pixel ratio calculation unit 16 refers to the FDG-PET image data storage unit 31 to obtain image data of the FDG-PET image. Then, the FDG pixel ratio calculator 16 calculates the pixel ratio between each pixel value and the FDG representative value 52 for any pixel of the FDG-PET image. The FDG pixel ratio calculation unit 16 may calculate the pixel ratio for all pixels, may calculate the pixel ratio for the brain region, or may calculate the pixel ratio for the region specified by the operator. good too. When the operator designates an arbitrary area consisting of multiple pixels, the value (statistical value) obtained by applying a statistical algorithm such as the mode, average or median of the pixel values in this area is used. , and the pixel ratio between this value and the FDG representative value 52 may be calculated.

Similar to the FDG-PET image, the MET pixel ratio calculator 17 calculates the pixel ratio (second pixel ratio) with the MET representative value 51 for a plurality of pixels of the MET-PET image. That is, the MET pixel ratio calculator 17 may calculate the pixel ratio of each pixel to the MET representative value 51 for all pixels, pixels in the brain region, or pixels in a region specified by the operator. When specifying an arbitrary area consisting of multiple pixels, calculate the value (statistical value) obtained by applying a statistical algorithm such as the mode, average or median value of the pixel values in this area and the pixel ratio between this value and the MET representative value 51 may be calculated.

Here, the MET representative value 51 and the FDG representative value 52 are considered to be values representing the normal gray matter region in each image. Therefore, the ratio calculated using the MET representative value 51 or the FDG representative value 52 as the denominator for the tumor site corresponds to the tumor activity index L/N. Hereinafter, the pixel ratio calculated using the FDG representative value 52 as the denominator is referred to as FDG/N (first pixel ratio), and the pixel ratio calculated using the MET representative value 51 as the denominator is referred to as MET/N (second pixel ratio ). In addition, in pixels corresponding to normal brain tissue (normal gray matter), MET/N and FDG/N show approximately 1.0.

Since sugar metabolism is accelerated in tumor cells, 18F-FDG is characteristically taken up by tumor tissue, but since it is highly accumulated in normal brain tissue, even at the tumor site, the accumulation is lower than in normal brain tissue. (sometimes higher than in normal brain tissue). Although 18F-FDG is incorporated into the infiltrated region that seeps out from the core region of the tumor site reflecting sugar metabolism, it is thought that there is a tendency for the amount to be lower than that in normal brain tissue. Those whose glucose metabolism is equivalent to or higher than that of normal brain tissue in the core region of the tumor site are considered to be a high risk group and excluded from this procedure. Therefore, in the FDG-PET image, a difference in FDG/N occurs between the core region and the infiltrated region of the tumor site and the normal brain tissue, so that they can be distinguished from each other. That is, in the pixels corresponding to the core region and the infiltration region (those in which risk discrimination is difficult in the conventional method) in the case targeted by this procedure, FDG/N does not show a value close to 1.0, for example, 0.9 is considered to show a smaller value. However, areas with decreased FDG/N may contain edema, and FDG alone is unreliable in determining tumor areas (core and infiltration areas). In addition, 18F-FDG does not accumulate outside the brain, so it is considered that the value is, for example, 0.3 or less.

The regions indicated by the values of FDG/N are summarized as follows.
・FDG/N≤0.3: extracerebral (not substantial brain region)
・0.3<FDG/N<0.9: infiltration area and core area, or edema area ・FDG/N≧0.9: normal area, or core area (high risk)
Among these, if there is a tumor that satisfies FDG/N≧0.9, it is a high risk group (excluding in this procedure), and if there is a tumor that satisfies 0.3<FDG/N<0.9 , It is difficult to distinguish between the tumor (infiltration area, core area) and the edematous area only by visual observation, and the risk evaluation is also difficult.

Also, 11C-methionine accumulates in tumor tissue where amino acid metabolism is active, but is hardly taken up in normal brain tissue. Even in the infiltrated region of the tumor site, amino acid metabolism tends to be incorporated, albeit more slowly than in the core region. For this reason, there is a difference in MET/N between the tumor and normal brain tissue, and it is possible to distinguish between the two (however, the values in the core region differ greatly and are clear, but the values in the infiltration region overlap with those in the normal region). is unclear). That is, it is considered that MET/N shows a value larger than 1.1 in the pixels corresponding to the infiltration area. In addition, since a large amount of methionine is incorporated in pixels corresponding to the core region of the tumor site, MET/N, for example, is considered to exhibit a value greater than 1.4. However, even in areas where MET/N is slightly higher than 1.1, there is a possibility that normal areas (pixels) may be included due to image blurring or statistical errors. unreliable to determine.

The regions indicated by the values of MET/N are summarized below.
・MET/N≧1.4: Core region ・1.1<MET/N<1.4: Invasive region or normal region ・MET/N≦1.1: Edema region or normal region Among these, A region that satisfies 1.4≦MET/N is a region that can be visually distinguished as a core region, but a region that satisfies 1.1<MET/N<1.4 cannot be visually distinguished as infiltrated or normal. This is a difficult area.

By combining the area indicated by the FDG/N value and the area indicated by the MET/N value, the tumor (invasion) area, tumor (core) area, edema area, and normal area are shown as shown in FIG.

FIG. 4 is a diagram showing the relationship between the FDG/N value and MET/N value and the tumor (invasion) region, tumor (core) region, edematous region, and normal region.

As shown in FIG. 4, FDG / N ≤ 0.3 is extracerebral, 0.3 < FDG / N < 0.9 and 1.1 < MET / N < 1.4 is infiltrated area, 0.3 < FDG /N and MET/N≧1.4 is the core region, 0.3<FDG/N<0.9 and MET/N<1.1 is the edema region, FDG/N≧0.9 and MET/N<1 .4 corresponds to the normal region. FDG or MET alone does not have high reliability in determining the infiltration area, but the infiltration area in FIG. It is considered highly probable.

The mask processing unit 18 performs mask processing based on FDG/N. That is, the mask processing unit 18 extracts a substantial brain region excluding the periphery of the brain, ventricles, etc., based on FDG/N. Specifically, as shown in the mask processing in FIG. 2, the mask processing unit 18 extracts pixels having a value of FDG/N greater than 0.3 from the FDG-PET image, and treats them as masked pixels. .

The first candidate pixel extraction unit 19 extracts pixels of the masked FDG-PET image having a FDG/N smaller than a predetermined value, and pixels of the MET-PET image having a predetermined MET/N. A pixel that satisfies both is extracted as a candidate pixel (first candidate pixel) from among the pixels showing a value greater than the value of . As shown in FIG. 2, pixels forming a plurality of regions F1 are extracted as first candidate pixels in the first candidate pixel extraction.

For example, the first candidate pixel extraction unit 19 selects candidate pixels satisfying both 0.3<FDG/N<0.9 and 1.1<MET/N among the pixels of the FDG-PET image and the MET-PET image. Extract as pixels. Here, 0.3<FDG/N indicates the above mask processing. As shown in FIG. 4, since the region of 0.3<FDG/N<0.9 and 1.1<MET/N is the tumor site (infiltration region and core region), this region is extracted as a candidate pixel. be done. Note that the threshold value for pixels to be extracted is not limited to 0.9 and 1.1, and may be appropriately set by the operator.

The second candidate pixel extracting unit 20 selects a pixel that satisfies both of the pixels of the masked FDG-PET image and the pixels of the MET-PET image whose MET/N is greater than a predetermined value. is extracted as a candidate pixel (second candidate pixel). As shown in FIG. 2, pixels forming a plurality of regions M1 are extracted as second candidate pixels in the extraction of the second candidate pixels.

For example, the second candidate pixel extraction unit 20 extracts pixels satisfying both 0.3<FDG/N and 1.4<MET/N among the pixels of the FDG-PET image and the MET-PET image as candidate pixels. . As shown in FIG. 4, the region where 0.3<FDG/N and 1.4≦MET/N is the core region, and is extracted as a candidate pixel. Note that the threshold for pixels to be extracted is not limited to 1.4, and may be appropriately set by the operator.

The first characteristic region extraction unit 21 extracts, from among the candidate pixels extracted by the first candidate pixel extraction unit 19, a region of pixels contiguous to pixels designated by an operator such as a doctor as a first characteristic region. As shown in FIG. 2, in the first feature region extraction, a region F2 is extracted as the first feature region. That is, the first characteristic region extraction unit 21 extracts the tumor site region as the first characteristic region. Note that a predetermined region (the largest region, the two largest regions, a region of a predetermined size or larger, etc.) may be automatically extracted as the first feature region instead of the region specified by the operator.

The second characteristic region extraction unit 22 extracts, from among the candidate pixels extracted by the second candidate pixel extraction unit 20, a region of pixels contiguous to pixels designated by an operator such as a doctor as a second characteristic region. As shown in FIG. 2, a region M2 is extracted as a second feature region in the second feature region extraction. That is, the second characteristic region extraction unit 22 extracts the core region of the tumor site as the second characteristic region. Note that a predetermined region (the largest region, the two largest regions, a region of a predetermined size or larger, etc.) may be automatically extracted as the second feature region instead of the region designated by the operator.

An image X shown at the bottom of FIG. 2 shows a state in which the first characteristic region F2 and the second characteristic region M2 are superimposed. As described above, the first characteristic region F2 is the tumor site (invasion region and core region), and the second characteristic region M2 is the core region. Therefore, the difference area I between the first characteristic area F2 and the second characteristic area M2 corresponds to the infiltration area.

The index calculator 23 calculates indices based on the first feature region F2 extracted by the first feature region extractor 21 and the second feature region M2 extracted by the second feature region extractor 22 . For example, the index calculation unit 23 calculates the volume or surface area of the difference region I, the ratio of the volume or surface area of the difference region I and the second characteristic region M2, or the overlap ratio of the first characteristic region F2 and the second characteristic region M2. is calculated as an index for tumor site invasion. The index calculator 23 then outputs the calculated index to the output device 3 . Note that the overlap rate is 100% in FIG. 2 because the entire area of the second characteristic area M2 overlaps the first characteristic area F2. When only a part of the second characteristic region M2 overlaps with the first characteristic region F2, that is, when the second characteristic region M has a region that does not overlap with the first characteristic region F2, the overlapping rate is less than 100%. .

According to this embodiment, it is possible to appropriately evaluate the degree of invasion at the tumor site without depending on the operator. In particular, in this embodiment, the degree of invasion at the tumor site can be identified objectively and reproducibly based on the FDG-PET image and the MET-PET image.

Furthermore, according to this embodiment, it is possible to extract areas with specific properties using multiple types of images having different properties. In particular, in this embodiment, two types of images of the same modality having different characteristics are used, the characteristics of one image are used to extract a candidate region for a tumor site, and the characteristics of the other image are used to extract a tumor site candidate region. A candidate region for the core region of the site is extracted, and an index of invasion can be calculated based on the two candidate regions.

The embodiments of the present invention described above are illustrative examples of the present invention and are not intended to limit the scope of the present invention only to those embodiments. Those skilled in the art can implement the invention in various other forms without departing from the spirit of the invention.

In the above embodiment, the first image and the second image were images obtained from different drugs with the same modality, but they may be images with different modalities, ie different imaging principles. For example, modalities include SPECT images, MRI images, X-ray images, ultrasound images, etc., in addition to PET images. That is, as long as the images have different accumulation (contrast, signal intensity, etc.) mechanisms, the pixel values (signal intensities) in the images will differ, so this embodiment can be applied. Examples applicable to this embodiment include those shown in Table 1 below (Table 1)

1 image processing device 16 FDG pixel ratio calculator 17 MET pixel ratio calculator 19 first candidate pixel extractor 20 second candidate pixel extractor 21 first feature region extractor 22 second feature region extractor 23 index calculator 31 FDG -PET image data storage unit 32 MET-PET image data storage unit

Claims (8)

A computer program for an image processing apparatus having storage means for storing image data of a single first image and a second image obtained by imaging the same part of the same subject,
In the step of extracting the region of the abnormal site as the first characteristic region, whether or not a certain pixel is extracted as being included in the first characteristic region is determined by the pixel value of the certain pixel in the first image. A first pixel ratio of a pixel value of a candidate pixel of normal tissue in the first image and a second pixel of a pixel value of the certain pixel in the second image and a pixel value of the candidate pixel of normal tissue in the second image extracting as the first feature region based at least on whether a combination of pixel ratios of ratios satisfies a first predetermined condition;
In the step of extracting the region of the abnormal site as a second characteristic region, whether or not a certain pixel is extracted as being included in the second characteristic region is determined by a combination of the pixel ratios corresponding to the certain pixel. is extracted as the second characteristic region, based at least on whether or not it satisfies a second predetermined condition different from the first predetermined condition;
A computer program that causes the image processing device to execute a step of calculating an index relating to the state of the abnormal site based on the first characteristic region and the second characteristic region. calculating, for pixels of the first image, a first pixel ratio between each pixel value and a pixel value of a candidate pixel of normal tissue;
calculating, for pixels of the second image, a second pixel ratio between each pixel value and a pixel value of a candidate pixel of normal tissue;
a step of extracting a plurality of pixels that are candidates for the abnormal site as first candidate pixels based on the calculated first pixel ratio and the second pixel ratio;
extracting a plurality of pixels that are candidates for the abnormal site as second candidate pixels based on the calculated first pixel ratio and the second pixel ratio; and
extracting the first feature region based on the first candidate pixel;
2. The computer program according to claim 1, extracting said second feature region based on said second candidate pixel. 3. The computer program according to claim 1 or 2, wherein the first image and the second image are images of different modalities, or images of the same modality but obtained with different drugs. receiving a designation of one pixel among the plurality of first candidate pixels;
further causing the image processing device to perform a step of accepting designation of one pixel among the plurality of second candidate pixels;
Extracting a region of pixels contiguous to the designated pixel among the plurality of first candidate pixels as the first feature region;
3. The computer program according to claim 2, wherein a region of pixels contiguous to said designated pixel among said plurality of second candidate pixels is extracted as said second feature region. The index is the volume or surface area of the difference area between the first characteristic area and the second characteristic area, the ratio of the volume or surface area between the difference area and the second characteristic area, or the first characteristic area and the 4. The computer program product according to any one of claims 1 to 3, which is a rate of overlap with the second feature region. The first characteristic region is a tumor site region,
the second characteristic region is the core region of the tumor site,
6. The computer program according to any one of claims 1 to 5, wherein the index regarding the state of the abnormal site is an index regarding tumor site invasion. The first image is a PET image taken by administering 18F-FDG (fluorodeoxyglucose) to the subject,
5. The computer program according to any one of claims 1 to 4, wherein the second image is a PET image taken after administering 11C-methionine to the subject. An image processing apparatus having storage means for storing image data of a single first image and a single second image obtained by imaging the same part of the same subject,
A first characteristic region extraction unit for extracting an abnormal site region as a first characteristic region, wherein whether or not a certain pixel is extracted as being included in the first characteristic region is determined by the first characteristic region of the certain pixel. A first pixel ratio between a pixel value in an image and a pixel value of a candidate pixel of normal tissue in the first image, a pixel value of the certain pixel in the second image, and a pixel value of the candidate pixel of normal tissue in the second image the first characteristic region extraction unit, based at least on whether a combination of pixel ratios consisting of a second pixel ratio of and satisfies a first predetermined condition;
A second characteristic region extraction unit for extracting the region of the abnormal site as a second characteristic region, wherein whether or not a certain pixel is extracted as being included in the second characteristic region corresponds to the certain pixel a second characteristic region extracting unit that satisfies at least whether the combination of pixel ratios satisfies a second predetermined condition different from the first predetermined condition;
An image processing apparatus comprising: an index calculator that calculates an index related to the state of the abnormal site based on the first characteristic region and the second characteristic region.

Images