JP5556674B2 - Medical image display apparatus and program - Google Patents

Description

  The present invention relates to a medical image display device and a program.

  In recent years, with an increase in the incidence of breast cancer in women, interest in breast cancer screening has increased. In breast cancer screening, a doctor interprets a medical image obtained by photographing a breast to diagnose the presence or absence of an abnormality. However, the number of interpretation doctors who perform diagnosis is insufficient, and there is a problem that diagnosis is delayed.

  In order to improve such problems, for the purpose of assisting diagnosis work, an abnormal shadow candidate detecting device (CAD (Computer-) that automatically detects an abnormal shadow candidate that is a region showing a feature of a lesion such as breast cancer from a medical image. Aided Detection)) has been developed.

  In general, a mark is displayed at the position of an abnormal shadow candidate detected by CAD. Further, for example, Patent Document 1 describes a technique for displaying a mark by changing the type according to the degree of malignancy certainty.

JP 2004-135868 A

  By the way, a mark for pointing out an abnormal shadow candidate detected by CAD is effective in preventing oversight of an abnormal shadow candidate by an interpreting doctor, but not all marks are effective for all interpreting doctors. A useful mark that is effective for an interpreting doctor is considered to indicate an abnormal shadow candidate that the interpreting doctor tends to overlook. In addition, for example, shadows close to the head of the breast region tend to be overlooked, those with low contrast with the surroundings tend to be overlooked, etc. Conceivable.

  However, in the conventional technology, since the mark is displayed uniformly regardless of the tendency of the interpreting doctor, the feeling that the interpreting doctor refers to the mark is diffused, and the effect of preventing oversight may not be exhibited.

  An object of the present invention is to further prevent oversight of abnormal shadow candidates by an interpretation doctor.

In order to solve the above-mentioned problem, the invention described in claim 1
The medical image and the position information of the abnormal shadow candidate are acquired from a storage device that stores the medical image and the position information of the abnormal shadow candidate detected from the medical image in the abnormal shadow candidate detection apparatus in association with each other, and the acquisition A medical image display device that marks abnormal shadow candidates on the medical image based on the positional information of the abnormal shadow candidates and displays the marks on the display means,
Operation means for designating a mark that the interpretation doctor has determined to be effective for diagnosis from among the marks displayed on the medical image in the display means;
The feature amount of the abnormal shadow candidate corresponding to the mark designated by the operation means is calculated, and the calculated feature amount is stored in the storage device as effective candidate feature information in association with the identification information of the interpretation doctor. A feature amount calculating means for causing
When a new medical image is acquired from the storage device and displayed on the display unit, the feature amount of each abnormal shadow candidate detected from the new medical image is calculated, and interpretation is performed from the storage device. The effective candidate feature information stored in association with the identification information of the interpretation doctor is acquired, and detected from the new medical image based on the feature amount represented by the effective candidate feature information and the calculated feature amount. Screening means for selecting abnormal shadow candidates that are estimated to be effective for diagnosis by the interpretation doctor from among abnormal shadow candidates;
When displaying a mark on the new medical image and the abnormal shadow candidate detected from the new medical image on the display means, the abnormal shadow candidate selected by the selecting means is different from other abnormal shadow candidates. Display control means for highlighting with a mark of an aspect;
Is provided.

The invention according to claim 2 is the invention according to claim 1,
The feature amount calculating means calculates a plurality of types of feature amounts,
The selecting means plots points representing the feature quantities of the valid candidate feature information on a coordinate space with a plurality of types of feature quantities included in the valid candidate feature information as axes, and is detected from the new medical image. Calculating the plurality of types of feature values for the abnormal shadow candidates, plotting points representing the calculated feature values of the abnormal shadow candidates in the coordinate space, and calculating the feature values of the abnormal shadow candidates in the coordinate space. An abnormal shadow candidate that is estimated to be effective for diagnosis by the interpreting doctor when the distance between the point to represent and the point representing the feature amount of the effective candidate feature information is within a predetermined distance Sort as

The invention according to claim 3 is the invention according to claim 1 or 2,
When there are a plurality of the new medical images, the display control unit gives priority to the display unit the medical image in which there is an abnormal shadow candidate estimated to be effective for the interpretation by the screening doctor. Display.

The program of the invention according to claim 4 is:
The medical image and the position information of the abnormal shadow candidate are acquired from a storage device that stores the medical image and the position information of the abnormal shadow candidate detected from the medical image in the abnormal shadow candidate detection apparatus in association with each other, and the acquisition A computer used for a medical image display device for marking the abnormal shadow candidate on the medical image based on the positional information of the abnormal shadow candidate and displaying the mark on the display means,
An operation means for designating a mark that the interpretation doctor has determined to be effective for diagnosis from the marks displayed on the medical image in the display means;
The feature amount of the abnormal shadow candidate corresponding to the mark designated by the operation means is calculated, and the calculated feature amount is stored in the storage device as effective candidate feature information in association with the identification information of the interpretation doctor. Feature amount calculation means
When a new medical image is acquired from the storage device and displayed on the display unit, the feature amount of each abnormal shadow candidate detected from the new medical image is calculated, and interpretation is performed from the storage device. The effective candidate feature information stored in association with the identification information of the interpretation doctor is acquired, and detected from the new medical image based on the feature amount represented by the effective candidate feature information and the calculated feature amount. A selection means for selecting an abnormal shadow candidate that is estimated to be effective for diagnosis by the interpretation doctor from among abnormal shadow candidates;
When displaying a mark on the new medical image and the abnormal shadow candidate detected from the new medical image on the display means, the abnormal shadow candidate selected by the selecting means is different from other abnormal shadow candidates. Display control means for highlighting with a mark of an aspect,
To function as.

  According to the present invention, it is possible to more firmly prevent oversight of abnormal shadow candidates by an interpreting doctor.

It is a figure which shows the example of whole structure of the medical image display system in this Embodiment. It is a figure showing an example of data storage of effective candidate feature DB. It is a block diagram which shows the functional structure of the image display apparatus of FIG. It is a flowchart which shows the medical image display process performed by the control part of FIG. It is a figure which shows an example of the feature-value space which plotted the point showing the feature-value of an abnormal shadow candidate, and the point showing the feature-value of an effective candidate. It is a figure which shows the example of a display of an abnormal shadow candidate. It is a figure which shows designation | designated of the effective candidate by an interpretation doctor.

(Configuration of Medical Image Display System 100)
First, the configuration of the embodiment of the present invention will be described.
FIG. 1 shows a system configuration of a medical image display system 100 in the present embodiment.
The medical image display system 100 is a system that captures a medical image, detects an abnormal shadow candidate from the medical image, and provides detection result information to the interpretation doctor together with the medical image.

  As shown in FIG. 1, the medical image display system 100 includes an image generation device 1, an abnormal shadow candidate detection device 2, an image server 3, and an image display device 4. These devices 1 to 4 are connected to each other through a communication network N constructed in a medical institution such as a LAN (Local Area Network) so that data can be transmitted and received between them. The DICOM (Digital Imaging and Communication in Medicine) standard is applied to the communication network N. The number of each device is not particularly limited.

Hereinafter, each component apparatus 1-4 is demonstrated.
The image generation apparatus 1 captures a human body and generates digital data of the captured image (medical image). For example, CR (Computed Radiography), FPD (Flat Panel Detector), CT (Computed Tomography), MRI (MRI) Modality such as Magnetic Resonance Imaging), US (ultrasonography), cassette-dedicated reader, film digitizer, etc. can be applied. In the present embodiment, it is assumed that breast image data is generated by applying a breast-specific CR that performs X-ray imaging of the left and right breasts as the image generation apparatus 1.

  The image generation apparatus 1 is an apparatus that complies with the above-mentioned DICOM standard, and can input various information attached to the generated medical image, for example, patient information and examination information from the outside, and can also automatically generate the information. it can. The patient information includes information such as patient identification information (for example, patient ID) for identifying the patient, patient name, sex, date of birth, and the like. The inspection information includes inspection identification information (for example, inspection ID), inspection date and time, inspection conditions (inspection site, laterality (left, right), direction (for example, vertical direction (CC), oblique direction) (MLO)), modality type, etc. The image generating apparatus 1 adds the above patient information, examination information, UID (Unique ID) for identifying the image as header information to the generated medical image. To the abnormal shadow candidate detection device 2 and the image server 3 via the communication network N. If the DICOM standard is not complied with, the accompanying information is transmitted to the image generation device 1 using a DICOM conversion device (not shown). It is also possible to make it input.

  The abnormal shadow candidate detection device (CAD) 2 is a computer that performs image analysis of a medical image supplied from the image generation device 1 and performs detection processing of an abnormal shadow candidate. The abnormal shadow candidate detection device 2 includes a storage unit such as a CPU (Central Processing Unit), a RAM (Random Access Memory), and an HDD (Hard Disk Drive), and a communication unit such as a LAN card. The storage unit of the abnormal shadow candidate detection device 2 stores a detection algorithm detection algorithm corresponding to the type of abnormal shadow, and the CPU of the abnormal shadow candidate detection device 2 stores the detection program stored in the storage unit. An abnormal shadow candidate detection process is executed in cooperation with each other, and an abnormal shadow candidate is detected from each medical image input via the communication unit. For example, an abnormal shadow candidate of a tumor or a microcalcification cluster in a breast image is detected.

  As an abnormal shadow candidate detection algorithm, a known algorithm can be applied. For example, as an algorithm for a tumor shadow candidate in a breast image, a method using an iris filter disclosed in Japanese Patent Laid-Open No. 10-91758, a method using a Laplacian filter (Journal of the Institute of Electronics, Information and Communication Engineers (D-II) , Vol. J76-D-II, no. 2, pp. 241-249, 1993), etc. are applicable. In addition, as a detection algorithm for micro-calcification cluster shadow candidates, for example, Morphology filter (The Institute of Electronics, Information and Communication Engineers (D-II), Vol.J71-D-II, no.7, pp.1170-1176, 1992), Laplacian filter (The Institute of Electrical, Information and Communication Engineers Journal (D-II), Vol. J71-D-II, no. 10, pp. 1994-2001, 1998) Applicable.

  When the detection of the abnormal shadow candidate ends, the CPU of the abnormal shadow candidate detection apparatus 2 generates detection result information (hereinafter referred to as CAD information) of the abnormal shadow candidate. The CAD information includes, for example, position information of each detected area (contour) of abnormal shadow candidates and information on the types of abnormal shadow candidates (for example, tumors, microcalcification clusters, etc.). Then, the abnormal shadow candidate detection device 2 adds the header information (at least UID) of the detection source medical image to the generated CAD information, and transmits it to the image server 3 by the communication unit.

  The image server 3 is a computer including a storage unit such as a CPU, a RAM, and an HDD, and a communication unit such as a LAN card. The storage unit of the image server 3 includes an image DB (Data Base) 351, an effective candidate feature DB 352, and the like. The image server 3 stores CAD information about the medical image received from the abnormal shadow candidate detection device 2 in association with the medical image received from the image generation device 1 and manages input / output thereof.

The image DB 351 is a database for storing medical images. For example, the image DB 351 has an image management table that stores management information regarding each medical image stored in the image DB 351. In the image management table, management information for each medical image is stored as one record. The management information includes UID, patient information, examination information, and file information (file name of medical image, file name of CAD information corresponding to this, file storage location, update date, file size, etc.).
In the image server 3, when a medical image is received from the image generation device 1, the received medical image is stored in the image DB 351, and management information is created based on the received medical image header information. Stored in the image management table. When the CAD information from the abnormal shadow candidate detection device 2 is received, the received CAD information is stored in the image DB 351, and a record in which the CAD information and the UID match is searched from the image management table. The file name, storage location, etc. of the CAD information are additionally written in each record. In this way, in the image DB 351, the medical image and the detection result information of the abnormal shadow candidate detected from the medical image are stored in association with each other so as to be searchable.

  The valid candidate feature DB 352 is a database that stores valid candidate feature information transmitted from the image display device 4 for each interpretation doctor. The effective candidate feature information is information indicating the feature amount of an abnormal shadow candidate pointed out by a mark (referred to as a CAD mark) indicating an abnormal shadow candidate (referred to as an effective candidate) designated as being effective by the interpretation doctor. FIG. 2 shows a data storage example of the valid candidate feature DB 352. As shown in FIG. 2, the effective candidate feature DB 352 includes items such as “interpretation physician ID”, “effective candidate ID”, “imaging direction”, “existing area”, “contrast”, and “peripheral density”. The feature amount of the abnormal shadow candidate pointed out by the CAD mark designated as being effective by the interpretation doctor ID corresponding to the interpretation doctor ID (for example, imaging direction, existing area, contrast, peripheral density, etc.) ) In association with each other.

  Returning to FIG. 1, the image display device 4 is a medical image display device that acquires and displays a medical image designated by an operation of an interpreting doctor and CAD information corresponding thereto from the image server 3.

FIG. 3 shows a functional configuration example of the image display device 4.
As shown in FIG. 3, the image display device 4 includes a control unit 41, an operation unit 42, a display unit 43, a communication unit 44, and a storage unit 45, and each unit is connected by a bus 46.

The control unit 41 includes a CPU, a RAM, and the like. The CPU of the control unit 41 reads out various programs such as system programs and processing programs stored in the storage unit 45, expands them in the RAM, and executes various processes according to the expanded programs.
For example, the control unit 41 executes a medical image display process described later.

  The operation unit 42 includes a keyboard having character input keys, numeric input keys, various function keys, and the like, and a pointing device such as a mouse, and a key pressing signal pressed by the keyboard and an operation signal by the mouse. Are output to the control unit 41 as an input signal.

  The display unit 43 includes, for example, a monitor such as a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display), and displays various screens according to instructions of a display signal input from the control unit 41.

  The communication unit 44 is configured by a LAN card or the like, and transmits / receives data to / from an external device connected to the communication network N via a switching hub.

  The storage unit 45 includes, for example, an HDD (Hard Disk Drive), a semiconductor nonvolatile memory, or the like. The storage unit 45 stores various programs as described above. In addition, the storage unit 45 stores image processing parameters (a lookup table defining a gradation curve used for gradation processing, an enhancement degree of frequency processing, and the like) for adjusting a medical image to an image quality suitable for diagnosis. doing.

(Operation of Medical Image Display System 100)
Next, the operation of the medical image display system 100 will be described.
FIG. 4 shows a flowchart of a medical image display process executed by the image display device 4. The medical image display process is executed in cooperation with the control unit 41 and a program stored in the storage unit 45. As a premise for executing the medical image display process, an interpreting doctor who is an operator of the image display apparatus 4 inputs authentication information such as an interpreting doctor ID and a password through the operation unit 42, and the image server 3 and the image display apparatus 4. Login authentication by.

  First, a medical image to be interpreted is selected by operating the operation unit 42 (step S1). Specifically, a medical image search screen is displayed on the display unit 43 in response to an operation by the operation unit 42. When a search condition (patient ID, examination site, laterality, etc.) is input by the operation unit 42 on the search screen, the input search condition and search request are transmitted to the image server 3 by the communication unit 44. In the image server 3, medical image management information that matches the search condition is searched from the image management table of the image DB 351, and list data of medical images that match the search condition is created and transmitted to the image display device 4. In the image display device 4, when list data is received by the communication unit 44, an image selection screen based on the list data is displayed on the display unit 43. In the image selection screen, for example, a list having items such as examination ID, patient ID, patient name, examination date and time, modality type, examination site, laterality, direction, and the like is displayed for each examination unit. One or a plurality of medical images to be selected can be selected via the operation unit 42. The interpretation doctor selects a medical image to be interpreted by the operation of the operation unit 42.

  When a medical image to be interpreted is selected, an acquisition request for the selected medical image to be interpreted is transmitted to the image server 3 by the communication unit 44, and the medical image to be interpreted, CAD information of the medical image, and login are performed. Valid candidate feature information corresponding to the interpreting doctor performing is acquired from the image server 3 (step S2). In the image server 3, when a request for acquiring a medical image to be interpreted is received, the requested medical image to be interpreted and the CAD information corresponding to the medical image are retrieved from the medical image DB 351 and read out. Valid candidate information corresponding to the interpreting doctor who has logged in is retrieved from the valid candidate information DB 352 and read out, and transmitted to the image display device 4.

When the medical image to be interpreted, CAD information, and valid candidate feature information corresponding to the interpretation doctor are acquired, a viewer screen 431 on which the acquired medical image is displayed is displayed on the display unit 43 (step S3).
When a medical image is displayed on the viewer screen 431 of the display unit 43, the interpretation doctor observes the displayed medical image and diagnoses whether or not there is a region of interest (which is a region suspected of having an abnormal shadow). Do. The viewer screen 431 displays operation buttons for instructing the display of CAD detection results. After diagnosis, the image interpretation doctor presses the operation buttons using the operation unit 42.

  It is determined whether or not display of the CAD detection result (that is, the abnormal shadow candidate detected by the abnormal shadow candidate detection device 2) is instructed by the operation unit 42 (step S4). If it is determined that the display of the CAD result is instructed by the operation unit 42 (step S4; YES), it is determined whether or not valid candidate feature information has been acquired (step S5). For example, effective candidate feature information is not acquired in step S2 because effective candidate feature information is not accumulated in the case of an interpreting physician who performs an interpretation using the medical image display system 100 for the first time this time. If it is determined that valid candidate feature information has not been acquired (step S5; NO), the process proceeds to step S7. If it is determined that the valid candidate feature information has been received, an estimated valid candidate is selected from the abnormal shadow candidates detected by CAD based on the valid candidate feature information (step S6).

Here, the estimated effective candidate is an abnormal shadow candidate that is estimated to be effective for a logged-in interpreting doctor (an interpreting doctor who is currently interpreting) among abnormal shadow candidates detected by CAD.
In step S6, first, a medical image is analyzed, and a predetermined feature amount is calculated for each abnormal shadow candidate pointed out by CAD information.

The feature amount calculated here is a feature amount used for selecting an estimated effective candidate, and matches the type of feature amount calculated for the effective candidate. As the feature amount, for example, in the case of a microcalcification cluster, the number of calcifications belonging to the cluster, distribution, shape, contrast with peripheral density, peripheral density, existing area (MLO-U (Upper) / M (Middle) / L (Lower), CC-I (inner) / O (outer)), the distance from the nipple, the distance from the skin line, the positional relationship with the pectoral muscle region, and the like.
In the case of a tumor, size, contrast with surrounding concentration, surrounding concentration, existing area (MLO-U (Upper) / M (Middle) / L (Lower), CC-I (inner) / O (outer)), papillae Distance from the skin line, distance from the skin line, positional relationship with the pectoral muscle region, and the like. It should be noted that any known method may be used for extracting the nipple from the medical image, extracting the skin line, and extracting the greater pectoral muscle region. For example, the method disclosed in Japanese Patent Laid-Open No. 2009-82564 can be used for extracting the nipple, and the method disclosed in Japanese Patent Laid-Open No. 2009-82651 can be used for extracting the pectoral muscle region and extracting the skinline.
In the present embodiment, the effective estimation candidates are selected based on a combination of a plurality of types of feature amounts.

A combination of feature amounts used for selection of estimation effective candidates may be set in advance by a manufacturer. Further, the user may be able to set from the operation unit 42. In addition, when the accumulated effective candidate feature information reaches a predetermined number (for example, 50), the optimum combination of feature quantities for selecting the estimated effective candidate based on the accumulated effective candidate feature information It is good also to decide.
For the determination of the combination of feature amounts, for example, a known clustering method such as hierarchical clustering, K-means method, division / merging method, or the like can be used (for example, reference 1: supervised by Hideyuki Tamura, Japan Industrial Technology Center). Ed. "Introduction to Computer Image Processing", Soken Publishing, pp.159-161, 1985. Reference 2: "Toyowaki Junichiro," Recognition Engineering-Pattern Recognition and Its Applications ", Corona, p.85-95, 1993. Reference Reference 3: Hideki Aso, Koji Tsuda, Noboru Murata, “Statistics of Pattern Recognition and Learning”, Iwanami Shoten, p.57-66, 2003.)

  Next, a point representing the feature amount of each effective candidate of the effective candidate feature information of the interpretation doctor acquired in step S2 and a point representing the feature amount of each abnormal shadow candidate of the CAD information are feature amount spaces (a plurality of types of feature amounts). Each coordinate axis is plotted in the coordinate space), and abnormal shadow candidates whose distance from the effective candidate group is within a predetermined distance d in this coordinate space are selected as estimated effective candidates.

  FIG. 5 shows an example of the feature amount space in which the effective candidate group and the abnormal shadow candidates A and B are plotted. FIG. 5 shows an example in which the feature amount used for selecting the effective estimation candidate from the abnormal shadow candidates is two of contrast and peripheral density, but the number and types of feature amounts to be used are shown. Is not limited to this.

Here, a CAD mark that is effective for an interpreting doctor is considered to be a CAD mark that points out abnormal shadow candidates that are often overlooked by the interpreting doctor. Further, it is considered that there is a certain tendency for abnormal shadow candidates that are often overlooked for each interpretation doctor. Therefore, if the feature amount of the abnormal shadow candidate (effective candidate) pointed out by the CAD mark that the interpreting physician felt to have been effective in the past is accumulated for each interpretation doctor, the feature amount of the effective candidate has a certain tendency. That is, it is considered that a group is formed on the feature amount space. In the present embodiment, an abnormal shadow candidate whose distance from a point representing a past valid candidate in the feature amount space is within a predetermined distance d is selected as an estimated valid candidate. Specifically, when there is a point representing an effective candidate within a distance d from a point representing an abnormal shadow candidate, the abnormal shadow candidate is selected as an estimated effective candidate.
For example, in FIG. 5, since there are three points representing valid candidates within the distance d from the point representing the abnormal shadow candidate A, the abnormal shadow candidate A is determined to be an estimated valid candidate. On the other hand, since no effective candidate group belongs within the distance d from the outer periphery of the abnormal shadow candidate B, it is determined that the abnormal shadow candidate B is not an estimated effective candidate.

  When the estimated effective candidate is selected, the CAD mark M1 is displayed at the position of the abnormal shadow candidate detected by CAD on the medical image displayed on the display unit 43. Further, among the abnormal shadow candidates detected by CAD, the abnormal shadow candidates selected as the estimation effective candidates are different from the CAD mark M1, for example, by the CAD mark M2 having a different color, shape, line type, and the like. It is highlighted (step S7).

  FIG. 6 shows an example of a medical image on which a CAD mark is displayed in step S7. M1 shown in FIG. 6 indicates the abnormal shadow candidate B in FIG. 5, and M2 indicates the abnormal shadow candidate A. As shown in FIG. 6, the abnormal shadow candidate A that is an estimated effective candidate is highlighted by a more prominent CAD mark M2 that is different from the abnormal shadow candidate B that is not an estimated effective candidate. In this way, an abnormal shadow candidate whose feature amount is close to an abnormal shadow candidate of a CAD mark designated as having been effective in the past is estimated as an effective candidate, and is highlighted so that the interpreting doctor can be overlooked. Thus, it is possible to focus attention on abnormal shadow candidates having different characteristics, and to further prevent oversight of an interpreting doctor.

  Next, a message (not shown) for prompting the user to specify the CAD mark that the interpreting physician has determined to be effective is displayed on the display screen, such as “Please click on the CAD mark that was effective for diagnosis”. Then, it is determined whether or not a valid CAD mark is designated by the operation unit 42 (step S8). As shown in FIG. 7, when a CAD mark that is determined to be valid by the interpretation doctor is designated by the operation unit 42 (step S8; YES), the feature amount of the abnormal shadow candidate corresponding to the designated CAD mark is calculated. (Step S9). The feature amount calculated here is a feature amount used for selecting an estimated effective candidate. If the feature amount to be calculated here has already been calculated in step S6, the calculated feature amount can be used as valid candidate feature information, and this step can be omitted.

  When the feature amount is calculated, the calculated feature amount is transmitted as valid candidate feature information to the image interpretation doctor ID in association with the interpretation doctor ID, and transmitted to the image server 3 to instruct saving (step S10). In the image server 3, the received valid candidate feature information is stored in the valid candidate feature DB 352.

  Next, it is determined whether or not an instruction to display the next image has been input by the operation unit 42. If it is determined that the instruction has been input (step S11; YES), the process proceeds to step S3, and the next medical image is displayed. The process from step S3 to S10 is executed. If it is determined that an instruction to display the next image is not input by the operation unit 42 and an instruction to end diagnosis is given (step S12; YES), this process ends.

  As described above, the control unit 41 of the image display device 4 is designated by the operation unit 42 from the marks displayed on the medical image on the display unit 43 by the interpretation doctor determining that it is effective for diagnosis. Then, the feature amount of the abnormal shadow candidate corresponding to the designated mark is calculated, and the calculated feature amount is stored in the image server 3 as the effective candidate feature information in association with the interpretation doctor identification information. In addition, when a new medical image is acquired from the image server 3 and displayed on the display unit 43, the feature amount of the abnormal shadow candidate detected from the medical image is calculated, and the identification information of the interpreting doctor who performs the interpretation is calculated. Valid candidate feature information stored in association with each other is acquired from the image server 3, and based on the valid candidate feature information and the calculated feature amount, interpretation is performed from among abnormal shadow candidates detected from a new medical image. The abnormal shadow candidates that are estimated to be particularly effective for the diagnosis by the interpretation doctor who performs the screening are selected, and the selected abnormal shadow candidates are highlighted with marks having a different form from the other abnormal shadow candidates.

  Therefore, the abnormal shadow candidates that featured features that approximate the useful marks that the interpreting doctor has determined in the past are highlighted, so that the abnormal shadow candidates that are often overlooked by the interpreting doctor can be emphasized, preventing oversight. Can be made stronger.

  In addition, the description content in the said embodiment is a suitable example of this invention, and is not limited to this.

  For example, in the above embodiment, the abnormal shadow candidate detection device 2 that detects abnormal shadow candidates, the image server 3 as a storage device that stores medical images, and the image display device 4 that displays medical images are separate devices. However, the present invention is not limited to this. For example, it is good also as a structure provided with the function of all the apparatuses in one apparatus, and it is good also as comprising by the apparatus which combined the function of any two apparatuses, and the apparatus provided with the function of the remaining apparatuses.

  In the above embodiment, a breast image has been described as an example. However, the present invention may be applied to a case where a detection result detected for another part is displayed.

  In the above-described embodiment, the case has been described as an example in which the selection process of the estimated effective candidate is performed after the medical image is displayed and then the interpretation doctor instructs the display of the CAD result. The timing for performing the process is not particularly limited. For example, when a plurality of medical images are selected as interpretation targets by the operation unit 42, the control unit 41 first selects an estimated effective candidate from each of the selected plurality of medical images, and the estimated effective candidate is selected. The existing medical images may be given priority, that is, the medical images having the estimated effective candidates may be displayed on the display unit 43 in order. In this way, it is possible to interpret a medical image having an abnormal shadow candidate that is likely to be overlooked by the interpreting doctor before the interpreting doctor becomes tired, and to further prevent oversight.

  Further, in the above embodiment, when an effective candidate determined to be effective by the image interpretation doctor is specified, the feature amount of this effective candidate is calculated, stored in the image server 3, and used for selection of the estimated effective candidate. However, when an abnormal shadow candidate (invalid candidate) that is determined to be invalid by the interpretation doctor is designated by the operation unit 42, the feature amount of the invalid candidate is calculated, stored in the image server 3, and fixed from the invalid valid candidate group. It is also possible to highlight abnormal shadow candidates that are more than a distance of.

  In the above description, an example in which a hard disk, a semiconductor nonvolatile memory, or the like is used as a computer-readable medium of the program according to the present invention is disclosed, but the present invention is not limited to this example. As another computer-readable medium, a portable recording medium such as a CD-ROM can be applied. A carrier wave is also applied as a medium for providing program data according to the present invention via a communication line.

  In addition, the detailed configuration and detailed operation of each device constituting the medical image display system can be changed as appropriate without departing from the spirit of the present invention.

DESCRIPTION OF SYMBOLS 100 Medical image display system 1 Image generation apparatus 2 Abnormal shadow candidate detection apparatus 3 Image server 351 Image DB
4 image display device 41 control unit 42 operation unit 43 display unit 44 communication unit 45 storage unit 46 bus

Claims (4)

The medical image and the position information of the abnormal shadow candidate are acquired from a storage device that stores the medical image and the position information of the abnormal shadow candidate detected from the medical image in the abnormal shadow candidate detection apparatus in association with each other, and the acquisition A medical image display device that marks abnormal shadow candidates on the medical image based on the positional information of the abnormal shadow candidates and displays the marks on the display means,
Operation means for designating a mark that the interpretation doctor has determined to be effective for diagnosis from among the marks displayed on the medical image in the display means;
The feature amount of the abnormal shadow candidate corresponding to the mark designated by the operation means is calculated, and the calculated feature amount is stored in the storage device as effective candidate feature information in association with the identification information of the interpretation doctor. A feature amount calculating means for causing
When a new medical image is acquired from the storage device and displayed on the display unit, the feature amount of each abnormal shadow candidate detected from the new medical image is calculated, and interpretation is performed from the storage device. The effective candidate feature information stored in association with the identification information of the interpretation doctor is acquired, and detected from the new medical image based on the feature amount represented by the effective candidate feature information and the calculated feature amount. Screening means for selecting abnormal shadow candidates that are estimated to be effective for diagnosis by the interpretation doctor from among abnormal shadow candidates;
When displaying a mark on the new medical image and the abnormal shadow candidate detected from the new medical image on the display means, the abnormal shadow candidate selected by the selecting means is different from other abnormal shadow candidates. Display control means for highlighting with a mark of an aspect;
A medical image display device comprising: The feature amount calculating means calculates a plurality of types of feature amounts,
The selecting means plots points representing the feature quantities of the valid candidate feature information on a coordinate space with a plurality of types of feature quantities included in the valid candidate feature information as axes, and is detected from the new medical image. Calculating the plurality of types of feature values for the abnormal shadow candidates, plotting points representing the calculated feature values of the abnormal shadow candidates in the coordinate space, and calculating the feature values of the abnormal shadow candidates in the coordinate space. An abnormal shadow candidate that is estimated to be effective for diagnosis by the interpreting doctor when the distance between the point to represent and the point representing the feature amount of the effective candidate feature information is within a predetermined distance The medical image display device according to claim 1, wherein the medical image display device is sorted as follows.   When there are a plurality of the new medical images, the display control unit gives priority to the display unit the medical image in which there is an abnormal shadow candidate estimated to be effective for the interpretation by the screening doctor. The medical image display device according to claim 1, wherein the medical image display device is displayed. The medical image and the position information of the abnormal shadow candidate are acquired from a storage device that stores the medical image and the position information of the abnormal shadow candidate detected from the medical image in the abnormal shadow candidate detection apparatus in association with each other, and the acquisition A computer used for a medical image display device for marking the abnormal shadow candidate on the medical image based on the positional information of the abnormal shadow candidate and displaying the mark on the display means,
An operation means for designating a mark that the interpretation doctor has determined to be effective for diagnosis from the marks displayed on the medical image in the display means;
The feature amount of the abnormal shadow candidate corresponding to the mark designated by the operation means is calculated, and the calculated feature amount is stored in the storage device as effective candidate feature information in association with the identification information of the interpretation doctor. Feature amount calculation means
When a new medical image is acquired from the storage device and displayed on the display unit, the feature amount of each abnormal shadow candidate detected from the new medical image is calculated, and interpretation is performed from the storage device. The effective candidate feature information stored in association with the identification information of the interpretation doctor is acquired, and detected from the new medical image based on the feature amount represented by the effective candidate feature information and the calculated feature amount. A selection means for selecting an abnormal shadow candidate that is estimated to be effective for diagnosis by the interpretation doctor from among abnormal shadow candidates;
When displaying a mark on the new medical image and the abnormal shadow candidate detected from the new medical image on the display means, the abnormal shadow candidate selected by the selecting means is different from other abnormal shadow candidates. Display control means for highlighting with a mark of an aspect,
Program to function as.

Images