JP5338420B2 - Image diagnosis support program, method and apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To immediately display a three-dimensional partial image of an abnormal shadow candidate. <P>SOLUTION: The image diagnosis support method includes: a step for searching an abnormal shadow candidate area considered as a lesion site in each tomographic image of a plurality of tomographic images where a subject is photographed; a step for specifying a partial area including the specified abnormal shadow candidate from the abnormal shadow candidate area detected from each tomographic image, the partial area that is a partial area in a virtual three-dimensional image in which a plurality of tomographic images are arranged, and extracting a pixel data corresponding to the partial area specified from the plurality of the tomographic images as the partial image data; and a step for corresponding the extracted partial image data with the position information of the partial area in a virtual three-dimensional image and storing it in a memory device. <P>COPYRIGHT: (C)2011,JPO&amp;INPIT

Description

  The present technology relates to a technology in the field of displaying a three-dimensional image of an abnormal shadow candidate regarded as a lesion.

  In recent years, for example, the performance of imaging apparatuses used for examinations such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) has improved, and accordingly, the number of tomographic images obtained in one examination has increased rapidly. The amount is also increasing. Here, for example, when the number of tomographic images becomes enormous, the burden on the doctor who interprets the tomographic images increases. Thus, there is a technique (for example, a technique described in Japanese Patent Laid-Open No. 2004-41490) that detects an abnormal shadow candidate from a tomographic image group and presents it to a doctor.

  On the other hand, for example, when a tomographic image group is to be displayed in a three-dimensional manner, in the conventional technique, image data for all the tomographic images is read in order from the first tomographic image, and then a three-dimensional image is drawn. It has become. Therefore, for example, even when a doctor wants to check only abnormal shadow candidates, in order to display the abnormal shadow candidates in a three-dimensional manner, image data for all tomographic images must be read. , It takes time. In particular, as described above, the amount of image data has increased, and it takes a very long time to read image data for all tomographic images.

JP 2004-41490 A

Kanae Shigemoto, Hotaka Takizawa, Junji Yamamoto, Toru Nakagawa, Toru Matsumoto, Norio Kanno, Takeshi Iinuma, Mitsumi Matsumoto, High-speed recognition ", MEDICAL IMAGING TECHNOLOGY, 2003, Vol. 21, No. 2, p. 147-155 Yongbum Lee, Takeshi Hara, Hiroshi Fujita, Shigeki Itoh, and Takeo Ishigaki, "Automated Detection of Pulmonary Nodules in Helical CT Images Based on an Improved Template-Matching Technique", IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (7), p .595-604 Qiang Li, Shusuke Sone, Kunio Doi, "Selective enhancement filters for nodules, vessels, and air walls in two- and three-dimensional CT scans", Medical Physics, 2003, 30 (8), p.2040-2051 Tomokazu Oda, Shinsuke Saita, Mitsuru Kubo, Yoshiki Kawata, Noboru Niki, Michizou Sasagawa, Hironobu Ohmatsu, Ryutaro Kakinuma, Masahiro Kaneko, Masahiro Kusumoto, Kenji Eguchi, Hiroyuki Nishiyama, Kiyoshi Mori and Noriyuki Moriyama: Nodule detection algorithm based on multi slice CT images for lung cancer screening, Proceedings of SPIE, Vol.5370, pp.1083-1090, San Diego, Feb. 2004. Yosuke Hayase, Yoshito Mekada, Kensaku Mori, Junichi Hasegawa, Junichiro Toriwaki, Masaki Mori, Hiroshi Natori, Technique for detecting multiple nodules from 3D chest X-ray CT images, IEICE Transactions, DII, J87-DII , 1, pp.219-227, (Jan. 2004)

  As described above, in the prior art, even if an abnormal shadow candidate is known in advance, the three-dimensional partial image of the abnormal shadow candidate cannot be displayed promptly.

  Accordingly, an object of the present technology is to provide a technology for enabling prompt display of a three-dimensional partial image of an abnormal shadow candidate.

  In this image diagnosis support method, for each of a plurality of tomographic images obtained by imaging a subject, a step of searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image, and a virtual three-dimensional image in which the plurality of tomographic images are arranged A partial area including a candidate for an abnormal shadow identified by an abnormal shadow candidate area detected from each tomographic image, and pixel data corresponding to the identified partial area from a plurality of tomographic images Are extracted as partial image data, and the extracted partial image data and the position information of the partial area in the virtual three-dimensional image are stored in the storage device in association with each other.

  It becomes possible to promptly display a three-dimensional partial image of an abnormal shadow candidate.

It is a functional block diagram of the diagnostic imaging support apparatus which concerns on this Embodiment. It is a figure which shows an example of the data stored in a test | inspection image data storage part. It is a figure which shows the table example of the abnormal shadow candidate list table stored in an abnormal shadow candidate list table storage part. It is a figure which shows an example of the data stored in a partial image data storage part. It is a figure which shows an example of test | inspection image data. It is a figure which shows the processing flow at the time of extracting and storing partial image data. It is a figure which shows the processing flow of an abnormal shadow candidate extraction process. It is a figure for demonstrating an abnormal shadow candidate extraction process. It is an image figure of an abnormal shadow candidate. It is a figure which shows the processing flow of a partial image data extraction process. It is a figure which shows an example of partial image data. It is a figure which shows the processing flow (1st part) of a partial image matching process. It is a figure for demonstrating the process which calculates the shift | offset | difference of the position of an organ. It is a figure which shows the processing flow (2nd part) of a partial image matching process. It is a figure which shows the processing flow of a display process. It is a figure which shows an example of the data stored in a partial image data storage part. It is a figure which shows the example of a display of a three-dimensional partial image. It is a functional block diagram of a computer.

  FIG. 1 shows a functional block diagram of an image diagnosis support apparatus 1 according to an embodiment of the present technology. The image diagnosis support apparatus 1 includes an examination image data storage unit 11, an input unit 12, an abnormal shadow candidate extraction unit 13, an abnormal shadow candidate list table storage unit 14, a partial image data extraction unit 15, and a partial image data storage. Unit 16, association processing unit 17, and output unit 18. The diagnostic imaging support apparatus 1 is connected to an imaging apparatus (not shown) used for examinations such as CT and MRI, and receives examination image data including a plurality of tomographic images obtained by imaging a subject from the imaging apparatus. The inspection image data is stored in the inspection image data storage unit 11 for each inspection.

  The input unit 12 reads examination image data of a certain patient from the examination image data storage unit 11 and outputs it to the abnormal shadow candidate extraction unit 13 together with examination information such as a patient ID and an examination date. In addition, when receiving a display instruction from a doctor or the like, the input unit 12 outputs the display instruction to the output unit 18. The abnormal shadow candidate extraction unit 13 receives the inspection image data from the input unit 12, performs abnormal shadow candidate extraction processing described later, and registers the extraction result in the abnormal shadow candidate list table storage unit 14. Further, the abnormal shadow candidate extraction unit 13 outputs the inspection information to the partial image data extraction unit 15 after performing the abnormal shadow candidate extraction process. When the partial image data extraction unit 15 receives the examination information from the abnormal shadow candidate extraction unit 13, the partial image data extraction unit 15 will be described later based on data stored in the examination image data storage unit 11 and the abnormal shadow candidate list table storage unit 14. Image data extraction processing is performed, and the extracted partial image data is stored in the partial image data storage unit 16. Further, the partial image data extraction unit 15 outputs the inspection information to the association processing unit 17 after performing the partial image data extraction process. When the association processing unit 17 receives the examination information from the partial image data extraction unit 15, the association processing unit 17 will be described later based on the data stored in the examination image data storage unit 11 and the partial image data storage unit 16. Processing is performed, and data for associating the partial image data with the previous partial image data is stored in the partial image data storage unit 16. The output unit 18 receives a display instruction from the input unit 12 and displays a list of abnormal shadow candidates based on the data stored in the abnormal shadow candidate list table storage unit 14 or is stored in the partial image data storage unit 16. The predetermined partial image data is subjected to predetermined three-dimensional image processing to generate and display three-dimensional partial image data. The output unit 18 displays the three-dimensional partial image data, and then performs predetermined three-dimensional image processing on the inspection image data stored in the inspection image data storage unit 11 to obtain the three-dimensional image data. Generate and display on a display device or the like.

  FIG. 2 shows an example of data stored in the inspection image data storage unit 11. In the example of FIG. 2, the examination image data storage unit 11 includes a patient ID column, an examination date column, an image size column, a pixel interval column, and an image data column. In the column of pixel intervals, the size (unit: mm) of one pixel is set. Note that the size of one pixel differs depending on the photographing apparatus. In the image data column, inspection image data including a plurality of tomographic images photographed in the inspection is registered.

  FIG. 3 shows a table example of the abnormal shadow candidate list table stored in the abnormal shadow candidate list table storage unit 14. In the example of FIG. 3, the abnormal shadow candidate list table includes a patient ID column, an examination date column, a region number column, a center coordinate column, and a size column. In the area number column, a number for identifying a solid area circumscribing the abnormal shadow candidate extracted by the abnormal shadow candidate extraction process described later is set. Further, the center coordinate in the solid circumscribing the abnormal shadow candidate is set in the center coordinate column, and the size of the solid is set in the size column.

  FIG. 4 shows an example of data stored in the partial image data storage unit 16. In the example of FIG. 4, the partial image data storage unit 16 includes a patient ID column, an examination date column, a region number column, a center coordinate column, a partial image size column, and a pixel interval column. And a column of region numbers at the time of previous inspection and a column of partial image data. The data set in the abnormal shadow candidate list table is set as it is for the patient ID, examination date, area number, and center coordinates. As for the pixel interval, the data set in the inspection image data storage unit 11 is set as it is. The partial image data extracted by the partial image data extraction process described later is registered in the partial image data column. In the column of the region number at the time of the previous inspection, the region number corresponding to the previous partial image data in which the extracted portion is regarded as the same as the current partial image data among the previous partial image data extracted from the previous inspection image data Is set.

  Next, processing of the diagnostic imaging support apparatus 1 will be described with reference to FIGS. First, a process of extracting partial image data from inspection image data and storing it in association with the previous partial image data will be described with reference to FIGS. For example, when receiving new examination image data from an imaging apparatus such as CT or MRI, the diagnostic imaging apparatus 1 stores the examination image data in the examination image data storage unit 11. FIG. 5 shows an example of inspection image data. As shown in FIG. 5, the inspection image data includes a plurality of tomographic images. FIG. 5 shows an example of a tomographic image of the lung field.

  Then, the input unit 12 reads the inspection image data from the inspection image data storage unit 11 (FIG. 6: step S1) and outputs it to the abnormal shadow candidate extraction unit 13. At this time, examination information such as patient ID and examination date is also output to the abnormal shadow candidate extraction unit 13.

  Then, the abnormal shadow candidate extraction unit 13 receives the inspection image data and the inspection information from the input unit 12, and temporarily stores them in the storage device. And the abnormal shadow candidate extraction part 13 implements an abnormal shadow candidate extraction process based on test | inspection image data (step S3). The abnormal shadow candidate extraction process will be described with reference to FIGS. Note that the method for extracting an abnormal shadow candidate is described in detail in Non-Patent Documents 2 to 5 and the like shown in the background art column, and will be briefly described here.

  First, the abnormal shadow candidate extraction unit 13 extracts an organ region from the tomographic image included in the examination image data (FIG. 7: Step S11). For example, as shown in FIG. 8, when the processing of this step is performed on the tomographic image group for the lung field, a lung field region 801 is extracted.

  Then, the abnormal shadow candidate extraction unit 13 extracts a region of an internal organ structure such as a blood vessel or a bronchus from the organ region (step S13). As shown in FIG. 8, when the processing of this step is performed on the lung field region 801, an internal organ structure region 802 is extracted.

  Then, the abnormal shadow candidate extraction unit 13 extracts an initial candidate region by removing a region regarded as an internal organ structure from the internal organ structure region according to the feature of the shape of the internal organ structure (step S15). . As shown in FIG. 8, when the process of this step is performed on the internal organ structure region 802, initial candidate regions 803 and 804 are extracted.

  Then, the abnormal shadow candidate extraction unit 13 identifies an abnormal shadow candidate area from the initial candidate area (step S17). For example, the initial candidate region may include a region such as a branching portion of a blood vessel in addition to a region regarded as a lesion. Therefore, in this step, in consideration of the connection relationship with the internal organ structure and the like, a portion regarded as a part of the blood vessel or bronchus is removed, and the finally remaining region is specified as an abnormal shadow candidate region. As shown in FIG. 8, when the process of this step is performed on the initial candidate areas 803 and 804, the initial candidate area 804 is removed and the initial candidate area 803 is identified as an abnormal shadow candidate area.

  Note that, by processing the above-described steps S11 to S17 for each tomographic image, for example, a three-dimensional abnormal shadow candidate as shown in FIG. 9 can be specified.

  Then, the abnormal shadow candidate extraction unit 13 calculates the size and center coordinates of the circumscribed rectangle (solid) of the abnormal shadow candidate for each abnormal shadow candidate, and together with the inspection information and the identification number received from the input unit 12, the abnormal shadow candidate Store in the list table (step S19). Then, the process returns to the original process.

  Returning to the description of FIG. 6, the abnormal shadow candidate extraction unit 13 outputs the examination information to the partial image data extraction unit 15 after performing the abnormal shadow candidate extraction process. When the partial image data extraction unit 15 receives the examination information from the abnormal shadow candidate extraction unit 13, the partial image data extraction unit 15 based on the data stored in the examination image data storage unit 11 and the abnormal shadow candidate list table storage unit 14. An extraction process is performed (step S5). The partial image data extraction process will be described with reference to FIGS.

  First, the partial image data extraction unit 15 searches the abnormal shadow candidate list table based on the inspection information received from the abnormal shadow candidate extraction unit 13, and unprocessed among the abnormal shadow candidates extracted from the current inspection image data. An abnormal shadow candidate is specified (FIG. 10: step S21). Further, the partial image data extraction unit 15 adds a record relating to the specified abnormal shadow candidate to the partial image data storage unit 16. For the patient ID, examination date, area number, and center coordinates, the data set in the abnormal shadow candidate list table is set in the record. For the pixel interval, the data set in the inspection image data storage unit 11 is set in the record.

Then, the partial image data extraction unit 15 determines the partial image size from the size of the circumscribed rectangle of the specific abnormal shadow candidate (step S23) and registers it in the partial image data storage unit 16. For example, when the circumscribed rectangle size of the nth abnormal shadow candidate is (w _n , h _n , d _n ), the partial image size (w ′ _n , h ′ _n , d ′ _n ) can be calculated by the following equation. .
w ′ _n = max (w _n × 2, MinSize / pitch _x )
h ′ _n = max (h _n × 2, MinSize / pitch _y )
d ′ _n = max (w _n × 2, MinSize / pitch _z )
MinSize represents the minimum size (unit: mm) of the partial image data, and pitch represents the pixel interval. In the present embodiment, the larger one of the value obtained by doubling the size of the circumscribed rectangle and the value of the minimum size is used as the partial image size.

Then, the partial image data extraction unit 15 has a range specified by the center coordinates of the circumscribed rectangle of the specific abnormal shadow candidate and the partial image size from the current inspection image data stored in the inspection image data storage unit 11. Pixel data is extracted as partial image data and stored in the partial image data storage unit 16 (step S25). For example, when the center coordinates of the circumscribed rectangle of the nth abnormal shadow candidate are (x _n , y _n , z _n ) and the partial image size is (w ′ _n , h ′ _n , d ′ _n ), the inspection image data Pixel data in the following range in (X, Y, Z) is extracted as partial image data 3DSubImage (x ′, y ′, z ′).
(X _n −w ′ _n / 2) ≦ X <(x _n + w ′ _n / 2)
(Y _n −h ′ _n / 2) ≦ Y <(y _n + h ′ _n / 2)
(Z _n −d ′ _n / 2) ≦ Z <(z _n + d ′ _n / 2)
For example, when (x _n −w ′ _n / 2) <0, the above range is set to 0 ≦ X. When (x _n + w ′ _n / 2) ≧ W (W: image size in the X-axis direction), the above range is set to X <W. The same applies to Y and Z. Note that the ranges of x ′, y ′, and z ′ are 0 ≦ x ′ <w ′ _n , 0 ≦ y ′ <h ′ _n , and 0 ≦ z ′ <d ′ _n .

  Then, the partial image data extraction unit 15 determines whether or not processing has been completed for all abnormal shadow candidates (step S27). If processing has not been completed for all abnormal shadow candidates (step S27: No route), the processing returns to step S21 and the above-described processing is repeated. On the other hand, when the processing is completed for all abnormal shadow candidates (step S27: Yes route), this processing ends and the processing returns to the original processing.

  For example, when partial image data extraction processing is performed on an abnormal shadow candidate as shown in FIG. 9, partial image data as shown in FIG. 11 is extracted. In FIG. 11, the partial image data is extracted in a form in which a certain margin area is provided around the abnormal shadow candidate.

  Returning to the description of FIG. 6, the partial image data extraction unit 15 outputs the examination information to the association processing unit 17 after performing the partial image data extraction process. Then, when the association processing unit 17 receives the examination information from the partial image data extraction unit 15, the association processing unit 17 searches the examination image data storage unit 11 based on the examination information, and the previous examination image data for the patient related to the examination information is examined. It is determined whether it is stored in the image data storage unit 11 (step S7). If the previous examination image data for the patient related to the examination information is not stored in the examination image data storage unit 11 (step S7: No route), the process ends without performing the partial image association process described below. .

  On the other hand, when the previous examination image data for the patient related to the examination information is stored in the examination image data storage unit 11 (step S7: Yes route), the association processing unit 17 includes the examination image data storage unit 11 and the partial image. Based on the data stored in the data storage unit 16, a partial image association process is performed (step S9). The partial image association process will be described with reference to FIGS.

  First, the association processing unit 17 reads the current inspection image data and the previous inspection image data from the inspection image data storage unit 11, and the tomography to be compared from each of the current inspection image data and the previous inspection image data. An image is extracted (FIG. 12: Step S31). Specifically, attention is paid to a certain organ, and based on the characteristics of the organ, tomographic images that are regarded as having the same imaging position are extracted. For example, in the case of a tomographic image of a lung field, a tomographic image in which bronchi begin to appear is searched and extracted. When the processing in this step is performed, for example, as shown in FIG. 13, a comparison target tomographic image is extracted from each of the current inspection image data and the previous inspection image data. Here, it is assumed that the i-th tomographic image is extracted from the current inspection image data, and the j-th tomographic image is extracted from the previous inspection image data.

  Then, the association processing unit 17 extracts an organ region from each comparison target tomographic image (step S33). In addition, the process of this step is the same process as step S11 (FIG. 7). When the processing of this step is performed, as shown in FIG. 13, an organ (lung field) region is extracted from the comparison target tomographic image.

Then, the association processing unit 17 compares the position of the circumscribed rectangle of the extracted organ region for each comparison target tomographic image, calculates the displacement of the organ position, and stores it as a position correction value in the storage device (step). S35). For example, as shown in FIG. 13, the upper left vertex of the circumscribed rectangle of the lung field region 1301 related to the current examination image data is (a1 _x , a1 _y ), and the circumscribing of the lung field region 1302 related to the previous examination image data is performed. When the upper left vertex in the rectangle is (a2 _x , a2 _y ), “a2 _x −a1 _x ” is a value representing a deviation in the X axis direction, and “a2 _y −a1 _y ” is a value representing a deviation in the Y axis direction. It becomes. In addition, when the distance from the first tomographic image to the comparison target tomographic image is a1 _z and a2 _z , “a2 _z −a1 _z ” is a value representing a deviation in the Z-axis direction. Here, a1 _z and a2 _z are represented by a1 _z = (i−1) × pitch _z and a2 _z = (j−1) × pitch _z .

Then, the association processing unit 17 searches the partial image data storage unit 16 based on the examination information, and specifies an unprocessed record among records including the current partial image data (step S37). Then, the association processing unit 17 corrects the center coordinates in the specific record using the position correction value calculated in step S35, and stores the corrected center coordinates in the storage device (step S39). For example, when the center coordinates before correction are (x _n , y _n , z _n ), the center coordinates after correction (p _n , q _n , r _n ) are expressed by the following equations.
_{p n = x n + (a2} x -a1 x)
q _n = y _n + (a2 _y −a1 _y )
r _n = z _n + (a2 _z −a1 _z )
And a process transfers to the process of step S41 (FIG. 14) via the terminal A. FIG.

  14, after the terminal A, the association processing unit 17 searches the partial image data storage unit 16 based on the inspection information, and the record including the previous partial image data is the partial image data storage unit. 16 is determined (FIG. 14: step S41). That is, it is determined whether or not partial image data has already been extracted from the previous inspection image data. If the record including the previous partial image data is not stored in the partial image data storage unit 16 (step S41: No route), the process proceeds to step S43.

  Then, the process proceeds to step S43, and the association processing unit 17 extracts the previous partial image data from the previous examination image data so that the extracted portion is the same as the current partial image data, and the partial image A record is added to the data storage unit 16 to store the extracted partial image data (step S43). At this time, a number for identifying the previous inspection image data is assigned and set as a region number in the record. For the patient ID, examination date, and pixel interval, the data set in the examination image data storage unit 11 is set in the record. Further, for the center coordinates and the partial image size, values corresponding to the extracted partial image data are set in the record.

  Then, the association processing unit 17 registers the data for associating the extracted previous partial image data with the current partial image data in the specific record in the specific record (step S45). Specifically, the area number corresponding to the extracted previous partial image data is registered in the previous inspection area number column in the specific record. Thereafter, the process proceeds to step S53.

  On the other hand, when it is determined in step S41 that the record including the previous partial image data is stored in the partial image data storage unit 16 (step S41: Yes route), for each record including the previous partial image data, The distance from the center coordinates in the record to the corrected center coordinates calculated in step S39 is calculated, and the minimum distance is specified (step S47). Then, the association processing unit 17 determines whether the minimum distance is less than a predetermined threshold (step S49). In the present embodiment, when the minimum distance is less than a predetermined threshold, it is assumed that the extracted part of the current partial image data and the extracted part of the previous partial image data are the same. When it is determined that the minimum distance is less than the predetermined threshold (step S49: Yes route), the association processing unit 17 uses the previous partial image data that minimizes the distance to the corrected center coordinates and the specific record. Data for associating with the current partial image data is registered in the specific record (step S51). Specifically, the area number corresponding to the previous partial image data that minimizes the distance to the corrected center coordinate is registered in the previous inspection area number column in the specific record. Thereafter, the process proceeds to step S53.

  On the other hand, when it is determined that the minimum distance is greater than or equal to the predetermined threshold (step S49: No route), the process proceeds to step S43, and the processes of steps S43 and S45 described above are performed. Then, the process proceeds to step S53.

  Then, the process proceeds to step S53, and the association processing unit 17 determines whether the processing has been completed for all records including the current partial image data (step S53). If the processing has not been completed for all the records including the partial image data this time (step S53: No route), the processing returns to step S37 via the terminal B, and the processing described above is repeated. On the other hand, when the processing has been completed for all the records including the current partial image data (step S53: Yes route), this processing ends.

  By performing the processing as described above, partial image data for an abnormal shadow candidate can be extracted, and when there is a display instruction from a doctor, a three-dimensional partial image of the abnormal shadow candidate can be quickly displayed. It becomes like this. In addition, when there is previous examination image data for the same patient, past three-dimensional partial images of abnormal shadow candidates can be quickly displayed.

  Next, display processing in the diagnostic imaging support apparatus 1 will be described with reference to FIGS. 15 to 17. It is assumed that the processing as described above is performed and the partial image data is stored in the partial image data storage unit 16. For example, a doctor operates the image diagnosis support apparatus 1 and inputs a display instruction including designation of a patient ID and an examination date. Note that the doctor may operate a computer connected to the image diagnosis support apparatus 1 via a network to transmit a display instruction to the image diagnosis support apparatus 1. Then, the input unit 12 accepts an input of a display instruction from the doctor (FIG. 15: step S61) and outputs the display instruction to the output unit 18.

  Then, the output unit 18 receives a display instruction from the input unit 12. Then, the output unit 18 searches the abnormal shadow candidate list table based on the patient ID and the examination date included in the display instruction, and identifies an unprocessed abnormal shadow candidate among the abnormal shadow candidates related to the display instruction (step S63). ). Then, the output unit 18 reads partial image data corresponding to the specified abnormal shadow candidate from the partial image data storage unit 16 (step S65).

  Then, the output unit 18 searches the partial image data storage unit 16 and determines whether there is previous partial image data corresponding to the specified abnormal shadow candidate (step S67). That is, in the partial image data storage unit 16, it is determined whether or not the previous inspection area number is set in the record related to the specified abnormal shadow candidate. When the previous partial image data corresponding to the specified abnormal shadow candidate exists (step S67: Yes route), the output unit 18 sends the previous partial image corresponding to the specified abnormal shadow candidate from the partial image data storage unit 16. Data is read (step S69). Then, the output unit 18 performs three-dimensional image processing or the like on each of the current partial image data and the previous partial image data, so that the current three-dimensional partial image data, the previous three-dimensional partial image data, Is generated and displayed on the display device (step S71). Thereafter, the process proceeds to step S75.

  On the other hand, when there is no previous partial image data corresponding to the specified abnormal shadow candidate (step S67: No route), the output unit 18 performs three-dimensional image processing on the current partial image data, etc. The current three-dimensional partial image data is generated and displayed on the display device (step S73). Thereafter, the process proceeds to step S75.

  For example, when data as shown in FIG. 16 is stored in the partial image data storage unit 16, a display instruction including designation of the patient ID “0000000001” and the examination date “20090201” is received, and the abnormal shadow candidate of the area number 3 is received. Is specified, “3DSubImage002-3” is read as the current partial image data, and “3DSubImage001-2” is read as the previous partial image data. Then, for example, a three-dimensional partial image as shown in FIG. 17 is displayed. In FIG. 17, a 3D image 1701 generated based on “3DSubImage002-3” and a 3D image 1702 generated based on “3DSubImage001-2” are displayed.

  Then, the output unit 18 determines whether processing has been completed for all abnormal shadow candidates related to the display instruction (step S75). If the processing has not been completed for all abnormal shadow candidates related to the display instruction (step S75: No route), the process returns to step S63 and the above-described processing is repeated. On the other hand, when the processing is completed for all abnormal shadow candidates related to the display instruction (step S75: Yes route), the output unit 18 reads the inspection image data related to the display instruction from the inspection image data storage unit 11, and the three-dimensional Three-dimensional image data is generated and displayed by performing image processing (step S77). That is, after displaying the 3D partial image of the abnormal shadow candidate, the entire 3D image is displayed. If the previous inspection image data exists, the previous three-dimensional image is also displayed. For example, when this step is performed, the entire three-dimensional images 1711 and 1712 are displayed on the screen shown in FIG. Then, this process ends.

  Note that a list of abnormal shadow candidates may be presented to the doctor, and the doctor may select an abnormal shadow candidate to be displayed. In this case, the three-dimensional partial image of the selected abnormal shadow candidate may be displayed first, and then the entire three-dimensional image may be displayed.

  By performing the processing as described above, it is possible to display a three-dimensional partial image of an abnormal shadow candidate without reading all of the plurality of tomographic images included in the inspection image data. For the doctor, the three-dimensional partial image of the abnormal shadow candidate can be quickly confirmed.

  Although one embodiment of the present technology has been described above, the present technology is not limited to this. For example, the functional block diagram of the image diagnosis support apparatus 1 described above does not necessarily correspond to an actual program module configuration.

  Further, the configuration of each table described above is an example, and the configuration as described above is not necessarily required. Further, in the processing flow, the processing order can be changed if the processing result does not change. Further, it may be executed in parallel.

  The present embodiment can be summarized as follows.

  In this image diagnosis support method, for each of a plurality of tomographic images obtained by imaging a subject, a step of searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image, and a virtual three-dimensional image in which the plurality of tomographic images are arranged A partial area including a candidate for an abnormal shadow identified by an abnormal shadow candidate area detected from each tomographic image, and pixel data corresponding to the identified partial area from a plurality of tomographic images Are extracted as partial image data, and the extracted partial image data and the position information of the partial area in the virtual three-dimensional image are stored in the storage device in association with each other.

  In this way, since the pixel data of the region including the abnormal shadow candidate is extracted as the partial image data and stored in the storage device, the three-dimensional partial image of the abnormal shadow candidate can be displayed from the partial image data. It becomes like this. That is, when displaying the three-dimensional partial image of the abnormal shadow candidate, it is not necessary to read the image data for all the tomographic images, and the three-dimensional partial image of the abnormal shadow candidate can be displayed quickly.

  Further, it may further include a step of reading out the partial image data from the storage device in accordance with a display instruction from the user, generating three-dimensional partial image data based on the partial image data, and displaying it. In this way, for example, a doctor who is a user can quickly confirm a three-dimensional partial image of an abnormal shadow candidate.

  Furthermore, when there are a plurality of tomographic images captured in the past for the same subject, past partial image data extracted from the tomographic images captured in the past and the extracted portion is regarded as the same as the partial image data A step of determining whether or not past partial image data is already stored in the storage device, and if the past partial image data is not stored in the storage device, the past partial image data is extracted from a plurality of past tomographic images and stored in the storage device. You may make it further contain the step which stores, The step which stores the data for matching partial image data and past partial image data in a memory | storage device. In this way, when there is a tomographic image taken in the past, the partial image data and the past partial image data are stored in the storage device in association with each other, so the past three-dimensional portion of the abnormal shadow candidate Images can be displayed promptly.

  Further, in response to a display instruction from the user, partial image data and past partial image data corresponding to the partial image data are read from the storage device, and three-dimensional partial image data is generated based on the partial image data. A step of generating past three-dimensional partial image data based on the data and displaying the three-dimensional partial image data and the past three-dimensional partial image data may be further included. In this way, for example, a doctor who is a user can quickly confirm a past three-dimensional partial image of an abnormal shadow candidate.

  In the determination step, when the distance between the predetermined reference points in the extracted part is less than a predetermined threshold, the extracted part may be regarded as the same.

  Further, in the determination step, if there is a deviation between the position of the subject in the plurality of tomographic images and the position of the subject in the plurality of tomographic images taken in the past, this represents a deviation in the position of the subject. In some cases, a position correction value is calculated, and the position of a predetermined reference point is corrected using the position correction value. In this way, since a predetermined reference point (for example, center coordinates) is corrected using the position correction value, there is a shift in the position of the subject between the tomographic image captured this time and the tomographic image captured in the past. Even if it occurs, the identity of the extracted part can be appropriately determined.

  A program for realizing the diagnostic imaging support apparatus 1 together with hardware can be created. The program can be a storage medium or storage device such as a flexible disk, a CD-ROM, a magneto-optical disk, a semiconductor memory, or a hard disk. Stored in The intermediate processing result is temporarily stored in a storage device such as a main memory.

  As shown in FIG. 18, the diagnostic imaging support apparatus 1 includes a memory 2501 (storage unit), a CPU 2503 (processing unit), a hard disk drive (HDD) 2505, a display control unit 2507 connected to the display device 2509, and a removable device. A drive device 2513 for the disk 2511, an input device 2515, and a communication control unit 2517 for connecting to a network are connected by a bus 2519. Application programs including the OS and the Web browser are stored in the HDD 2505, and are read from the HDD 2505 to the memory 2501 when executed by the CPU 2503. If necessary, the CPU 2503 controls the display control unit 2507, the communication control unit 2517, and the drive device 2513 to perform necessary operations. Further, data in the middle of processing is stored in the memory 2501 and stored in the HDD 2505 if necessary. Such a computer realizes various functions as described above by organically cooperating hardware such as the CPU 2503 and the memory 2501 described above with the OS and necessary application programs.

  The following supplementary notes are further disclosed with respect to the embodiments including the above examples.

(Appendix 1)
For each of a plurality of tomographic images obtained by imaging a subject, searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Storing the extracted partial image data and position information of the partial area in the virtual three-dimensional image in association with each other;
Diagnostic support program for causing a computer to execute the program.

(Appendix 2)
When there are a plurality of tomographic images captured in the past for the same subject, past partial image data extracted from the plurality of tomographic images captured in the past and the extracted portion is regarded as the same as the partial image data Determining whether or not is already stored in the storage device;
If the past partial image data is not stored in the storage device, the past partial image data is extracted from the plurality of tomographic images taken in the past and stored in the storage device;
Storing in the storage device data for associating the partial image data with the past partial image data;
The diagnostic imaging support program according to appendix 1, for causing the computer to further execute the above.

(Appendix 3)
The supplementary note 1 for causing the computer to further execute a step of reading the partial image data from the storage device in accordance with a display instruction from the user, generating three-dimensional partial image data based on the partial image data, and displaying the three-dimensional partial image data. Image diagnosis support program.

(Appendix 4)
In response to a display instruction from a user, the partial image data and the past partial image data corresponding to the partial image data are read from the storage device, and three-dimensional partial image data is generated based on the partial image data. The image according to appendix 2, for causing the computer to further execute a step of generating past three-dimensional partial image data based on the past partial image data and displaying the three-dimensional partial image data and the past three-dimensional partial image data. Diagnosis support program.

(Appendix 5)
The image diagnosis support program according to claim 2, wherein, in the determination step, if the distance between predetermined reference points in the extracted part is less than a predetermined threshold, the extracted parts are considered to be the same.

(Appendix 6)
In the determination step, if there is a deviation between the position of the subject in the plurality of tomographic images and the position of the subject in the plurality of tomographic images taken in the past, the position of the subject is determined. The image diagnosis support program according to claim 5, wherein a position correction value representing a deviation is calculated, and the position of the predetermined reference point is corrected using the position correction value.

(Appendix 7)
For each of a plurality of tomographic images obtained by imaging a subject, searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Storing the extracted partial image data and position information of the partial area in the virtual three-dimensional image in association with each other;
A diagnostic imaging support method executed by a computer.

(Appendix 8)
For each of a plurality of tomographic images obtained by imaging a subject, a means for searching for an abnormal shadow candidate region that is regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Means for extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Means for associating the extracted partial image data with positional information of the partial area in the virtual three-dimensional image in a storage device;
An image diagnosis support apparatus.

DESCRIPTION OF SYMBOLS 1 Image diagnosis assistance apparatus 11 Test | inspection image data storage part 12 Input part 13 Abnormal shadow candidate extraction part 14 Abnormal shadow candidate list table storage part 15 Partial image data extraction part 16 Partial image data storage part 17 Matching process part 18 Output part

Claims (6)

For each of a plurality of tomographic images obtained by imaging a subject, searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Storing the extracted partial image data and position information of the partial area in the virtual three-dimensional image in association with each other;
When there are a plurality of tomographic images photographed in the past for the same subject, the distance from a predetermined reference point extracted from the plurality of tomographic images photographed in the past and the partial image data extraction site is A determination step of determining whether past partial image data relating to an extraction part having the predetermined reference point that is less than a predetermined threshold is already stored in the storage device;
If the past partial image data is not stored in the storage device, the past partial image data is extracted from the plurality of tomographic images taken in the past and stored in the storage device;
Storing in the storage device data for associating the partial image data with the past partial image data;
Diagnostic support program for causing a computer to execute the program. In the determination step, if there is a deviation between the position of the subject in the plurality of tomographic images and the position of the subject in the plurality of tomographic images taken in the past, the position of the subject is determined. A position correction value representing a deviation is calculated, and the position of the predetermined reference point in the extracted portion of the partial image data is corrected using the position correction value.
The diagnostic imaging support program according to claim 1. In accordance with the display instruction from the user, from said storage device reads the partial image data to generate 3-dimensional partial image data based on the partial image data, according to claim 1 for executing the computer to further step of displaying or 2. The diagnostic imaging support program according to 2. In response to a display instruction from a user, the partial image data and the past partial image data corresponding to the partial image data are read from the storage device, and three-dimensional partial image data is generated based on the partial image data. based on past partial image data generated in the past 3 dimensional partial image data, the 3-dimensional partial claims for image data and further a step of the display and the past three-dimensional partial image data to be executed by the computer 1 or 2 The diagnostic imaging support program described. For each of a plurality of tomographic images obtained by imaging a subject, searching for an abnormal shadow candidate region regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Storing the extracted partial image data and position information of the partial area in the virtual three-dimensional image in association with each other;
When there are a plurality of tomographic images photographed in the past for the same subject, the distance from a predetermined reference point extracted from the plurality of tomographic images photographed in the past and the partial image data extraction site is A determination step of determining whether past partial image data relating to an extraction part having the predetermined reference point that is less than a predetermined threshold is already stored in the storage device;
If the past partial image data is not stored in the storage device, the past partial image data is extracted from the plurality of tomographic images taken in the past and stored in the storage device;
Storing in the storage device data for associating the partial image data with the past partial image data;
A diagnostic imaging support method executed by a computer. For each of a plurality of tomographic images obtained by imaging a subject, a means for searching for an abnormal shadow candidate region that is regarded as a lesion in the tomographic image;
A partial region in the virtual three-dimensional image in which the plurality of tomographic images are arranged, the partial region including the abnormal shadow candidate specified by the abnormal shadow candidate region detected from each of the tomographic images, Means for extracting pixel data corresponding to the specified partial area as partial image data from a plurality of tomographic images;
Means for associating the extracted partial image data with positional information of the partial area in the virtual three-dimensional image in a storage device;
When there are a plurality of tomographic images photographed in the past for the same subject, the distance from a predetermined reference point extracted from the plurality of tomographic images photographed in the past and the partial image data extraction site is Determination means for determining whether past partial image data relating to an extraction part having the predetermined reference point that is less than a predetermined threshold is already stored in the storage device;
Means for extracting the past partial image data from the plurality of tomographic images taken in the past and storing the past partial image data in the storage device when the past partial image data is not stored in the storage device;
Means for storing in the storage device data for associating the partial image data with the past partial image data;
An image diagnosis support apparatus.

Images