JP2010188042A - Medical image processor and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To increase a processing speed and accuracy for detecting image marker information embedded in medical images. <P>SOLUTION: A control part 10 of an image inspection device 1 generates a luminance distribution histogram based on medical image data acquired from a modality through a communication part 40. Then, the control part 10 detects the image marker information embedded in actual image data of the medical image data based on the luminance distribution histogram. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

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

  In medical facilities such as hospitals and clinics, an interpreting physician displays an image (medical image) obtained by radiography or the like on a monitor and observes (interprets) the displayed image. The image interpretation doctor performs image diagnosis to determine the presence or absence of a lesion and the state of a lesion. In this image diagnosis, an interpreting doctor needs to perform interpretation after correctly recognizing which part of a patient is taken from which direction.

  By the way, among images obtained by imaging, there are also images that are easily confused in direction, such as an image on the left side and an image on the right side of the imaging region. For this reason, a radiographer who normally performs radiography usually displays images obtained by radiography on a monitor, confirms the radiographing site and radiographing direction, and arranges the display style so that the direction can be easily identified. Provide images to the interpreting physician For example, the imaging engineer sets the display style so that the left side image is displayed on the left side of the monitor screen and the right side image is displayed on the right side of the monitor screen. With this setting, the image interpretation doctor can instantly grasp from which direction each image displayed on the monitor is taken of the imaging region.

  However, the above method is convenient for an image interpretation doctor who performs image diagnosis, but it is a heavy burden for an imaging engineer who performs a setting operation for confirming an imaging direction and adjusting a display style. In order to solve such a problem, a mark indicating the type of subject (subject type mark) is arranged at a position corresponding to the shooting direction in the image, and the shooting direction of the subject is determined based on the detected position of the subject type mark. Has been disclosed (see Patent Document 1). Specifically, the information processing apparatus used for the image inspection operation of medical image data composed of medical images (actual medical image data) and supplementary information of the medical images includes information on the imaging direction included in the supplementary information and medical information. The consistency of the shooting direction of the subject is determined by comparing the information recognized from the actual image data (the type and position of the subject type mark).

JP 2007-260062 A

  By the way, in order to detect (recognize) the information of the subject type mark included in the actual medical image data, that is, the image marker information embedded in the medical image, a character recognition technique is required. However, since the character recognition technique requires a complicated algorithm, it takes time to detect the information of the subject type mark. In addition, the character recognition technology is not necessarily accurate. For this reason, the image interpretation doctor takes time to perform an image inspection operation that requires character recognition processing by the information processing apparatus, which is inconvenient.

  The present invention has been made in view of the above-described problems, and an object thereof is to improve the processing speed and accuracy of detecting image marker information embedded in a medical image.

In order to solve the above problem, a medical image processing apparatus according to claim 1 is provided.
Control means for detecting image marker information embedded in the actual image data of the medical image data based on the luminance information of the medical image data;
Is provided.

The invention according to claim 2 is the invention according to claim 1,
The control means generates a luminance distribution histogram based on the luminance information of the medical image data, and detects the image marker information based on the luminance distribution histogram.

The invention according to claim 3 is the invention according to claim 2,
The control means detects the image marker information based on a peak value on the high luminance side in the luminance distribution histogram.

The invention according to claim 4 is the invention according to any one of claims 1 to 3,
A first acquisition means for acquiring order information relating to the medical image data;
The control unit detects marker information from the order information acquired by the first acquisition unit, compares the marker information with the image marker information, determines consistency, and if mismatched, displays warning information. Display on the display means.

The invention according to claim 5 is the invention according to any one of claims 1 to 3,
The control means detects marker information from incidental information attached to the medical image data, compares the marker information with the image marker information, determines consistency, and displays warning information in the case of inconsistency. To display.

The invention according to claim 6 is the invention according to claim 4 or 5,
The control means determines the consistency based on whether or not the image marker information is detected.

The invention according to claim 7 is the invention according to any one of claims 1 to 6,
The apparatus further comprises second acquisition means for acquiring the medical image data.

The program according to claim 8 is:
Computer
Control means for detecting image marker information embedded in the actual image data of the medical image data based on the luminance information of the medical image data;
To function as.

  According to the first and eighth aspects of the present invention, the image marker information embedded in the actual image data of the medical image data is detected based on the luminance information of the medical image data. Therefore, it is possible to improve the processing speed and accuracy of detecting image marker information embedded in a medical image.

  According to the second aspect of the present invention, since the image marker information is detected based on the luminance distribution histogram, the processing speed and accuracy can be further improved.

  According to the third aspect of the invention, since the image marker information is detected based on the peak value on the high luminance side in the luminance distribution histogram, the processing speed and accuracy can be further improved.

  According to the fourth aspect of the present invention, the marker information detected from the order information is compared with the image marker information to determine consistency, and warning information is displayed in the case of mismatch. Therefore, the user can know the mismatch between the marker information and the image marker information. In addition, since the marker information is detected from the order information, it is possible to accurately determine the consistency.

  According to the fifth aspect of the present invention, the marker information detected from the supplementary information attached to the medical image data is compared with the image marker information to determine consistency, and in the case of inconsistency, warning information is displayed. Therefore, the user can know the mismatch between the marker information and the image marker information.

  According to the sixth aspect of the present invention, it is possible to determine the consistency more accurately.

  According to the seventh aspect of the invention, the processing speed and accuracy of detecting image marker information embedded in a medical image acquired from the outside can be improved.

It is a system configuration figure showing an example of a system configuration of a radiology system. It is a block diagram of an image inspection apparatus. It is a data block diagram of a conversion table. It is a flowchart which shows a marker determination process. It is a flowchart which shows an image marker detection process. It is an image figure which shows a histogram production | generation area | region. It is an example of creation of a luminance distribution histogram. It is a flowchart which shows the modification of a marker determination process.

  Hereinafter, an embodiment when the medical image processing apparatus of the present invention is applied to the imaging apparatus 1 of FIG. 1 will be described with reference to FIGS.

[System configuration of radiology system]
First, the outline of the radiology system S having the imaging device 1 will be described with reference to FIG.

  FIG. 1 is a block diagram illustrating an example of a system configuration of the radiology system S. According to FIG. 1, the radiology system S includes an imaging apparatus 1, a RIS 2, a modality 3, and a PACS 4. Each of the above-described devices and systems are connected via a communication network N2 such as a LAN (Local Area Network) so that data communication is possible. Further, the RIS 2 is connected to the HIS 5 via the in-hospital network N1 so that data communication is possible.

  The HIS (Hospital Information System) 5 is composed of a computer having a control unit, a storage unit, an input unit, a display unit, a communication unit, etc., and each department such as medical office accounting, medical appointment reservation, electronic medical record management, examination and medicine It is a system that comprehensively manages hospital information such as ordering. The HIS 5 receives an imaging request in the radiology system S from a doctor and generates order information including the content of the imaging request. Then, the HIS 5 transmits the order information to the RIS 2 via the hospital network N1. The order information is data including patient information such as the name, ID, and gender of the patient to be imaged, and examination information indicating examination conditions such as an examination ID that identifies the examination ordered by the doctor, examination site, imaging direction, and body position. is there.

  The RIS (Radiologic Information System) 2 is composed of a computer having a control unit, a storage unit, an input unit, a display unit, a communication unit, etc., and makes medical appointments in the radiology department, reports on diagnosis results, results management, material inventory management. This is a system that manages information in the radiology system S in an integrated manner. The RIS 2 receives the order information transmitted from the HIS 5 and includes the RIS code in the order information. The RIS 2 transmits order information including the RIS code to the modality 3 and the imaging device 1.

  The RIS code is a code (integer string) for linking RIS2, modality 3, PACS4, etc. in the radiology department. In general, the RIS code includes a technique code part (indicating modality, major classification, small classification, technique extension, etc.), a part code part (indicating small part, left and right, etc.), and a photographing code part (posture, body position, photographing direction). Etc.). For example, the RIS code has a value such as “016110044000000”.

  The modality 3 is a medical imaging apparatus that images a patient and generates image data (actual image data) of a captured image (medical image). As the modality 3, modalities for photographing various types of medical images such as CT, CR, MRI, mammography apparatus, and ultrasonic diagnostic apparatus can be applied.

  The modality 3 generates incidental information having various information (patient information, examination information, series information, etc.) regarding the actual image data of the generated medical image based on the order information received from the RIS 2. Then, the modality 3 adds incidental information to the actual image data, and generates medical image data that conforms to the DICOM standard. The modality 3 transmits the generated medical image data to the image inspection apparatus 1. Then, the image inspection apparatus 1 transfers the medical image data to the PACS 4.

  When the modality 3 generates medical image data, it generates image marker information and embeds it in the actual image data according to the operation of the imaging engineer. That is, the modality 3 uses the image marker information as part of the actual image data. The image marker information is actual image data such as “L” and “R”, and is information indicating an annotation such as an inspection condition at the time of photographing. An interpreting physician can check examination information and the like with reference to the image marker information.

  The image inspection apparatus 1 receives the order information transmitted from the RIS 2 and the medical image data transmitted from the modality 3 and waits for the image capturing of the radiographer. “Image inspection” refers to whether a medical image is taken according to the order information, whether the actual image data of the medical image data has an image quality suitable for diagnosis, whether the order information and the incidental information are consistent, etc. This is an act of checking and correcting data before transferring it to PACS4. At this time, the image inspection apparatus 1 performs a marker determination process. The marker determination process will be described later. When the imaging engineer examines each medical image data, the imaging apparatus 1 transfers (transmits) the medical image data to the PACS 4 in accordance with the operation of the imaging engineer.

  The PACS 4 is a database system that stores and manages medical image data generated in the modality 3 and performs search and data analysis. The PACS 4 is configured to include a control unit, a storage unit, a communication unit, and the like, and accumulates and stores the medical image data in, for example, a relational database based on incidental information included in the medical image data received from the imaging device 1. To go. Then, the PACS 4 searches the medical image data using the patient ID, examination ID, etc. designated in accordance with the operation instruction from the interpretation doctor or the like as a search key, and outputs it to a viewer or imager (not shown).

[Functional structure of image inspection device]
FIG. 2 shows a functional configuration of the image inspection apparatus 1.

  As shown in FIG. 2, the imaging apparatus 1 includes a control unit 10, an operation unit 20, a display unit 30, a communication unit 40, and a storage unit 50, and each unit is connected by a bus 60.

  The control unit 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and comprehensively controls the processing operation of each unit of the imaging device 1. Specifically, the CPU reads various processing programs stored in the storage unit 50 according to an operation signal input from the operation unit 20 or an instruction signal received by the communication unit 40, and is formed in the RAM. The work area is expanded and various processes are performed in cooperation with the program.

  The operation unit 20 includes a keyboard having cursor keys, numeric input keys, various function keys, and the like, and a pointing device such as a mouse. The operation unit 20 controls operation signals input by key operations or mouse operations on the keyboard. 10 is output.

  The display unit 30 is configured by an LCD (Liquid Crystal Display), and displays various screens based on display data input from the control unit 10.

  The communication unit 40 includes a LAN (Local Area Network) adapter, a router, a TA (Terminal Adapter), and the like, and transmits and receives data to and from external devices such as the RIS2, the modality 3, and the PACS4 connected via the communication network N2. I do.

  The storage unit 50 is composed of a hard disk or the like, and stores a control program, parameters and files necessary for executing the program. In addition, the storage unit 50 temporarily stores medical image data waiting for image inspection transmitted from the modality 3. The storage unit 50 stores a conversion table 52.

  FIG. 3 shows the data structure of the conversion table 52. As shown in FIG. 3, the conversion table 52 includes items of “RIS code”, “imaging region / direction / procedure”, and “marker”. Based on the conversion table 52, the control unit 10 detects (identifies) marker information from the RIS code included in the order information. For example, when the RIS code included in the order information is “016110044000000”, the marker information is “R”. When the item “marker” is blank (invalid value), it indicates that no marker is necessary. Hereinafter, marker information detected from the RIS code included in the order information is referred to as order marker information.

  Returning to FIG. 2, when receiving the medical image data from the modality 3 via the communication unit 40, the control unit 10 stores the medical image data in the storage unit 50. In addition, when receiving the order information from the RIS 2 via the communication unit 40, the control unit 10 stores the order information in the storage unit 50. And the control part 10 displays a medical image, incidental information, order information, etc. on the display part 30 based on the operation signal from the operation part 20 by imaging technicians. The imaging engineer performs image inspection with reference to the displayed information.

  The control unit 10 performs a marker determination process. The marker determination processing is processing for determining consistency by comparing image marker information embedded in actual image data of medical image data with order marker information detected from corresponding order information.

[Marker judgment processing]
Next, specific processing contents of the marker determination processing performed by the control unit 10 of the imaging device 1 will be described with reference to FIG.

  The control unit 10 receives medical image data from the modality 3 via the communication unit 40 (step S1).

  Next, the control unit 10 performs an image marker detection process (step S2). Specifically, the control unit 10 detects image marker information embedded in the actual image data of the medical image data received in step S1. Details of the image marker detection process will be described later.

  Next, the control part 10 receives order information from RIS2 via the communication part 40 (step S3). This order information is order information corresponding to the medical image data received in step S1. That is, the medical image data received in step S1 is data generated based on this order information in the modality 3.

  Next, the control unit 10 refers to the conversion table 52 and detects order marker information from the received order information (step S4). Specifically, the control unit 10 reads the conversion table 52 from the storage unit 50. The control unit 10 reads the value of the “marker” of the record having a value that matches the value of the RIS code included in the received order information. The control unit 10 uses this value as order marker information.

  If the image marker information is detected from the actual image data of the medical image data in the image marker detection process in step S2 (step S5; YES), the control unit 10 matches the image marker information and the order marker information. It is determined whether or not (step S6). For example, when the image marker information is “R” and the order marker information is “R”, the control unit 10 determines that they match. On the other hand, when the image marker information is “L” and the order marker information is “R”, the control unit 10 determines that they do not match.

  When the image marker information matches the order marker information (step S6; YES), the control unit 10 ends the marker determination process. When the image marker information does not match the order marker information (step S6; NO), the control unit 10 displays warning information indicating that fact on the display unit 30 (step S9). And the control part 10 complete | finishes a marker determination process.

  On the other hand, if the image marker information is not detected from the actual image data of the medical image data in the image marker detection process in step S2 (step S5; NO), the control unit 10 determines the examination site information from the incidental information of the medical image data. (Imaging region / direction / procedure) is acquired (step S7). Specifically, the control unit 10 acquires examination part information which is one of examination information items included in the incidental information. For example, the examination site information takes a value such as “shoulder joint right front AP”.

  The control unit 10 determines whether an image marker is necessary based on the conversion table 52 and the examination site information (imaging site / direction / procedure) acquired in step S7 (step S8). Specifically, the control unit 10 determines that the value of the item “marker” of the record having the item “imaging site / direction / procedure” having a value that matches the value of the examination site information acquired in step S7 is blank (invalid value). It is determined whether or not.

  When determining that the image marker is not necessary in step S8 (step S8; NO), the control unit 10 ends the marker determination process. On the other hand, when the control unit 10 determines that an image marker is necessary (step S8; YES), the control unit 10 displays warning information on the display unit 30 (step S9). And the control part 10 complete | finishes a marker determination process.

  In this flowchart, the control unit 10 acquires examination site information from the supplementary information of the medical image data (step S7), and determines whether an image marker is necessary based on the examination site information and the conversion table 52. Although determined (step S8), the processing may be executed as follows. That is, in step S4, the control unit 10 refers to the conversion table 52, determines whether the “marker” value of the corresponding record is blank (invalid value), and holds the determination result. . And the control part 10 determines whether the image marker in step S8 is required based on this determination result, without performing the process of step S7.

[Image marker detection processing]
Next, specific processing contents of the image marker detection processing (step S2 in FIG. 4) will be described with reference to FIG.

  The control unit 10 of the image inspection apparatus 1 extracts a region (histogram generation region) for generating a luminance distribution histogram from actual image data of medical image data (step S101). Specifically, as illustrated in FIG. 6, the control unit 10 sets the predetermined pixels (for example, 20 pixels) on the outer periphery of the real image data, which is a region where there is a lot of noise close to the luminance of the image marker information, as real image data. And a histogram generation region is extracted.

  Returning to FIG. 5, the control unit 10 generates a luminance distribution histogram (see FIG. 7) indicating the number of pixels for each luminance based on the histogram generation region extracted in step S101 (step S102).

  FIG. 7 shows an example of creating a luminance distribution histogram. In this luminance distribution histogram, the horizontal axis represents luminance, and the vertical axis represents the number of pixels. Here, when image marker information is embedded in real image data, a peak appears on the high luminance side. Based on the number of pixels at the peak, the control unit 10 detects the image marker information and determines the type. Specifically, when the number of pixels at this peak is “1670 ± 40”, the control unit 10 determines that the image marker information “L” is embedded in the actual image data. Further, when the number of pixels at this peak is “2920 ± 40”, the control unit 10 determines that the image marker information “R” is embedded in the actual image data. The value (peak value) of the number of pixels can be obtained and changed by experience. Further, the width “± 40” of the number of pixels takes into account errors based on gradation processing and the like.

  Returning to FIG. 5, the control unit 10 detects the image marker information based on the luminance distribution histogram generated in step S102 (step S103). In addition, when the peak is not detected on the high luminance side of the luminance distribution histogram, the control unit 10 determines that there is no image marker information. This completes the image marker detection process.

  As described above, according to the present embodiment, the control unit 10 of the imaging apparatus 1 generates a luminance distribution histogram based on the medical image data acquired from the modality 3 via the communication unit 40. And the control part 10 detects the image marker information embedded in the real image data of medical image data based on this luminance distribution histogram. Therefore, the control part 10 can detect image marker information, without using a character recognition technique. Therefore, it is possible to improve the processing speed and accuracy of detecting image marker information embedded in a medical image.

Further, the control unit 10 detects the order marker information from the order information acquired from the RIS 2 via the communication unit 40. Then, the control unit 10 compares the order marker information and the image marker information to determine consistency. When the determination result is inconsistent, the control unit 10 causes the display unit 30 to display warning information. Therefore, the user can know the mismatch between the order marker information and the image marker information. In addition, since the marker information is detected from the order information, it is possible to accurately determine the consistency.
[Modification]

  Next, a modified example of the embodiment when the medical image display apparatus of the present invention is applied to the imaging apparatus 1 of FIG. 1 will be described. In this description, the description will be focused on differences from the above-described embodiment.

  In the embodiment described above, the control unit 10 of the imaging device 1 determines whether or not the order marker information detected from the order information matches the image marker information. However, in the modification of the embodiment, the control unit 10 determines whether or not the accompanying marker information detected from the accompanying information of the medical image data matches the image marker information. Here, the accompanying marker information is marker information detected from the accompanying information of the medical image data.

[Marker judgment processing]
A modification of specific processing contents of the marker determination processing performed by the control unit 10 of the image inspection device 1 will be described with reference to FIG.

  First, the control unit 10 receives medical image data from the modality 3 via the communication unit 40 (step S201).

  Next, the control unit 10 performs an image marker detection process (step S202). Specifically, the control unit 10 detects image marker information embedded in the actual image data of the medical image data received in step S201.

  Next, the control unit 10 refers to the conversion table 52 and detects incidental marker information from the incidental information of the medical image data received in step S201 (step S203). Specifically, the control unit 10 reads the conversion table 52 from the storage unit 50. The control unit 10 sets the “marker” value of the record having the value of the item “imaging site / direction / procedure” that matches the examination site information (imaging site / direction / procedure) included in the incidental information of the received medical image data. Is read. The control unit 10 uses this value as incidental marker information.

  When the image marker information is detected from the actual image data of the medical image data in the image marker detection process in step S202 (step S204; YES), the control unit 10 matches the image marker information with the accompanying marker information. It is determined whether or not (step S205). When the image marker information matches the accompanying marker information (step S205; YES), the control unit 10 ends the marker determination process. When the image marker information does not match the accompanying marker information (step S205; NO), the control unit 10 displays warning information indicating that fact on the display unit 30 (step S208). And the control part 10 complete | finishes a marker determination process.

  On the other hand, when the image marker information is not detected from the actual image data of the medical image data in the image marker detection process in step S202 (step S204; NO), the control unit 10 determines whether an image marker is necessary. Determination is made (step S206). Specifically, the control unit 10 determines that the image marker is not necessary when the incidental marker information detected in step S203 is an invalid value. In other cases, the control unit 10 determines that an image marker is necessary.

  When determining that the image marker is not necessary in step S206 (step S206; NO), the control unit 10 ends the marker determination process. On the other hand, when the control unit 10 determines that an image marker is necessary (step S206; YES), the control unit 10 displays warning information on the display unit 30 (step S207). And the control part 10 complete | finishes a marker determination process.

  As described above, according to the present modification, the control unit 10 of the imaging device 1 detects the accompanying marker information from the accompanying information of the medical image data. Then, the control unit 10 compares the incidental marker information and the image marker information to determine consistency. When the determination result is inconsistent, the control unit 10 causes the display unit 30 to display warning information. Therefore, the user can know the mismatch between the incidental marker information and the image marker information.

  The description in the present embodiment is an example of a medical image processing apparatus according to the present invention, and the present invention is not limited to this. The detailed configuration and detailed operation of the system and each device can be changed as appropriate.

  In this embodiment, an example in which a hard disk is used as a computer-readable medium storing a program is disclosed, but the present invention is not limited to this example. As other computer-readable media, a portable storage medium such as a CD-ROM, a non-volatile memory such as a flash memory, and the like can be applied. Also, a carrier wave can be applied as a medium for providing program data via a communication line.

1 Image detector 2 RIS
3 Modality 4 PACS
5 HIS
DESCRIPTION OF SYMBOLS 10 Control part 20 Operation part 30 Display part 40 Communication part 50 Storage part 52 Conversion table 60 Bus N1 Hospital network N2 Communication network S Radiology system

Claims (8)

Control means for detecting image marker information embedded in the actual image data of the medical image data based on the luminance information of the medical image data;
A medical image processing apparatus comprising: The control means generates a luminance distribution histogram based on the luminance information of the medical image data, and detects the image marker information based on the luminance distribution histogram;
The medical image processing apparatus according to claim 1. The control means detects the image marker information based on a peak value on the high luminance side in the luminance distribution histogram.
The medical image processing apparatus according to claim 2. A first acquisition means for acquiring order information relating to the medical image data;
The control unit detects marker information from the order information acquired by the first acquisition unit, compares the marker information with the image marker information, determines consistency, and if mismatched, displays warning information. Display on the display means,
The medical image processing apparatus according to any one of claims 1 to 3. The control means detects marker information from incidental information attached to the medical image data, compares the marker information with the image marker information, determines consistency, and displays warning information in the case of inconsistency. To display
The medical image processing apparatus according to any one of claims 1 to 3. The control means determines the consistency based on the presence or absence of detection of the image marker information;
The medical image processing apparatus according to claim 4 or 5. A second acquisition means for acquiring the medical image data;
The medical image processing apparatus according to any one of claims 1 to 6. Computer
Control means for detecting image marker information embedded in the actual image data of the medical image data based on the luminance information of the medical image data;
Program to function as.

Images