JP5019220B2 - Medical image display device and medical image display program - Google Patents

Medical image display device and medical image display program Download PDF

Info

Publication number
JP5019220B2
JP5019220B2 JP2007262541A JP2007262541A JP5019220B2 JP 5019220 B2 JP5019220 B2 JP 5019220B2 JP 2007262541 A JP2007262541 A JP 2007262541A JP 2007262541 A JP2007262541 A JP 2007262541A JP 5019220 B2 JP5019220 B2 JP 5019220B2
Authority
JP
Japan
Prior art keywords
portion
image display
cross
luminance
abnormal shadow
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
JP2007262541A
Other languages
Japanese (ja)
Other versions
JP2009089847A (en
Inventor
アルトウロ・カルデロ
恭子 佐藤
重治 大湯
仁 山形
敦子 杉山
Original Assignee
東芝メディカルシステムズ株式会社
株式会社東芝
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 東芝メディカルシステムズ株式会社, 株式会社東芝 filed Critical 東芝メディカルシステムズ株式会社
Priority to JP2007262541A priority Critical patent/JP5019220B2/en
Publication of JP2009089847A publication Critical patent/JP2009089847A/en
Application granted granted Critical
Publication of JP5019220B2 publication Critical patent/JP5019220B2/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to a medical image display device and a medical image display program used in diagnosing an abnormal shadow candidate region included in a medical image.

  In recent years, for the purpose of reducing oversight of a lesioned part due to interpretation by a doctor or the like, a lesioned part is automatically obtained by performing image processing on medical image data generated by an X-ray apparatus or an X-ray CT apparatus in accordance with digitization of a medical image. Has been devised (Computed-Aided Diagnosis: hereinafter referred to as CAD) (see Patent Document 1, for example). With such a CAD, conventionally, when interpreting on a film image, differences in judgment criteria of doctors and the like, lack of experience, lack of clinical data (such as being indistinguishable from surrounding tissues with only one-way images), human Oversight of the lesion due to mistakes (distraction of attention, optical illusion, etc.) was reduced, and it became possible to extract abnormal shadow candidate regions with a certain degree of accuracy.

  Currently, diagnosis using CAD takes into account the validity of benign / malignant judgment by CAD, and a doctor or the like looks at a medical image to check each of the abnormal shadow candidate areas extracted by CAD. The method is taken. In the case of a CT image, an imaging section (Axial section) is confirmed while feeding the section, and a treatment policy is determined for an abnormal shadow candidate region that can be clearly determined to be benign or malignant. On the other hand, for abnormal shadow candidate areas where it is difficult to judge benign or malignant, a doctor or the like manually rotates, moves, or enlarges the CT image to generate an image in an arbitrary cross section, and the generated arbitrary cross section image is used for shadowing. After confirming the above, the benign / malignant decision and the treatment policy are determined for the shadow. The number of CT images generated for lung cancer diagnosis is about 300 to 1000 per imaging, and the number of abnormal shadow candidate regions extracted by CAD is as large as several to several tens. Therefore, for the purpose of further improving the efficiency of interpretation work and reducing oversight of malignant shadows, the following techniques for devising a method of re-extracting CAD extraction results under predetermined conditions and a display method have been disclosed.

  1. Only the extraction information of abnormal shadow candidate areas that are difficult to determine whether they are true-positive or false-positive based on image feature quantities or abnormal shadow candidate areas with low visibility are provided, and image feature quantities (abnormal shadows) calculated in the process are provided. The display order is determined based on the area of the candidate area, contrast with the surrounding area, shape, and at least one feature amount from the distance from the edge of the image to the extraction position), and the abnormal shadow candidate areas are sequentially displayed according to the determined order. (For example, refer to Patent Document 2).

  2. In order to make it possible to easily grasp the position of the extracted abnormal shadow candidate area, the position of the abnormal shadow candidate area is pointed out with a marker such as an arrow and displayed. When a large number of abnormal shadow candidate areas are concentrated in one place, the abnormal shadow candidate areas to be connected without the overlapping of the markers are regarded as one candidate, and the outline of the connected area is displayed as a marker (for example, see Patent Document 3). ).

  3. The abnormal shadow candidate area extracted from the entire image is subjected to pixel density conversion, and extracted and displayed in a display area different from the entire image (see, for example, Patent Document 4).

Conventionally, the follow-up confirmation of the abnormal shadow candidate area extracted by CAD is performed by the medical image in which the abnormal shadow candidate area is displayed and the feature amount of the abnormal shadow candidate area displayed in text or table (calculated in the CAD extraction process). Value). For example, the image processing apparatus determines the display order for a plurality of abnormal shadow candidate areas according to the respective feature amounts, and sequentially moves the Axial cross section to display the abnormal shadow candidate areas. Therefore, a doctor or the like mainly confirms the shape of the abnormal shadow candidate region on the Axial section by an operation of moving the Axial section. That is, depending on the unevenness of the abnormal shadow candidate region, the low luminance, and the high luminance region, there is a possibility of overlooking the malignant findings such as the unevenness, the low luminance, and the high luminance region on the axial cross section. In addition, when creating a medical image in an arbitrary cross section where a medical doctor arbitrarily rotates, moves, and enlarges a medical image, the operation becomes complicated and takes time, and the determination of the cross section position is not reproducible. Problems remain in terms of operation.
JP 2006-239005 A JP 2006-325640 A JP 2003-265450 A Japanese Patent Laid-Open No. 2002-028154

  An object of the present invention is to provide a medical image display device and a medical image display program that can improve diagnosis accuracy and reduce an operation burden in the follow-up confirmation of an abnormal shadow candidate region.

  In order to achieve the above object, the medical image display device of the present invention, in one aspect, a storage unit that stores volume data relating to a subject, and an abnormal shadow candidate area specification that specifies an abnormal shadow candidate area included in the volume data Section, a concavo-convex extraction section for extracting a concave portion and a convex portion of the specified abnormal shadow candidate region, and data of a cross-sectional image relating to a cross section including at least one portion of the extracted concave portion and the convex portion And an image display unit for displaying the generated cross-sectional image.

  In another aspect, the medical image display device of the present invention is a storage unit that stores volume data related to a subject, an abnormal shadow candidate region specifying unit that specifies an abnormal shadow candidate region included in the volume data, and the specified A low-brightness extraction unit that extracts a low-brightness part and a high-brightness part of the abnormal shadow candidate area, and cross-sectional image data relating to a cross section including at least one part of the extracted low-brightness part and high-brightness part And an image display unit for displaying the generated cross-sectional image.

  In one aspect, the medical image display program according to the present invention includes an abnormal shadow candidate area specifying function for specifying an abnormal shadow candidate area included in volume data relating to a subject, and the specified abnormal shadow candidate area. A concave / convex extracting function for extracting a concave portion and a convex portion, an image generating function for generating cross-sectional image data relating to a cross section including at least one portion of the extracted concave portion and convex portion, and the generated cross section And an image display function for displaying an image.

  According to another aspect of the medical image display program of the present invention, an abnormal shadow candidate area specifying function for specifying an abnormal shadow candidate area included in the volume data related to the subject, and the specified abnormal shadow candidate specified in the control means of the computer A low and high luminance extraction function for extracting a low luminance portion and a high luminance portion of an area, and an image generation function for generating cross-sectional image data relating to a cross section including at least one portion of the extracted low luminance portion and high luminance portion And an image display function for displaying the generated cross-sectional image.

  According to the present invention, it is possible to improve the diagnostic accuracy and reduce the operation burden in the additional confirmation of the abnormal shadow candidate region.

  Embodiments of the present invention will be described below with reference to the drawings. The medical image display apparatus according to the present embodiment identifies a nodule region that is a region having a possibility of an abnormal shadow (hereinafter referred to as an abnormal shadow candidate region) from a medical image related to the chest of the subject, and the identified nodule region Are extracted and displayed on the concave portion, the convex portion, the low luminance portion, and the high luminance portion. The concave portion or the convex portion is a basis for determining whether the nodule is cancer. The low luminance portion or the high luminance portion is a portion that exists in the nodule region and has a luminance value lower or higher than the luminance value of the nodule region. Low brightness is attributed to the hollowing out of the nodules and air bronco. The bright part is due to calcification of the nodule. That is, a nodule region having a concave portion, a convex portion, a low luminance portion, or a high luminance portion is highly likely to be medically malignant. Therefore, the technology to extract the part showing malignancy such as the concave part and the convex part of the nodule area, the low luminance part, the high luminance part, etc., determine the cross section that remarkably shows the malignant part and display the cross section is very is important.

  FIG. 1 is a diagram illustrating a configuration of a medical image display apparatus 1. As shown in FIG. 1, a medical image display apparatus 1 is a volume of a subject generated by a medical image generation apparatus such as an X-ray apparatus, an X-ray CT apparatus, or an MRI, with a control unit 10 having a CPU and a memory as a center. A storage unit 11 for storing data, an abnormal shadow candidate region specifying unit 13 for specifying an abnormal shadow candidate region included in the volume data, an unevenness extracting unit 15 for extracting concave portions and convex portions included in the abnormal shadow candidate region, abnormal A low / high luminance extraction unit 17 that extracts a low luminance portion and a high luminance portion included in the shadow candidate region, an axis determination unit 19 that determines an axis related to a concave portion, a convex portion, a low luminance portion, or a high luminance portion, and the determined axis A cross section determining unit 21 for determining the position and direction of the display cross section based on the image, an image generating unit 23 for generating cross section image data based on the determined direction and position of the display cross section, Display order determining unit 25 which determines the shown order, the image display unit 27, a mouse or the operation unit 29 such as a keyboard that displays the generated cross-sectional image, and a city.

  The medical image display apparatus 1 is connected to a medical image generation apparatus over a network via a communication line as a device integrated with a medical image generation apparatus such as an X-ray apparatus, an X-ray CT apparatus, or an MRI. It is provided as a device or as a device not connected to the network. The medical image display device 1 is typically a computer device such as a PC (Personal Computer).

  Hereinafter, the operation of the medical image display apparatus 1 will be described. The volume data may include a plurality of nodule areas. When the volume data includes a plurality of nodule regions, the medical image display device 1 extracts and displays display objects such as a concave portion, a convex portion, a low luminance portion, and a high luminance portion for each of the plurality of nodule regions. Therefore, display rules for a plurality of display objects to be extracted are necessary. First, display rules will be described.

  As shown in FIG. 2, there are two display rules. First, the display order of the display rule A is determined according to a predetermined rule described later for all the nodule regions. Next, the display order is determined for the display target included in the nodule area as the next hierarchy. As a specific display example in the case of the display rule A, as shown in FIG. 2A, first, the entire nodule region numbered 1 is displayed, and then the number 1-1 of the nodule region number 1 is displayed. , The display object of number 1-2,..., The display object of number 1-4 are displayed in order. When the display object of the nodule area of number 1 is displayed, the nodule area of number 2 is displayed next, and the display object of the nodule area of number 2 is sequentially displayed according to the number. With this display rule, all nodule areas and all display objects are displayed.

  As shown in FIG. 2B, the display order of the display rule B is determined according to a predetermined rule for all the nodule regions and all the display objects. First, the nodule areas are displayed in numerical order, and then the display object is displayed.

  The display order is determined by the display order determination unit 25. When the nodule region is displayed (display type A), the cross section where the maximum number of display objects is drawn is displayed. The display order of the nodule areas is the order in which the number of display objects on the display section is large or small. When displaying a display target (display type B), a cross section including one display target is displayed. The display order of the display objects is, for example, the order of large or small feature amounts regarding the display objects. For example, as the feature amount related to the unevenness, the area of the concave portion or the convex portion on the display cross section, the curved distance of the concave portion or the vertex of the convex portion (curve distance will be described later), the acute angle (surface of the concave portion or convex portion) Curvature), the volume of the concave portion or the convex portion. In addition, the feature quantity related to luminance includes the area on the display cross section of the low luminance portion or the high luminance portion, the volume connected with the same luminance, and the like. In addition, the display order can be determined based on the feature amount obtained from the shape and the luminance value. A method for calculating individual feature amounts will be described later.

  Note that the nodule region, display rule for display object, and display type according to the present embodiment are not limited to the above example, for example, the display object includes the maximum area display object and the display object displays the maximum number of cross sections, etc. Various combinations of display rules A and B and display types A and B are possible.

  It is assumed that the display rule and the feature quantity to be displayed are set before the operation of the medical image display apparatus 1 shown in FIG. 3 is performed.

  Hereinafter, a schematic procedure of the operation of the medical image display apparatus 1 will be described with reference to FIG.

  First, in step S <b> 1, the control unit 10 reads volume data generated by a medical image generation apparatus such as an X-ray apparatus, an X-ray CT apparatus, or an MRI apparatus from the storage unit 11.

  In step S2, the control unit 10 causes the abnormal shadow candidate region specifying unit 13 to perform an abnormal shadow candidate region specifying process. In the abnormal shadow candidate area specifying process, the abnormal shadow candidate area specifying unit 13 can specify a nodule area as an abnormal shadow candidate area included in the volume data by a known technique. Known techniques include, for example, Japanese Patent Application Laid-Open No. 7-299053 and paper: CT for lung cancer screening (LSCT) (Toshiaki Okumura, Michiko Miwa, Nobuaki Mado, Koji Yamamoto, Mitsumi Matsumoto, Yukio Kanno , Takeshi Iinuma, Toru Matsumoto, Journal of Computer Aided Image Diagnosis, Vol. 2, No. 3, 1998). The number of abnormal shadow candidate regions included in the volume data may be one or plural. It may also be zero. Therefore, the number of nodule regions specified in step S1 may be one, plural, or zero. If zero, the process ends.

  In step S3, the control unit 10 controls the image generation unit 23 to perform image generation processing. In the image generation process, the image generation unit 23 generates display image data in which all the identified nodule regions are drawn. For example, the display image is an MPR image, a 3D image, or the like. When the display image data is generated, the control unit 10 causes the image display unit 27 to display the display image. In the image displayed in step S3, the entire identified nodule region is depicted. In addition, various analysis results for the nodule area calculated when specifying the nodule area are displayed in a table, a graph, or the like. In this case, the conventional techniques described in Japanese Patent Laid-Open Nos. 2003-265450, 2002-28154, 2004-73488, and the like may be used.

  In step S <b> 4, the control unit 10 waits for the operator to select whether to extract the concavo-convex part of the nodule region or the low-high brightness part via the operation part 29. When the selection for extracting the uneven portion is made, the control unit 10 proceeds to step S5. When the selection to extract the low and high luminance part is made, the control unit 10 proceeds to step S8. Note that whether to extract the uneven portion of the nodule region or the low and high luminance portion may be set in advance. In this case, the control unit 10 automatically proceeds to step S5 or step S8 according to the setting without waiting for selection by the operator. Hereinafter, the case where the uneven portion is selected and the case where the low and high luminance portion is selected will be individually described. First, the case where the uneven part is selected will be described.

(Unevenness)
In step S <b> 5, the control unit 10 causes the unevenness extraction unit 15 to perform extraction processing for the concave portion and the convex portion. In the extraction processing of the concave portion and the convex portion, the concave and convex extraction unit 15 extracts the concave portion and the convex portion of the nodule region from the identified nodule region. There are two types of extraction processing of the concave portion and the convex portion, a method based on the curve distance and a method based on the surface curvature. First, extraction processing of the concave portion and the convex portion based on the curve distance will be described according to the processing flow shown in FIG. The definition of the curve distance will be described later. The extraction process of the concave portion and the convex portion is performed for all the nodule regions specified in step S2.

  In step SA1, the concavo-convex extraction unit 15 extracts a nodule region including a concave portion and a convex portion from the volume data (step SA1). Specifically, the following procedure is performed.

  Procedure SA1-1: In step S2, as shown in FIG. 6, a substantially spherical region R1 centering on the center or center of gravity (hereinafter referred to as a reference point) O of the nodule region KR is specified. The substantially spherical region R1 does not include all convex portions present on the surface of the nodule region KR. Usually, the length of the convex part coming out from the nodule is less than 20 mm, and if it is longer than that, the possibility of feeding blood vessels passing through the nodule increases. Therefore, the unevenness extraction unit 15 sets a substantially spherical region R2 having a radius approximately 20 [mm] longer than the radius of the substantially spherical region R1 with the reference point of the substantially spherical region R1 as the center, and extracts the set substantially spherical region R2. To do.

  Procedure SA1-2: The unevenness extraction unit 15 uses the luminance value that is a boundary between the luminance value of the nodule region KR and the luminance value of the region other than the nodule region KR as a threshold value, and extracts the nodule region KR from the extracted sphere region R2. To extract. At this time, the unevenness extraction unit 15 replaces the luminance value of the low-luminance portion in the nodule region KR with the luminance value of the nodule region using a phase unwrapping method such as a Flood Fill method. Specifically, in order to extract the nodule region KR including the low luminance part existing in the nodule region KR, a search point is set and set in the low luminance part using the luminance value of the nodule region KR as a threshold value. A process of replacing the luminance value of the area connected to the search point with the luminance value of the nodule area is performed.

  This completes the process of step SA1.

  In step SA2, the unevenness extraction unit 15 identifies the vertices of the concave portion and the convex portion included in the nodule region extracted in step SA1. Typically, the unevenness extraction unit 15 counts the number of voxels in the adjacent nodule region for each of all surface voxels in the nodule region. The surface voxel having the maximum number of adjacent voxels is specified as the vertex of the concave portion, and the surface voxel having the minimum number of adjacent voxels is specified as the vertex of the convex portion.

  In step SA3, the unevenness extraction unit 15 calculates the curve distance for all the surface voxels specified in step SA1. The curve distance is the length of a path from a surface voxel having a nodule region to the reference point of the nodule region through the inside of the nodule region. That is, the curve distance is a distance along the shape of the nodule region between a certain surface voxel and the reference point of the nodule region, and is an index regarding the shape of the unevenness.

For example, the curve distance of the surface voxel P1 of the nodule region KR having the convex portion T1 shown in FIG. 6 is calculated by the following procedure.
Procedure SA3-1: First, the unevenness extraction unit 15 calculates a line segment distance OP1 between the surface voxel P1 and the reference point O of the nodule region. This surface voxel P1 is set as the first reference voxel.

  Step SA3-2: For the voxels Wi of all the nodule regions adjacent to the reference voxel P1, the unevenness extraction unit 15 performs processing on a plane including the line segment distance DOWi of the line segment OWi, the line segment OP1, and the line segment OWi. An angle α1i between the line segment OP1 and the line segment OWi is calculated.

  Procedure SA3-3: A voxel having an angle α1i close to 0 and a distance DOWi closest to the line segment distance OP1 is specified. The identified voxel is set as the next reference voxel P2.

  Procedure SA3-4: Procedure SA-1 to procedure SA-3 are also performed on the reference voxel P2, and the next reference voxel P3 is specified. Thereafter, the same processing is repeated for the reference voxels P3, P4,... Pn-1, and is repeated until the voxel O at the center of the nodule region is specified as the reference voxel Pn in step 3.

  Procedure SA3-5: The sum of the distances of the line segments of the plurality of identified reference voxels P1, P2,... Pn is set as the curve distance L1 of the surface voxel P1.

  Procedure SA3-1 to procedure SA3-5 are performed for all surface voxels. The curve distance of each surface voxel is stored in association with the coordinates of each surface voxel expressed in an orthogonal coordinate system. Above, the process of step SA3 is complete | finished.

  In step SA4, the control unit 10 determines whether to generate a concavo-convex map. An uneven | corrugated map is an image which shows distribution of the curve distance of a surface voxel. By utilizing this concavo-convex map, it becomes possible to appropriately extract the concave portion and the convex portion from the nodule region. Whether to generate the uneven map may be set in advance, or may be designated by the operator via the operation unit 29. If the control unit 10 determines to generate a concavo-convex map, the process proceeds to step SA5, and if it is determined not to generate, the process proceeds to step SA8.

  In step SA5, the unevenness extraction unit 15 generates an unevenness map based on the plurality of curve distances calculated in step SA3. Hereinafter, a procedure for generating the unevenness map will be described. The coordinates of the surface voxel in the orthogonal coordinate system are expressed as f (x, y, z). The curve distance d of the surface voxel at the coordinates f (x, y, z) is expressed as d = f (x, y, z). A polar coordinate system centered on the center of the nodule region is expressed as g (r, θ, φ). The curve distance d of the surface voxel at the coordinates g (r, θ, φ) is expressed as d = g (r, θ, φ).

  Procedure SA5-1: The concave / convex extraction unit 15 uses the polar distance centered on the reference point O of the nodule region KR, with the curve distance d = f (x, y, z) expressed in the orthogonal coordinate system as shown in FIG. A curve distance d = g (θ, φ) having coordinates obtained by deleting information on the distance r from the system is converted. When there are a plurality of surface voxels at the coordinates g (θ, φ), the one having the larger curve distance d is adopted.

  Procedure SA5-2: The unevenness extracting unit 15 generates a contour map-like image (unevenness map) having the horizontal axis as the polar angle θ, the vertical axis as the azimuth angle φ, and the pixel value as the curve distance d. Moreover, it is good also as an image colored by the value of the curve distance so that an unevenness | corrugation may become clear.

  This completes the process of step SA5.

  In step SA6, the control unit 10 causes the image display unit 27 to display the uneven map generated in step SA5.

  In step SA <b> 7, the control unit 10 waits for the operator to specify the curve distance that is regarded as a flat portion of the nodule region by looking at the displayed unevenness map via the operation unit 29. The curve distance may be specified by a single value or a range. When the curve distance value is designated, the control unit 10 sets the designated curve distance value as a threshold value.

  On the other hand, if it is determined in step SA4 that a concave / convex map is not generated (step SA4: NO), the concave / convex extraction unit 15 sets a threshold value based on the plurality of curve distances calculated in step SA3. . For example, as one method, the unevenness extraction unit 15 calculates an average value by an arithmetic average of a plurality of curve distances or a weighted average weighted by the frequency of the curve distances. A predetermined width (for example, −2 to +2 mm) around the calculated average value A is set as a threshold value.

  In step SA9, the unevenness extraction unit 15 extracts the concave portion and the convex portion from the nodule region based on the curve distance set in step SA7 or step SA8. For example, as one method, the concavo-convex extraction unit 15 uses a set threshold as a radius, specifies voxels in a substantially spherical region centered on a reference point of a nodule region, and binarizes it. Separately, the voxels in the nodule region are binarized. Based on the difference between the binarized voxel in the substantially spherical region and the voxel in the nodule region, data on the concave portion and the convex portion of the nodule region is generated. For example, the substantially spherical region is subtracted from the nodule region, and voxels having a positive value are defined as convex portions and voxels having a negative value are defined as concave portions. When a threshold value with a width is set, for example, a substantially spherical region whose radius is the maximum value of the threshold value is subtracted from the nodule region, a voxel having a positive value is defined as a convex portion, and the threshold value A nodule region is subtracted from a substantially spherical region having a radius of the minimum value, and a voxel having a positive value is defined as a concave portion. The extracted concave portion and convex portion are clustered (numbered) for each region to be connected. The extracted individual concave portions and convex portions include respective vertices.

  This completes step SA9, and the extraction processing of the concave portion and the convex portion based on the curve distance is completed.

  Next, the extraction processing of the concave portion and the convex portion based on the surface curvature will be described according to the flow of processing shown in FIG.

  In step SB1, the concavo-convex extraction unit 15 extracts a nodule region including a concave portion and a convex portion from the volume data by the same method as in step SA1.

  In step SB2, the unevenness extraction unit 15 specifies the vertices of the concave portion and the convex portion included in the nodule region by the same method as in step SA2.

  In step SB3, the unevenness extraction unit 15 divides the surface voxels of the nodule region into meshes, generates a plurality of mesh-like surface regions (hereinafter referred to as meshes), and calculates a surface curvature for each of the generated meshes.

  In step SB4, the unevenness extraction unit 15 determines whether each mesh is a mesh in a concave portion or a mesh in a convex portion based on the calculated plurality of surface curvatures.

  In step SB5, the unevenness extraction unit 15 extracts the concave portion and the convex portion from the nodule region based on the determination result in step SB4. The specific procedure of step SB4 and step SB5 is as follows.

  Procedure SB4and5-1: A mesh having a surface curvature having a large difference from the average value is extracted as a mesh in the concavo-convex part (although it is a concave part or a mesh in the convex part, which is not specified).

  Procedure SB4and5-2: For meshes other than those extracted in procedure SB4and5-1, the distance between each mesh and the nodule center is calculated, and the radius of the nodular approximate spherical portion is calculated from these values.

  Procedure SB4and5-3: The distance between each mesh and the nodule center is calculated for the mesh extracted in Procedure 1, and if the distance is larger than the radius of the nodular approximate spherical part, it is judged as a convex part, and when it is smaller, it is judged as a concave part. .

  Procedure SB4and5-4: A region between the mesh determined to be a concave portion and the surface of the approximately spherical portion is defined as a concave portion, and a region between the mesh determined to be a convex portion and the surface of the approximately spherical portion is extracted as a convex portion. .

  Thus, step SB5 is completed, and the extraction process of the concave portion and the convex portion based on the surface curvature is completed. If neither the concave portion nor the convex portion is extracted, the process of the medical image display device 1 ends.

  When the extraction process (step S5) of the concave portion and the convex portion based on the curve distance or the surface curvature is completed, the control unit 10 proceeds to the process of step S6.

  In step S <b> 6, the control unit 10 causes the axis determination unit 19 to perform axis determination processing. In the axis determination process, the axis determination unit 19 calculates a reference axis for determining the position and direction of the display cross section of the concave portion and the convex portion extracted in step S5. There are mainly two types of reference axes. When a plurality of concave portions and convex portions are displayed on one display cross section (display type A), the reference axis A which is the reference axis of the display cross section and individual concave portions or convex portions There is a reference axis B which is a reference axis of a display section in the case where the portions are individually displayed (display type B). Hereinafter, a method for calculating each reference axis will be described.

Reference axis A: As shown in FIG. 9 (a), the axis determination unit 19 makes the respective vertexes (u1, u2, t1, t1) for the respective concave portions (U1, U2) and convex portions (T1, T2). The voxels on the path (S1, S2, S3, S4) of the curved distance of t2) are specified. As shown in FIG. 9B, the axis determination unit 19 determines the distance to each voxel by the least square method with respect to the voxels on the path of each specified curve distance (S1, S2, S3, S4). A straight line existing at a position that minimizes is calculated, and the calculated straight line is set as a reference axis A.
Reference axis B: As shown in FIG. 10, the axis determining unit 19 starts from each vertex (u1, u2, t1, t2) for each concave portion (U1, U2) and convex portion (T1, T2). Voxels (referred to as end points) (uu1, uu2, tt1, tt2) having the maximum distance are identified. The axis determination unit 19 sets the axis passing through each vertex and end point as a reference axis B (BU1, BU2, BT1, BT2).

  In step S7, the control unit 10 causes the cross-section determining unit 21 to perform a cross-section determining process. In the cross section determination process, the cross section determination unit 21 determines the direction of the cross section based on the reference axis determined in step S6. The process of step S7 is performed for all the nodule areas specified in step S2. First, processing for determining the direction of the cross section based on the display type A, that is, the reference axis A will be described. First, the cross section determining unit 21 sets a cross section including the reference axis A through the nodule region. At this stage, the position of the display cross section is determined. Next, the cross section determination unit 21 rotates the set cross section around the reference axis A by a predetermined constant angle (for example, 1 °), and counts the number of concave portions and convex portions on the cross section at every constant angle. The cross section determining unit 21 calculates the direction of the cross section in which the number of the concave portions and the convex portions is maximum, and sets the cross section in that direction as the display cross section.

  Next, processing for determining the position and direction of the cross section based on the display type B, that is, the reference axis B will be described. The convex portion will be described as an example, but the same processing is performed for the concave portion. The cross section determination unit 21 sets a cross section including the reference axis B. The set cross section is rotated by a predetermined constant angle (for example, 1 °) around the reference axis B, and the area of the convex portion on the cross section is calculated at every constant angle. Alternatively, the convex portions on the cross section may be projected onto a cross section having a predetermined position and orientation (hereinafter referred to as a projected cross section) at regular intervals, and the area of the convex portion on the projected cross section may be calculated. The maximum area is specified from the calculated plurality of areas, and the maximum area is set as the area of the convex portion. And the cross-section determination part 21 calculates the direction of the cross section in the maximum area, and makes the cross section in the direction the display cross section regarding a convex part.

  In the above method, the direction of the cross section is determined based on the area of the convex portion and the concave portion, but may be determined based on the curve distance of the apex between the convex portion and the concave portion. Hereinafter, the calculation process of the direction of the cross section in that case will be described. First, the cross section determination unit 12 sets a cross section including the reference axis B. The cross section determination unit 12 rotates the set cross section by a predetermined constant angle around the reference axis A, and calculates a curve distance on the cross section at every constant angle. Alternatively, the curved route on the cross section may be projected on the projected cross section at regular intervals, and the curved distance of the curved route on the projected cross section may be calculated. The cross section determination unit 12 specifies the maximum curve distance from the calculated plurality of curve distances, and sets the maximum curve distance as the curve distance between the concave portion and the convex portion. Moreover, the cross-section determination part 12 makes the direction of the cross section in the maximum curve distance the direction of a cross section in the case of displaying a recessed part and a convex part separately.

  In step S8, the control unit 10 causes the display order determination unit 25 to perform display order determination processing. In the display order determination process, the display order determination unit 25 assigns numbers to the nodule regions in descending order of the maximum number of the concave portions and the convex portions calculated in step S7, and uses the number order as the display order. . Next, the display order determination unit 25 calculates feature amounts related to the concave and convex portions for the individual concave portions and the convex portions, and determines the display order of the individual concave portions and the convex portions based on the calculated feature amounts. As described above, the feature amount regarding the unevenness includes the area on the cross section of the unevenness, the curve distance of the peak of the unevenness (the depth of the unevenness), the acute angle of the unevenness, the volume of the unevenness, and the like.

Hereinafter, a method for calculating individual feature amounts will be described.
Uneven area: The method for calculating the uneven area has already been described in the description of the calculation process of the direction of the cross section, and will be omitted.
Curve distance of uneven vertex: Since the curve distance of the uneven vertex is already described in the description of the calculation process of the direction of the cross section, the description is omitted.
Sharp angle of irregularities: Calculate the curvature of the mesh including the apex of irregularities and set it as the acute angle of irregularities.
Concavity and convexity volume: The volume of the concavity and convexity is the sum of the extracted concave part or convex part.

  It is not necessary to calculate all the above four feature amounts, and any one of the preset feature amounts may be calculated. When the feature amounts are calculated for all the concave portions and the convex portions, the display order determining unit 25 numbers the concave portions and the convex portions in descending order of the characteristic amounts, and displays the numbers individually. Display order. When step S8 ends, the control unit 10 proceeds to step S13.

  Next, a process when the selection to extract the low-luminance portion and the high-luminance portion is made in step S4 will be described.

(Luminance)
In step S <b> 9, the control unit 10 causes the low / high luminance extraction unit 17 to perform the low / high luminance extraction process in response to selection of extracting the low luminance portion and the high luminance portion. In the low and high luminance extraction processing, the low and high luminance extraction unit 17 extracts the low luminance portion and the high luminance portion in the nodule region from the nodule region specified in step S1 by multi-value processing. Specifically, first, the low-brightness extraction unit 17 performs processing similar to that in step SA1, and a sphere having a radius that is the center of the same position as the sphere region R1 and is approximately 20 mm longer than the radius of the sphere region R1. A region R2 is set, and the set sphere region R2 is extracted. Next, the low-brightness extraction unit 17 performs multi-value processing on the nodule region in the sphere region R2, and separates the low-brightness portion, the high-brightness portion, and the other portions. Then, the low and high luminance extraction unit 17 extracts a plurality of low luminance portions and high luminance portions by performing clustering for each connected region. Note that if neither the low-luminance portion nor the high-luminance portion is extracted, the processing of the medical image display device 1 ends.

  In step S10, the control unit 10 causes the axis determination unit 19 to perform axis determination processing. In the axis determination process, the axis determination unit 19 calculates a reference axis of the low luminance portion and the high luminance portion extracted in step S10. There are mainly two types of reference axes. When a plurality of low-intensity parts and high-intensity parts are displayed in one section (display type A), the reference axis A, which is the reference axis of the section, and individual low-intensity parts or high-intensity parts There is a reference axis B that is a reference axis of a cross section in the case where the luminance portions are individually displayed (display type B). Hereinafter, a method for calculating each reference axis will be described.

  First, the axis determination unit 19 calculates the major axis in the extracted low-luminance part and high-luminance part. The calculated major axis is defined as a reference axis B. The axis determination unit 19 calculates a straight line that exists at a position that minimizes the distances to all the calculated reference axes by the least square method, and sets the calculated straight line as the reference axis A.

  In step S11, the control unit 10 causes the cross-section determining unit 21 to perform a cross-section determining process. In the cross section determination process, the cross section determination unit 21 determines the position and direction of the cross section based on the reference axis determined in step S10. First, processing for determining the position and direction of the cross section based on the display type A, that is, the reference axis A will be described. First, the cross section determination unit 21 sets a cross section including the reference axis A through the nodule region. At this stage, the position of the display cross section is determined. Next, the cross section determining unit 21 rotates the set cross section around the reference axis A by a predetermined constant angle (for example, 1 °), and counts the number of low luminance portions and high luminance portions on the cross section at every constant angle. . The cross section determination unit 21 calculates the direction of the cross section in which the number of low-luminance portions and high-luminance portions is maximum, and sets the cross section in that direction as the display cross section.

  Next, processing for determining the position and direction of the cross section based on the display type B, that is, the reference axis B will be described. The low luminance portion will be described as an example, but the same applies to the high luminance portion. First, the cross section determination unit 21 sets a cross section including the reference axis B. The cross section determination unit 21 rotates the set cross section by a predetermined constant angle around the reference axis B, and calculates the area of the low-luminance portion on the cross section at every constant angle. The cross-section determining unit 21 specifies the maximum area from the calculated plurality of areas, and sets the maximum area as the area of the low-luminance portion. Then, the direction of the cross section in the maximum area is calculated, and the cross section in that direction is set as the display cross section for the low luminance portion.

  In step S12, the control unit 10 causes the display order determination unit 25 to perform display order determination processing. In the display order determination process, the display order determination unit 25 assigns numbers to the nodule regions in descending order of the maximum number of the low-luminance portion and the high-luminance portion calculated in step S11. And Next, the display order determination unit 25 calculates a feature value related to the luminance for each low-luminance portion and high-luminance portion, and determines the display order of each low-luminance portion and high-luminance portion based on the calculated feature amount. As described above, the feature quantity related to luminance includes a low luminance portion, a volume of a high luminance portion, an area on a cross section, and the like. Further, the feature amount may be a depth of unevenness, an acute angle, a fluttering degree, or the like of each luminance portion based on the contours of the low luminance portion and the high luminance portion.

Hereinafter, a method for calculating individual feature amounts will be described.
Area between low-luminance portion and high-luminance portion: Since the method for calculating the area of the low-luminance portion has already been described in the description of the calculation process of the direction of the cross section, it will be omitted.
Volume of low-luminance portion and high-luminance portion: The voxel sum of the extracted low-luminance portion or high-luminance portion is used as the volume of the unevenness.

  It is not necessary to calculate all of the above two feature amounts, and any one of the preset feature amounts may be calculated. When the feature amounts are calculated for all the low-luminance portions and the high-luminance portions, the display order determining unit 25 numbers the low-luminance portions and the high-luminance portions in descending order of the feature amounts, and assigns the numbers individually. The display order when displaying on the screen.

  In step S <b> 13, the control unit 10 causes the image generation unit 23 to perform image generation processing. In the image generation process, the image generation unit 23 generates cross-sectional image data based on the position and direction of the display cross-section calculated in step S7 or step S11.

  In step S14, the control unit 10 causes the image display unit 27 to display the cross-sectional image generated in step S13 according to the display order determined in step S8 or step S12, as shown in FIG. When displaying a 3D image in a clipped state, a target grayscale image may be displayed on the cross-sectional image.

  Above, the process in this embodiment is complete | finished.

  According to the above configuration, the operator can rotate and move the display image with a display cross section that remarkably depicts a malignant part such as a concave portion, a convex portion, a low luminance portion, and a high luminance portion of the abnormal shadow candidate region. It is possible to automatically extract and display. Therefore, thanks to simple operation, the interpretation time is shortened and the probability of overlooking a malignant site is reduced, and the operator can instantly visually check the presence and extent of a malignant site in each abnormal shadow candidate region. It becomes possible. Thus, according to the present embodiment, it is possible to improve the diagnostic accuracy and reduce the operation burden in the additional confirmation of the abnormal shadow candidate region.

  Note that the method of determining the display cross section according to the present embodiment is not limited to the above example. For example, in the display type B, a cross section including the reference axis B and the center of the nodule region may be used as the display cross section. Further, the plane f including the reference axis B is set to fi (a, b, c, d) = Tbi, a plane expression that minimizes Σfi is calculated by the method of least squares, and a section related to the calculated plane expression is set as a display section. It's also good. Also, display the cross section. A cross-sectional image with thickness (MPR image with thickness) or a projection image with thickness (IP image with thickness) may be used.

  Note that each function according to the present embodiment can also be realized by installing a program for executing the processing in a computer such as a workstation and developing the program on a memory. At this time, a program capable of causing the computer to execute the technique is stored in a recording medium such as a magnetic disk (floppy (registered trademark) disk, hard disk, etc.), an optical disk (CD-ROM, DVD, etc.), or a semiconductor memory. It can also be distributed.

  Note that the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

The figure which shows the structure of the medical image display apparatus which concerns on embodiment of this invention. The figure which shows the display rule which concerns on this embodiment. The figure which shows the schematic procedure of the process which concerns on the medical image display apparatus of this embodiment. The figure which shows the schematic procedure of the extraction process of the part for a recessed part based on the curve distance which concerns on this embodiment, and a convex part. The figure for demonstrating step SA1 of FIG. The figure for demonstrating step SA3 of FIG. The figure for demonstrating step SA5 and step SA6 of FIG. The figure which shows the schematic procedure of the extraction process of the recessed part part and convex part based on the surface curvature which concerns on this embodiment. The figure for demonstrating the process which calculates the reference axis A in step S6 of FIG. The figure for demonstrating the process for calculating the reference axis B in step S6 of FIG. The figure which shows an example of the display cross section displayed in step S14 of FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Medical image display apparatus, 10 ... Control part, 11 ... Memory | storage part, 13 ... Abnormal shadow candidate area | region specific part, 15 ... Concavity and convexity extraction part, 17 ... Low-intensity extraction part, 19 ... Axis determination part, 21 ... Cross-section determination Reference numeral 23: Image generation unit 25: Display order determination unit 27: Image display unit 29: Operation unit

Claims (16)

  1. A storage unit for storing volume data relating to the subject;
    An abnormal shadow candidate area specifying unit for specifying an abnormal shadow candidate area included in the volume data;
    A concavo-convex extraction unit that extracts a concave portion and a convex portion of the specified abnormal shadow candidate region,
    An image generating unit that generates data of a cross-sectional image related to a cross section including at least one portion of the extracted concave portion and convex portion;
    An image display unit for displaying the generated cross-sectional image;
    A medical image display apparatus comprising:
  2. The concavo-convex extraction unit extracts the concave portion and the convex portion based on the feature amount related to the concavo-convex portion, and the image generation unit generates cross-sectional image data related to the cross section where the feature amount related to the concavo-convex portion is maximum or minimum. ,
    The medical image display device according to claim 1.
  3. The image generation unit is configured to determine the concave portion and the convex portion based on the area of each of the concave portion and the convex portion, or the value of the distance between the vertex of each of the convex portion and the concave portion and another point. Generating at least one cross-sectional image data for each;
    The image display unit displays the at least one cross-sectional image in a predetermined order;
    The medical image display device according to claim 2.
  4. An axis determining unit that determines a reference axis that passes through at least one of the concave portion and the convex portion based on the concave portion and the vertex of each convex portion;
    Further comprising
    The image generation unit generates the data of the at least one cross-sectional image related to a cross-section including the determined reference axis and having a maximum or minimum feature amount related to the unevenness.
    The image display unit displays data of the generated at least one cross-sectional image in a predetermined order;
    The medical image display device according to claim 2.
  5. The area of each of the concave portion and the convex portion, the curved distance of the concave portion and the convex portion, the acute angle of the concave portion and the convex portion, and the volume of the concave portion and the convex portion, respectively. A display order determining unit that determines the order according to any one value or a combination thereof;
    The medical image display device according to claim 3, wherein the medical image display device is a medical image display device.
  6. The unevenness extraction unit is
    A curve that is the length of a path from each of a plurality of surface voxels of the abnormal shadow candidate region to the reference point provided in the abnormal shadow candidate region as a feature amount related to the unevenness Calculate the distance,
    Extracting the concave portion and the convex portion from the abnormal shadow candidate region based on the calculated plurality of curve distances;
    The medical image display device according to claim 2.
  7. The unevenness extraction unit is
    A curve distance distribution map is generated by plotting the curve distance on a coordinate having one of the polar angle and azimuth angle of the three-dimensional polar coordinate centered on the reference point and the other is the horizontal axis. ,
    Determining a predetermined curve distance based on the generated curve distance distribution map;
    Extracting the concave portion and the convex portion from the abnormal shadow candidate region based on the determined curve distance;
    The medical image display apparatus according to claim 4, wherein:
  8. The unevenness extraction unit is
    Dividing the surface of the abnormal shadow candidate region into a plurality of mesh-like surfaces;
    For each of the plurality of divided mesh-like surfaces, a surface curvature is calculated as a feature amount related to the unevenness,
    Extracting the concave portion and the convex portion from the abnormal shadow candidate region based on each of the calculated surface curvatures;
    The medical image display device according to claim 2.
  9. An axis determining unit that calculates one reference axis that passes through at least one of the concave portion and the convex portion based on the concave portion and the top of each convex portion;
    The image generation unit includes the calculated one reference axis, and generates cross-sectional image data relating to a cross section in which the area or the number of the concave portions and the convex portions is substantially maximum,
    The image display unit displays the generated cross-sectional image;
    The medical image display device according to claim 2.
  10. A storage unit for storing volume data relating to the subject;
    An abnormal shadow candidate area specifying unit for specifying an abnormal shadow candidate area included in the volume data;
    A low-high luminance extraction unit that extracts a low-luminance portion and a high-luminance portion of the identified abnormal shadow candidate region;
    An image generating unit that generates data of a cross-sectional image relating to a cross section including at least one portion of the extracted low-luminance part and high-luminance part;
    An image display unit for displaying the generated cross-sectional image;
    A medical image display apparatus comprising:
  11. The low and high luminance extraction unit extracts the low luminance portion and the high luminance portion based on a feature amount relating to luminance,
    The image generation unit generates data of a cross-sectional image related to a cross-section in which the feature quantity related to the luminance is maximum or minimum.
    The medical image display device according to claim 10.
  12. The image generation unit includes at least a part of a major axis of each of the low-luminance part and the high-luminance part, and generates data of at least one cross-sectional image relating to a cross-section having a maximum or minimum feature amount relating to the luminance;
    The image display unit displays the at least one cross-sectional image in a predetermined order;
    The medical image display apparatus according to claim 11.
  13. A display order determining unit that determines the order according to the volume of each of the low-luminance portion and the high-luminance portion, the value of the area on the cross section, or a combination thereof;
    The medical image display apparatus according to claim 11.
  14. An axis determination unit that calculates one reference axis that passes through the low-brightness part and the high-brightness part based on the long axis of each of the low-brightness part and the high-brightness part;
    The image generation unit includes a cross-sectional image including the calculated one reference axis and having a maximum or minimum area or number on a cross-section of each of the low-luminance portion and the high-luminance portion, which is a feature amount related to the luminance. Generating data,
    The image display unit displays the generated cross-sectional image;
    The medical image display apparatus according to claim 11.
  15. For computer control means,
    An abnormal shadow candidate area specifying function for specifying an abnormal shadow candidate area included in the volume data relating to the subject;
    Concavity and convexity extraction function for extracting the concave portion and the convex portion of the specified abnormal shadow candidate region,
    An image generation function for generating cross-sectional image data relating to a cross section including at least one portion of the extracted concave portion and convex portion;
    An image display function for displaying the generated cross-sectional image;
    A medical image display program characterized by realizing the above.
  16. For computer control means,
    An abnormal shadow candidate area specifying function for specifying an abnormal shadow candidate area included in the volume data relating to the subject;
    A low-brightness extraction function that extracts a low-brightness portion and a high-brightness portion of the identified abnormal shadow candidate region;
    An image generation function for generating data of a cross-sectional image relating to a cross section including at least one portion of the extracted low-luminance portion and high-luminance portion;
    An image display function for displaying the generated cross-sectional image;
    A medical image display program characterized by realizing the above.
JP2007262541A 2007-10-05 2007-10-05 Medical image display device and medical image display program Expired - Fee Related JP5019220B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2007262541A JP5019220B2 (en) 2007-10-05 2007-10-05 Medical image display device and medical image display program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2007262541A JP5019220B2 (en) 2007-10-05 2007-10-05 Medical image display device and medical image display program

Publications (2)

Publication Number Publication Date
JP2009089847A JP2009089847A (en) 2009-04-30
JP5019220B2 true JP5019220B2 (en) 2012-09-05

Family

ID=40662441

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2007262541A Expired - Fee Related JP5019220B2 (en) 2007-10-05 2007-10-05 Medical image display device and medical image display program

Country Status (1)

Country Link
JP (1) JP5019220B2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5258694B2 (en) 2009-07-27 2013-08-07 富士フイルム株式会社 Medical image processing apparatus and method, and program
JP5421756B2 (en) * 2009-12-11 2014-02-19 富士フイルム株式会社 Image display apparatus and method, and program
JP5652227B2 (en) * 2011-01-25 2015-01-14 ソニー株式会社 Image processing apparatus and method, and program
JP5901930B2 (en) * 2011-10-11 2016-04-13 株式会社東芝 Image processing device

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4549093B2 (en) * 2004-04-12 2010-09-22 キヤノン株式会社 Image processing apparatus and method, and program
JP2005328977A (en) * 2004-05-19 2005-12-02 Hitachi Medical Corp Image diagnosis supporting device and method
JP4644449B2 (en) * 2004-07-12 2011-03-02 富士通株式会社 Image display device and image display program
JP4599191B2 (en) * 2005-03-01 2010-12-15 国立大学法人神戸大学 Diagnostic imaging processing apparatus and diagnostic imaging processing program

Also Published As

Publication number Publication date
JP2009089847A (en) 2009-04-30

Similar Documents

Publication Publication Date Title
Erdt et al. Regmentation: A new view of image segmentation and registration
US10079071B1 (en) Method and system for whole body bone removal and vascular visualization in medical image data
US9375195B2 (en) System and method for real-time ultrasound guided prostate needle biopsy based on biomechanical model of the prostate from magnetic resonance imaging data
JP6534707B2 (en) Region expansion algorithm
JP5654557B2 (en) System and method for performing computerized simulation for image-guided treatment using patient-specific models
Li et al. Optimal surface segmentation in volumetric images-a graph-theoretic approach
US8351670B2 (en) Region data editing apparatus, region data editing method, and recording medium
Castillo et al. A reference dataset for deformable image registration spatial accuracy evaluation using the COPDgene study archive
KR20150108701A (en) System and method for visualizing anatomic elements in a medical image
US20160300343A1 (en) Organ detection and segmentation
US7706600B2 (en) Enhanced virtual navigation and examination
Falcão et al. A 3D generalization of user-steered live-wire segmentation
US8750585B2 (en) Method and system for segmenting a liver object in an image
US8605978B2 (en) Medical image processing apparatus and method, and computer readable recording medium on which is recorded program for the same
US8929635B2 (en) Method and system for tooth segmentation in dental images
US8577115B2 (en) Method and system for improved image segmentation
Kaus et al. Assessment of a model-based deformable image registration approach for radiation therapy planning
US7746340B2 (en) Method and apparatus for generating a 2D image having pixels corresponding to voxels of a 3D image
Sluimer et al. Toward automated segmentation of the pathological lung in CT
US7865002B2 (en) Methods and apparatus for computer automated diagnosis of mammogram images
US10517690B2 (en) Instrument guidance system for sinus surgery
US7853064B2 (en) Method for the processing of radiological images in tomosynthesis for a detection of radiological signs
EP2036040B1 (en) Automated hierarchical splitting of anatomical trees
US7545979B2 (en) Method and system for automatically segmenting organs from three dimensional computed tomography images
US9262827B2 (en) Lung, lobe, and fissure imaging systems and methods

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20101005

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20120423

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20120508

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20120529

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20120601

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20150622

Year of fee payment: 3

LAPS Cancellation because of no payment of annual fees