JP2009061175A - Medical image processor and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a medical image processor which reduces the burdens of diagnostic reading on a doctor and performs an objective diagnostic support high in the degree of freedom. <P>SOLUTION: In the medical image processor 10, a detection part detects a lesion candidate in a medical image using two or more kinds of medical images for a decision tree stored in a storage part (step M1). A detected result is displayed at a display part (step M2), and when a threshold adjusting operation is performed through an operation part (step M3; Y), the detection part detects the lesion candidate again using a changed threshold (step SM4). The detected result is displayed by the display part (step M5). <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a medical image processing apparatus and a program.

  In the medical field, many modalities such as CR (Computed Radiography) apparatus, CT (Computed Tomography) apparatus, and MRI (Magnetic Resonance Imaging) apparatus are used. Since medical images obtained by each modality have different image characteristics, various information can be obtained. The doctor interprets these multiple types of medical images at the same time, comprehensively determines the characteristics of each medical image, and specifies the position and type of the lesion.

At the time of interpretation, comparative interpretation is performed by simultaneously displaying a plurality of types of medical images on a display. At this time, since the medical images of the modalities have different shooting dates and times, the shooting position of the subject (patient) may be shifted or the shooting conditions such as the slice thickness may be different even when shooting the same part. In this way, in order to make it easy for a doctor to interpret medical images with different conditions, a method for unifying conditions, such as alignment of each medical image by image processing, is disclosed (for example, see Patent Document 1). ).
Japanese Patent Laid-Open No. 10-137231

At present, a large number of medical images are generated by examination for one patient due to multifunctional modality and high-speed processing. Under such circumstances, doctors have to find characteristics of many types of medical images and make comprehensive judgments, which increases the burden of interpretation.
Although objective diagnosis is desirable, the identification of lesions is often subject to a doctor's subjective judgment based on the doctor's experience and knowledge.

  An object of the present invention is to reduce diagnostic burden on doctors and to provide objective and highly flexible diagnosis support.

According to the invention of claim 1,
Storage means for storing information of a decision tree in which a plurality of determination steps for determining a lesion candidate based on a plurality of types of medical images are determined in a branched manner;
Detecting means for detecting lesion candidates in a medical image using a plurality of types of medical images in the stored decision tree;
Operating means for adjusting the determination conditions in the plurality of determination steps;
A medical image processing apparatus is provided.

According to invention of Claim 2,
In each determination step of the decision tree, the type of medical image used for determination and a threshold value of the feature amount of the medical image are determined,
The determination condition for performing the adjustment operation by the operation means is a threshold value of the feature amount of the medical image,
The detection means discriminates and detects the position and type of a lesion candidate in the medical image based on the result of comparing the threshold adjusted by the operation means and the feature amount of the medical image in each discrimination step. As a result, the medical image processing apparatus according to claim 1 is provided.

According to invention of Claim 3,
Display means for displaying a detection result by the detection means;
Control means for switching and displaying the detection result after the adjustment operation every time the threshold adjustment operation is performed by the operation means and detection is performed using the threshold adjusted by the detection means,
A medical image processing apparatus according to claim 2 is provided.

According to invention of Claim 4,
The said control means displays the said multiple types of medical image with the said detection result by the said display means, and displays the operation information for adjusting the threshold value corresponding to the said medical image for every these medical images. The medical image processing apparatus described in 1) is provided.

According to the invention of claim 5,
5. The medical image processing according to claim 4, wherein the control unit displays the operation information only for a medical image used in a determination process that has been performed when the lesion candidate is detected by the detection unit among the plurality of types of medical images. An apparatus is provided.

According to the invention of claim 6,
Computer
A program for causing the medical image processing apparatus according to any one of claims 1 to 5 to function is provided.

  According to the first, second, and sixth aspects of the invention, in detecting a lesion candidate based on a decision tree, a doctor can arbitrarily adjust a threshold value that is a determination condition. As a result, not only the predetermined determination condition but also the detection result when the determination condition is changed can be obtained, and the detection result under various conditions can be simulated. In other words, it is possible to provide information on detection results of lesion candidates to a doctor so that the doctor's interpretation burden can be reduced, and the doctor himself / herself can perform adjustment operations, thereby providing objective and highly flexible diagnosis support. be able to.

  According to the invention described in claim 3, the doctor can easily confirm the detection result after the adjustment operation in real time. It can also be used when explaining a lesion to a patient.

  According to the fourth aspect of the invention, it is possible to perform the adjustment operation after the doctor knows which medical image is to be subjected to the adjustment operation for the determination condition.

  According to the fifth aspect of the present invention, the threshold adjustment operation can be performed only for the medical image related to the detected lesion candidate, and the adjustment operation can be facilitated by narrowing down the operation target of the doctor. .

First, the configuration will be described.
FIG. 1 shows a functional configuration of a medical image processing apparatus 10 in the present embodiment.
As shown in FIG. 1, the medical image processing apparatus 10 includes a control unit 11, an operation unit 12, a display unit 13, a communication unit 14, a storage unit 15, and a detection unit 16.

  The control unit 11 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like. The control unit 11 performs various calculations and centrally controls the operation of each unit in cooperation with various programs stored in the storage unit 15.

  The operation unit 12 includes a keyboard, a mouse, and the like, generates operation signals according to these operations, and outputs them to the control unit 11. That is, the user can perform various instruction operations via the operation unit 12.

The display unit 13 has a display. The display unit 13 displays a medical image and a detection result of a lesion candidate by the detection unit 16 in addition to various operation screens according to the display control of the control unit 11.
The communication unit 14 includes a communication interface, and communicates with an external device such as an image server that stores medical images.

  The storage unit 15 stores programs used in the control unit 11 and the detection unit 16, parameters necessary for executing the programs, setting data, and the like. For example, information on a decision tree used for executing a program related to lesion candidate detection processing is stored. The decision tree will be described later.

The detection unit 16 detects lesion candidates using a plurality of types of medical images. Detection of a lesion candidate is performed based on decision tree information stored in the storage unit 15.
FIG. 2 is a diagram illustrating a decision tree T according to the present embodiment.
The decision tree T is one of classification models for discriminating lesion candidates based on a plurality of types of medical images. In the decision tree T, as shown in FIG. 2, a plurality of discriminating steps S1 to S14 are determined in a branched manner, and the structure branches to the next discriminating step determined by the discriminating condition in a discriminating step. It has become. In the decision tree T, information on lesion candidates that are determined as a result of the determination steps S1 to S14 is defined. The information on the candidate lesion is the presence / absence of the candidate lesion and the type of information when the candidate lesion exists. The storage unit 15 stores configuration information, determination conditions, lesion candidate information, and the like of each of the determination steps S1 to S14 as information about the decision tree T.

In each of the determination steps S1 to S14, as the determination conditions, the type of medical image related to the determination and threshold values Th1 to Th14 for the feature amount of the medical image are determined. In this embodiment, an example will be described in which pixel values indicating image density and luminance are used as the feature amount of a medical image.
In FIG. 2, the types of medical images used in the determination steps S1 to S14 are described inside the rhombuses indicating the determination steps S1 to S14. “Simple CT” indicates a medical image captured by a CT apparatus without using a contrast agent, and “Contrast CT” indicates a medical image captured by a CT apparatus using a contrast agent. “T1”, “T2”, and “STIR” are medical images taken by the MRI apparatus with different imaging methods, and indicate a T1-weighted image, a T2-weighted image, and a STIR image, respectively. “Contrast MRI” is a medical image taken with an MRI apparatus using a contrast agent.

Next, a method for detecting a lesion candidate using the decision tree T will be described.
Detection is performed for each pixel. Different types of medical images are used depending on the discrimination steps S1 to S14, but as shown in FIG. 3, all target pixels are the same position (hereinafter referred to as target pixels). At this time, if the position of the subject (patient) is shifted due to the medical image, accurate detection cannot be performed. Therefore, preprocessing for adjusting these in advance is performed so that the position, shape, distortion, resolution, pixel value range (range), and the like do not vary depending on the medical image. A known technique can be used as the pretreatment. For example, as a pre-processing for alignment, as described in Japanese Patent Laid-Open No. 10-137231, a certain anatomical position (for example, the spine) is specified, and this specific position is matched in a plurality of types of medical images. Perform coordinate transformation on. Moreover, the process etc. which normalize the range of a pixel value are also mentioned.

Each medical image for which preprocessing has been completed is input to the decision tree T.
In the first discrimination step S1 of the decision tree T, the pixel value of the target pixel in the “simple CT” medical image is compared with the threshold value Th1 defined in the discrimination step S1. If the pixel value exceeds the threshold value Th1 (S1; Y), the process branches to the determination step S2. Conversely, if the pixel value is equal to or less than the threshold value Th1 (S1; N), the process branches to the determination step S2. Here, a case where it is equal to or less than the threshold Th1 will be described.

  In the determination step S2, the pixel value of the target pixel in the “contrast CT” medical image is compared with the threshold Th2. As in the determination step S1, if the pixel value exceeds the threshold value Th2 (S2; Y), the process branches to the determination step S5. If the pixel value is equal to or less than the threshold value Th2 (S2; N), the process branches to the determination step S4. In this manner, the pixel values of the types of medical images determined in the determination steps S1 to S14 are compared with the threshold values Th1 to Th14, and the process sequentially branches to the next determination step determined according to the comparison result. Go. Since information on a lesion candidate is determined as a final discrimination result in each discrimination step S1 to S14, information on the lesion candidate is obtained. For example, when the pixel value of the medical image “T2” is equal to or less than the threshold value Th8 (S8; N), information on cirrhosis or fatty liver is obtained as the lesion candidate information. This information indicates that there is a high possibility that a lesion exists at the position of the target pixel, and that the type of the lesion is highly likely to be cirrhosis or fatty liver.

On the other hand, when the determination step S14 is reached and it is determined that the pixel value of the medical image of “contrast MRI” is equal to or less than the threshold Th14 (S14; N), information on normality is obtained as information on the lesion candidate. This information indicates that there is a low possibility that a lesion exists at the position of the target pixel, and a high possibility that the target tissue is a normal tissue.
Thus, by passing through each discrimination | determination process S1-S14, the presence or absence of a lesion candidate finally, and the kind when a lesion candidate exists can be determined. Further, if the above detection process is repeated for all the pixels of the medical image, it can be classified into the pixels constituting the lesion candidate and the pixels of the normal tissue, and the position of the lesion candidate in the medical image can also be determined.

  The determination conditions of the determination steps S1 to S14 in the decision tree T are determined based on a doctor's interpretation method. That is, the doctor first suspects the presence of a lesion based on the pixel value Th1 using the “simple CT” medical image and then suspects the lesion based on the pixel value Th2 of the “contrast CT” medical image. The decision tree T is constructed in consideration of the types and order of medical images to be interpreted when specifying the image, and the pixel values when determining the presence or absence of a lesion. In the construction, a medical image in which the presence of a lesion is clear is previously used as learning data, and the threshold values Th1 to Th14 of the determination steps S1 to S14 are optimized and stored in the storage unit 15 as initial setting values.

  Although only an example of performing discrimination using a medical image has been described, a discrimination process for performing discrimination using a result of a sample test such as a blood test may be incorporated.

Next, the operation of the medical image processing apparatus 10 will be described.
FIG. 4 is a flowchart for explaining detection adjustment processing performed by the medical image processing apparatus 10. The detection adjustment process is a process for adjusting the determination condition in the decision tree T according to the operation of the doctor. As a premise for explanation, a plurality of types of medical images obtained by examination for a patient designated in advance are acquired from an image server or the like and stored in the storage unit 15 and used for detection processing.

  First, as illustrated in FIG. 4, the detection unit 16 performs lesion candidate detection processing using the default threshold values Th1 to Th14 (step M1). Since the contents of the detection process are as described above, description thereof is omitted here. Subsequently, the control part 11 displays the detection result by the detection part 16 on the display part 13 (step M2).

FIG. 5 shows an example of the result screen d1 displaying the detection result.
As shown in FIG. 5, in the result screen d1, the control unit 11 displays an arbitrary medical image d11 among a plurality of types of medical images as a detection result of the detection unit 16, and a lesion candidate exists in the medical image d11. Only the determined pixels are displayed in a color so that they can be distinguished from the pixels determined to be normal. If multiple types of lesion candidates, such as cirrhosis and liver cyst, are detected, the pixels that are determined to be cirrhosis are red, and the pixels that are determined to be liver cysts are blue. By changing, each lesion candidate can be identified.

  Further, the control unit 11 displays a list of a plurality of types of medical images d12 acquired for detection together with the medical image d11 indicating the detection result. Of the medical images d11 displayed as a list, the medical image d12s actually used for discrimination in each of the discrimination steps S1 to S14 when a lesion candidate is detected is distinguished from other medical images by displaying a frame or the like. Display as possible.

  Further, for the medical image d12s, an operation bar d13 capable of adjusting the determination conditions of the threshold values Th1 to Th14 in the determination process using the medical image d12s is displayed. The operation bar d13 is operation information obtained by displaying the button d132 on the indicator d131, and the indicator d131 indicates an adjustable threshold range. The doctor can adjust the threshold value by moving the button d132 on the indicator d131. The indicator d131 displays a marker d133 indicating thresholds Th1 to Th14 of initial setting values. The doctor can use the marker d133 as an index for determining how much the threshold values Th1 to Th14 should be changed.

  When there are a plurality of lesion candidates, the control unit 11 switches the display of the medical image d12s according to the selection of the lesion candidate by the operation unit 13. Referring to the example of FIG. 5, if a cirrhosis image region shown in red is selected and operated, the medical images (for example, “T2”, “simple CT”) used in the determination steps S1 to S14 that have been performed at the time of detection of cirrhosis. The operation bar d13 is displayed on the medical image). Thereafter, if the image region of the liver cyst shown in blue is selected and operated, the medical image d12s displaying the operation bar d13 is used as the medical image (for example, “ (STIR "medical image).

  In the result screen d1, when the operation bar d13 is operated to adjust the threshold values Th1 to Th14 (step M3; Y), the detection unit 16 performs detection processing again using the changed threshold values Th1 to Th14. (Step M4). When the determination steps S1 to S14 that are branched by changing the threshold values Th1 to Th14 change, the detection result should also change. For example, in the decision tree T shown in FIG. 2, liver cirrhosis candidate lesions have been detected through the discrimination steps S1, S2, S4, and S8. As a result of changing the threshold Th4 in the discrimination step S4, the process branches to the discrimination step S7. If so, it is not liver cirrhosis but liver cysts or candidiasis.

The control unit 11 switches the detection result of the lesion candidate displayed on the display unit 13 to the detection result based on the changed threshold values Th1 to Th14 and causes the display unit 13 to display the detection result (step M5). Also at this time, the same display as the result screen d1 displayed at the time of the first detection is performed. That is, among the plural types of medical images d12, the medical image d12s used in each of the determination steps S1 to S14 is identified and displayed at the time of detection by the changed threshold values Th1 to Th14, and the operation bar d13 is displayed.
Note that if the threshold Th1-Th14 is not adjusted (Step M3; N), the process proceeds to Step M6 without performing re-detection.

  Thereafter, when an end instruction operation is performed on the result screen d1 (step M6; Y), this process ends. When there is no end instruction operation in particular, the process returns to step M3 and steps M3 to M6 are performed. Repeat the process.

As described above, according to the present embodiment, after detecting a lesion candidate based on the decision tree T based on the determination condition according to the initial setting, the medical image d12s used in the determination steps S1 to S14 at the time of detection is detected. The operation bar d13 is displayed, and the threshold values Th1 to Th14 in the determination steps S1 to S14 can be operated. Therefore, when detecting a lesion candidate based on the decision tree T, the doctor can arbitrarily adjust the threshold values Th1 to Th14. Thereby, not only the detection result by the predetermined initial setting but also the detection result when the discrimination condition is changed can be obtained, and the detection result under various conditions can be simulated.
As a result, information on the detection results of lesion candidates can be provided to doctors, reducing the burden of interpretation on the doctors, and providing an objective and flexible diagnosis by providing detection results adjusted by the doctors themselves. Can provide support.

  Each time an adjustment operation is performed, detection is performed again using the adjusted threshold values Th1 to Th14, and the detection result is switched and displayed. Therefore, the doctor can easily check the detection result after the adjustment operation in real time. It can also be used when explaining a lesion to a patient.

In addition, since the operation bar d13 for performing the adjustment operation is displayed corresponding to the medical image used in the determination process, the adjustment operation is performed after the doctor grasps which medical image the threshold value is adjusted for. Can do.
Furthermore, since the operation bar d13 displays only the medical image actually used for the determination of the lesion candidate among the multiple types of medical images acquired for detection, only the medical image related to the detected lesion candidate is displayed. The threshold adjustment operation can be performed, and the doctor's adjustment operation can be facilitated.

In addition, the said embodiment is a suitable example to which this invention is applied, and is not limited to this.
For example, in the above embodiment, the operation bar d13 is displayed only for the medical image used for discrimination during the detection process on the result screen d1, and the adjustment operation of the threshold values Th1 to Th14 is enabled. d13 may be displayed to allow adjustment of the threshold values Th1 to Th14. Since adjustment operations can be performed in all discrimination steps, the degree of freedom of adjustment is improved.

  Further, in the above embodiment, the detection operation is performed once using the threshold values Th1 to Th14 of the initial setting values, and then the adjustment operation of the threshold values Th1 to Th14 by the doctor is enabled and detected again. Alternatively, the doctor may be able to adjust the threshold values Th1 to Th14. In this case, before performing the detection process, the setting screen is displayed, a plurality of types of medical images are displayed on the screen, and the operation bar d13 is displayed for all the displayed medical images. Then, detection processing is performed by changing the threshold values Th1 to Th14 of the determination steps S1 to S14 using the corresponding medical image in accordance with the operation of the operation bar d13.

  Further, as the operation information, as long as the changed threshold values Th1 to Th14 can be instructed, it is possible to display not only the operation bar d13 but also an input area where the numerical value itself can be input. Further, instead of always displaying, the operation bar d13 may be displayed by a pop-up window only while the medical image d12s is selected and operated.

  Further, as shown in FIG. 6, the decision tree T used for detection may be displayed on the operation screen d2 for the adjustment operation, and the operation bar d13 may be displayed in the diagram of the decision tree T. By displaying the decision tree T itself, the doctor can grasp the whole process of detecting a lesion candidate, and which threshold of the discrimination process should be changed, and how much the detection result is affected. Can be determined while predicting. In addition, as shown in FIG. 6, you may be able to grasp | ascertain the background of the discrimination | determination process when it detects using the default threshold value Th1-Th14 by showing with a thick line.

  Further, among the medical images d12s used in the determination process, the operation bar d13 may be displayed only for the medical image d12s in the determination process in which the pixel value of the target pixel is slightly different from the threshold and difficult to determine. For example, the operation bar d12s is displayed only in the determination process in which the difference between the threshold value and the pixel value is within a predetermined range. In such a determination step, even if the threshold value slightly changes, the detection result becomes different. Therefore, it is very effective for diagnosis to confirm the detection result by adjusting the threshold values Th1 to Th14.

Further, in the image d12s shown in FIG. 5, the pixels that have branched to the lesion candidates detected by the thresholds Th1 to Th14 in the determination steps S1 to S14 using the image d12s correspond to the lesion candidates. It is good also as highlighting by displaying with a color. When the threshold values Th1 to Th14 are adjusted by the operation of the operation bar d13, which pixels are greatly involved in the determination using the threshold values Th1 to Th14 by updating and displaying the highlight display in conjunction with the adjustment. The doctor can easily grasp whether or not.
Further, the threshold value of the pixel value has been described as an example of the determination condition that can be operated. However, when another feature amount such as a pixel position or frequency is used as the determination condition, these may be operated.

  Further, information on the adjusted threshold values Th1 to Th14 is stored in the storage unit 15, and the value stored in the storage unit 15 is used instead of the default threshold values Th1 to Th14 when performing the next detection process. It is good also as using. The doctor can customize it according to his / her interpretation style.

  In addition, when judging the branch of each decision tree T with a threshold value, fuzzy inference or the like is applied using the difference between each pixel value and the threshold value, and the degree of lesion likelihood may be output as a continuous value. Good. In this case, when the detection result is displayed, the doctor can be a useful reference for the possibility of a true lesion by indicating the degree of likelihood of the lesion. For example, in the result screen d11 of FIG. 5, the cirrhosis degree is expressed as a concentration, such as increasing the red density indicating cirrhosis if the degree of cirrhosis is large, and decreasing the red density if the degree of cirrhosis is small. By doing so, the doctor can grasp to what extent the detected cirrhosis lesion candidate is likely to be cirrhosis and use it as a reference for diagnosis.

It is a figure which shows the functional structure of the medical image processing apparatus in this embodiment. It is a figure which shows an example of the decision tree used for the detection of a lesion candidate. It is a figure explaining targeting at the pixel of the same position, when performing detection using a plurality of kinds of medical images. It is a flowchart explaining the detection adjustment process performed by a medical image processing apparatus. It is a figure which shows the example of a display of the result screen which can perform adjustment operation. It is a figure which shows an example of the operation screen for adjustment operation.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Medical image processing apparatus 11 Control part 12 Operation part 13 Display part 14 Communication part 15 Storage part 16 Detection part

Claims (6)

Storage means for storing information of a decision tree in which a plurality of determination steps for determining a lesion candidate based on a plurality of types of medical images are determined in a branched manner;
Detecting means for detecting lesion candidates in a medical image using a plurality of types of medical images in the stored decision tree;
Operating means for adjusting the determination conditions in the plurality of determination steps;
A medical image processing apparatus comprising: In each determination step of the decision tree, the type of medical image used for determination and a threshold value of the feature amount of the medical image are determined,
The determination condition for performing the adjustment operation by the operation means is a threshold value of the feature amount of the medical image,
The detection means discriminates and detects the position and type of a lesion candidate in the medical image based on the result of comparing the threshold adjusted by the operation means and the feature amount of the medical image in each discrimination step. The medical image processing apparatus according to claim 1 as a result. Display means for displaying a detection result by the detection means;
Control means for switching and displaying the detection result after the adjustment operation every time the threshold adjustment operation is performed by the operation means and detection is performed using the threshold adjusted by the detection means,
A medical image processing apparatus according to claim 2.   The said control means displays the said multiple types of medical image with the said detection result by the said display means, and displays the operation information for adjusting the threshold value corresponding to the said medical image for every these medical images. The medical image processing apparatus described in 1.   5. The medical image processing according to claim 4, wherein the control unit displays the operation information only for a medical image used in a determination process that has been performed when the lesion candidate is detected by the detection unit among the plurality of types of medical images. apparatus. Computer
The program for functioning as a medical image processing apparatus as described in any one of Claims 1-5.

Images