JP2004267450A - Image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing technique capable of efficiently extracting a desired area from a medical image without being influenced by the fluctuation of the size of an object in the medical image. <P>SOLUTION: An image input part 1 inputs the medical image and auxiliary information relating to the medical image. A geometric parameter extraction part 2 decides the size of an area which can include a specified part existing in the medical image on the basis of the auxiliary information. A reference position detection part 3 decides the reference position of the object in the medical image. A search range decision part 4 decides an analysis area of the medical image on the basis of the reference position and the area size. An analysis part 5 analyzes the analysis area, and decides a specified area in the object. Then, an output part 6 outputs positional information indicating the position of the specified area. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to image processing for medical images such as simple X-ray images.
[0002]
[Prior art]
In recent years, digital images have been increasingly used in the field of medical image diagnosis. For example, an imaging apparatus that captures an X-ray image using a semiconductor sensor has a practical advantage that an image can be recorded over an extremely wide radiation exposure area as compared with a conventional radiographic system using silver halide photography. ing.
[0003]
That is, in such a photographing apparatus, an X-ray having a very wide dynamic range is read by a photoelectric conversion unit, converted into an electric signal, and converted into a digital signal. By using this digital signal to output a radiation image as a visible image on a recording material such as a photographic photosensitive material or a display device such as a CRT, it is possible to obtain a radiation image which is not affected by a change in radiation exposure. .
[0004]
Digitizing the medical image in this way has created a possibility of a diagnostic form that has been difficult with conventional silver halide photography.
[0005]
For example, when a medical image is output to a display device such as a CRT to perform observation, image processing is performed on a necessary portion of a digitalized image of a subject (object) to emphasize that portion. Attempts have been made to further improve the diagnosis by detecting a suspected lesion by performing image analysis and further performing image analysis.
[0006]
In performing such image processing, it is often necessary to extract a region to be diagnosed from a digital image of a subject image.
[0007]
For example, when performing an enhancement process on a chest X-ray image, it is desirable to extract a lung field region and perform processing only on the region. In CAD (computer aided diagnosis), which has been researched and developed in recent years, in order to reduce false positives in the course of analysis processing, it is necessary to limit the processing range to the region of the target organ. It is effective in improvement.
[0008]
As a method of extracting a region corresponding to a desired organ from an image in which a subject is depicted, a method of analyzing an image signal to extract a feature point in the image, and extracting a region using the feature point is known. It has been proposed (Patent Document 1).
[0009]
[Patent Document 1]
Japanese Patent Application Laid-Open No. 8-335271 [Problems to be Solved by the Invention]
However, in Patent Literature 1, an image actually handled at a clinical site may have a significantly different area occupied by a subject in the image if processing conditions such as imaging conditions are different.
[0010]
That is, since the imaging devices used in actual medical sites are not always under the same conditions, the pixel pitch of the detector used for imaging is different or the distance between the X-ray source and the detector is always constant. Since there is no guarantee, the size of the subject in the image may be different.
[0011]
In addition, when extracting a desired region from an image, a feature point is often extracted by searching within the image. However, since the range of the search may change in the clinical image as described above, There is a problem that it is difficult to determine an appropriate range in advance.
[0012]
The solution to this problem is to increase the range of the search. However, in this case, the probability of erroneous detection of the desired area increases, and the processing time increases.
[0013]
SUMMARY An advantage of some aspects of the invention is to provide an image processing technique capable of appropriately determining a processing target area in a medical image.
[0014]
[Means for Solving the Problems]
An image processing apparatus according to the present invention for achieving the above object has the following configuration. That is,
Medical image, input means for inputting incidental information related to the medical image,
Size determining means for determining the size of the area based on the incidental information,
Reference position determination means for determining a reference position in the medical image,
A region determining unit that determines a processing target region in the medical image based on the size and the reference position.
[0015]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
[0016]
<First embodiment>
FIG. 1 is a basic configuration diagram of the image processing apparatus according to the first embodiment of the present invention, and FIG. 2 is a schematic flowchart illustrating an operation of the image processing apparatus according to the first embodiment of the present invention.
[0017]
Hereinafter, an example of performing image processing on a chest X-ray image captured by an imaging apparatus having an X-ray source (radiation source) and a detector (composed of a plurality of detection elements) will be described. Details of the operation of the apparatus will be described with reference to these drawings.
[0018]
The hardware for realizing the image processing apparatus may be realized by a general-purpose computer such as a personal computer or a workstation. In this case, the general-purpose computer includes, as standard components, for example, a CPU, a RAM, a ROM, and the like. , A hard disk, an external storage device, a network interface, a display, a keyboard, a mouse, and the like.
[0019]
[Step S100]
The image input unit 1 inputs a medical image to be analyzed as an image file via an image storage device (not shown) or an external interface such as a network. Here, the image file is accompanied by actual image data and various parameters (supplementary information) at the time of capturing the image, and these are combined into a header different from the image data as a header of the image file. I have.
[0020]
[Step S200]
Next, the image input unit 1 separates the header from the input image file. As a result, the header is input to the geometric parameter extraction unit 2, and the image data in the image file is input to the reference position detection unit 3.
[0021]
[Step S300]
Next, the geometric parameter extraction unit 2 extracts parameters at the time of capturing the image data from the separated header. Here, in the first embodiment, the parameters to be extracted are values indicating the pixel pitch (pixel sense) of the detector of the imaging device and the distance (imaging distance) between the X-ray source and the detector.
[0022]
[Step S400]
The geometric parameter extraction unit 2 determines the size (size) of a window (a region that can include a specific part included in the image) when searching for image data based on the extracted pixel pitch and shooting distance. FIG. 3 shows an example of a window for a chest front image, and FIG. 3A shows an example of setting a window for a chest X-ray front image in a standard state (hereinafter, a standard state).
[0023]
Here, the standard state indicates that the pixel pitch of the detector of the imaging apparatus is a predetermined value, and the imaging distance between the X-ray source and the detector is a standard value. Further, W0 and H0 represent a search range (analysis area) for searching for a lung field when an adult patient is imaged in this standard state in pixel units. These values in the standard state are stored in a memory (not shown) in the geometric parameter extraction unit 2 in advance.
[0024]
On the other hand, if the photographing environment (such as the environment of a car-mounted photographing device) does not allow a sufficient photographing distance, or if the pixel pitch becomes smaller due to improved detector performance, As shown in FIG. 3B, the subject is photographed larger than in FIG.
[0025]
In this case, the geometric parameter extraction unit 2 corrects W0 and H0 based on the pixel pitch and the photographing distance extracted from the header of the image file, and calculates and outputs W1 and H1.
[0026]
W1 = α ・ β ・ W0 (1)
H1 = α · β · H0 (2)
Here, α and β are correction coefficients based on the photographing distance and the pixel pitch change, respectively, and are calculated as follows.
[0027]
α = γ · L / (L−t0) (3)
β = p0 / p (4)
γ = (L0−t0) / L0 (5)
Here, γ is a coefficient calculated from a standard photographing distance L0 as shown in FIG. 4 and a distance t0 based on a standard adult body size. P0 is a standard pixel pitch. L and p are the shooting distance and pixel pitch at the time of shooting read from the header of the image file.
[0028]
[Step S500]
The reference position detection unit 3 detects the axis of symmetry in the image from the characteristics of the input image data. In this detection, as shown in FIG. 5, first, two windows rl and rr are set at an equal distance d with respect to the temporary symmetry axis Tx, and each window rl at a position symmetrical about the temporary symmetry axis Tx. , Rr are subtracted from each other, and the sum of squares is calculated. Then, the temporary symmetry axis Tx is moved within a predetermined range, and the position where the sum of squares is minimized is determined as the horizontal position (reference position) of the symmetry axis Tx.
[0029]
[Step S600]
The search range determining unit 4 searches for a rib cage position in a target image based on the output (parameter) of the geometric parameter extracting unit 2 and the output (reference position) of the reference position detecting unit 3 (analysis region). To determine. FIG. 6 is an example of the determined search range, in which the search ranges Wsr and Wsl are set symmetrically with respect to the axis of symmetry Sx.
[0030]
[Step S700]
The analysis unit 5 detects the rib cage (region of interest in the subject) from within the search windows rr and rl. As a method of detecting the rib cage, for example, as disclosed in Japanese Patent Application Laid-Open No. 8-335271, an edge is extracted from a result obtained by integrating and projecting an image on one-dimensional data, and interpolation is performed between the edges. Can be detected.
[0031]
FIG. 6 illustrates an example of detection, in which a search area (analysis area) set at a position symmetrical with respect to the symmetry axis Sx (reference position) is compared with lung fields Fr and Fl (region of interest in the subject). ) Shows the result of detection.
[0032]
[Step S800]
The output unit 6 outputs position information indicating the position of the detected lung field to the outside (external device). The position information is represented by information such as coordinate points representing the outline of each lung field, and the output unit 6 is specifically configured as a device that transfers the position information for subsequent processing, a device such as an interface, or the like. Function.
[0033]
Here, the subsequent external device itself is not within the scope of the present invention, but is, for example, a device such as an analysis device that detects gradation processing or a lesion, and performs processing such as gradation processing based on detected position information. Processing is performed.
[0034]
As described above, according to the first embodiment, the reference position of the image that is not affected by the size of the subject is detected, and the predetermined anatomical information is used using the information about the imaging device or the subject added to the image. By determining a search range (analysis region) for searching for a feature point, highly accurate detection can be realized while suppressing an increase in processing time.
[0035]
<Embodiment 2>
In the first embodiment, the shooting distance and the pixel pitch are read from the header of the image file to determine the search range. However, information on the subject (patient or the like) included in the header may be further reflected.
[0036]
That is, although t0 and h0 in FIG. 4 are set in advance from the values of the standard body dimensions of an adult, these values are corrected based on factors such as age and gender in the header that are correlated with the body dimensions. Then, the search range may be determined based on the result.
[0037]
For example, if the patient is a child and has a smaller body size than an adult, a correction coefficient is calculated in advance based on a standard value of the corresponding age. The calculation formula at this time is as follows.
[0038]
α = ε · hc / (L0−tc) (6)
ε = (L0−ta) / ha (7)
Here, ha, hc and ta, tc are representative values of adults and children corresponding to h0 and t0 in FIG.
[0039]
As described above, according to the second embodiment, the search range can be appropriately set according to the body dimensions of the patient to be imaged.
[0040]
<Embodiment 3>
In the first embodiment, the reference position detection unit 3 detects the symmetry axis of the image, but may use another reference position. For example, the center of gravity may be obtained by binarizing the input image, and the search range may be determined using the center of gravity as a reference position.
[0041]
<Embodiment 4>
In each of the embodiments described above, the input to the image processing apparatus is an image file composed of image data and a header including parameters, but the present invention is not limited to this. For example, data (supplementary information) corresponding to the header may be input as a separate file separately from the image data.
[0042]
As described above, the embodiment has been described in detail. However, the present invention can take an embodiment as, for example, a system, an apparatus, a method, a program, a storage medium, or the like. The system may be applied to a system including a single device or an apparatus including one device.
[0043]
The image processing apparatuses according to the first to third embodiments described above can be realized by an information processing apparatus such as a personal computer. Further, the processing procedure can be regarded as a method invention. In addition, since the present invention can be realized by a computer, the present invention stores a computer program to be executed by each device, and further stores the computer program in a computer-readable storage medium such as a CD-ROM that can be read by a computer. It will be clear that also can be applied.
[0044]
Therefore, the embodiments according to the first to third embodiments are listed as follows. That is, the image processing apparatus, method, and program are as follows.
[0045]
[Embodiment 1] Input means for inputting a medical image and incidental information related to the medical image,
Size determining means for determining the size of the area based on the incidental information,
Reference position determination means for determining a reference position in the medical image,
An image processing apparatus comprising: an area determining unit that determines an area to be processed in the medical image based on the size and the reference position.
[0046]
Second Embodiment The image processing apparatus according to the first embodiment, further comprising a region-of-interest determination unit that determines a region of interest in the medical image by analyzing the processing target region.
[0047]
Third Embodiment The image processing apparatus according to the second embodiment, further comprising an output unit that outputs position information indicating a position of the region of interest.
[0048]
[Embodiment 4] The image processing apparatus according to Embodiment 1, wherein the supplementary information includes information on a pixel pitch of a detector in the radiation imaging apparatus that has generated the medical image.
[0049]
[Fifth Embodiment] The image processing apparatus according to the first embodiment, wherein the supplementary information includes information on an imaging distance in radiation imaging in which the medical image is generated.
[0050]
[Sixth Embodiment] The image processing apparatus according to the first embodiment, wherein the supplementary information includes information correlated with the size of a subject in the medical image.
[0051]
[Seventh Embodiment] The image processing apparatus according to the first embodiment, wherein the reference position is a position of a symmetry axis in a subject region in the medical image.
[0052]
[Eighth Embodiment] The image processing apparatus according to the first embodiment, wherein the reference position is a center of gravity of a subject area in the medical image.
[0053]
[Embodiment 9] An input step of inputting a medical image and incidental information related to the medical image,
Based on the incidental information, a size determination step of determining the size of the area,
A reference position determination step of determining a reference position in the medical image,
An area determining step of determining a processing target area in the medical image based on the size and the reference position.
[0054]
[Embodiment 10] A program code of an input step of inputting a medical image and incidental information related to the medical image,
A program code for a size determination step of determining the size of the area based on the incidental information;
Program code of a reference position determination step of determining a reference position in the medical image,
An image processing program comprising: an area determining step of determining a processing target area in the medical image based on the size and the reference position.
[0055]
According to the present invention, a software program (for example, a program corresponding to the illustrated flowchart) for realizing the functions of the above-described embodiments is directly or remotely supplied to a system or an apparatus. It is also achieved by reading and executing the supplied program code.
[0056]
Therefore, the program code itself installed in the computer to implement the processing of the present invention by the computer also implements the present invention. That is, the present invention includes the computer program itself for realizing the processing of the present invention.
In this case, the program may be in the form of an object code, a program executed by an interpreter, script data supplied to an OS, or the like as long as the program has the function of the program.
[0057]
As a recording medium for supplying the program, for example, a floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card , ROM, DVD (DVD-ROM, DVD-R) and the like.
[0058]
Alternatively, by connecting to a homepage on the Internet using a browser of a client computer, and downloading the computer program itself of the present invention or a compressed file including an automatic installation function from the homepage to a recording medium such as a hard disk, the program is also executed. Can be supplied. The program can also be supplied by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. In other words, the present invention also includes a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer.
[0059]
In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and downloaded to a user who satisfies predetermined conditions by downloading key information for decrypting from a homepage via the Internet. The program can also be supplied by executing the encrypted program using the key information and installing the program on a computer.
The functions of the above-described embodiments are implemented when the computer executes the read program, and the OS or the like running on the computer executes a part of the actual processing based on the instructions of the program. Alternatively, the functions of the above-described embodiments can be realized by performing all of them.
[0061]
Further, after the program read from the recording medium is written into the memory provided in the function expansion board inserted into the computer or the function expansion unit connected to the computer, the function expansion board or the The functions of the above-described embodiments can also be realized when a CPU or the like provided in the function expansion unit performs part or all of the actual processing.
[0062]
【The invention's effect】
As described above, according to the present invention, it is possible to provide an image processing technique capable of appropriately determining a processing target area in a medical image.
[Brief description of the drawings]
FIG. 1 is a basic configuration diagram of an image processing apparatus according to a first embodiment of the present invention.
FIG. 2 is a schematic flowchart illustrating an operation of the image processing apparatus according to the first embodiment of the present invention.
FIG. 3 is a diagram illustrating an example of an arrangement of windows according to the first embodiment of the present invention.
FIG. 4 is a schematic diagram illustrating an arrangement of a photographing system according to the first embodiment of the present invention.
FIG. 5 is a diagram illustrating an example of an axis of symmetry and a search range of an image according to the first embodiment of the present invention.
FIG. 6 is a diagram illustrating an example of detecting a rib cage according to the first embodiment of the present invention.
[Explanation of symbols]
Reference Signs List 1 Image input unit 2 Geometric parameter extraction unit 3 Reference position detection unit 4 Search range determination unit 5 Analysis unit 6 Output unit

Claims (1)

Medical image, input means for inputting incidental information related to the medical image,
Size determining means for determining the size of the area based on the incidental information,
Reference position determination means for determining a reference position in the medical image,
An image processing apparatus comprising: an area determining unit that determines an area to be processed in the medical image based on the size and the reference position.

Images