JP2004046594A - Device for supporting video diagnosis - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To constitute a video diagnosis supporting device so that it can detect an appropriate abnormal shading by using diagnosis history. <P>SOLUTION: An adjusting means 16 adjusts a detection result by an abnormal shading detection means 13 on the basis of a diagnosis history table 141 stored in a storing means 14. When the same abnormal shading candidate of the same patient as the detected abnormal shading candidate is stored in the diagnosis history table 141, the adjusting means 16 compares positions, sizes, and forms of the abnormal shading candidates with one another and determines whether or not there is any deterioration with age. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an image diagnosis support device that detects an abnormal shadow candidate from image information obtained by imaging a subject.
[0002]
[Prior art]
In the medical field, a medical image obtained by imaging a patient as a subject using a medical imaging device such as CT (Computed Tomography) or MRI (Magnetic Resonance Imaging) is converted into digital data, and when a doctor makes a diagnosis, , A medical image has been displayed on an image display device such as a CRT, and interpretation has been performed. In particular, in recent years, image diagnosis support called a computer assisted device (Computed-Aided Dianosis; hereinafter, referred to as CAD) for detecting abnormal shadow candidates such as lung cancer and breast cancer for the purpose of reducing the burden on the radiologist and reducing oversight of abnormal shadows. Equipment has been developed.
[0003]
[Problems to be solved by the invention]
In the CAD, an abnormal shadow candidate detected when displaying an image is pointed out by a marker such as an arrow, and the position of the abnormal shadow candidate is notified to a user, a radiologist, but for example, a previous operation was performed. In some cases, normal tissues such as surgical scars may be detected as abnormal shadow candidates and reported to the user, causing a decrease in diagnostic efficiency. In addition, the conventional CAD does not have a function of reflecting a diagnosis result previously diagnosed by a doctor with respect to a detection result of an abnormal shadow candidate in the current abnormal shadow detection of the CAD.
[0004]
The present invention is configured to enable the image diagnosis support apparatus to detect an appropriate abnormal shadow using a diagnosis history.
[0005]
[Means for Solving the Problems]
The invention according to claim 1 is
Abnormal shadow candidate detecting means for detecting an abnormal shadow candidate from image information obtained by imaging the subject;
Storage means for storing a diagnosis history for the abnormal shadow candidate detected by the abnormal shadow candidate detection means,
Adjusting means for adjusting the detection result by the abnormal shadow candidate detecting means based on the diagnosis history stored by the storing means,
It is characterized by having.
[0006]
According to a second aspect of the present invention, in the image diagnosis support apparatus according to the first aspect,
A display unit for displaying the image information indicating the detection result adjusted by the adjustment unit.
[0007]
According to the first and second aspects of the present invention, the diagnostic history of the detected abnormal shadow candidate is stored, and the detection result of the abnormal shadow candidate is adjusted and displayed based on the diagnostic history. , An appropriate detection result can be displayed, and the detection accuracy of abnormal shadows can be improved. Therefore, diagnostic accuracy and diagnostic efficiency can be improved.
[0008]
According to a third aspect of the present invention, in the image diagnosis support apparatus according to the second aspect,
The adjusting means determines whether or not the abnormal shadow candidate detected by the abnormal shadow candidate detecting means has changed with time based on the diagnosis history, and determines that the abnormal shadow candidate has not changed with time based on the abnormal shadow candidate. It is characterized in that the detection result is adjusted so that no candidate is indicated by the display means.
[0009]
According to the third aspect of the present invention, when it is determined that there is no temporal change of the abnormal shadow candidate detected based on the diagnosis history, the abnormal shadow candidate is adjusted so as not to be indicated and displayed. Abnormal shadows that are not likely to be malignant and that are not likely to be malignant are not included in the detection result, and the detection accuracy of abnormal shadows can be further improved. In addition, the burden on the user who observes the detection result can be reduced, and the diagnosis efficiency can be improved.
[0010]
According to a fourth aspect of the present invention, in the image diagnosis support apparatus according to the second or third aspect,
The adjusting unit determines whether there is a temporal change in the abnormal shadow candidate detected by the abnormal shadow candidate detecting unit based on the diagnosis history, and when it is determined that the abnormal shadow candidate has a temporal change, the abnormal shadow candidate is determined. Adjusting the detection result so that the candidate is indicated by the display means,
A warning unit is provided for warning that the abnormal shadow candidate has a temporal change.
[0011]
According to a sixth aspect of the present invention, in the image diagnosis support apparatus according to the fourth aspect,
The warning means causes the display means to display a warning message warning that the abnormal shadow candidate has a temporal change.
[0012]
According to the fourth and sixth aspects of the present invention, it is determined whether or not there is a temporal change in the abnormal shadow candidate detected based on the diagnosis result, and when it is determined that there is a temporal change, the abnormal shadow candidate is indicated and indicated. Warning message that warns that there is a change with time, it is possible to alert the user observing the detection result that the abnormal shadow candidate has a change with time, thereby improving the diagnostic accuracy and diagnostic efficiency. Can be achieved.
[0013]
According to a fifth aspect of the present invention, in the image diagnosis support apparatus according to the fourth aspect,
The warning means outputs a warning sound to warn that the abnormal shadow candidate has a temporal change.
[0014]
According to the fifth aspect of the present invention, since the warning sound warns that the abnormal shadow has a temporal change, it is possible to audibly alert a user who is not watching the display.
[0015]
According to a seventh aspect of the present invention, in the image diagnosis support apparatus according to the fourth aspect,
The warning means identifies and displays an abnormal shadow candidate determined to have a temporal change by the adjusting means when indicating the detection result adjusted by the adjusting means by the display means, and displays the abnormal shadow candidate. Is warned that there is a change with time.
[0016]
The invention according to claim 8 is the image diagnosis support device according to claim 7,
The warning unit is characterized in that the abnormal shadow candidate determined to have a temporal change by the adjusting unit is colored and identified and displayed.
[0017]
According to the seventh and eighth aspects of the present invention, the abnormal shadow candidate determined to have a temporal change is colored and displayed for identification to warn of the temporal change, so that the user has a temporal change. This can be visually alerted, and the abnormal shadow candidate area can be easily confirmed.
[0018]
According to a ninth aspect of the present invention, in the image diagnosis support apparatus according to the seventh aspect,
The warning means blinks and displays an abnormal shadow candidate determined to have a temporal change by the adjustment means to identify the abnormal shadow candidate.
[0019]
According to the ninth aspect of the present invention, the abnormal shadow candidate determined to have a temporal change is blinked to warn of the temporal change, so that the user is visually alerted to the temporal change. In addition, the abnormal shadow candidate area can be easily confirmed.
[0020]
According to a tenth aspect, in the image diagnosis support apparatus according to the second aspect,
The adjusting means displays the abnormal shadow candidate in the case where a diagnosis result previously diagnosed that the abnormal shadow candidate detected by the abnormal shadow candidate detecting means is a normal shadow is stored in the diagnostic history. It is characterized in that the detection result is adjusted so as not to be indicated by the means.
[0021]
According to the tenth aspect, when the detected abnormal shadow candidate has been diagnosed as a normal shadow in the past, the detection result is adjusted so that the abnormal shadow candidate is not indicated and displayed. Detection accuracy can be further improved, and diagnostic efficiency can be improved.
[0022]
According to an eleventh aspect of the present invention, in the image diagnosis support apparatus according to the tenth aspect,
The normal shadow includes a shadow of a surgical scar.
[0023]
According to the eleventh aspect of the present invention, since the normal shadow includes the shadow of the surgical scar, the surgical scar that is not a lesion is not indicated and indicated as an abnormal shadow candidate, so that the detection accuracy of the abnormal shadow can be further improved. It is possible to improve the diagnosis efficiency.
[0024]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
First, the configuration will be described.
FIG. 1 is a diagram showing an internal configuration of an image diagnosis support apparatus 10 according to the present embodiment.
In FIG. 1, an image diagnosis support apparatus 10 includes an image data input unit 11, an image data storage unit 12, an abnormal shadow candidate detection unit 13, a storage unit 14, an image processing unit 15, an adjustment unit 16, a display unit 17, and an operation input unit. 18, a warning means 19 is provided.
[0025]
The image data input unit 11 scans a film on which a medical image of a patient is recorded with a laser beam using a laser digitizer, measures the amount of transmitted light, and converts the value into an analog-to-digital signal. It is input as digital image data S.
[0026]
The input of the image by the image data input means 11 is not limited to the laser digitizer, and an optical sensor such as a CCD may be used. In this case, optical scanning is performed on the film, and the reflected light is photoelectrically converted by a CCD to obtain digital image data S. Further, as disclosed in Japanese Patent Application Laid-Open No. 55-12429, a photographing apparatus for converting a medical image photographed using a stimulable phosphor into a digital image and outputting the digital image instead of reading an image recorded on a film is disclosed. The image data S may be obtained from this photographing apparatus by connecting. In this case, a film is not required and cost can be reduced.
[0027]
Alternatively, image data S obtained from a flat panel detector (FPD) that captures a radiation image with a plurality of two-dimensionally arranged detection elements and outputs the image as an electric signal may be input. For example, Japanese Patent Application Laid-Open No. Hei 6-342098 discloses a photoconductive layer that generates electric charges in accordance with the intensity of irradiated radiation, and a technique for storing the generated electric charges in a plurality of two-dimensionally arranged capacitors. It has been disclosed.
[0028]
Further, as described in Japanese Patent Application Laid-Open No. 9-90048, radiation is absorbed by a phosphor layer such as an intensifying screen to generate fluorescent light, and the intensity of the fluorescent light is adjusted by a light source such as a photodiode provided for each pixel. The medical image may be input by detecting the image with the detector. As another means for detecting the fluorescence intensity, there is a method using a CCD or a C-MOS sensor. Further, a configuration in which a radiation scintillator that emits visible light by irradiation with radiation, a lens array, and an area sensor corresponding to each lens may be combined.
[0029]
When a digital medical image is obtained by the above-described various configurations, for example, for a mammogram (radiation image of the breast), the effective pixel size of the image is 200 μm or less, depending on the imaging site and the purpose of diagnosis. It is more preferable that the thickness be 100 μm or less. In order to maximize the performance of the image diagnosis support apparatus of the present invention, it is preferable to store and display image data input with an effective pixel size of about 50 μm, for example.
[0030]
Further, the image data input means 11 receives information on the image data S together with the input of the image data, for example, patient information on the patient, such as the patient name, patient ID, and gender of the patient, the imaging site, the imaging date, the imaging device, etc. When the imaging information is input and the image data S is output to the image data storage unit 12, the patient information and the imaging information are output in association with the image data S.
The image data input means does not necessarily need to be provided. For example, the image data input means may read image data from various storage media such as a CD-ROM or a floppy (registered trademark) in which image data is stored, or may be connected via a network. Alternatively, the data may be transferred from an external device connected.
[0031]
The image data storage unit 12 compresses and stores the image data S input by the image data input unit 11 as necessary. Here, as a data compression method, lossless compression or irreversible compression using a known method such as JPEG, DPCM, or wavelet compression is used, but lossless compression in which diagnostic information does not deteriorate due to data compression is preferable.
[0032]
The image data storage means 12 is composed of a magnetic or optical recording medium or a semiconductor memory. However, in a small-scale diagnosis, the amount of data input from the image data input means 11 is not so large. Can be stored on the magnetic disk without compression. In this case, storing and reading of the image data S can be performed at a very high speed as compared with the magneto-optical disk. At the time of image reading, a high-speed cycle time is required, so that necessary image data is also stored in a semiconductor memory.
[0033]
The abnormal shadow candidate detecting means reads out the image data S from the image data storing means 12 and performs image analysis to detect candidates considered to be abnormal shadows such as microcalcification clusters and tumor shadows as shown in FIG. FIG. 2A shows an example of the microcalcification cluster. The presence of clustered microcalcifications is an important finding for early detection of breast cancer, as it is likely to be early stage cancer. On the mammogram, it is seen as a whitish and round shade with a generally conical structure. Further, the tumor shadow shown in FIG. 2B is seen as a whitish round shadow close to a Gaussian distribution on a mammogram having a certain size.
[0034]
As described above, two major findings of breast cancer include a tumor shadow and a microcalcification cluster. As a tumor shadow detection method, a known detection method described in the following article can be used.
(1) tumor shadow
.Detection method by comparing left and right breasts
(Med. Phys., Vol. 21. No. 3, pp. 445-452)
・ Detection method using iris filter
(Theory of IEICE (D-11), Vol. J75-D-11, no. 3, pp. 663-670, 1992)
・ Detection method using a Quoit filter
(Theoretical theory (D-11), Vol. J76-D-11, no. 3, pp. 279-287, 1993)
.Detection method by binarization based on a histogram of pixel values of the divided breast cancer area
(JAMIT Frontier Lecture Papers, pp.84-85, 1995)
・ Minimum direction difference filter that takes the minimum output of many directional Laplacian filters)
(Theoretical theory (D-11), Vol. J76-D-11, no. 2, pp. 241-249, 1993)
[0035]
・ A method to distinguish benign or malignant tumor shadows using fractal dimension
(Medical Imaging Technology 17 (5), pp. 577-584, 1999).
[0036]
As a method for detecting an abnormal shadow candidate of a microcalcification cluster, a known detection method described in the following paper can be used.
(2) Microcalcification cluster
・ A method to localize the area suspected of calcification from the breast area and remove false positive candidates from the optical density difference of the shadow image and the standard deviation value of the boundary density difference
(TEEE Transform Biomed Eng BME-26 (4): 213-219, 1979)
・ Detection method using Laplacian filtered image
(IEICE (D-11), Vol. J71-D-11, no. 10, pp. 1994-2001, 1988).
・ Detection method using morphologically analyzed image to suppress the influence of background pattern such as mammary gland
(IEICE (D-11), Vol. J71-D-11, no. 7, pp. 1170-1176, 1992)
[0037]
The storage unit 14 stores, in an updatable file format, a diagnosis history table 141 that stores a diagnosis result for the abnormal shadow candidate detected by the abnormal shadow candidate detection unit 13. As shown in FIG. 3, the diagnosis history table 141 stores patient IDs, imaging regions, imaging directions, information on abnormal shadow candidates, a diagnosis result given by a doctor for the abnormal shadow candidates, and a diagnosis date. They are stored in association with each other. The imaging part stores names of each part such as a breast, a chest, an abdomen, and the like. When the imaging part is a breast, for example, MLO (oblique direction), CC (vertical direction), ML (side direction) ) Is stored, and when the imaging part is the chest or abdomen, a symbol indicating the imaging direction such as P → A (from back to front) or LAT (side direction) is stored. You.
[0038]
Note that information such as the patient ID, the imaging region, and the imaging direction is obtained from the patient information and the imaging information added to the image data S, and the diagnosis result and the diagnosis date are input by the operation input unit 18 after the diagnosis by the doctor. The information such as the patient ID, the imaging region, the imaging direction, and the like may be stored in a bar code. Alternatively, a dialog box of each information candidate is displayed on the display unit 17 to input appropriate information. The user 18 may be made to input by the means 18.
[0039]
Describing the information of the abnormal shadow candidate in detail, information on the position, size, shape, edge, and density value for specifying the abnormal shadow is stored for each candidate. The position information indicates the position of the center of gravity of the abnormal shadow candidate as a coordinate value (for example, (x, y) = (100, 1200) or the like) as shown in FIG. 3, but indicates, for example, an image region of the abnormal shadow candidate. It may be a coordinate value. Also, it may be indicated by a distance to a characteristic normal tissue.For example, when the imaging region is the chest, the position is determined by the distance between the center of gravity of the abnormal shadow candidate and the center of gravity of the lung field region that is a characteristic normal tissue. It may be indicated. The characteristic normal tissue is a biological tissue having a small change in position, such as an organ or bone such as the heart, lungs, and vertebrae, and is preferably a tissue that can serve as an index of a change over time in the position of an abnormal shadow candidate.
[0040]
The size information of the abnormal shadow candidate is, as shown in FIG. ² Etc.), but may be indicated by the average distance from the center of gravity of the abnormal shadow candidate to the edge or the longest distance (for example, 15 mm). In addition, the information on the shape of the abnormal shadow candidate is shown so that the shape (for example, a circle, a lobed shape, etc.) including the edge of the abnormal shadow candidate can be grasped. Exhibiting gender or its properties (eg, clear, unclear, spicular, etc.).
[0041]
Here, the shape and the edge of the abnormal shadow will be described in detail. Abnormal shadows of the tumor are classified into circular, elliptical, polygonal, lobulated, and irregular shapes as shown in FIG. 4A, and as shown in FIG. Although the boundary of the margin becomes clear, the abnormal malignant shadow has a clear boundary as shown in FIGS. 4 (b) and 4 (c), or has a specular shape as shown in FIG. 4 (d). There is a characteristic that a low-density white streak radially extends from the center of the shadow called “shadow” to the periphery, or a fine streak as shown in FIG. Therefore, when the abnormal shadow changes malignantly over time, the shape and size of the peripheral portion change, and the position of the center of gravity of the abnormal shadow is likely to change.
[0042]
As shown in FIG. 3, the information on the density value of the abnormal shadow candidate is represented by an average density value (for example, 300, 400, etc.) in the image area of the abnormal shadow candidate. It may be indicated by the contrast of the edge (difference in average density value of each part).
[0043]
Further, the diagnosis result for the abnormal shadow candidate will be described in detail. The detection result of the abnormal shadow candidate includes a true positive candidate that is truly a lesion, and a false positive candidate in which a normal shadow is erroneously detected as an abnormal shadow. Therefore, the diagnosis result is stored as “normal shadow” for an abnormal shadow candidate which is diagnosed as a normal shadow, for example, a surgical scar by the doctor who observes the detection result, and is an abnormal shadow but benign. Therefore, when observing the change over time, the abnormal shadow candidate diagnosed by the doctor is stored as “an abnormal shadow over time observation” and the diagnosis result is stored. In addition, a diagnosis result is stored as “abnormal shadow” for an abnormal shadow candidate that is an abnormal shadow and is diagnosed as malignant by a doctor.
[0044]
The image processing unit 15 performs various types of image processing on the image data S input from the image data storage unit 12 and outputs the processed image data to the display unit 17. Various types of image processing include frequency emphasis processing for adjusting image sharpness, gradation processing for adjusting contrast, and dynamic range for placing images with a wide dynamic range in an easily viewable density range without reducing the contrast of the subject details. Compression processing and the like are included.
[0045]
The adjustment unit 16 adjusts the detection result by the abnormal shadow detection unit 13 based on the diagnosis history table 141 stored in the storage unit 14. The adjusting means 16 determines whether or not the same abnormal shadow candidate of the same patient as the detected abnormal shadow candidate is stored in the diagnosis history table 141, and if not, the detected abnormal shadow candidate is marked with a marker. Is displayed on the display means 17.
[0046]
When the same abnormal shadow candidate of the same patient as the detected abnormal shadow candidate is stored in the diagnosis history table 141, the adjusting unit 16 determines the position, size, shape, margin, and density value of the abnormal shadow candidate. By comparison, it is determined whether or not the abnormal shadow candidate has changed with time. If the abnormal shadow candidate has a temporal change, the abnormal shadow candidate is adjusted so as to be included in the detection result, and when the image data S is displayed on the display means 17, the abnormal shadow candidate is pointed out and displayed. Is warned by the warning means 19. On the other hand, when there is no change with time in the abnormal shadow candidate, the abnormal shadow candidate is adjusted so as not to be included in the detection result, and when displaying the image data S on the display unit 17, the abnormal shadow candidate is not indicated and displayed. . Further, in the diagnosis history table 141, if a diagnosis result of a past diagnosis that the detected abnormal shadow candidate is a normal shadow is stored, adjustment is performed so that the abnormal shadow candidate is not included in the detection result. When displaying S on the display unit 17, the abnormal shadow candidate is not pointed out and displayed.
[0047]
As the display unit 17, a display unit such as a CRT (Cathode Ray Tube), a liquid crystal display, or a plasma display can be used. Among them, a high-definition CRT or a liquid crystal display dedicated to medical images is most preferable. Further, a high-definition display having a display pixel number of about 1000 × 1000 or more is preferable, and a high-definition display having a display pixel number of about 2000 × 2000 or more is preferable.
[0048]
The display unit 17 can compare and examine images from various directions by performing image display positions, image inversions, and image rotations for each of the displayed images. It can be used easily and quickly to perform accurate image diagnosis.
[0049]
As the operation input means 18, a pointing device such as a keyboard or a mouse having function keys corresponding to various functions such as a cursor key, a number input key, and an enter key can be used. Further, a touch panel integrated with the display unit 17 may be used. The operation input unit 17 outputs the diagnosis result input from the keyboard or the like to the storage unit 14.
[0050]
The warning unit 19 warns that there is a temporal change when the adjusting unit 16 determines that the detected abnormal shadow candidate has a temporal change. The warning by the warning unit 19 may be, for example, displaying a warning message for warning that there is a temporal change on the display unit 17, or when displaying the image data S on the display unit 17, an abnormal shadow with a temporal change A warning may be given by giving a color to each candidate to identify and display the candidate, or blinking and displaying an abnormal shadow candidate having a temporal change or a marker indicating the abnormal shadow candidate. Further, the warning means 19 may include a speaker or the like and output a warning sound to warn that there is a temporal change.
[0051]
Further, the warning unit 19 may issue a warning according to the degree of the temporal change of the abnormal shadow candidate. For example, a different warning is given when the size of the abnormal shadow candidate has a temporal change of 10% or less with respect to the past size, and a different warning is given when there is a temporal change of 10% or more. In this case, only the abnormal shadow candidate is colored and a warning is given. If there is a large temporal change of 10% or more, the abnormal shadow candidate is colored and the abnormal shadow candidate blinks, a warning sound is output or a warning message is output. May be displayed, and a plurality of warning methods may be combined to give a more emphasized warning.
[0052]
Next, an abnormal shadow display process executed by the image diagnosis support apparatus 10 of the present embodiment will be described with reference to FIG.
In FIG. 5, first, when image data S obtained by imaging a patient as a subject is input to the image diagnosis support apparatus 10 by the image data input unit 11, the image data storage unit 12 stores the patient information and the imaging information of the image data S. It is stored in association with the image data S. Next, the abnormal shadow candidate detection unit 13 reads out the image data S stored in the image data storage unit 12, performs image analysis, and detects an abnormal shadow candidate (step S1). At this time, the abnormal shadow candidate detecting means 13 outputs the information on the detected abnormal shadow candidate, that is, the abnormal shadow candidate information indicating the patient ID, the imaging region, the position, the size, and the shape of the abnormal shadow candidate to the storage means 14, The diagnosis history table 141 is stored.
[0053]
Next, the adjustment unit 16 refers to the diagnosis history table 141 of the storage unit 14 and determines whether or not there is a diagnosis history of the same patient as the image data S (step S2). The image data S indicating the detected abnormal shadow candidate by the marker is displayed on the display unit 17 (step S3), and the process proceeds to step S10 described later.
[0054]
On the other hand, if there is a diagnosis history of the same patient, the detected abnormal shadow candidate is compared with the abnormal shadow candidate of the same patient stored in the diagnosis history table 141 (step S4), and the same abnormal shadow candidate is determined. It is determined whether or not it is in the diagnosis history table 141 (step S5). More specifically, the detected abnormal shadow candidate is compared with the abnormal shadow candidate of the same patient in the diagnosis history table 141 to determine whether the detected abnormal shadow is the same abnormal shadow. More specifically, the detected abnormal shadow candidate is compared with the abnormal shadow candidate stored in the diagnosis history table 141, and if the positions match or fall within a predetermined range, it is determined that they are the same abnormal shadow. It shall be.
[0055]
If there is no abnormal shadow candidate identical to the detected abnormal shadow candidate, the image data S indicating the detected abnormal shadow candidate by the marker is displayed on the display unit 17 (step S3), and the process proceeds to step S10 described later. On the other hand, when there is the same abnormal shadow candidate as the detected abnormal shadow candidate, the diagnosis history table 141 refers to the diagnosis result corresponding to the abnormal shadow candidate to determine whether or not the normal shadow has been diagnosed in the past. (Step S6). If it has been diagnosed as a normal shadow in the past, the detected abnormal shadow candidate is adjusted so as not to be included in the detection result, and the image data S not indicating the abnormal shadow candidate is displayed on the display means 17 (step S7), the abnormal shadow candidate detection processing ends.
[0056]
On the other hand, if it has not been diagnosed as a normal shadow in the past, that is, if it has been diagnosed as an abnormal shadow, the adjusting unit 16 determines the detected abnormal shadow candidate and the abnormal shadow stored in the diagnosis history table 141. It is determined whether or not there is a temporal change by comparing with the shadow candidate information (step S8). More specifically, the presence / absence of a temporal change is determined by comparing the detected abnormal shadow candidate with the position, size, shape, margin, and density value of the abnormal shadow candidate stored in the diagnosis history table 141. The determination of the presence or absence of the temporal change of the position by the adjusting unit 16 may be performed, for example, by comparing the coordinate values of the center of gravity of the abnormal shadow candidate and determining that there is a temporal change when the change amount exceeds a predetermined amount. Alternatively, the distance between the center of gravity of the abnormal shadow candidate and a characteristic normal tissue located around the abnormal shadow candidate may be compared, and if the distance exceeds a predetermined value, it may be determined that there is a temporal change in the position.
[0057]
The determination of the presence / absence of the temporal change in the size is performed, for example, by comparing the area of the abnormal shadow candidate stored in the diagnosis history table 141 with the area of the detected abnormal shadow candidate area, and determining the difference between the areas by a predetermined value. It is determined that there is a time-dependent change in the magnitude when the value exceeds. Further, the comparison of the shape and the edge is performed, for example, by matching the position of the center of gravity of the saved abnormal shadow candidate with the position of the center of gravity of the detected abnormal shadow candidate, and comparing the image region of the abnormal shadow candidate, If the ratio of the area exceeds the predetermined ratio, it may be determined that there is a temporal change.
[0058]
Further, whether or not the density value has changed with time by the adjusting unit 16 is determined by comparing the density value of the past abnormal shadow candidate stored in the diagnosis history table 141 with the density value of the detected abnormal shadow candidate, for example. When the difference between the values exceeds a predetermined value, it is determined that there is a temporal change. Further, the contrast values of the center portion and the edge portion of the abnormal shadow candidate may be compared, and if the difference between the past and current contrast values exceeds a predetermined value, it may be determined that there is a temporal change. At this time, since the radiation dose varies between the past and present images depending on the photographing conditions at the time of photographing, the adjusting unit 16 performs the matching. Specifically, in the past image and the current image, the difference between the density values of the radiation-free portion (the portion where the radiation has reached without passing through the subject) is calculated, and the difference between the calculated density values is calculated as the density value. Is corrected by adding it to the density value of the image with the lower value, and matching is achieved. Alternatively, at the time of imaging, a substance whose radiation transmission amount is known in advance may be photographed together with the subject, and the same correction may be performed based on the density value of the substance to perform matching.
[0059]
Specifically, referring to FIG. 6, the abnormal shadow candidate detected in the past and stored in the diagnosis history table 141 has a polygonal shape as shown in FIG. When the abnormal shadow candidates have shapes and edges where the area is large and the streaks occur as shown in FIG. 6B, collation is performed by matching the positions of the centers of gravity of these abnormal shadow candidates as shown in FIG. 6C. Thus, an overlapping area and a non-overlapping area (indicated by hatching in the figure) are formed. If the ratio of the area of the overlapping region to the non-overlapping region is, for example, 1 and the predetermined ratio is set to 0.3, the ratio exceeds the predetermined ratio. Is determined. Also, the coordinates (x, y) of the center of gravity of the past abnormal shadow candidate shown in FIG. 6A are (300, 700), and the area is 200 mm. ² 6B, the coordinates of the current center of gravity are (305, 705), and the area is 400 mm. ² The predetermined change amount of the coordinate value is ± 10, and the predetermined value of the area difference is 100 mm. ² Is set, the coordinate value does not exceed the predetermined change amount, so it is determined that there is no change with time in the position, and since the difference in the area exceeds the predetermined value, it is determined that there is a change with time. .
[0060]
As described above, it is determined whether or not the abnormal shadow candidate has changed with time. If it is determined that there is no temporal change in all of the position, size, shape, edge, and density value of the abnormal shadow candidate, the adjusting unit 16 Is adjusted so that the abnormal shadow candidate determined not to have changed with time is not included in the detection result, the image data S that does not point out the abnormal shadow candidate is displayed on the display unit 17, and the abnormal shadow display processing ends. On the other hand, when it is determined that any one of the position, size, shape, edge, and density value of the abnormal shadow candidate has a temporal change, the adjusting unit 16 determines that there is a temporal change. Adjustment is made so that the abnormal shadow candidate is included in the detection result, and the image data S indicating the abnormal shadow candidate indicated by the marker is displayed on the display unit 17 as shown in FIG. The means 19 is warned (step S9).
[0061]
Then, after displaying the image data S on the display means 17, a diagnosis result input screen is displayed on the display means 17, and the user is caused to input a diagnosis result of the detected abnormal shadow candidate by the operation input means 18 (step S10). For example, in FIG. 7, when the user performs an image interpretation on the abnormal shadow candidate 1 and diagnoses that the observation is to be performed over time because the image is an abnormal shadow but is benign, the user inputs “an abnormal shadow over time observation”. As a result of the interpretation, for example, if the abnormal shadow candidate 2 is a surgical scar obtained in the past and is diagnosed as not an abnormal shadow, “normal shadow” is input. The operation input unit 18 outputs the input diagnosis result to the storage unit 14, and the storage unit 14 stores the diagnosis result in the diagnosis history table 141 in association with the corresponding abnormal shadow candidate (step S11), and displays the abnormal shadow. The process ends.
[0062]
As described above, the detected abnormal shadow candidate and the diagnosis result of the doctor for the abnormal shadow candidate are stored as a diagnosis history, and the adjustment result of the abnormal shadow candidate is adjusted by the adjusting unit 16 based on the diagnosis history. Appropriate detection results can be displayed using the diagnosis history, and the detection accuracy of abnormal shadows can be improved. Therefore, the diagnostic efficiency and the diagnostic accuracy can be improved.
[0063]
Further, when the adjusting unit 16 determines that the detected abnormal shadow candidate has a temporal change based on the diagnosis history, the adjusting unit 16 warns the temporal change by the warning unit 19. The doctor can be warned.
[0064]
The adjusting unit 16 determines whether the detected abnormal shadow candidate is a normal shadow or determines that the detected abnormal shadow candidate does not change with time based on the diagnosis history. Adjustment is made so that the shadow candidate is not included in the detection result, and when the image data S is displayed on the display unit 17, the abnormal shadow candidate is not pointed out and displayed. Thus, the burden on the user who diagnoses by image interpretation can be reduced, and the efficiency of diagnosis can be improved.
[0065]
Note that the description in the present embodiment is an example of a suitable image diagnosis support apparatus 10 according to the present invention, and the present invention is not limited to this.
For example, in the above description, when it is determined that the abnormal shadow candidate has a temporal change, when displaying the image data S including the abnormal shadow candidate, the user is warned of the temporal change. At the same time, a past diagnosis date may be displayed to notify the user of the elapsed time. The diagnosis efficiency and accuracy can be improved by providing more information.
[0066]
In addition, when the abnormal shadow candidate does not change with time, the image data S is displayed without indicating the abnormal shadow candidate. However, the present invention is not limited to this. A message with no change may be displayed to notify the user that there is no change with time. By notifying that there is no change with time, the user can confirm that the same abnormal shadow has been detected in the past.
[0067]
In addition, the detailed configuration and detailed operation of each unit constituting the image diagnosis support apparatus 10 according to the present embodiment can be appropriately changed without departing from the spirit of the present invention.
[0068]
【The invention's effect】
According to the first and second aspects of the present invention, the diagnostic history of the detected abnormal shadow candidate is stored, and the detection result of the abnormal shadow candidate is adjusted and displayed based on the diagnostic history. Utilization can be used to display an appropriate detection result, and the detection accuracy of abnormal shadows can be improved. Therefore, diagnostic accuracy and diagnostic efficiency can be improved.
[0069]
According to the third aspect of the present invention, when it is determined that there is no temporal change in the abnormal shadow candidate detected based on the diagnosis history, the abnormal temporal shadow candidate is adjusted so as not to be indicated and displayed. Abnormal shadows that are unlikely to be malignant are not included in the detection result, and the detection accuracy of abnormal shadows can be further improved. In addition, the burden on the user who makes a diagnosis based on the detection result can be reduced, and the efficiency of diagnosis can be improved.
[0070]
According to the fourth and sixth aspects of the present invention, the presence or absence of a temporal change of the abnormal shadow candidate detected based on the diagnosis result is determined, and when it is determined that there is a temporal change, the abnormal shadow candidate is pointed out and displayed. In addition, a warning message that warns that there is a change with time is displayed, so that it is possible to alert the user observing the detection result that there is a change with time in the abnormal shadow candidate, thereby improving diagnosis accuracy and diagnosis efficiency. Can be planned.
[0071]
According to the fifth aspect of the present invention, since the warning sound warns that the abnormal shadow has a temporal change, it is possible to audibly alert a user who is not watching the display.
[0072]
According to the seventh and eighth aspects of the present invention, the abnormal shadow candidate determined to have a temporal change is colored and identified and displayed to warn the user of the temporal change, so that the user has a temporal change. Can be visually alerted, and the abnormal shadow candidate area can be easily confirmed.
[0073]
According to the ninth aspect of the present invention, the abnormal shadow candidate determined to have a temporal change is blinked to warn of the temporal change, so that the user can be visually alerted to the temporal change. At the same time, the abnormal shadow candidate area can be easily confirmed.
[0074]
According to the tenth aspect, when the detected abnormal shadow candidate has been diagnosed as a normal shadow in the past, the detection result is adjusted so that the abnormal shadow candidate is not indicated and displayed. Accuracy can be further improved, and diagnostic efficiency can be improved.
[0075]
According to the eleventh aspect of the present invention, since the normal shadow includes the shadow of the surgical scar, the surgical scar that is not a lesion is not indicated as an abnormal shadow candidate, so that the detection accuracy of the abnormal shadow can be further improved. In addition, the efficiency of diagnosis can be improved.
[Brief description of the drawings]
FIG. 1 is a diagram showing a configuration of an image diagnosis support apparatus 10 according to an embodiment to which the present invention is applied.
FIG. 2A is an example of a tumor shadow, and FIG. 2B is an example of a microcalcification cluster.
FIG. 3 is a diagram showing an example of data storage of a diagnosis history table 141 stored by a storage unit 14 of FIG. 1;
FIGS. 4A to 4E are schematic diagrams showing detected tumor shadows.
FIG. 5 is a flowchart illustrating an abnormal shadow display process performed in the image diagnosis support apparatus 10 according to the present embodiment.
6 is a diagram illustrating a comparison between a detected abnormal shadow candidate and an abnormal shadow candidate stored in a diagnosis history table 141. FIG.
FIG. 7 is a diagram showing a display example of image data S in which an abnormal shadow candidate having a temporal change is indicated and displayed.
[Explanation of symbols]
10 Image diagnosis support device
11 Image data input means
12. Image data storage means
13 Abnormal shadow candidate detection means
14 Storage means
15 Image processing means
16 Adjusting means
17 Display means
18 Operation input means
19 Warning means

Claims (11)

Abnormal shadow candidate detecting means for detecting an abnormal shadow candidate from image information obtained by imaging the subject;
Storage means for storing a diagnosis history for the abnormal shadow candidate detected by the abnormal shadow candidate detection means,
Adjusting means for adjusting the detection result by the abnormal shadow candidate detecting means based on the diagnosis history stored by the storing means,
An image diagnosis support device comprising: The image diagnosis support device according to claim 1, further comprising a display unit that displays the image information indicating the detection result adjusted by the adjustment unit. The adjusting unit determines whether there is a temporal change in the abnormal shadow candidate detected by the abnormal shadow candidate detecting unit based on the diagnosis history, and determines that there is no temporal change in the abnormal shadow candidate. 3. The image diagnosis support apparatus according to claim 2, wherein the detection result is adjusted so that no candidate is indicated and displayed by the display unit. The adjusting unit determines whether there is a temporal change in the abnormal shadow candidate detected by the abnormal shadow candidate detecting unit based on the diagnosis history, and when it is determined that the abnormal shadow candidate has a temporal change, the abnormal shadow candidate is determined. Adjusting the detection result so that the candidate is indicated by the display means,
The image diagnosis support apparatus according to claim 2, further comprising a warning unit that warns that the abnormal shadow candidate has a temporal change. The apparatus according to claim 4, wherein the warning unit outputs a warning sound to warn that the abnormal shadow candidate has a temporal change. 5. The image diagnosis support apparatus according to claim 4, wherein the warning unit causes the display unit to display a warning message that warns that the abnormal shadow candidate has a temporal change. 6. The warning means identifies and displays an abnormal shadow candidate determined to have a temporal change by the adjusting means when the detection result adjusted by the adjusting means is indicated by the display means, and displays the abnormal shadow candidate. The image diagnosis support apparatus according to claim 4, wherein a warning is given that there is a change with time. 8. The image diagnosis support apparatus according to claim 7, wherein the warning unit adds a color to the abnormal shadow candidate determined to have a temporal change by the adjustment unit and displays the abnormal shadow candidate. The image diagnosis support apparatus according to claim 7, wherein the warning unit blinks and displays an abnormal shadow candidate determined to have a temporal change by the adjustment unit. The adjustment means displays the abnormal shadow candidate when the diagnosis history stores a diagnosis result previously diagnosed that the abnormal shadow candidate detected by the abnormal shadow candidate detection means is a normal shadow. 3. The image diagnosis support apparatus according to claim 2, wherein the detection result is adjusted so as not to be indicated by the means. The image diagnosis support apparatus according to claim 10, wherein the normal shadow includes a shadow of a surgical scar.

Images