JP4756756B2 - Image processing method and program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an apparatus for analyzing a medical image and extracting a specific anatomical region.
[0002]
[Prior art]
When displaying data captured by an imaging device such as a sensor or camera on a monitor screen or an X-ray diagnostic film, the image data is subjected to gradation conversion and converted into a density value that is easy to observe. Is common. For example, when imaging data such as knee joints are displayed on a film for X-ray diagnosis, a feature amount for gradation conversion is extracted, and the extracted feature amount is converted to a constant density. .
[0003]
As a method for performing such gradation conversion, for example, a method is known in which a histogram of an entire image is created, and the created histogram is analyzed to obtain a feature amount. When calculating the feature amount from such a histogram, the irradiation field region recognition is performed, and the feature amount is calculated from the histogram of the image in the irradiation field region.
[0004]
[Problems to be solved by the invention]
However, when the pixel value of the bone region is extracted by the histogram analysis as described above, the pixel value of the rough bone region can be extracted, but it is difficult to accurately extract the pixel value of the bone region. It is. Therefore, it is difficult to perform gradation conversion with high accuracy.
[0005]
In addition, when a histogram of pixels in the irradiation area is used, there is a problem that the accuracy of the feature amount extraction process is affected by the accuracy of the irradiation area extraction.
[0006]
The present invention has been made in view of the above points, and an object of the present invention is to extract feature amounts stably with high accuracy.
[0007]
[Means for Solving the Problems]
In order to achieve the above object, the present invention has the following configuration.
[0008]
The invention according to claim 1 of the present application is an image processing apparatus for analyzing a medical image and extracting a specific anatomical region, the means for detecting a recessed region in the medical image, and the extracted recessed portion Extraction means for extracting the specific anatomical region based on pixel values in the region.
[0009]
The invention according to claim 5 of the present application is an image processing method for analyzing a medical image including a bone part to obtain a feature amount of the bone part region, detecting a concave region in the medical image, and detecting the detected Based on the recessed region, a central part of the bone part region is estimated, and based on the estimated central part of the bone part region, the bone part region in the medical image is extracted, and from the pixels belonging to the bone part region, the bone The feature amount of the part is obtained.
[0010]
DETAILED DESCRIPTION OF THE INVENTION
(Embodiment 1)
FIG. 1 shows an X-ray imaging apparatus 100 used in the first embodiment. The X-ray imaging apparatus 100 is an X-ray imaging apparatus having an image processing function, and includes a preprocessing circuit 106, a CPU 108, a main memory 109, an operation panel 110, and an image conversion circuit 111, via a CPU bus 107. Exchange data with each other.
[0011]
Furthermore, the X-ray imaging apparatus 100 includes a data acquisition circuit 105 connected to the preprocessing circuit 106, a two-dimensional X-ray sensor 104 and an X-ray generation circuit 101 connected to the data acquisition circuit 105, and these These circuits are also connected to the CPU bus 107.
[0012]
In the X-ray imaging apparatus 100 as described above, the main memory 109 stores various data necessary for processing by the CPU 108 and the CPU 108 used as a work memory for work of the CPU 108 Using the main memory 109, operation control of the entire apparatus is performed in accordance with an operation from the operation panel 110. Thereby, the X-ray imaging apparatus 100 operates as follows.
[0013]
First, the X-ray generation circuit 101 emits an X-ray beam 102 to the object 103 to be inspected. The X-ray beam 102 emitted from the X-ray generation circuit 101 passes through the object 103 while being attenuated, and reaches the two-dimensional X-ray sensor 104. The two-dimensional X-ray sensor 104 outputs an X-ray image. The X-ray image output from the two-dimensional X-ray sensor 104 is a human body image such as a knee image, for example.
[0014]
The data acquisition circuit 105 converts the X-ray image output from the two-dimensional X-ray sensor 104 into an electrical signal and supplies it to the preprocessing circuit 106. The preprocessing circuit 106 performs preprocessing such as offset correction processing and gain correction processing on the signal (X-ray image signal) from the data acquisition circuit 105. The X-ray image signal preprocessed by the preprocessing circuit 106 is transferred as an original image to the main memory 109 and the image processing circuit 111 via the CPU bus 107 under the control of the CPU 108.
[0015]
Reference numeral 111 denotes an image processing circuit. The image processing circuit includes a recessed area extracting circuit 112 that extracts a recessed area of the image, an area extracting circuit 113 that extracts a predetermined area from the recessed area extracted by the recessed area extracting circuit 112, and an area extracting circuit. A feature extraction circuit 114 that calculates a feature amount for tone conversion from the predetermined region extracted in 113 and a tone conversion circuit 115 that performs tone conversion of an image based on the feature amount calculated by the feature extraction circuit 114 are provided.
[0016]
2 and 3 are diagrams showing the flow of processing in the first embodiment. FIG. 3 is a diagram showing a processing flow of the recessed area extraction circuit 112 and the area extraction circuit 113. FIG. 4A is an image of the knee, 31 indicates a line that horizontally crosses the subject, and 32 indicates an end of the irradiation field region. FIG. 4B shows a profile on the line 31. In the figure, a, b, and c indicate three points in the same row, and d indicates a certain distance range from the point b. FIG. 5 is a bone region line extracted from FIG. 4, and 41 indicates the bone region. FIG. 6A is a spine image, 52 indicates an irradiation region, line 53 indicates a linear bone region extracted, and 51 indicates a line horizontally across the subject. FIG. 6B shows a profile on the line 51, and the interval a indicates a certain distance from the minimum image point of the recess. FIG. 7 shows an image obtained by extracting the bone region in FIG. 6A, 62 is the irradiation end, and 63 is the bone region.
[0017]
The operation of the image processing circuit 111 will be described with reference to FIGS. First, the bone region is extracted by the concave region extraction circuit 112 and the region extraction circuit 113 (s101).
[0018]
Details of the processing in step s101 will be described with reference to FIG. The recessed area extracting circuit 112 extracts a recessed area in each row. Specifically, pixel points in the same row are sequentially extracted from the edge of the image, and it is sequentially determined whether or not the extracted pixel points come out of the recess. In order to determine whether or not it is a recess, for example, as shown in FIG. 3B, the extracted pixel point b and two points a and c at regular intervals around it are extracted (s201). Then, it is determined whether or not the pixel point b is a recess by comparing the extracted pixel value values of the three points. For example, if the pixel values at the three points in FIG. 3B are a> b and c> b, it is determined that the point b is concave, and if not, it is determined that it is not a concave (s202, s203). If it is a recess, the coordinates and the pixel value of the pixel point are stored in the main memory 109 (s204). If it is not a recess, the adjacent pixel point is extracted without saving, and the same determination process is performed. The processes in steps s201 to s204 are repeated up to the other image edge to extract the recessed area from the entire image.
[0019]
The area extraction circuit 113 extracts a pixel value point indicating the maximum pixel value in the recessed area for each row (s205). Further, the lowest pixel value point of the recessed area in the same row within a certain distance (for example, the distance d shown in FIG. 3B) from the extracted maximum pixel value point is extracted (s206).
[0020]
The pixel points extracted in step s206 are pixel points around the center of the bone. A pixel point indicating the maximum pixel value in the recessed area is extracted from the irradiation area. Furthermore, when the subject is composed of soft tissue and bone, the pixel value decreases in the order of omission, soft tissue, and bone, and the pixel value around the center of the bone is the lowest in the irradiation area. Indicates a pixel value. In normal imaging, the distance between the pixel point indicating the maximum pixel value in the recessed area and the bone portion is shorter than the distance between the pixel point indicating the maximum pixel value in the recessed area and the point at the irradiation end. For this reason, the lowest pixel value point in the recessed area within a certain distance from the pixel value point indicating the maximum pixel value in the recessed area is near the center of the bone.
[0021]
A region within a certain distance from the extracted lowest pixel value point is set as a bone region (s207). This process is performed for all rows to extract the bone region of the entire image. This is because the width of the bone part is almost determined, and the bone part region is within a certain distance from the center of the bone part.
[0022]
Note that the following method may be used for extracting the bone region in step s207. A line 53 in FIG. 6A is the center of the bone extracted by the processing up to s206. As shown in FIG. 6B, a region within a certain pixel value range (for example, a) from the pixel value of the line 53 indicating the lowest pixel value is defined as a bone region. The result of this method is shown in FIG. Since there is no great difference in the thickness of the bone part among people, the bone part region can be extracted by setting a pixel value within a certain range from the central pixel value of the bone part as the bone part region.
[0023]
The feature extraction circuit 114 calculates the average of the pixel values of the bone region extracted by the region extraction circuit 113, and sets it as a feature amount for gradation conversion (s102). The gradation conversion circuit 115 performs gradation conversion based on the feature amount extracted by the feature extraction circuit 114 (s103).
[0024]
According to the present embodiment, since the bone region is extracted based on the highest pixel value point of the recessed region, the bone region can be stably extracted without using irradiation region information. Therefore, since the calculation time of the irradiation area extraction process can be omitted, the time of the entire process can be shortened. In addition, since the recessed area is extracted from the arrangement of the three points of the image, the recessed area can be stably extracted without taking calculation time. Furthermore, by setting the lowest pixel value point within a certain distance from the highest pixel value point in the recessed area as a predetermined area, the central area of the bone can be extracted stably, and the bone area can be extracted with high accuracy. can do.
[0025]
(Other embodiments)
Software program code for realizing the functions of the above-described embodiment in an apparatus or a computer in the system connected to the various devices so as to operate the various devices so as to realize the functions of the above-described embodiments. Is implemented by operating the various devices according to a program stored in a computer (CPU or MPU) of the system or apparatus.
[0026]
In this case, the program code of the software itself realizes the functions of the above-described embodiment, and the program code itself and means for supplying the program code to the computer, for example, the program code is stored. The storage medium constitutes the present invention.
[0027]
As a storage medium for storing the program code, for example, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.
[0028]
Further, by executing the program code supplied by the computer, not only the functions of the above-described embodiments are realized, but also the OS (operating system) in which the program code is running on the computer, or other application software, etc. It goes without saying that the program code is also included in the embodiment of the present invention even when the functions of the above-described embodiment are realized in cooperation with the embodiment.
[0029]
Further, the supplied program code is stored in the memory provided in the function expansion board of the computer or the function expansion unit connected to the computer, and then the CPU provided in the function expansion board or function storage unit based on the instruction of the program code However, it is needless to say that the present invention also includes a case where the function of the above-described embodiment is realized by performing part or all of the actual processing.
[0030]
【The invention's effect】
According to the present invention, it is possible to extract feature amounts from medical images stably with high accuracy.
[0031]
According to the first aspect of the present invention, since the feature amount is extracted from the recessed area detected from the medical image, the feature amount can be stably extracted with high accuracy by a simple process.
[0032]
According to the invention of claim 5 of the present application, a bone region can be extracted from a medical image with high accuracy and with a simple process. Therefore, the feature amount of the bone can be obtained with high accuracy and with a simple process.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a first embodiment.
FIG. 2 is a diagram showing a flow of processing in the first embodiment.
FIG. 3 is a diagram showing a flow of processing in the first embodiment.
FIG. 4 is a diagram for explaining processing from knee images and their profiles.
5 is a diagram in which a bone region is extracted from the knee image of FIG. 4;
FIG. 6 is a diagram illustrating processing from a spinal column image and its profile.
7 is a diagram in which a bone region is extracted from the spinal column image of FIG.

Claims (2)

An image processing method for image processing a medical image including a bone part,
When the pixel value of the pixel of interest is lower than the pixel values of pixels located on the same line as the pixel of interest, the position of the pixel of interest is detected as a concave region, and based on the concave region, the center of the bone region Estimating a portion, and extracting a bone region in a medical image based on a central portion of the estimated bone region ;
And a step of gradation-converting a medical image including the bone part based on a feature amount calculated from the extracted bone part region. A program for causing a computer to execute an image processing method for image processing of a medical image including a bone part, wherein a pixel value of a pixel of interest is lower than pixel values of pixels located on the same line as the pixel of interest In this case, the position of the pixel of interest is detected as a recessed area, the central portion of the bone area is estimated based on the recessed area, and the bone area in the medical image is based on the estimated central area of the bone area. A program for realizing that a region is extracted and a medical image including the bone portion is subjected to gradation conversion based on a feature amount calculated from the extracted bone region.

Images