JP6688642B2 - Image processing apparatus and medical information management system - Google Patents

Description

  Embodiments of the present invention relate to an image processing apparatus and a medical information management system.

  In recent years, regional collaboration of medical information is progressing. In such a case, for example, medical images are shared between medical institutions that cooperate with each other.

  However, when different patient IDs are assigned to the same patient in each medical institution, identification of the patient becomes important.

  In order to identify a patient, there are mechanisms such as PIX (patient information mutual reference) and PDQ (inquiry of patient basic information). However, for example, there are cases in which accurate information cannot be obtained in cases where the patient is unaware and cases such as dementia.

  There is also a system called My Number. However, My Number can only be used for procedures other than social security and tax disaster measures stipulated by laws and regulations. Even if some kind of unified ID is used in the future, it cannot be used to identify data captured before the start of use.

  Further, there is a technique for identifying an individual based on a dental treatment history, fingerprints, voice prints, and the like. However, in some cases, additional information input may be required to identify the individual, and thus the annoyance may be unbearable.

JP, 2011-257854, A JP, 2004-126738, A

  The problem to be solved by the present invention is to provide an image processing apparatus and a medical information management system capable of identifying a patient.

The image processing apparatus according to the embodiment includes a calculation unit and a control unit. The calculation unit , based on the anatomical landmark for specifying the origin of the medical image , calculates the first origin that is the origin of the first medical image and the second medical image that is obtained from the predetermined database. The second origin, which is the origin, is specified, and each of the plurality of first anatomical landmarks extracted from the first medical image is extracted from the second medical image obtained from the predetermined database. Which of the plurality of second anatomical landmarks corresponds to which anatomical landmark is identified, and the first origin is used as a reference for each of the plurality of first anatomical landmarks. First relative coordinates, which are relative coordinates of the first anatomical landmark, and second relative coordinates, which are relative coordinates of the corresponding second anatomical landmark based on the second origin. Based on A first value, which is a value determined to decrease as the difference in distance between the first relative coordinate and the second relative coordinate increases, is set to the type of anatomical landmark or the object at the time of imaging. A second value is calculated by using a weight determined according to the body position of the sample and averaging the calculated first value for the plurality of first anatomical landmarks . The control unit causes the display unit to display the second value .

FIG. 1 is a configuration example of an image processing apparatus according to the first embodiment and a medical information management system in which the image processing apparatus is installed. FIG. 2 is a block diagram showing the arrangement of the image processing apparatus according to the first embodiment. FIG. 3 is a flowchart showing a procedure of processing performed by the image processing apparatus according to the first embodiment. FIG. 4 is a flowchart showing a procedure of processing performed by the image processing apparatus according to the first embodiment. FIG. 5 is a diagram illustrating processing performed by the image processing apparatus according to the first embodiment. FIG. 6 is a diagram illustrating a process performed by the image processing apparatus according to the first embodiment. FIG. 7 is a diagram illustrating processing performed by the image processing apparatus according to the first embodiment. FIG. 8 is a diagram illustrating processing performed by the image processing apparatus according to the first embodiment. FIG. 9 is a diagram illustrating processing performed by the image processing apparatus according to the first embodiment. FIG. 10 is a diagram illustrating processing performed by the image processing apparatus according to the first embodiment. FIG. 11 is a flowchart showing a procedure of processing performed by the image processing apparatus according to the first modification of the first embodiment. FIG. 12 is a diagram illustrating a process performed by the image processing device according to the first modification of the first embodiment. FIG. 13 is a diagram showing a hardware configuration of the image processing apparatus according to the embodiment.

  Hereinafter, an image processing apparatus and a medical information management system according to embodiments will be described in detail with reference to the accompanying drawings.

(First embodiment)
The overall configuration including the image processing apparatus according to the first embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to the first embodiment and an apparatus to which the image processing apparatus is connected. FIG. 2 is a block diagram showing the arrangement of the image processing apparatus according to the first embodiment.

  The image processing device 100 is connected to the modality device 200, the storage device 220, the patient information database 230, the image database 240, and the display device 250 via a network as necessary, and constitutes a medical information management system. Here, the configuration of the medical information management system may or may not include the modality device 200, the storage device 220, the patient information database 230, the image database 240, and the display device 250. Here, an example of the network is an in-hospital LAN (Local Area Network), for example. The Internet is another example of the network.

  The modality device 200 is a medical modality device, and performs an inspection by, for example, imaging a subject. Here, the modality is a generic term for, for example, medical devices and related devices and accessories. Examples of the modality apparatus 200 include, for example, an X-ray CT apparatus, a magnetic resonance imaging apparatus, a nuclear medicine diagnostic apparatus, a PET (Positron Emission Tomography) apparatus, and the like.

  The storage device 220 is a storage device that stores data, such as image data, acquired by the modality device 200 taking an image of a subject. The storage device 220 stores various data such as shooting conditions. The patient information database 230 is an information database that stores various data such as patient name, patient ID, date of birth, and appointment time. The image database 240 is an information database that stores various medical images in association with the patient name stored in the patient information database 230.

  Here, the range of patients stored in the patient information database 230 is not limited to, for example, patients who have visited a medical institution in which the modality device 200 is installed. It may be a patient who has visited the institution. Similarly, the range of the medical image stored in the image database 240 is not limited to the medical image of the patient who has visited the medical institution where the modality device 200 is installed, for example, any one of a plurality of medical institutions nationwide. It may be a medical image of a patient who has visited such a medical institution. Further, the patient information database 230 and the image database 240 may be installed, for example, in a medical institution where the modality device 200 is installed, or may be configured by a server outside the medical institution.

  The storage device 220, the patient information database 230, and the image database 240 are, for example, a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like.

  The display device 250 is a display device that displays various information such as image data under the control of the processing circuit 150 in the image processing device 100. The display device 250 is, for example, a display device such as a liquid crystal display.

  The image processing apparatus 100 is an apparatus that performs a predetermined process based on a medical image generated based on the imaging of the subject performed by the modality apparatus 200 and stored in the storage device 220 as necessary. The overall configuration of the image processing apparatus 100 is shown in FIG.

  The image processing apparatus 100 includes a processing circuit 150, a storage circuit 132, an input device 134, and a display device 135. The processing circuit 120 also has a search function 150a, an extraction function 150b, a calculation function 150c, a correction function 150d, and a control function 150e. Details of each of the search function 150a, the extraction function 150b, the calculation function 150c, the correction function 150d, and the control function 150e will be described later.

  In the first embodiment, each processing function performed by the search function 150a, the extraction function 150b, the calculation function 150c, the correction function 150d, and the control function 150e is stored in the storage circuit 132 in the form of a computer-executable program. ing. The processing circuit 150 is a processor that realizes a function corresponding to each program by reading the program from the storage circuit 132 and executing the program. In other words, the processing circuit 150 in a state where each program is read out has each function shown in the processing circuit 150 of FIG. In FIG. 2, the single processing circuit 150 has been described as realizing the processing functions of the search function 150a, the extraction function 150b, the calculation function 150c, the correction function 150d, and the control function 150e. The processing circuit 150 may be configured by combining a plurality of independent processors, and each processor may implement a function by executing a program.

  In other words, each function described above may be configured as a program, and one processing circuit may execute each program, or a specific function may be implemented in a dedicated independent program execution circuit. May be.

  The calculation function 150c and the correction function 150d included in the processing circuit 150 are an example of a calculation unit. The display device 135 or the display device 250 is an example of a display unit. The control function 150e included in the processing circuit 150 is an example of a control unit. The input device 134 is an example of an input unit. The extraction function 150b included in the processing circuit 150 is an example of an extraction unit.

  The word "processor" used in the above description is, for example, a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), or an application-specific integrated circuit (ASIC), a programmable logic device (for example, simple logic device). Programmable logic device (SPLD), complex programmable logic device (Complex Programmable Logic Device: CPLD), field programmable gate array (Field Programmable Gate Array: FPGA), and the like. Means. The processor realizes the function by reading and executing the program stored in the storage circuit 132. Instead of storing the program in the memory circuit 132, the program may be directly incorporated in the circuit of the processor. In this case, the processor realizes the function by reading and executing the program incorporated in the circuit.

  The storage circuit 132 stores data and the like associated with various processes performed by the image processing apparatus 100 as needed. For example, the storage circuit 132 is a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like. Further, the processing performed by the storage circuit 132 in the processing circuit 150 may be replaced by the storage device 220 outside the image processing apparatus 100.

  The input device 134 receives various instructions and information inputs from the operator. The input device 134 is, for example, a pointing device such as a mouse or a trackball, or an input device such as a keyboard.

  The display device 135 displays various information such as image data under the control of the control function 150e in the processing circuit 150. The display device 135 is, for example, a display device such as a liquid crystal display. The processing performed by the display device 135 in the processing circuit 150 may be replaced by the display device 250 outside the image processing device 100.

  Subsequently, processing performed by the image processing apparatus 100 according to the first embodiment will be described with reference to FIGS. 3 to 10. 3 and 4 are flowcharts showing the procedure of processing performed by the image processing apparatus according to the first embodiment. More specifically, FIG. 3 is a flowchart illustrating the flow of the entire processing. Further, FIG. 4 is a flowchart illustrating in detail the process of step S140 of FIG. In addition, FIGS. 5 to 10 are diagrams illustrating a procedure of processing performed by the image processing apparatus according to the first embodiment.

  In FIG. 3, the input device 134 included in the image processing apparatus 100 receives an input of information for identifying an individual (step S100). The process of step S100 will be described with reference to FIG.

  The input device 134 receives an input of information serving as a clue for identifying the subject relating to the first medical image as an individual. Here, the first medical image is a medical image related to a specific target subject, and is, for example, a medical image generated by imaging the subject using the modality device 200. The first medical image is, for example, a medical image when a patient with dementia visits a medical institution and the modality device 200 provided in the medical institution is used to image the patient with the dementia. Further, as another example, when the patient in an unconscious state is brought to a medical institution by an emergency, the first medical image may be displayed by using the modality device 200 provided in the medical institution. It is a medical image when a patient is photographed.

  In addition, the information serving as a clue to identify the individual is, for example, name, address, telephone number, insurance card number information, and the like. The information serving as a clue may be information that can identify the subject by itself, or may be information that is difficult to identify the subject only with the information. That is, these pieces of information may be incomplete information or fragmentary information.

  Here, as a first example of information in which it is difficult to identify a subject with information alone, for example, the name of Kana or the name of Roman alphabet can be cited. For example, if Kana's name is "Tokkyo Taro", it is not clear whether "Taro" represents "Taro" or "Taro", so it is not possible to completely identify the subject. There is also. Further, for example, the case where it is found that the Roman alphabet name is "TOKYO TARO" is the same. However, for example, if a person with dementia can hear information that his / her name is “Tokkyo Taro”, or if he / she is unconscious and the credit card name of his / her belonging is “TOKKYO TARO”. When it becomes clear, the input device 134 accepts the input of information including such incomplete information. As a result, the image processing apparatus 100 can improve the accuracy of identifying the subject as compared with the case where there is no information.

  In addition, as another example, even when only the family name is known, conversely only the name is known, or only the gender is known, the input device 134 does not perform such an incomplete operation. Accept input of information including information.

  FIG. 5 shows an example of the input screen for such information. The input device 134 displays the input field to the user, for example, with a message "Please enter patient information". The user who referred to the message inputs information, which is a clue for identifying the subject related to the first medical image as an individual, in the displayed input field by using, for example, a keyboard. The input device 134 receives input of such information. For example, the input device 134 receives an input indicating that the name of the subject is “Tokkyo Taro” and the gender of the subject is “male”. When the user completes the input of the necessary information, he / she clicks the button displaying "Search", for example. At this time, the input device 134 confirms the received input content.

  Next, the processing circuit 150 extracts a plurality of first anatomical landmarks from the first medical image (step S110). Here, as an example of the first anatomical landmark, there is, for example, information indicating a characteristic part of bone. Further, as an example of the first anatomical landmark, there is information indicating a predetermined part of a predetermined organ. In addition, examples of the first anatomical landmark include morphological information of a specific portion of the blood vessel, for example, blood vessel morphology information, and information indicating the stenosis status of the blood vessel.

  When the first medical image is a three-dimensional CT image, the processing circuit 150 uses the extraction function 150b to determine a predefined anatomical position such as the center of the left eyeball, the right apex of the lung, the aortic valve, etc. And extracting a plurality of first anatomical landmarks by using a geometric landmark extraction technique.

  Then, the processing circuit 150 uses the extraction function 150b to input a predetermined database to the predetermined database based on the information that the input device 134 has received in step S100 and serves as a clue for identifying the subject related to the first medical image as an individual. A second medical image is extracted from (patient information database 230 and image database 240) (step S120).

  Here, the predetermined database is, for example, a database that collects medical images collected over a plurality of medical institutions. An example of such a database is the patient information database 230 and the image database 240 shown in FIG. In such a database, for example, information such as the name of the subject and the medical image related to the imaging of the subject are stored in association with each other.

  The processing circuit 150 uses the extraction function 150b to extract the second medical image, which is a candidate medical image to be compared with the first medical image in the subsequent process, using the information input in step S100 as a key. Here, as the second medical image, for example, one medical image that best matches the information input in step S100 may be selected. Further, as the second medical image, for example, a predetermined number of medical images that match the information input in step S100 may be selected. Further, as the second medical image, for example, a medical image whose degree of coincidence a with the information input in step S100 exceeds a predetermined threshold may be selected.

  When there are a plurality of second medical images extracted in step S120, the processing from step S130 is performed for each extracted image, for example.

  Subsequently, the processing circuit 150 causes the extraction function 150b to extract a plurality of second anatomical landmarks from the second medical image obtained from the predetermined database in step S120 by a predetermined anatomical landmark extraction technique. The mark is extracted (step S130). Similar to the case of step S110, examples of the second anatomical landmark include, for example, information indicating a characteristic part of bone, information indicating a predetermined part of a predetermined organ, and a specific part of a blood vessel such as a blood vessel. Examples include morphological information and information indicating the stenosis status of blood vessels.

  Subsequently, the processing circuit 150 uses the calculation function 150c to extract the plurality of first anatomical landmarks extracted from the first medical image in step S110 and the second medical image obtained from the predetermined database. , The degree of similarity with the plurality of second anatomical landmarks extracted in step S130 is calculated (step S140).

  This step will be described in detail with reference to the flowchart of FIG. 4 and FIGS. FIG. 4 is a flowchart illustrating the process of step S140 of FIG. 3 in more detail.

  FIG. 6 illustrates an example of the plurality of first anatomical landmarks extracted from the first medical image and the plurality of second anatomical landmarks extracted from the second medical image.

  In FIG. 6, “target New” represents a landmark of a new patient, that is, a plurality of first anatomical landmarks extracted from the first medical image. On the other hand, the “target Old” represents the landmark of the existing image of the patient candidate, that is, the plurality of second anatomical landmarks extracted from the second medical image.

  Also, each row in FIG. 6 represents each anatomical landmark. For example, as an example of the plurality of first anatomical landmarks (or the plurality of second anatomical landmarks), for example, the upper end of the dentition (cervical vertebra II), the upper surface of the right eye, the upper surface of the left eye, the center of the right eye , The center of the left eyeball, and the anterior arch (nodule) of the first cervical spine (cervical spine I).

  Further, “z”, “x”, and “y” in each row of FIG. 6 represent the position of z coordinate, the position of x coordinate, and the position of y coordinate of each anatomical landmark. For example, the position of the z coordinate of the anatomical landmark “upper end of the tooth (cervical vertebra II)” extracted from the first medical image is 37, the position of the x coordinate is −8, and the position of the y coordinate is 18. . Further, for example, the z coordinate position of the anatomical landmark “anterior arch (nodule) of the first cervical vertebra (cervical spine I)” extracted from the second medical image is 14, the x coordinate position is −5, and the y coordinate is The position of is 2.

  The processing circuit 150 identifies which anatomical landmark of the plurality of second anatomical landmarks each of the plurality of first landmarks corresponds to (step S141). For example, in the example of FIG. 6, in the first medical image, the anatomical landmark whose z-coordinate position is 37, x-coordinate position is −8, and y-coordinate position is 18 is “upper end of tooth projection ( Cervical vertebra II) ". Further, in the second medical image, the anatomical landmark whose z coordinate position is 35, x coordinate position is −10, and y coordinate value is 19 is “upper end of dentition (cervical vertebra II)”. Is specified. Therefore, based on these pieces of information, the processing circuit 150 determines the anatomical landmark whose z coordinate position is 37, x coordinate position is -8, and y coordinate position is 18 in the first medical image. However, in the second medical image, it corresponds to an anatomical landmark whose z coordinate position is 35, z coordinate position is −10, and y coordinate value is 19. The processing circuit 150 performs the same processing for other anatomical landmarks.

  Subsequently, the processing circuit 150 uses the calculation function 150c to identify the origin in the medical image. Specifically, the processing circuit 150 uses the calculation function 150c to identify the first origin, which is the origin in the first medical image. Further, the processing circuit 150 uses the calculation function 150c to identify the second origin, which is the origin in the second medical image (step S142).

  Such an example is shown in FIG. In the example of FIG. 7, the processing circuit 150 uses the calculation function 150c to specify the anterior arch (nodule) of the first cervical spine (spine I) as the first origin that is the origin in the first medical image. In addition, the processing circuit 150 uses the calculation function 150c to identify the anterior arch (nodule) of the first cervical spine (spine I) as the second origin that is the origin in the second medical image.

  Here, the anatomical landmark specified as the origin by the processing circuit 150 is, for example, the landmark located at the uppermost position among the landmarks shared by the first medical image and the second medical image. is there.

  Subsequently, the processing circuit 150 uses the calculation function 150c to calculate the first relative coordinates that are the relative coordinates of the first anatomical landmark with respect to the first origin. In addition, the processing circuit 150 calculates the second relative coordinates that are the relative coordinates of the corresponding anatomical landmark with respect to the second origin (step S143).

  For example, in FIG. 7, the processing circuit 150 uses the calculation function 150c to determine the anterior arch (nodule) of the first origin “first cervical vertebra (cervical vertebra I)” for the anatomical landmark “upper end of dentition (cervical vertebra II)”. ) ”As a reference, the first relative coordinate is calculated as 37−15 = 22 for the z coordinate, −8−1 = −9 for the x coordinate, and 18−3 = 15 for the y coordinate. . In addition, the processing circuit 150 uses the calculation function 150c as a reference with respect to the anatomical landmark “upper end of dentition (cervical vertebra I)” based on the second origin “anterior arch (nodule) of the first cervical vertebra (cervical vertebra I)”. The second relative coordinate is calculated as 35-14 = 21 for the z coordinate, −10 − (− 5) = − 5 for the x coordinate, and 19−2 = 17 for the y coordinate.

Subsequently, the processing circuit 150 calculates the distance between the same anatomical landmarks by the calculation function 150c. Here, the distance between the same anatomical landmarks is, for example, the distance introduced by the Euclidean norm in the three-dimensional space. The embodiment is not limited to this, and the processing circuit 150 uses the calculation function 150c to calculate the distance between the same anatomical landmarks by using another type of distance, for example, the distance introduced by the L ₁ norm. You may.

  An example of the calculation of such a distance is shown in FIG. For example, in FIG. 8, the distance between the same anatomical landmarks with respect to the anatomical landmark "upper end of dentition (cervical vertebra II)" is sqrt ((22-21) ^ 2 + (-9- (-5)) ^ 2+ (15-17) ^ 2) = 4.58. Also, the distance between the same anatomical landmarks with respect to the anatomical landmark “upper surface of the right eye” is sqrt ((70−73) ^ 2 + (19−26) ^ 2 + (9−10) ^ 2) = 7.68.

  Subsequently, the processing circuit 150 uses the calculation function 150c to calculate, for each of the plurality of first anatomical landmarks, the degree of coincidence a with the corresponding anatomical landmark (step S144).

  Here, the degree of coincidence a is, for example, a value determined so as to decrease as the difference between the first relative coordinate and the second relative coordinate increases. The degree of coincidence a is determined to be 1 when the difference between the first relative coordinate and the second relative coordinate is 0, and the degree of coincidence a between the first relative coordinate and the second relative coordinate is determined. It is a value determined so as to be 0 in the limit where the absolute value of the difference is infinite.

  As a concrete expression of the degree of coincidence a, for example, a = 1 / (1 + x) is given, where x is the distance calculated in step S144. In other words, the degree of coincidence a is a value determined as a value obtained by adding 1 to the distance x between the first relative coordinate and the second relative coordinate and taking the reciprocal.

  That is, at this time, when the distance x is 0, the degree of coincidence a is 1. Also, as the distance x increases from 0, the degree of coincidence a decreases monotonically. Further, the degree of coincidence a becomes 0 in the limit where the distance x is infinite. Therefore, the degree of coincidence a is a real number greater than 0 and less than or equal to 1.

  FIG. 8 shows an example of the anatomical landmarks calculated in this way. For example, with respect to the anatomical landmark “upper end of dentition (cervical vertebra II)”, the distance x is 4.58, so the degree of coincidence a is a = 1 / (1 + 4.58) = 0.18. . Further, for the anatomical landmark “upper surface of the right eyeball”, the distance x is 7.68, and thus the degree of coincidence a is a = 1 / (1 + 7.68) = 0.12.

  Subsequently, the processing circuit 150 causes the calculation function 150c to determine whether the plurality of first anatomical landmarks and the plurality of second anatomical landmarks are present on the basis of the degree of coincidence calculated in step S145. Is calculated (step S146).

  As an example, the processing circuit 150 calculates the average of the degrees of coincidence of all landmarks, and calculates the calculated average value as the degree of similarity. For example, in the example of FIG. 8, the degree of coincidence of each anatomical landmark is 0.18 for the upper end of the dentition (cervical vertebra II), 0.12 for the upper surface of the right eye, and 0. 11, 0.14 for the center of the right eyeball, 0.12 for the center of the left eyeball, and 1.00 for the anterior arch (nodule) of the first cervical vertebra (cervical vertebra I), so the average degree of coincidence of all landmarks Is (0.18 + 0.12 + 0.11 + 0.14 + 0.12 + 1.00) /6=0.28. In this way, the operation of step S140 is completed.

  Returning to FIG. 3, the processing circuit 150 causes the control function 150e to display the information obtained based on the calculation result calculated in step S140 (that is, step S141 to step S146 in FIG. 4) in the display device 250 (or the display device). 135).

  An example of such a situation is shown in FIG. For example, the processing circuit 150 uses the control function 150e to display on the display device 250 the name of the medical institution where the second medical image was taken, the patient ID, the patient name, and the value of the degree of similarity (degree of coincidence) calculated in step S146. Are displayed in a list format.

  The example of FIG. 9 shows a case where the first medical image is a medical image associated with the patient name “Tokkyo Taro” and the patient ID “emergency0101”. At this time, the processing circuit 150 causes the display device 250 to display the data related to the second medical image, for example, in descending order of similarity (coincidence). For example, the data with the patient name “Patent Taro”, the patient ID “CBA2548”, and the medical institution name (facility) “Clinic” has a similarity (coincidence) of 0.65 and the highest similarity. Therefore, the processing circuit 150 displays it on the top. Next, for example, the data of the patient name is “Taro Tokkyo”, the patient ID is “ABC1563”, the medical institution name (facility) is “ΔΔ hospital”, and the similarity (coincidence) is 0.28. Since the degree is the second highest, the processing circuit 150 causes the second display. Then, the processing circuit 150 displays other data.

  Here, the processing circuit 150 may change and display the color depending on whether the value of the similarity is large or small. For example, the processing circuit 150 sets the threshold value of the similarity to 0.1 and displays the first and second data from the top, which exceeds the threshold of the similarity, in a color different from that of the third and fourth data from the top. By doing so, the data whose degree of similarity exceeds the threshold value may be visually highlighted.

  In addition, the processing circuit 150 uses the control function 150e to combine a plurality of pieces of information with the information obtained based on the calculation result calculated in step S140 (steps S141 to S146 of FIG. 4) or in place of the information. At least one of the information representing the first anatomical landmark and the information representing the plurality of second anatomical landmarks may be displayed on the display device 250 or the display device 135.

  At this time, an example of information indicating a plurality of first (or second) anatomical landmarks displayed by the processing circuit 150 on the display device 250 or the display device 135 is shown in FIG. 8, for example. The degree of coincidence for each landmark may be the same. Further, as another example of the information, for example, the distance for each landmark as shown in FIG. 8 may be used.

  Further, as another example, the processing circuit 150 may display a 3D image of a human body or a projection view (MIP: Maximum intensity projection, etc.) and an image showing the position of a landmark on the display device 250 or the display device 135. Good. This situation is shown in FIG.

  The diagram on the left end of FIG. 10 shows information related to the first medical image. That is, the processing circuit 150 displays the first medical image, which is a medical image of the patient ID: emergency0101 and the patient name: Tokkyotaro, on the symbol indicating the position of the landmark. At the left end of FIG. 10, each asterisk indicates an anatomical landmark in the first medical image.

  The central diagram and the rightmost diagram in FIG. 10 show information relating to the second medical information. That is, the processing circuit 150 uses the patient ID: ABC1563, the patient name: the second medical image that is the medical image of Taro Tokkyo, and the patient ID: CBA2548, the patient name: the second medical image that is the medical image of Taro Tokkyo. Are overlaid on the symbols indicating the positions of the anatomical landmarks. In the center and rightmost views of FIG. 10, each asterisk indicates an anatomical landmark in the second medical image. The processing circuit 150 also displays the degree of similarity (degree of coincidence). As a result, for example, the degree of similarity (coincidence) of the medical image relating to patient name: Taro Patent is 0.28, and the degree of similarity (concordance degree) of the medical image relating to patient name: Taro Patent is 0.65. Information to that effect is displayed.

  As shown in FIG. 10, the position of the anatomical landmark is displayed so as to be superimposed on the medical image. As a result, the degree of similarity between the first medical image and the second medical image is visually It is displayed clearly. As a result, the user can intuitively understand which patient is likely to be the same as the specific target patient.

  Further, the processing circuit 150 may display these pieces of information from the beginning, or may display these pieces of information when receiving an input to display these pieces of information from the user.

  The embodiment is not limited to the example described above.

  For example, the case where the image processing apparatus according to the first embodiment is used for the purpose of identifying an individual has been described, but the embodiment is not limited to this. For example, the image processing apparatus according to the first embodiment may be used for the purpose of preventing duplicate ID numbers for the same patient. In such a case, the processing circuit 150 uses the calculation function 150c to calculate the degree of possibility that the same subject is registered with a plurality of different identifiers (IDs). When the calculated possibility exceeds the predetermined threshold value, the processing circuit 150 determines that the same subject is likely to be registered with a plurality of different identifiers (IDs), and the subject information (name, etc.). Also, the plurality of different identifiers (ID) are displayed on the display device 250 (or the display device 135). As a result, the user can notice the possibility that the same subject is registered with a plurality of different identifiers (IDs).

  Further, for example, the image processing apparatus according to the first embodiment may be used for the purpose of preventing mistaking the patient. In such a case, the processing circuit 150 further calculates, by the calculation function 150c, the magnitude of the possibility that the patient is confused based on the similarity calculated in step 146. For example, if the similarity calculated in step S146 is lower than the predetermined threshold, the processing circuit 150 determines that there is a high possibility that a patient is confused. Subsequently, the processing circuit 150 causes the display device 250 (or the display device 135) to display information indicating the degree of possibility that the patient is confused by the control function 150e. Specifically, the processing circuit 150 displays a warning that there is a high possibility that a patient mix-up has occurred, and displays the ID of the patient who has a high mix-up possibility on the screen.

  Further, the processing circuit 150 may align the orientation of the first medical image and the orientation of the second medical image after specifying the position of the origin in step S142. Specifically, for example, the processing circuit 150 extracts at least two anatomical landmarks suitable for determining the orientation from the first medical image and the second medical image. The processing circuit 150 calculates the “direction” of the subject in the first medical image and the second medical image using the extracted at least two anatomical landmarks. The processing circuit 150 rotates the second medical image by a predetermined angle based on the calculated orientation of the subject, and aligns the orientations of the first medical image and the second medical image. After that, the processing circuit 150 executes the processing from step S144. As another example, the processing circuit 150 identifies the position of the origin in step S142, and then uses the data of DICOM (Digital Imaging and Communication in Medicine), for example, to determine the orientation of the first medical image and the second orientation. The directions of the medical images may be aligned.

Further, the method of calculating the degree of coincidence in step S145 is not limited to the example described in the embodiment. For example, the processing circuit 150 may give the degree of coincidence a as a function of the distance x in a functional system other than a = 1 / (1 + x). For example, the processing circuit 150 may give the degree of coincidence a as a function of the distance x in a functional system such as a = 1-tan ⁻¹ (x) / (π / 2). In such a case, when the distance x is 0, the degree of coincidence a is 1. Further, the degree of coincidence a decreases as the distance x increases. Also, since the distance x is an infinite limit and tan ⁻¹ (x) approaches π / 2, the degree of coincidence a becomes 0 at this time.

  Further, the functional system with the degree of coincidence a does not necessarily have to be a = 1 at the distance x = 0, and does not necessarily have to be a = 0 at the limit where the distance x is infinite. Further, the processing circuit 150 does not need to use the functional system that decreases as the distance x increases to calculate the similarity in the subsequent stage. For example, the processing circuit 150 may calculate the similarity by using the dissimilarity b = 1−a.

Further, the distance x is not necessarily limited to the distance in the Euclidean space. For example, the distance x may be a distance derived from the L _p norm, where p is a real number.

The examples of the degree of coincidence a are not limited to these. For example, when the distance x is smaller than the first threshold value x ₁ , the processing circuit 150 sets the value of the matching degree a to “high matching degree”, and the distance x is equal to or larger than the first threshold value x ₁ . If less than the first threshold value x ₁ is greater than the second threshold value x ₂ is "during matching degree", the distance x is a second threshold x ₂ or more, if greater than the second threshold value x ₂ May be determined to be “low degree of coincidence”.

  Further, although the case where the processing circuit 150 calculates the value of the degree of similarity as the average value of the degrees of coincidence of the anatomical landmarks has been described, the embodiment is not limited to this. The processing circuit 150 may calculate the degree of similarity by using a simple sum, a maximum value, a median, a mode, a weighted addition sum, or the like of the matching degrees of the anatomical landmarks. In addition, the processing circuit 150 does not need to use the data of all the anatomical landmarks, but may calculate the similarity using a part of the data of each anatomical landmark. .

  As described above, the image processing apparatus according to the first embodiment can identify a patient. As a result, the patient can be identified even when there is no accurate information such as a case where the patient does not have consciousness as in the case of emergency transportation or a case of dementia. In addition, since the patient can be specified using the medical image data itself used for diagnosis, no additional processing for specifying the patient is required, and the convenience for the user can be improved.

(First Modification of First Embodiment)
In the first embodiment, the processing circuit 150 does not consider the type of each landmark, for example, bone, organ, or blood vessel, in the calculation of the degree of coincidence a, and considers only the distance x and determines a predetermined functional system. The case of using is explained. In the first modification of the first embodiment, the processing circuit 150 calculates the degree of coincidence and the degree of similarity in consideration of the landmark type and the like.

  Processing according to the first modification of the first embodiment will be described with reference to FIGS. 11 and 12. FIG. 11 is a flowchart showing a procedure of processing performed by the image processing apparatus according to the first modification of the first embodiment. In addition, FIG. 12 is a diagram illustrating a process performed by the image processing apparatus according to the first modification of the first embodiment.

  In the first modification of the first embodiment, the overall processing flow shown in FIG. 3 is the same as in the first embodiment. In the first modified example of the first embodiment, the step corresponding to step S140 in FIG. 3 is different from that of the first embodiment. FIG. 11 shows a step corresponding to step S140 in the first modification of the first embodiment. Here, in FIG. 11, since the processes of steps S141 to S144 are the same as those of the first embodiment, detailed description thereof will be omitted.

  In the first modification of the first embodiment, in steps S145a to S146, the processing circuit 150 uses the calculation function 150c to determine the type of the first anatomical landmark and the second anatomical landmark. The degree of coincidence in step S145 is calculated based on the type and the degree of similarity is calculated based on the calculated degree of coincidence. Hereinafter, these processes will be described.

In step S145a, the processing circuit 150 calculates a weight for each anatomical landmark. In the first modification of the first embodiment, the processing circuit 150 uses the calculation function 150c to calculate the weight value w ₁ (p) corresponding to the anatomical landmark type p for each anatomical landmark. Is calculated by, for example, obtaining it from a predetermined database (for example, the storage circuit 132) (step S145a).

  Here, the anatomical landmark type p is the anatomical landmark type. For example, “organ”, “bone”, “blood vessel”, and “cartilage” belong to different anatomical landmark types p.

FIG. 12 shows an example of the anatomical landmark type p and the value of the weight w ₁ (p) corresponding to the anatomical landmark type p. For example, in the case of a chest landmark, the type p of the anatomical landmark “tracheal bifurcation” belongs to “organ”, and the weight w ₁ (p = organ) in that case is “0.2”. Further, the type p of the anatomical landmark “lower shoulder blade angle” corresponds to “bone”, and the weight w ₁ (p = bone) in that case is “1”. The type p of the anatomical landmark “left subclavian artery start point” belongs to “blood vessel”, and the weight w ₁ (p = blood vessel) in that case is “0.2”.

The weight w ₁ (p) corresponding to the type p of the anatomical landmark is an amount corresponding to the reliability of identifying an individual using data regarding the type. For example, if the type p of the anatomical landmark is a blood vessel or an organ, the position of the blood vessel or the organ is considered to change depending on the body position (standing position, supine position, prone position, etc.). Is less reliable. Also, in the case of blood vessels and organs, the position of blood vessels and organs may change due to the medical condition or treatment, such as thinning due to radiation therapy or conversely becoming fat due to side effects of the drug, etc. Is less reliable to use for. Therefore, the weight w ₁ (p) becomes low. On the other hand, when the type p of the anatomical landmark is bone, the bone position is considered to be relatively unlikely to change, so that the bone position is highly reliable to be used for individual identification. Therefore, the weight w ₁ (p) becomes high.

Subsequently, the processing circuit 150 calculates the degree of coincidence a in consideration of the weight w ₁ (p) for each anatomical landmark (step S145b). For example, if the type of the first anatomical landmark and the second anatomical landmark is p and the weight of the anatomical landmark of the type p is w ₁ (p), the distance is x and the processing circuit is The 150 calculates the (weighted) degree of coincidence a, for example, by the following formula: a = w ₁ (p) / (1 + x).

In other words, the degree of coincidence a is obtained by adding 1 to the distance x, taking the reciprocal of the same, and determining the type p of the anatomical landmark (or the first imaging state and the second imaging state in which the first medical image described later is imaged). It is a value determined as a value obtained by multiplying by a coefficient w ₁ that represents a weight determined based on the second image capturing state in which the medical image was captured. Here, the distance x is the first relative coordinate of the predetermined anatomical landmark of the first medical image with respect to the first origin, and the anatomical landmark corresponding to the predetermined anatomical landmark. , The distance between the second origin and the second medical image.

  Subsequently, the processing circuit 150 causes the calculation function 150c to distinguish between the plurality of first anatomical landmarks and the plurality of second anatomical landmarks based on the weighted coincidence degree calculated in step S145b. Calculate the similarity between them. For example, the processing circuit 150 calculates a similarity by taking a simple average of the weighted coincidences calculated in step S145b.

  As described above, in the first modification of the first embodiment, the image processing apparatus 100 changes the weight when calculating the degree of similarity according to the type of anatomical landmark. By performing such processing, as a result, the weight of highly reliable data for individual identification can be increased, and the identification accuracy can be improved.

(Second Modification of First Embodiment)
In the first modified example of the first embodiment, the case where the processing circuit 150 calculates the similarity according to the weight w ₁ (p) corresponding to the type p of each anatomical landmark has been described.

  In the second modified example of the first embodiment, the processing circuit 150 sets the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured. Based on, the similarity is calculated.

  Such processing will be described with reference to FIG. 4 again. In the second modification of the first embodiment, for example, the processing circuit 150 uses the correction function 150d to perform the processes of steps S142 to S146 of FIG. 4 and then based on the imaging state in which the medical image is captured. Then, the similarity calculated in step S146 is corrected to calculate the similarity. The second modified example of the first embodiment has the same processing as that of the first embodiment except for this additional step, and thus repeated description will be omitted.

  In the second modification of the first embodiment, the processing circuit 150 changes the weight depending on the shooting state. Here, the shooting state represents, for example, a body position such as supine / prone. In this case, the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are the posture of the subject at the time of imaging.

  For example, an image taken in a supine state and an image taken in a prone state differ in accuracy when individual identification is performed using anatomical landmarks. That is, the processing circuit 150 uses the correction function 150d to correct the similarity using different weights for the image captured in the supine state and the image captured in the prone state.

  For example, the processing circuit 150, when the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are both “back to back”, or both In the case of "prone", a value obtained by multiplying the similarity calculated in step S146 by "1.0" is set as the final similarity as a correction coefficient. That is, the processing circuit 150 uses the maximum weight when the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are the same imaging state. And the degree of similarity is calculated.

  On the other hand, in the first imaging state in which the first medical image is captured and in the second imaging state in which the second medical image is captured, one is "supine" and the other is "prone". In this case, since the body positions are different, it is considered that the accuracy of individual identification decreases. Therefore, in this case, the processing circuit 150 sets the value obtained by multiplying the similarity calculated in step S146 by, for example, “0.8” as the final similarity as the correction coefficient. When the weighting according to the type of anatomical landmark is performed as in the first modification of the first embodiment, the weighting according to the type according to the type of anatomical landmark is performed. The weighting according to the shooting state is repeated.

  In addition, the processing circuit 150 can obtain the information of these body positions from data of DICOM (Digital imaging and Communication in Medicine) at any time, for example.

  In addition, as another example of the photographing state, there is information indicating whether or not there is a breath-hold in photographing. In this case, the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are information indicating whether or not breath-holding is performed.

  For example, the image taken during breath-holding and the image taken during periods other than breath-holding differ in the accuracy with which an anatomical landmark is used to identify an individual. For example, when holding a breath, the position of the anatomical landmark hardly changes because there is no blurring of the position due to breathing. On the other hand, when the image is taken at a time other than when the user holds his / her breath, the position of the anatomical landmark changes because of the blurring of the position due to breathing. The processing circuit 150 uses the correction function 150d to correct the similarity using different weights for the image captured during breath-holding and the image captured during periods other than breath-holding.

  For example, the processing circuit 150 uses the correction function 150d to indicate that the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are both "hold breath. In the case of “”, a value obtained by multiplying the similarity calculated in step S146 by “1.0” is set as the final similarity. That is, the processing circuit 150 uses the maximum weight when the first imaging state in which the first medical image is captured and the second imaging state in which the second medical image is captured are the same imaging state. And the degree of similarity is calculated.

  On the other hand, when both the first shooting state in which the first medical image is shot and the second shooting state in which the second medical image is shot are “no breath hold”, there is no breath hold. , It is thought that the accuracy of individual identification will decrease. Therefore, in this case, the processing circuit 150 uses the correction function 150d as a correction coefficient, and determines the value obtained by multiplying the similarity calculated in step S146 by, for example, “0.8” as the final similarity. The weights according to the types of anatomical landmarks and the weights regarding the body position at the time of imaging may be weighted in an overlapping manner.

  As described above, in the second modified example of the first embodiment, weighting is performed according to the imaging state in which the medical image was captured, and the degree of similarity is calculated. Since the accuracy of individual identification generally differs depending on the shooting state, the image processing apparatus according to the embodiment can improve the accuracy of individual identification by performing weighting according to the shooting state.

  Further, the image processing apparatus 100 according to the above embodiments may be provided as a part of the medical information management system. In addition to the image processing apparatus 100, the medical information management system includes, for example, a storage device that stores a first medical image generated based on an inspection performed by the medical inspection apparatus, and medical images of a plurality of subjects. And a database for storing. Here, the storage device 220 is an example of such a storage device. The patient information database 230 and the image database 240 are examples of such databases.

  Further, the image processing apparatus 100 according to the embodiment may be provided as a function of a PACS (Picture Archiving and Communication System) or a RIS (Radiology Information System). The image processing apparatus 100 according to the embodiment may be provided as one function of the image processing workstation or the modality apparatus 200. In this case, typically, the patient information database 230 and the image database 240 can search by integrating information other than the medical institution in which the image processing apparatus 100 is provided.

(program)
The instructions shown in the processing procedures shown in the above-described embodiments can be executed based on a program that is software. A general-purpose computer system may store the program in advance and read the program to obtain the same effect as that of the image processing apparatus 100 according to the above-described embodiment. The instructions described in the above embodiments are magnetic disks (flexible disks, hard disks, etc.), optical disks (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD) as programs that can be executed by a computer. ± R, DVD ± RW, etc.), a semiconductor memory, or a recording medium similar thereto. The storage format may be any form as long as it is a storage medium readable by a computer or an embedded system. If the computer reads the program from this recording medium and causes the CPU to execute the instructions described in the program based on this program, the same operation as that of the image processing apparatus 100 of the above-described embodiment can be realized. . Of course, when the computer acquires or reads the program, it may be acquired or read via a network.

  In addition, the OS (operating system) running on the computer based on the instructions of the program installed in the computer or the embedded system from the storage medium, the database management software, the MW (middleware) such as the network, and the like are the embodiments described above. You may perform a part of each process for implement | achieving.

  Further, the storage medium is not limited to a medium independent of a computer or an embedded system, but includes a storage medium in which a program transmitted via a LAN (Local Area Network), the Internet, etc. is downloaded and stored or temporarily stored.

  Further, the number of storage media is not limited to one, and when the processing in the above-described embodiment is executed from a plurality of media, it is included in the storage media in the embodiment, and the configuration of the medium may be any configuration. .

  The image processing apparatus according to the embodiment is for executing each processing according to the above-described embodiments based on a program stored in a storage medium. The image processing apparatus includes one device such as a personal computer and a microcomputer, and a plurality of devices. It may have any configuration such as a system in which the devices are network-connected.

  In addition, the computer in the embodiment is not limited to a personal computer, but includes an arithmetic processing unit, a microcomputer, and the like included in information processing equipment, and is a generic term for equipment and devices that can realize the functions in the embodiment by a program. .

  FIG. 13 is a diagram showing a hardware configuration of the image processing apparatus 100 according to the embodiment. The signal processing device (image processing device) according to the above-described embodiment includes a control device such as a CPU (Central Processing Unit) 310 and a storage device such as a ROM (Read Only Memory) 320 or a RAM (Random Access Memory) 330. A communication interface 340 that connects to a network for communication and a bus 301 that connects each unit are provided.

  The program executed by the image processing apparatus according to the above-described embodiment is provided by being incorporated in the ROM 320 or the like in advance. In addition, the program executed by the image processing apparatus according to the above-described embodiment may cause a computer to function as each unit of the above-described image processing apparatus. In this computer, the CPU 310 can read the program from the computer-readable storage medium onto the main storage device and execute the program.

  As described above, according to at least one embodiment, it is possible to identify a patient.

  Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the invention described in the claims and the equivalents thereof as well as included in the scope and the gist of the invention.

150 Processing Circuit 150a Search Function 150b Extraction Function 150c Calculation Function 150d Correction Function 150e Control Function

Claims (17)

Based on the anatomical landmark for identifying the origin of the medical image, the first origin that is the origin in the first medical image and the origin that is the origin in the second medical image obtained from the predetermined database. 2 origins, and each of the plurality of first anatomical landmarks extracted from the first medical image is extracted from the second medical image obtained from the predetermined database. Of the anatomical landmarks corresponding to the first anatomical landmarks, the anatomical landmarks corresponding to the anatomical landmarks are identified, and the first anatomy is based on the first origin for each of the first anatomical landmarks. Based on a first relative coordinate which is a relative coordinate of the geometrical landmark and a second relative coordinate which is a relative coordinate of the corresponding second anatomical landmark based on the second origin. , The first The first value, which is a value determined to be smaller as the difference in distance between the relative coordinates and the second relative coordinates increases, is set as the type of anatomical landmark or the body position of the subject at the time of imaging. A calculation unit that calculates a second value by averaging the calculated first value with respect to the plurality of first anatomical landmarks, using a weight determined according to
An image processing apparatus comprising: a control unit that causes the display unit to display the second value . The calculation unit calculates the second value based on a first imaging state in which the first medical image is captured and a second imaging state in which the second medical image is captured. The image processing apparatus according to claim 1.   The image processing apparatus according to claim 2, wherein the first imaging state and the second imaging state are body positions of the subject at the time of imaging.   The image processing apparatus according to claim 2, wherein the first shooting state and the second shooting state are information indicating presence / absence of breath holding. The image processing according to claim 1, wherein the calculation unit calculates the second value based on a type of the first anatomical landmark and a type of the second anatomical landmark. apparatus. The first value is set to be 1 when the difference in distance between the first relative coordinate and the second relative coordinate is 0, and the first relative coordinate and the first relative coordinate The image processing device according to claim 1 , wherein the absolute value of the difference from the relative coordinate of 2 is a value determined to be 0 in the limit of infinity. The first value, the first relative coordinate plus 1 to the distance between the second relative coordinate is a value determined as a value obtained by taking the inverse image of claim 1 Processing equipment. The first value, adds 1 to the distance between said first relative coordinate second relative coordinate, take the reciprocal is the determined value as a value obtained by multiplying the coefficient representing the weight The image processing apparatus according to claim 1 . The first anatomical landmark and the second anatomical landmark is information indicating the characteristic part of the bone, the image processing apparatus according to any one of claims 1-8. The first anatomical landmark and the second anatomical landmark is information including at least one of information representing the shape information and the narrowing conditions of the vessel of the vessel, according to claim 1-9 The image processing device according to any one of claims. An input unit for receiving input of information on the name, address, telephone number, or insurance card number of the subject relating to the first medical image;
Further comprising an extraction unit that extracts the second medical image from the predetermined database based on the input of the information ,
The calculating unit, said extraction unit is extracted based on the second medical image, it calculates the second value, the image processing apparatus according to any one of claims 1-10. The image processing apparatus according to claim 11 , wherein the information is incomplete or fragmentary personal information . The predetermined database is a database that collects medical images acquired over a plurality of medical institutions, the image processing apparatus according to any one of claims 1 to 12. The calculating unit, when the second value exceeds the threshold value, it is determined that the same subject is likely to have been registered in a plurality of different identifiers, according to any one of claims 1 to 13 Image processing device. When the second value is less than the threshold value , the calculation unit determines that there is a high possibility that a patient mix-up has occurred ,
Wherein the control unit, the information indicating high the possibility, to be displayed on the display unit, the image processing apparatus according to any one of claims 1 to 13. The control unit, in combination with the second value or in place of the second value , information indicating the plurality of first anatomical landmarks and the plurality of second anatomical landmarks. at least one of information representing, to be displayed on the display unit, the image processing apparatus according to any one of claims 1 to 15. A storage device that stores a first medical image generated based on an examination performed by the medical examination device;
A database for storing medical images of a plurality of subjects,
A first origin, which is the origin in the first medical image, and a second origin, which is the origin in the second medical image obtained from the database, based on the anatomical landmarks for identifying the origin of the medical image. And a plurality of second anatomical landmarks extracted from the first medical image, the plurality of first anatomical landmarks extracted from the second medical image obtained from the database , respectively . The anatomical landmarks corresponding to the anatomical landmarks are identified, and the first anatomy based on the first origin is specified for each of the plurality of first anatomical landmarks. Based on a first relative coordinate that is a relative coordinate of the dynamic landmark and a second relative coordinate that is a relative coordinate of the corresponding second anatomical landmark based on the second origin. The first The first value, which is a value determined to be smaller as the difference in distance between the relative coordinates and the second relative coordinates increases, is set as the type of anatomical landmark or the body position of the subject at the time of imaging. A calculation unit that calculates a second value by averaging the calculated first value with respect to the plurality of first anatomical landmarks, using a weight determined according to
A medical information management system, comprising: a control unit that causes the display unit to display the second value .

Images