WO2015076406A1 - 骨粗鬆症診断支援装置 - Google Patents
骨粗鬆症診断支援装置 Download PDFInfo
- Publication number
- WO2015076406A1 WO2015076406A1 PCT/JP2014/081056 JP2014081056W WO2015076406A1 WO 2015076406 A1 WO2015076406 A1 WO 2015076406A1 JP 2014081056 W JP2014081056 W JP 2014081056W WO 2015076406 A1 WO2015076406 A1 WO 2015076406A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cortical bone
- mandibular
- line segment
- contour
- image
- Prior art date
Links
- 208000001132 Osteoporosis Diseases 0.000 title claims abstract description 135
- 238000003745 diagnosis Methods 0.000 title claims abstract description 132
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 287
- 230000001054 cortical effect Effects 0.000 claims abstract description 279
- 238000000605 extraction Methods 0.000 claims abstract description 60
- 238000003384 imaging method Methods 0.000 claims abstract description 35
- 238000005259 measurement Methods 0.000 claims description 71
- 238000004364 calculation method Methods 0.000 claims description 63
- 210000004373 mandible Anatomy 0.000 claims description 28
- 230000037182 bone density Effects 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 15
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 description 38
- 238000010191 image analysis Methods 0.000 description 31
- 238000010586 diagram Methods 0.000 description 18
- 239000013598 vector Substances 0.000 description 16
- 230000006870 function Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 6
- 101100494265 Caenorhabditis elegans best-15 gene Proteins 0.000 description 4
- 230000007423 decrease Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000013170 computed tomography imaging Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000004439 roughness measurement Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000006386 Bone Resorption Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000024279 bone resorption Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- ALEXXDVDDISNDU-JZYPGELDSA-N cortisol 21-acetate Chemical compound C1CC2=CC(=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@@](C(=O)COC(=O)C)(O)[C@@]1(C)C[C@@H]2O ALEXXDVDDISNDU-JZYPGELDSA-N 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 235000020061 kirsch Nutrition 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007788 roughening Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4504—Bones
- A61B5/4509—Bone density determination
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0082—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes
- A61B5/0088—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes for oral or dental tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4542—Evaluating the mouth, e.g. the jaw
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7278—Artificial waveform generation or derivation, e.g. synthesising signals from measured signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/501—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of the head, e.g. neuroimaging or craniography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/505—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of bone
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20116—Active contour; Active surface; Snakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
Definitions
- the present invention relates to an apparatus for supporting diagnosis of osteoporosis using X-ray photographs, and in particular, the thickness, roughness, and / or shape index of mandibular cortical bone by dental panoramic X-ray photographs (hereinafter abbreviated as panoramic images).
- the present invention relates to an apparatus for measuring osteoporosis and assisting diagnosis of osteoporosis.
- Patent Document 1 discloses a technical idea for semi-automatically identifying whether the inner surface of the cortical bone portion of the mandible is smooth or rough from a dental panoramic image, and supporting diagnosis of osteoporosis. Is disclosed.
- Patent Document 2 discloses a technique for measuring the thickness of the cortical bone portion of the mandible from a dental panoramic image and comparing the data accumulated in the osteoporosis database with the thickness of the cortical bone to assist in the diagnosis of osteoporosis. The idea is disclosed.
- Patent Document 3 supports the diagnosis of osteoporosis by detecting the contour of the mandible from a dental panoramic image and comparing the stored contour model data with the thickness of the mandibular cortical bone in particular. The technical idea is disclosed.
- Non-Patent Document 1 discloses a method for automatically measuring the thickness of the mandibular cortical bone from a dental panoramic image, and in particular, obtains a vertical gray value profile from the mandibular contour, and based on that, obtains a mandibular cortical bone. A technical idea for measuring the thickness of the film is disclosed.
- Patent Document 4 discloses a technical idea that automatically identifies a bone density change site from a dental panoramic X-ray image and supports diagnosis of osteoporosis.
- the diagnosis support method of Patent Document 2 has a problem that the means for determining the outer and inner edges of the cortical bone of the mandible are complicated and the accuracy thereof is not good.
- the present invention provides a device for measuring the thickness, roughness, and / or morphological index of the mandibular cortical bone from a dental panoramic image and supporting the diagnosis of osteoporosis.
- An object of the present invention is to provide a device capable of more accurately measuring roughness and / or morphological index and more accurately assisting diagnosis of osteoporosis.
- the present invention is an osteoporosis diagnosis support device, A contour extracting unit that extracts a mandibular contour from a mandibular cortical bone image captured by an imaging device that images the mandibular cortex and its surroundings; A line segment extraction unit that extracts a line segment from an image of a mandibular cortical bone imaged by the imaging device; A cortical bone state calculating unit for calculating a cortical bone state based on the extracted mandibular contour and line segment;
- the cortical bone thickness calculation unit that calculates the thickness of the cortical bone can be used as the cortical bone state calculation unit.
- the cortical bone thickness calculating unit may calculate the cortical bone thickness based on the cortical bone line segment extracted by the line segment extracting unit.
- the osteoporosis diagnosis support apparatus according to the above configuration, wherein the cortical bone thickness calculation unit calculates the thickness of the cortical bone based on the line segment of the cortical bone extracted in the line segment extraction unit; You can also
- the position that satisfies the predetermined condition in the range of the predetermined distance is set as the inner edge of the cortical bone, thereby eliminating the influence of noise and the like, and accurately measuring the thickness of the cortical bone. Can greatly assist in diagnosis of osteoporosis.
- the osteoporosis diagnosis support apparatus is based on the cortical bone line segment and the rough segment line segment extracted by the line segment extraction unit as the cortical bone thickness calculation unit. It can also be set as the aspect which calculates the thickness of a bone.
- the inner edge of the cortical bone can be accurately determined, and the thickness of the cortical bone can be measured with high accuracy.
- the osteoporosis diagnosis support apparatus may include a cortical bone roughness calculation unit that calculates cortical bone roughness as the cortical bone state calculation unit.
- the osteoporosis diagnosis support apparatus is used, and as the cortical bone roughness calculation unit, the cortical bone roughness is calculated based on the line segment extracted by the rough segment extracted by the line segment extraction unit. It can also be set as the aspect to do.
- the osteoporosis diagnosis support apparatus may be configured such that a line concentration filter is used as the line segment extraction unit. According to this, extraction of a line segment can be performed easily and accurately.
- the osteoporosis diagnosis support apparatus may include an aspect including detecting a mandibular angle when determining a measurement reference point in the cortical bone state calculation unit. According to this, the measurement reference point can be accurately determined by a simple method.
- the contour extracting unit is the contour extracting unit
- the line segment extracting unit is the line segment extracting unit
- the cortical bone state calculating unit is the cortical bone state calculating unit.
- a contour extracting means for extracting a mandibular contour from an image of a mandibular cortical bone imaged by an imaging device that images the mandibular cortical bone and its surroundings A line segment extracting means for extracting a line segment from an image of the mandibular cortical bone imaged by the imaging device; -It may be an aspect of an osteoporosis diagnosis support program that causes a computer to execute a cortical bone state calculating means for calculating a cortical bone state based on the extracted mandibular contour and line segment.
- the present invention can be realized by a program regardless of the configuration of the apparatus.
- a cortical bone roughness calculation unit is a cortical bone roughness calculation unit, and these units are executed by a computer. Also good.
- an osteoporosis diagnosis support device a contour extraction unit that extracts a mandibular contour from an image of a mandibular cortical bone imaged by an imaging device that images the mandibular cortical bone and its surroundings;
- a line segment extraction unit that extracts a line segment formed by the light and shade distribution, including a line segment of the cortical bone and a line segment of the rough portion, from the image of the mandibular cortical bone photographed by the photographing apparatus, and extraction
- a feature amount is extracted based on at least one of the contours and line segments of the mandible, and a mandibular cortical bone shape index identifying unit for identifying a mandibular cortical bone shape index from the feature amount is provided.
- type I has a smooth inner surface of bilateral cortical bone
- type II has an irregular inner surface of cortical bone
- linear resorption is seen inside the cortical bone near the inner side
- III The mold has a high degree of linear resorption and cortical bone tear throughout the cortical bone.
- the feature amount, -Feature of cortical bone thickness -The number of pixels of the line element in the cortical bone region estimated dense by estimating the density-specific region based on the extracted mandibular contour and line segment, -The number of pixels of the line element in the cortical bone area estimated to be coarse in the density-specific area estimation, -The area of the cortical bone area that was estimated to be rough in the estimation of the area by density, -The ratio of the average value of the concentration of the linear element between the cortical bone area estimated to be dense and the cortical bone area estimated to be coarse in the estimation of the density-specific area, -Variance of 0, 45, 90, or 135 degrees of the cortical bone area estimated to be coarse by density-specific area estimation, -Difference Variance of 0, 45, 90, or 135 degrees of the cortical bone area estimated to be coarse in the density-specific area estimation, -45, 90, or 135 degree difference entropy of the cortical bone region estimated to
- the shape index can be obtained with high accuracy by selecting or using a feature amount effective for diagnosis support for osteoporosis.
- mandibular cortical bone shape index identifying unit may be a identifying unit using a support vector machine. According to this, even when identifying using a large amount of feature quantity, it can identify efficiently.
- the mandibular cortical bone shape index identification unit may have a bone density estimation function. Bone density can be estimated quantitatively by using the feature amount described so far, and thereby appropriate osteoporosis diagnosis can be supported.
- the contour extracting unit is the contour extracting unit
- the line segment extracting unit is the line segment extracting unit
- the mandibular cortical bone form index identifying unit is the mandibular cortical bone form index identifying unit.
- a contour extracting means for extracting a mandibular contour from an image of a mandibular cortical bone imaged by an imaging device that images the mandibular cortical bone and its surroundings;
- a line segment extracting means for extracting a line segment from the image of the mandibular cortical bone imaged by the imaging device; -Supporting diagnosis of osteoporosis by extracting a feature quantity based on at least one of the extracted mandibular contour and line segment, and causing the computer to execute a mandibular cortical bone form index identifying means for identifying a mandibular cortical bone form index from the feature quantity It is good also as an aspect of a program.
- the present invention can be realized by a program regardless of the configuration of the apparatus.
- the osteoporosis diagnosis support apparatus In the osteoporosis diagnosis support apparatus according to the present invention, useful information is required for diagnosis of osteoporosis from the image of the mandibular cortical bone, and it exerts a great effect on diagnosis support.
- the cortical bone thickness can be accurately calculated regardless of the presence or absence of the rough portion, or the roughness of the rough portion can be calculated quantitatively. This facilitates the diagnosis of osteoporosis.
- an index relating to cortical bone morphology (type I, type II, type III) that is useful for the diagnosis of osteoporosis is required, thereby assisting in the diagnosis of osteoporosis.
- FIG. 1 is a block diagram of an osteoporosis diagnosis support apparatus according to a first embodiment of the present invention. It is operation
- FIG. 1 is a block diagram of an osteoporosis diagnosis support apparatus according to the first embodiment of the present invention.
- the osteoporosis diagnosis support apparatus 1 analyzes an image captured by the imaging apparatus 10 and an imaging apparatus 10 for imaging a target image of a patient or the like connected to each other by wire and / or wireless.
- the image analysis device 20 is configured to include an image captured by the image capturing device 10 and a display device 70 that displays information obtained by the image analysis device 20.
- the image analysis apparatus 20 includes a CPU 30, a memory 40, and interfaces 50 and 60, which are connected as shown in FIG.
- the memory 40 includes an outline extraction unit 41, a cortical bone thickness calculation unit 42, a cortical bone roughness calculation unit 43, a line segment extraction unit 44, and an osteoporosis diagnosis support unit 45.
- a panoramic X-ray image capturing apparatus which is one of the image capturing apparatuses 10, is an apparatus that captures a panoramic image of a dental region using X-rays.
- the imaging apparatus 10 is not limited to a panoramic X-ray imaging apparatus, and may be a normal X-ray imaging apparatus, an MRI / CT imaging apparatus, an ultrasonic imaging apparatus, or a combination thereof. Also good. In some cases, appropriate diagnosis support can be performed based on the obtained image.
- the panoramic image photographed by the panoramic X-ray image photographing device as the photographing device 10 is sent to the image analyzing device 20.
- the image analysis device 20 includes at least computer resources such as a CPU 30, a memory 40, an interface 50 with the photographing device 10, and an interface 60 with a display device 70 described later, and performs image analysis.
- it may be a server or personal computer installed in the vicinity, a similar device connected by wire and / or wireless, or a computer resource by cloud using the Internet.
- the display device 70 is connected to the image analysis device 20 via the interface 60, and includes an image photographed by the photographing device 10, a mandibular outline and line segment image extracted by the image analysis device 20, and the image analysis device 20. Information such as the calculated thickness and roughness of the cortical bone, information on osteoporosis diagnosis support obtained by the image analysis apparatus 20, and the like can be displayed.
- a contour extraction unit 41 is provided as a program stored in the memory 40 of the image analysis apparatus 20.
- the contour extraction unit 41 extracts the contour of the mandible from the panoramic image.
- the contour of the mandible is the part that defines the outer edge of the mandible.
- a cortical bone thickness calculation unit 42 which is one of the cortical bone state calculation units, is provided.
- the cortical bone thickness calculation unit 42 is a program stored in the memory, and can cause the computer to execute a function of calculating the thickness of the cortical bone from the panoramic image.
- a cortical bone roughness calculation unit 43 which is one of the cortical bone state calculation units, is provided.
- the cortical bone roughness calculation unit 43 is a program stored in the memory, and can cause the computer to execute a function of calculating the roughness of the cortical bone from the panoramic image.
- a line segment extraction unit 44 is provided as a part of the image analysis apparatus 20.
- the line segment extraction unit 44 such as a line concentration degree filter is a program stored in a memory, and can cause a computer to execute a function of extracting a line segment from a panoramic image. This is used as a part of the cortical bone thickness calculation unit 42 and also as a part of the cortical bone roughness calculation unit 43.
- cortical bone thickness calculation unit 42 and the cortical bone roughness calculation unit 43 may have either one or both.
- the osteoporosis diagnosis support unit 45 has an osteoporosis that is a part of the osteoporosis diagnosis support unit 45 based on the calculation results of the cortical bone thickness calculation unit 42 and the cortical bone roughness calculation unit 43. It can be compared with data stored in a diagnosis support database (not shown).
- FIG. 2 is an operation explanatory diagram of the osteoporosis diagnosis support apparatus according to the first embodiment of the present invention.
- edge detection is performed from the image by the Canny method. This is done in the order of a) smoothing the image, b) calculating edge strength and direction, c) suppressing non-maximum values, and d) hysteresis threshold processing, but suppressing detection of edges not related to the mandible. Therefore, the Kirsch method, which is a template type edge detection operator, is also used.
- FIG. 3 is an example of an image obtained by overlaying the extracted result of the contour of the mandible obtained by using these techniques on a panoramic image.
- the cortical bone thickness calculation unit 42 (related to step S30) includes a function for realizing the following steps.
- ⁇ Measurement reference point determination> (S31) ⁇ Acquisition of profile> (S32) ⁇ Extraction of ridge line by line concentration degree filter> (S33) ⁇ Profile group selection> (S34) ⁇ Thickness measurement> (S35)
- S31 ⁇ Measurement reference point determination>
- S32 ⁇ Acquisition of profile>
- S33 ⁇ Extraction of ridge line by line concentration degree filter>
- S34 Profile group selection>
- Thickness measurement> S35
- a measurement reference point is obtained from the mandibular contour.
- FIG. 4 is an explanatory diagram of measurement reference points. Specifically, the measurement reference points X L and X R on both sides are obtained by the following method. a) The mandibular angle is detected. This is the point at which the angle formed by the tangent line of the contour of the mandible and the vertical line becomes 15 degrees or less for the first time, and exists on both the left and right sides. b) A distance obtained by multiplying the distance Y between the left and right mandibular angles by a predetermined coefficient is the distance between the left and right measurement reference points. Here, the predetermined coefficient is preferably set to 0.48 as a position corresponding to the pit hole based on data accumulated so far, but is not limited to this value. c) The distance between the measurement reference points is distributed to the left and right from the central part of the mandibular contour, and is set as two measurement reference points X L and X R.
- the angle formed by the tangent line of the contour of the mandible and the vertical line is initially 15 degrees or less.
- the detection of the mandible is not limited to 15 degrees or less, and 20 degrees
- An angle such as the following may be used.
- the angle is not limited to 15 degrees and is larger than that. (For example, 25 degrees) or small (for example, 10 degrees).
- the determination method of the measurement reference point is not limited to this method, and the position detection of the pit hole by the enhancement of light and dark as described in Patent Document 1 and the method described in Patent Document 3 are detailed.
- a method may be used in which a measurement reference point is determined by collating with a contour model database in which a position corresponding to the hole is recorded.
- 1 pix 0.1 mm.
- FIG. 6 is an explanatory diagram of profile acquisition.
- the Gaussian filter has the following formula.
- ⁇ 0.8, but the value may be changed according to the image quality.
- the filter for removing noise is not limited to the Gaussian filter, and various filters such as a moving average method, a median filter, a bilateral filter, an anisotropic diffusion filter, and a non-local averaging filter are conceivable. It may be applied according to.
- the lower right figure (c) of FIG. 6 is a diagram in which the peak of the profile is extracted, and if the relationship between the peaks is observed with this, the peak of the gray value and the gray value of the cortical bone to be extracted are in the horizontal direction of the image. It can be seen that it is long and continuous. That is, if the continuity of peaks on a plurality of profiles is used, it is possible to specify a peak of a gray value due to roughing.
- a line concentration filter is applied to the image created by the profile in order to extract the ridge line (the part where the gray value peaks are long and continuous).
- the line concentration filter is a line detection filter when a straight line is considered as a target.
- FIG. 8 is an explanatory diagram showing an outline of the line concentration degree filter in this method.
- the area shown in FIG. 8A in which the central portion is brightest and the luminance lines extend in parallel corresponds to these areas. Is called a linear convex region.
- the luminance gradient vector distribution is concentrated in the direction perpendicular to the center line, and this is called a line concentration vector field, which is a basic model.
- a line where vectors concentrate is called a vector concentration line.
- the degree of vector concentration on a line is referred to as a line concentration degree.
- FIG. 9 is an explanatory diagram of search lines in this method.
- a straight line 90 in the direction ⁇ which is assumed to be a vector concentration line.
- a search line 91 and a search line 92 parallel to this, and consider a rectangular region of width W R or W L and length l on both sides (R side and L side) surrounded by the search lines 91 and 92.
- the evaluation value C R of the R-side as follows Can be defined.
- Wmax is the maximum search width.
- Evaluation value C L of the L-side is the same.
- Linear concentrations of the target point relative to the assumed direction ⁇ is the average value of C R and C L. Since the direction of the true vector concentration line is unknown, the range of FIG. 9 is divided according to the purpose, the degree of concentration is obtained for each direction, and the maximum value among them is used as the output C of the line concentration degree filter. .
- the line concentration filter is less affected by the contrast with the background and can be adapted to fluctuations in the line width.
- the output is the maximum value 1 at the point of interest on the vector concentration line, that is, the portion corresponding to the ridge line when the luminance is the third axis. As the distance from the vector concentration line increases, the output decreases monotonically and becomes 0.5 at the edge.
- the line concentration degree filter is used to extract a ridge line from an image created by a profile. And in order to implement
- FIG. 10 is an explanatory view showing the result of the line concentration degree filter. As shown in FIG. 10, it is recognized that the portion corresponding to the ridge in the image reacts strongly.
- FIG. 11 is an explanatory diagram showing the result of ridge line extraction. Further, in order to extract the ridge as a line, when the output C of the line concentration degree filter is 0.50 or less (when the angle ⁇ ij ( ⁇ )> 45 degrees with the perpendicular to the vector concentration line), the output is 0. Finally, a line that becomes a ridge line is extracted by performing thinning and threshold processing with a very low value.
- ridge line extracted by applying the line concentration filter is classified into three types: ridge line formed by cortical bone intensity peak, ridge line formed by coarse intensity peak, and noise. Assume.
- the lines on the image extracted from the ridge line as shown in FIG. 11 are classified by the following method.
- the “ridge line formed by the cortical bone intensity peak” is referred to as the “cortical bone ridge line”
- the “ridge line formed by the rough intensity peak” is referred to as the “crude ridge line”.
- a line having an x-axis width of less than 15 pix is determined as noise and deleted from the image. Since the measurement is finally performed using 15 profiles, a value of 15 pix is used.
- Cortical bone ridge line After the noise is removed, the line existing at the lower end of the image is defined as the ridge line of the cortical bone.
- the line selected in b) and the line whose number of coordinates on the x-axis is less than 15 is also deleted. . This value is because there are finally 15 profiles used for thickness measurement. 12 and 13 are images before and after the ridge line is selected.
- the profile group that seems to be most effective for measuring the thickness of the mandibular cortical bone is selected.
- the cortical bone and the rough structure are selected from the many existing peaks on the acquired profile using the previously extracted cortical bone and the rough ridge line.
- the horizontal axis represents the distance [pix] from the measurement start point
- the vertical axis represents the gray value.
- the search range is up to the peak due to the rough gray value, it is possible to select a profile where the boundary between cortical bone and cancellous bone is clear.
- the method of determining the search range is determined as follows. b-1) When there is a point corresponding to the rough ridge line on the profile, using the obtained ridge line, the search start point Ts is a cortical bone density value peak, and the search end point Te is a rough shade value. The peak value. b-2) If there is no point corresponding to the rough ridge line on the profile, using the obtained ridge line, the search start point Ts is a cortical bone density peak, and the search end point Te is Ts + 20 pix.
- c-1) Selection of the best profile candidate based on the presence or absence of a crude ridge line
- a peak corresponding to the ridge line due to the coarse tone value peak is present on the profile.
- the profile is set as the best profile candidate group, and the non-existing profile is excluded from the best profile candidates.
- the best profile candidates are not narrowed down, and all the profiles in which the extracted cortical bone gray value peaks exist are candidates.
- Figure 15 is an explanatory diagram showing the effect of the presence or absence of the measurement results of ridge lines of Sozo, upon thickness measurement, than the measurement results R B using the profile P B in the absence of a ridge line of Sozo, Sozo
- the measurement result R A using the profile P A in which the ridge line is present provides a more stable measurement result.
- FIG. 16 is an explanatory diagram showing the gradation value decrease width, and the decrease width D between Ts and Te shown in the left figure (a) of the cortex and cancellous bone as shown in the right figure (b). Choosing a profile with a large reduction width is the same as choosing a profile suitable for cortical bone thickness measurement. Therefore, after selecting the best profile candidate based on the presence or absence of a rough ridge line, by selecting a profile group that maximizes the total reduction ⁇ D of 15 adjacent profiles, the best profile is selected. Realize the selection.
- the thickness is measured using the selected profile group. Using the best 15 adjacent profiles obtained by the above method and the dynamic search range, the cortical bone and cancellous bone boundaries are set using the profile inclination described below. Measure thickness.
- the average value Aave calculated using is obtained.
- the point Tresult closest to Ts satisfying the condition of Ai ⁇ Aave is determined, and the distance from the measurement start point to Tresult is defined as the thickness of the cortical bone.
- the thickness of the cortical bone is displayed on the display device 70 and used for assisting diagnosis of osteoporosis by a doctor, or compared with data stored in an osteoporosis diagnosis support database that is a part of the osteoporosis diagnosis support unit 50. By doing so, the degree of progression of osteoporosis can be determined, and diagnosis of osteoporosis can be supported.
- the cortical bone roughness calculation unit 43 (related to step S40) includes a function for realizing the following steps. ⁇ Measurement reference point determination> (S41) ⁇ Acquisition of profile> (S42) ⁇ Line Extraction by Line Concentration Filter> (S43) ⁇ Calculation of area of line segment> (S44) ⁇ Roughness measurement> (S45) These are described in detail below. Note that the numerical values shown therein are preferable examples, but are not limited thereto, and can be appropriately selected according to the image status, the accuracy of diagnosis support, and the like. .
- the measurement reference point determination and profile acquisition are performed in the same manner as the cortical bone thickness calculation unit 42.
- FIG. 18 shows images before and after application of the line concentration degree filter.
- FIG. 19 is an example of a result image.
- (A) is an example in which there are many crude artifacts and osteoporosis is suspected, and (b) is an example in which no artifacts appear to be normal.
- This cortical bone roughness information is displayed on the display device 70 and used to assist the diagnosis of osteoporosis by a doctor, or data stored in the osteoporosis diagnosis support database that is part of the osteoporosis diagnosis support unit 45 As a result, the degree of progression of osteoporosis can be determined, and diagnosis of osteoporosis can be supported.
- cortical bone thickness calculation part 42 and the cortical bone roughness calculation part 43 demonstrated so far may be used independently, and may be used together.
- a cortical bone coarse calculation unit may be provided as the cortical bone state calculation unit. It is also possible to support rough osteoporosis diagnosis depending on whether or not there is a rough line segment inside or outside the cortical bone.
- an osteoporosis diagnosis support apparatus according to a second embodiment in another aspect of the present invention will be described.
- the range necessary for the description for achieving the object of the present invention is schematically shown, and the range necessary for the description of the relevant part of the present invention will be mainly described. According to a known technique.
- FIG. 20 is a block diagram of an osteoporosis diagnosis support apparatus according to the second embodiment of the present invention.
- the osteoporosis diagnosis support apparatus 100 analyzes the images captured by the imaging apparatus 110 and the imaging apparatus 110 for imaging a target image of a patient or the like connected to each other by wire and / or wireless.
- a display device 170 for displaying an image photographed by the photographing device 110 and information obtained by the image analyzing device 120.
- the image analysis apparatus 120 includes a CPU 130, a memory 140, and interfaces 150 and 160, which are connected as shown in FIG.
- the memory 140 includes a contour extraction unit 141, a line segment extraction unit 144, a mandibular cortical bone shape index identification unit 146, and an osteoporosis diagnosis support unit 145.
- a panoramic X-ray image capturing apparatus which is one of the imaging apparatuses 110, is an apparatus that captures a panoramic image of a dental region using X-rays.
- the imaging apparatus 110 is not limited to a panoramic X-ray imaging apparatus, and may be a normal X-ray imaging apparatus, an MRI / CT imaging apparatus, an ultrasonic imaging apparatus, or a combination thereof. Also good. In some cases, appropriate diagnosis support can be performed based on the obtained image.
- the panoramic image photographed by the panoramic X-ray image photographing device as the photographing device 110 is sent to the image analyzing device 120.
- the image analysis device 120 includes at least computer resources such as a CPU 130, a memory 140, an interface 150 with the imaging device 110, and an interface 160 with a display device 170 described later, and performs image analysis.
- it may be a server or personal computer installed in the vicinity, a similar device connected by wire and / or wireless, or a computer resource by cloud using the Internet.
- the display device 170 is connected to the image analysis device 120 via the interface 160, and includes an image photographed by the photographing device 110, an image of a mandibular contour or line segment extracted by the image analysis device 120, and an image analysis device 120.
- Information such as the shape index of the identified mandibular cortical bone, information on diagnosis support for osteoporosis obtained by the image analysis device 120, and the like can be displayed.
- a contour extraction unit 141 is included as a program stored in the memory 140 of the image analysis device 120.
- the contour extracting unit 141 extracts the contour of the mandible from the panoramic image.
- the contour of the mandible is the part that defines the outer edge of the mandible.
- a line segment extraction unit 144 is provided.
- the line segment extraction unit 144 such as a line concentration degree filter is a program stored in the memory 140, and can cause a computer to execute a function of extracting a line segment from a panoramic image.
- a mandibular cortical bone shape index identification unit 146 is provided.
- the mandibular cortical bone shape index identifying unit 146 is also a program stored in the memory 140, and identifies the shape index of the mandibular cortical bone based on the results of either the contour extracting unit 141, the line segment extracting unit 144, or both. To do.
- the osteoporosis diagnosis support unit 145 is provided as a part of the image analysis device 120, and the identification result of the mandibular cortical bone shape index identification unit 146 is obtained as an osteoporosis diagnosis support database (not shown) which is a part of the osteoporosis diagnosis support unit 145. ) Can be compared with the data stored in.
- FIG. 21 is an operation explanatory diagram of the osteoporosis diagnosis support apparatus according to the second embodiment of the present invention.
- the region of interest (ROI) including cortical bone is first set in the mandibular cortical bone shape index identifying unit 146 using the captured image and the extracted contour.
- This is the same content as the measurement reference point determination and profile acquisition of the first embodiment, but the size of the region of interest is enlarged so as to be suitable for identification of the mandibular cortical bone morphology index. That is, centering on the left and right measurement reference points, the lateral width along the mandibular contour is 151 pixels (pix) (50 pix in the median direction from the measurement reference point, 100 pix in the reverse direction), and the vertical width in the vertical direction from the mandibular contour. A region of 100 pix is set as a region of interest.
- FIG. 22 is an explanatory diagram for setting the region of interest. Note that the length and width of 1 pix correspond to 0.1 mm, respectively.
- the mandibular cortical bone shape index identifying unit 146 uses the line concentration degree filter for the set region of interest and uses a linear structure (a linear image formed by bone resorption) and a density peak value of a dense cortical bone part.
- a line composed of is extracted.
- the ridge line is extracted by the line concentration degree filter, further thinned and noise-removed, and the ridge line formed by the cortical bone density peak ( Cortic bone ridge line) and ridge line (crude ridge line) formed by coarse tone value peaks are detected.
- FIG. 23 shows an image of a linear structure after application of the line concentration degree filter.
- the line existing at the lowest end is defined as a line composed of the density value peak of the dense cortical bone, and the line up to the upper end of the line is dense. Presumed to be the cortical bone region.
- 151 100 pix profiles are acquired vertically from the lower end of the region of interest.
- FIG. 24 shows a method of acquiring one profile. As shown in FIG. 24A, a 100 pix profile is acquired. As shown in FIG. 24B, the vertical axis indicates the intensity and the horizontal axis indicates the region of interest. The graph is displayed as the distance from the lower end, that is, the contour.
- FIG. 25 shows an estimation result of a dense region portion (indicated by a one-dot chain line in the figure) in the region of interest estimated in this way.
- the mandibular cortical bone shape index identifying unit 146 extracts a feature amount for identifying the shape index (type I, type II, type III).
- the following five types are used as feature amounts.
- (1) Feature value of thickness (2) Number of pixels of line elements in dense cortical bone region (3) Number of pixels of line elements in rough cortical bone region (4) Area of rough cortical bone region (5)
- Each region Here, the ratio of the average value of the line element concentration is set to 6 measurement reference points on the left and right sides of the mandible to obtain the total thickness of the cortical bone. As shown in FIG.
- measurement reference points L1 and R1 are set one by one on the left and right, and two new measurement reference points L2 and L3 are set at both sides of the mandibular contour from the measurement reference points at 101 pix intervals. , R2 and R3 are set.
- a function equivalent to that of the cortical bone thickness calculation unit 42 in the first embodiment is built in the mandibular cortical bone shape index identification unit 146, and this is used to measure cortical bone thickness, Considering the error value, the average value of the four measurement results obtained by removing the minimum value and the maximum value from the six measurement values is used as the feature value of the thickness.
- the feature values (2) to (4) are calculated using the figure generated by the density-specific region estimation. Specifically, as shown in FIG. 28, (2) the number of line elements in the dense cortical bone region, (3) the number of line elements in the rough cortical bone region, and (4) the rough cortical bone region. Area is required.
- the feature quantity of (5) is the ratio of the density average value of the line elements in each of the dense and coarse areas, for example, the density average value of the pixels where the line elements in the dense cortical bone area are 3453, If the same average density value in the rough cortical bone region is 3212, the ratio of the average density values is 0.93 (3212/3453).
- the area of the rough cortical bone region shows a difference in the area of the rough region depending on the degree of roughening, as a feature amount for identifying the form index (type I, type II, type III), It is considered effective.
- the mandibular cortical bone form index identifying unit 146 identifies the form of cortical bone from these feature quantities.
- SVM support vector machine
- SVM is one of the learning models with the best discrimination performance.
- the feature values of (1) to (5) are obtained, and these cases are determined as type I by doctor's diagnosis.
- Type II and type III morphological indicators the separation hyperplane with the margin maximized can be obtained from these feature values by applying SVM here, and new A form index of a case (unlearned sample) can be identified with high accuracy.
- SVM support vector machine
- Other identification methods such as Random Forest, Boosting, Neural Network may be used, and any method can be used as long as it can appropriately identify the shape index from a large amount of features.
- the number of feature amounts is five. However, not all of the five feature amounts, but one or more feature amounts may be used, and in order to improve the accuracy of identification. It is also effective to add feature amounts.
- the cortical bone morphology index has been classified into type I, type II, and type III. Instead, bone density may be estimated.
- the previous five feature quantities used for the form index identification and all or any one or more of the 14 feature quantities and the bone density of existing DXA or the like When the bone density measured by the measurement method was applied to SVM and regression analysis was performed using Leave-one-out, a highly reliable correlation was found. Using this, it is possible to estimate the bone density with high reliability for a new case (unlearned sample). According to this, since the bone density as a specific numerical value can be estimated, it will be very useful for support of osteoporosis diagnosis by a doctor.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Optics & Photonics (AREA)
- High Energy & Nuclear Physics (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Physiology (AREA)
- Rheumatology (AREA)
- Quality & Reliability (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Physical Education & Sports Medicine (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
Abstract
Description
-下顎皮質骨とその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から、下顎骨輪郭を抽出する輪郭抽出部と、
-前記撮影装置によって撮影された下顎皮質骨の画像から、線分を抽出する線分抽出部と、
-抽出された下顎骨輪郭と線分に基づき、皮質骨の状態を算出する皮質骨状態算出部とを有することを特徴とする。
-下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
-前記撮影装置によって撮影された下顎皮質骨の画像から、線分を抽出する線分抽出手段と、
-抽出された下顎骨輪郭及び線分に基づき、皮質骨の状態を算出する皮質骨状態算出手段と
をコンピュータに実行させる骨粗鬆症診断支援プログラムという態様としてもよい。
-皮質骨の厚みの特徴量、
-抽出された下顎骨輪郭及び線分に基づき、密度別領域を推定して密と推定された皮質骨領域での線素の画素数、
-密度別領域の推定で、粗と推定された皮質骨領域での線素の画素数、
-密度別領域の推定で、粗と推定された皮質骨領域の面積、
-密度別領域の推定で、密と推定された皮質骨領域と、粗と推定された皮質骨領域とにおける線素の濃度平均値の比、
-密度別領域の推定で、粗と推定された皮質骨領域の0、45、90、または、135度の分散(Variance)、
-密度別領域の推定で、粗と推定された皮質骨領域の0、45、90、または、135度の差分散(Difference Variance)、
-密度別領域の推定で、粗と推定された皮質骨領域の45、90、または、135度の差エントロピー(Difference Entropy)、
-密度別領域の推定で、密及び粗と推定された皮質骨領域全体の0度の逆差分モーメント(Inverse Difference Moment)、
-密度別領域の推定で、密及び粗と推定された皮質骨領域全体の0度の差エントロピー(Difference Entropy)、
-密度別領域の推定で、密及び粗と推定された皮質骨領域全体の0度の差分散(Difference Variance)
のいずれか1つまたは2つ以上を含むことを特徴としてもよい。
-下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
-撮影装置によって撮影された下顎皮質骨の画像から、線分を抽出する線分抽出手段と、
-抽出された下顎骨輪郭、線分の少なくとも1つに基づき特徴量を抽出し、特徴量から、下顎皮質骨形態指標を識別する下顎皮質骨形態指標識別手段と
をコンピュータに実行させる骨粗鬆症診断支援プログラムという態様としてもよい。
まず、撮影装置10のひとつである、パノラマエックス線画像撮影装置にて下顎骨及びその周辺の画像を撮影する。
次に、撮影された歯科のパノラマ画像を、画像解析装置20に入力し、画像解析装置20の一部である輪郭抽出部41を用いて、下顎骨の輪郭を抽出する。
<計測基準点決定>(S31)
<プロファイルの取得>(S32)
<線集中度フィルタによる尾根線抽出>(S33)
<プロファイル群選択>(S34)
<厚み測定>(S35)
これらについて、以下に詳述する。なお、その中に示された数値については、好ましい例を挙げたものであるが、これに限定されず、画像の状況、診断支援の精度などに対応して、適宜、選定しうるものである。
下顎骨輪郭から計測基準点を求める。下顎骨の状態(厚みまたは粗さ)を算出するためには、安定して算出ができる、左右両側のオトガイ孔の直下付近の位置を計測基準点とすることが望ましい。
a)下顎角を検出する。これは、下顎骨の輪郭の接線と鉛直線とがなす角が初めて15度以下となる地点であり、左右両側に存在する。
b)左右の下顎角の距離Yに、所定の係数を掛けた距離を、左右の計測基準点の間の距離とする。ここで、所定の係数は、これまでに蓄積されたデータなどから、オトガイ孔に相当する位置としては好ましくは0.48とするが、この数値に限定されるものではない。
c)計測基準点間の距離を、下顎骨輪郭の中央部から左右に振り分け、2ヶ所の計測基準点XL、XRとする。
次に、計測基準点を中心として、その周辺の下顎骨輪郭上で、所定の間隔の複数の点を定め、各点から、下顎骨輪郭に垂直な線を取得し、その垂線上で、所定の間隔での濃淡値を求める。この濃淡値の変化を表したものをプロファイルと呼ぶ。
a)左右の計算基準点とその周辺の下顎骨輪郭上の100点とから、計101個の垂線上の画素値を求めて画像化する。つまり、使用した輪郭上の点において、輪郭左側からxi番目の点と輪郭から求められるプロファイルの計算開始地点からの距離yi(yi=1~100)における画素値とを先に作成した画像上での座標(xi,yi)での画素値にすることによって画像を作成する。作成した画像の最下端は下顎骨輪郭、またはプロファイルの計算開始点に対応する。
b)取得したそれぞれのプロファイルのピークの位置を抽出して、画像に対応する箇所の画素値を最大に、すなわち白くする。
次に、濃度分布によって形成される線分(尾根線と呼ぶ)の抽出のため、プロファイルによって作られた画像に対して線集中度フィルタを適用する手法について説明する。なお、この手法の概要については非特許文献2に開示されている。
・最大探索幅Wmax=3[pix]
・幅R=8、L=8
・仮定する方向 φ=0度、15度、30度、45度、135度、150度、165度
これは、皮質骨と粗造が画像最下端(画像最下端は下顎骨輪郭に相当する)に対して水平方向にベクトル集中線を持つことから、この角度とするのが好適である。
線集中度フィルタを応用することで抽出した尾根線は、皮質骨の濃淡値ピークによって形成される尾根線、粗造の濃淡値ピークによって形成される尾根線、ノイズの3種類に分類されると仮定する。図11のような尾根線抽出された画像上の線に対し、以下のような方法で分類する。
画像に対して、x軸の幅15pix未満の線をノイズと判定して削除する。最終的に15個のプロファイルを用いて測定するため、15pixという値を用いている。
b)皮質骨の尾根線
ノイズの削除後、画像の最も下端に存在する線を皮質骨の尾根線とする。
c)粗造の尾根線
プロファイルにおいて、皮質骨と海綿骨との境界は皮質骨の濃淡値ピークTsからTe+20[pix]までの地点に存在することが試料データから推測される。よってノイズの削除後、画像において、b)で選択された線からy軸上に20pix以上離れて存在する線は厚み測定には影響を与えないと考え削除する。
その後、下顎皮質骨の厚み測定に最も有効と思われるプロファイル群を選択する。厚み測定を行う皮質骨領域に粗造が存在する場合、先に抽出された皮質骨及び粗造の尾根線を用いて、取得されるプロファイル上で多数存在するピークの中から皮質骨と粗造の濃淡値のピークを選択することができる。つまり、図14の適切な検索範囲の説明図に示すように、皮質骨の尾根線LAと粗造の尾根線LBを用いて、プロファイル上の検索範囲Zの開始時点Ts及び終了時点Teをプロファイルごとに適した位置に動的に変化させることができ、精度が高く厚み測定が可能となる。なお、図14右図(b)の横軸は、測定開始点からの距離[pix]、縦軸は濃淡値を示す。
皮質骨の尾根線が存在しないx軸がある、つまり、そのx軸に対応するプロファイルは皮質骨の濃淡値ピークが安定して形成されていないと考えられるため、皮質骨の厚み測定に適さないとし使用しない。
画像に抽出された皮質骨の尾根線が存在するプロファイルのみを厚み測定に使用する。検索範囲の決定方法は以下のように決められる。
b-1)プロファイル上に粗造の尾根線に対応する地点がある場合は、求めた尾根線を用いて、検索開始地点Tsは皮質骨の濃淡値ピーク、検索終了地点Teは粗造の濃淡値のピークとする。
b-2)プロファイル上に粗造の尾根線に対応する地点がない場合は、求めた尾根線を用いて、検索開始地点Tsは皮質骨の濃淡値ピーク、検索終了地点TeはTs+20pixとする。
最良な隣接する15個のプロファイルを求めるために、粗造の尾根線の有無によって最良なプロファイルの候補を絞る。そして、検索範囲の減少幅を用いて最良な15個の隣接したプロファイルを見つけるという手法を用いる。最良なプロファイルの選択のための手法の詳細を以下に示す。
画像上に粗造の尾根線が存在する場合は、プロファイル上に粗造の濃淡値ピークによる尾根線に対応するピークが存在する場合、そのプロファイルを最良なプロファイルの候補群とし、存在しないプロファイルは最良なプロファイルの候補から除外する。
画像上に粗造の尾根線が存在しない場合は、最良なプロファイルの候補を絞るということはせず、抽出した皮質骨の濃淡値ピークが存在するプロファイルすべてが候補となる。
図15は粗造の尾根線の有無の測定結果への影響を示す説明図であり、厚み測定に際し、粗造の尾根線の存在しないプロファイルPBを用いた測定結果RBよりも、粗造の尾根線が存在するプロファイルPAを用いた測定結果RAの方が、より安定した測定結果が得られる。
最後に、「粗造の尾根線の有無による最良なプロファイルの候補選択」によって選ばれたプロファイルに対し、検索開始点Tsでの濃淡値と検索範囲の最小の濃淡値との減少幅を求める。図16は濃淡値減少幅を示す説明図であり、同図左図(a)に示すTs-Te間の減少幅Dは、同図右図(b)に示すように皮質骨と海綿骨との境界の明瞭さを表しており、減少幅が大きいプロファイルを選ぶということは皮質骨の厚み測定に適するプロファイルを選ぶと同意である。よって、「粗造の尾根線の有無による最良なプロファイルの候補選択」の次に、さらに隣接する15個のプロファイルの減少幅の合計ΣDが最大となるプロファイル群を選ぶことで、最良なプロファイルの選択を実現する。
最後に、選択されたプロファイル群を用いて厚み測定を行う。
上の手法により求めた、最良な隣接する15個のプロファイルと、動的な検索範囲を用いて、次に述べるプロファイルの傾きを用いた皮質骨と海綿骨の境界設定を行うことで皮質骨の厚み測定を行う。
<計測基準点決定>(S41)
<プロファイルの取得>(S42)
<線集中度フィルタによる線分抽出>(S43)
<線分の面積算出>(S44)
<粗さ測定>(S45)
これらについて、以下に詳述する。なお、その中に示された数値については、好ましい例を挙げたものであるが、これに限定されず、画像の状況、診断支援の精度などに対応して、適宜、選定しうるものである。
線集中度フィルタの適用に際しては、粗さ算出の場合も、厚み算出の場合と同様に、線集中度フィルタの出力Cが0.50以下の場合、出力をC=0とする。なお、粗さ検出の場合には、画像の状況などを考慮して、この閾値を小さくするなどの変更を加えることも可能である。
図18は、線集中度フィルタの適用前後を示した画像であり、同図左図(a)が適用前の画像であり、同図右図(b)が適用後で、C<0.50をC=0、C>=0.50をC=1とし、2値化した画像である。線集中度フィルタ適用後、C=0.50を閾値として作成された画像を2値化し構成した画像の正画素の合計を算出する。ROI(関心領域)は左右に2つ存在するため、結果は左右の正画素数の平均としてもよいし、左右の正画素数の最小値としてもよい。
この数の多寡により、皮質骨の粗さの度合いを判定する。図19は、結果画像の例であり、(a)が粗造が多く、骨粗鬆症が疑われる例、(b)が粗造が全くない正常と思われる例である。
まず、撮影装置110のひとつである、パノラマエックス線画像撮影装置にて下顎骨及びその周辺の画像を撮影し、入力する。ここは、第1の実施形態の画像撮影と同内容である。
次に、撮影された歯科のパノラマ画像を、画像解析装置120に入力し、画像解析装置120の一部である輪郭抽出部141を用いて、下顎骨の輪郭を追跡する。ここは、第1の実施形態の輪郭抽出と同内容である。
次に、撮影された画像及び抽出された輪郭を用いて、下顎皮質骨形態指標識別部146において、まず、皮質骨が含まれる関心領域(ROI)を設定する。ここは、第1の実施形態の、計測基準点決定、プロファイルの取得と同内容であるが、下顎皮質骨形態指標の識別に適するように、関心領域のサイズを拡大している。すなわち、左右の計測基準点を中心として、それぞれ、下顎骨輪郭に沿った横幅151ピクセル(pix)(計測基準点から正中方向に50pix、逆方向に100pix)、下顎骨輪郭から垂直方向に縦幅100pixの領域を関心領域として設定する。図22に関心領域の設定についての説明図を示す。なお、1pixの縦横はそれぞれ0.1mmに相当する。
引き続き下顎皮質骨形態指標識別部146において、設定した関心領域について、線集中度フィルタを用いて、線状構造(骨吸収によって形成された線状の像)及び密な皮質骨部の濃淡値ピークから構成される線を抽出する。具体的には、第1の実施形態に述べられたように、線集中度フィルタによって尾根線を抽出し、更に細線化とノイズ除去を行い、皮質骨の濃淡値ピークによって形成される尾根線(皮質骨の尾根線)、粗造の濃淡値ピークによって形成される尾根線(粗造の尾根線)を検出する。図23に線集中度フィルタ適用後の線状構造の画像を示す。
次に、下顎皮質骨形態指標識別部146において、最下端(下顎骨輪郭側)に存在する線を密な皮質骨部の濃淡値ピークから構成される線とし、この線の上端までを密な皮質骨部の領域と推定する。また、関心領域の下端から垂直に100pixのプロファイルを151個取得する。図24は1個のプロファイルの取得の方法を示しており、同図(a)のように100pixのプロファイルを取得し、同図(b)のように縦軸を濃淡度、横軸を関心領域下端、すなわち輪郭からの距離としてグラフ表示する。そして、図25に示すように、それぞれのオリジナルのプロファイルOrに対する3次多項式近似曲線Apを取得し、この曲線Apの変曲点Anを皮質骨全体CBと海綿骨の境界線と推定する。そして、先に推定した密な皮質骨部DCBの領域を除く、皮質骨全体と海綿骨の境界線までの領域を粗な皮質骨部SCBの領域と推定する。図26にはこのようにして推定した関心領域における密粗な領域部(図中の一点鎖線で境界を示す)の推定結果を示す。
次に、下顎皮質骨形態指標識別部146において、形態指標(I型、II型、III型)を識別するための特徴量を抽出する。特徴量としては、以下の5種を用いる。
(1)厚みの特徴量
(2)密な皮質骨領域における線素の画素数
(3)粗な皮質骨領域における線素の画素数
(4)粗な皮質骨領域の面積
(5)各領域における線素の濃度平均値の比
ここで、厚みの特徴量は、皮質骨の総合的な厚みを求めるために下顎骨左右に3点、計6点の計測基準点を設定する.図27に示すように、まず、左右に1ヵ所ずつ計測基準点L1、R1を設定し、その計測基準点から下顎骨輪郭に沿って両側に101pix間隔で新たに2つの計測基準点L2、L3、R2、R3を設定する。各計測基準点から、第1の実施形態における皮質骨厚み算出部42と同等の機能を下顎皮質骨形態指標識別部146に内蔵しておき、これを用いて皮質骨厚みの計測を行い、更に、エラー値を考慮して、6つの計測値から最小値と最大値を除いた4ヵ所の計測結果の平均値を厚みの特徴量とする 。
次に、下顎皮質骨形態指標識別部146において、これらの特徴量から、皮質骨の形態を識別する。この識別には、「教師あり学習」を用いる識別手法の一つであるサポートベクターマシン(SVM)を用いる。SVMは、最も優れた識別性能を有する学習モデルの1つである。
最後に、形態指標の識別(分類)結果を表示装置170に提示するとともに、骨粗鬆症診断支援部145によって、骨粗鬆症に関する医師の診断を支援する。
-距離 5pixels
-角度別 0度、45度、90度、135度 (濃度共起行列を作成するときの角度)
-関心領域 皮質骨全体、粗な皮質骨領域のみ
-種類
コントラスト(Contrast)、相関(Correlation)、分散(Variance)、エントロピー(Entropy)、和エントロピー(Sum Entropy)、逆差分モーメント(Inverse Difference Moment)、和平均(Sum Average)、和分散(Sum Variance)、差分散(Difference Variance)、差エントロピー(Difference Entropy) 、2次モーメント(Angular Second
Moment)
-粗な皮質骨領域の0、45、90、または、135度の分散(Variance)、
-粗な皮質骨領域の0、45、90、または、135度の差分散(Difference Variance)、
-粗な皮質骨領域の45、90、または、135度の差エントロピー(Difference Entropy)、
-皮質骨領域全体の0度の逆差分モーメント(Inverse Difference Moment)、
-皮質骨領域全体の0度の差エントロピー(Difference Entropy)、
-皮質骨領域全体の0度の差分散(Difference Variance)
10 撮影装置
20 画像解析装置
30 CPU
40 メモリー
41 輪郭抽出部
42 皮質骨厚み算出部
43 皮質骨粗さ抽出部
44 線分抽出部
45 骨粗鬆症診断支援部
50 インターフェース
60 インターフェース
70 表示装置
100 骨粗鬆症診断支援装置
110 撮影装置
120 画像解析装置
130 CPU
140 メモリー
141 輪郭抽出部
144 線分抽出部
145 骨粗鬆症診断支援部
146 下顎皮質骨形態指標識別部
150 インターフェース
160 インターフェース
170 表示装置
Claims (17)
- 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出部と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分を含む線分を抽出する線分抽出部と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の厚みを算出する皮質骨厚み算出部と
を有する骨粗鬆症診断支援装置であって、
皮質骨厚み算出部においては、前記輪郭抽出部で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出部において抽出された皮質骨の線分に基づき最適な前記プロファイルの群を選定することによって、前記選定された最適なプロファイルの群から皮質骨の厚みを算出することを特徴とする骨粗鬆症診断支援装置。 - 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出部と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分及び粗造部の線分を含む線分を抽出する線分抽出部と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の厚みを算出する皮質骨厚み算出部と
を有する骨粗鬆症診断支援装置であって、
皮質骨厚み算出部においては、前記輪郭抽出部で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出部において抽出された皮質骨の線分及び粗造部の線分に基づき最適な前記プロファイルの群を選定することによって、前記選定された最適なプロファイルの群から皮質骨の厚みを算出することを特徴とする骨粗鬆症診断支援装置。 - 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出部と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって粗造部の線分を含む線分を抽出する線分抽出部と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の粗さを算出する皮質骨粗さ算出部と
を有する骨粗鬆症診断支援装置であって、
皮質骨粗さ算出部においては、前記輪郭抽出部で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出部において抽出された粗造部の線分の面積を算出することによって、皮質骨の粗さを算出することを特徴とする骨粗鬆症診断支援装置。 - 前記線分抽出部は、前記線分を抽出するにおいて線集中度フィルタを用いることを特徴とする請求項1乃至3のうち1項記載の骨粗鬆症診断支援装置。
- 前記皮質骨厚み算出部における計測基準点の決定に際し、下顎角を検出することを含むことを特徴とする請求項1もしくは2記載の骨粗鬆症診断支援装置。
- 前記皮質骨粗さ算出部における計測基準点の決定に際し、下顎角を検出することを含むことを特徴とする請求項3記載の骨粗鬆症診断支援装置。
- 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分を含む線分を抽出する線分抽出手段と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の厚みを算出する皮質骨厚み算出手段と
をコンピュータに実行させる骨粗鬆症診断支援プログラムであって、該骨粗鬆症診断支援プログラムは、
皮質骨厚み算出手段において、前記輪郭抽出手段で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出手段において抽出された皮質骨の線分に基づき最適な前記プロファイルの群を選定することによって、前記選定された最適なプロファイルの群から皮質骨の厚みを算出することを特徴とする骨粗鬆症診断支援プログラム。 - 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分及び粗造部の線分を含む線分を抽出する線分抽出手段と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の厚みを算出する皮質骨厚み算出手段と
をコンピュータに実行させる骨粗鬆症診断支援プログラムであって、該骨粗鬆症診断支援プログラムは、
皮質骨厚み算出手段において、前記輪郭抽出手段で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出手段において抽出された皮質骨の線分及び粗造部の線分に基づき最適な前記プロファイルの群を選定することによって、前記選定された最適なプロファイルの群から皮質骨の厚みを算出することを特徴とする骨粗鬆症診断支援プログラム。 - 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって粗造部の線分を含む線分を抽出する線分抽出手段と、
前記抽出された下顎骨輪郭及び線分に基づき、皮質骨の粗さを算出する皮質骨粗さ算出手段と
をコンピュータに実行させる骨粗鬆症診断支援プログラムであって、該骨粗鬆症診断支援プログラムは、
皮質骨粗さ算出手段において、前記輪郭抽出手段で抽出された下顎骨輪郭から計測基準点を決定し、前記決定された計測基準点からプロファイルを取得し、前記線分抽出手段において抽出された粗造部の線分の面積を算出することによって、皮質骨の粗さを算出することを特徴とする骨粗鬆症診断支援プログラム。 - 前記線分抽出手段は、前記線分を抽出するにおいて線集中度フィルタを用いることを特徴とする請求項7乃至9のうち1項に記載の骨粗鬆症診断支援プログラム。
- 前記皮質骨厚み算出手段における計測基準点の決定に際し、下顎角を検出することを含むことを特徴とする請求項7もしくは8記載の骨粗鬆症診断支援装置。
- 前記皮質骨粗さ算出手段における計測基準点の決定に際し、下顎角を検出することを含むことを特徴とする請求項9記載の骨粗鬆症診断支援装置。
- 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出部と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分及び粗造部の線分を含む線分を抽出する線分抽出部と、
前記抽出された下顎骨輪郭及び線分に基づき特徴量を抽出し、前記特徴量から、下顎皮質骨形態指標を識別する下顎皮質骨形態指標識別部と
を有することを特徴とする骨粗鬆症診断支援装置。 - 前記特徴量が、
-皮質骨の厚みの特徴量、
-前記抽出された下顎骨輪郭及び線分に基づき、密度別領域を推定して密と推定された皮質骨領域での線素の画素数、
-前記密度別領域の推定で、粗と推定された皮質骨領域での線素の画素数、
-前記密度別領域の推定で、粗と推定された皮質骨領域の面積、
-前記密度別領域の推定で、密と推定された皮質骨領域と、粗と推定された皮質骨領域とにおける線素の濃度平均値の比、
-前記密度別領域の推定で、粗と推定された皮質骨領域の分散(Variance)、
-前記密度別領域の推定で、粗と推定された皮質骨領域の差分散(Difference Variance)、
-前記密度別領域の推定で、粗と推定された皮質骨領域の差エントロピー(Difference Entropy)、
-前記密度別領域の推定で、密及び粗と推定された皮質骨領域全体の逆差分モーメント(Inverse Difference Moment)、
-前記密度別領域の推定で、密及び粗と推定された皮質骨領域全体の差エントロピー(Difference Entropy)、
-前記密度別領域の推定で、密及び粗と推定された皮質骨領域全体の差分散(Difference Variance)
のいずれか1つまたは2つ以上を含むことを特徴とする請求項13に記載の骨粗鬆症診断支援装置。 - 前記下顎皮質骨形態指標識別部が、サポートベクターマシンによる識別部であることを特徴とする請求項13に記載の骨粗鬆症診断支援装置。
- 前記下顎皮質骨形態指標識別部が、骨密度推定機能を有することを特徴とする請求項13に記載の骨粗鬆症診断支援装置。
- 下顎皮質骨及びその周囲を撮影する撮影装置によって撮影された下顎皮質骨の画像から下顎骨輪郭を抽出する輪郭抽出手段と、
前記撮影装置によって撮影された下顎皮質骨の画像から、濃淡分布によって形成される線分であって皮質骨の線分及び粗造部の線分を含む線分を抽出する線分抽出手段と、
前記抽出された下顎骨輪郭及び線分に基づき特徴量を抽出し、前記特徴量から、下顎皮質骨形態指標を識別する下顎皮質骨形態指標識別手段と
をコンピュータに実行させることを特徴とする骨粗鬆症診断支援プログラム。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015549222A JP6544648B2 (ja) | 2013-11-25 | 2014-11-25 | 骨粗鬆症診断支援装置 |
DE112014005372.4T DE112014005372B4 (de) | 2013-11-25 | 2014-11-25 | Vorrichtung und Programm zur Unterstützung der Diagnose einer Osteoporose |
US15/162,447 US10004448B2 (en) | 2013-11-25 | 2016-05-23 | Osteoporosis diagnostic support apparatus |
US16/017,066 US11672471B2 (en) | 2013-11-25 | 2018-06-25 | Osteoporosis diagnostic support apparatus |
US18/309,815 US20230263463A1 (en) | 2013-11-25 | 2023-04-30 | Osteoporosis diagnostic support apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013242678A JP5722414B1 (ja) | 2013-11-25 | 2013-11-25 | 骨粗鬆症診断支援装置 |
JP2013-242678 | 2013-11-25 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/162,447 Continuation-In-Part US10004448B2 (en) | 2013-11-25 | 2016-05-23 | Osteoporosis diagnostic support apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015076406A1 true WO2015076406A1 (ja) | 2015-05-28 |
Family
ID=53179665
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/081056 WO2015076406A1 (ja) | 2013-11-25 | 2014-11-25 | 骨粗鬆症診断支援装置 |
Country Status (4)
Country | Link |
---|---|
US (3) | US10004448B2 (ja) |
JP (2) | JP5722414B1 (ja) |
DE (1) | DE112014005372B4 (ja) |
WO (1) | WO2015076406A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017164412A (ja) * | 2016-03-18 | 2017-09-21 | メディア株式会社 | 骨粗鬆症診断支援装置 |
CN108463172A (zh) * | 2015-11-13 | 2018-08-28 | 新泽西州立拉特格斯大学 | 基于图像分析结果对根尖周疾病的鉴别诊断 |
US20210104048A1 (en) * | 2019-10-07 | 2021-04-08 | J. Morita Manufacturing Corporation | Segmentation device and method of generating learning model |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5722414B1 (ja) | 2013-11-25 | 2015-05-20 | メディア株式会社 | 骨粗鬆症診断支援装置 |
EP3098780A1 (en) * | 2015-05-28 | 2016-11-30 | Galgo Medical, S.L. | A method, a system and a computer program for determining data defining an estimate of the thickness and density of a tissue structure of interest from imaging data |
JP6836250B2 (ja) * | 2017-01-05 | 2021-02-24 | 佳知 高石 | 骨質評価装置,方法およびプログラム |
US10115197B1 (en) | 2017-06-06 | 2018-10-30 | Imam Abdulrahman Bin Faisal University | Apparatus and method for lesions segmentation |
US11090014B2 (en) * | 2017-10-23 | 2021-08-17 | Niigata University | Dental image processing device, dental imaging system, dental image processing method, and program |
WO2019102480A1 (en) * | 2017-11-26 | 2019-05-31 | Dentlytec G.P.L. Ltd | Tracked toothbrush and toothbrush tracking system |
LU101008B1 (en) * | 2018-11-26 | 2020-05-26 | Metamorphosis Gmbh | Bone fracture detection and classification |
WO2021201908A1 (en) * | 2020-04-03 | 2021-10-07 | New York Society For The Relief Of The Ruptured And Crippled, Maintaining The Hospital For Special Surgery | Mri-based textural analysis of trabecular bone |
CN111724357B (zh) * | 2020-06-09 | 2023-05-16 | 四川大学 | 基于数字放射图像及支持向量回归的手臂骨密度测量方法 |
CN113129286B (zh) * | 2021-04-21 | 2024-03-08 | 中国人民解放军空军特色医学中心 | 一种检测骨质疏松的方法、装置、设备及存储介质 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006043523A1 (ja) * | 2004-10-19 | 2006-04-27 | Hiroshima University Independent Administrative Agency | 骨粗鬆症診断支援装置 |
JP2012143387A (ja) * | 2011-01-12 | 2012-08-02 | Hiroshima Univ | 骨粗鬆症診断支援装置及び骨粗鬆症診断支援プログラム |
JP2013116293A (ja) * | 2011-12-05 | 2013-06-13 | Hiroshima Univ | 骨粗鬆症診断支援装置、骨粗鬆症診断支援プログラム、及び骨密度変化部位特定方法 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7840247B2 (en) * | 2002-09-16 | 2010-11-23 | Imatx, Inc. | Methods of predicting musculoskeletal disease |
US8965075B2 (en) * | 2002-09-16 | 2015-02-24 | Imatx, Inc. | System and method for predicting future fractures |
JP3964795B2 (ja) * | 2003-01-07 | 2007-08-22 | 独立行政法人科学技術振興機構 | パノラマx線画像を用いた骨粗鬆症診断支援装置 |
JP4850927B2 (ja) * | 2009-06-02 | 2012-01-11 | キヤノン株式会社 | 画像処理装置、画像処理方法及びコンピュータプログラム |
KR101554272B1 (ko) | 2011-03-18 | 2015-09-18 | 고꾸리츠 다이가꾸호오징 기후다이가꾸 | 파노라마 엑스선 사진을 이용한 진단 지원 시스템, 및 파노라마 엑스선 사진을 이용한 진단 지원 프로그램 |
US20140329194A1 (en) * | 2013-05-05 | 2014-11-06 | Rohit Sachdeva | Orthodontic treatment planning using biological constraints |
JP5722414B1 (ja) | 2013-11-25 | 2015-05-20 | メディア株式会社 | 骨粗鬆症診断支援装置 |
-
2013
- 2013-11-25 JP JP2013242678A patent/JP5722414B1/ja active Active
-
2014
- 2014-11-25 JP JP2015549222A patent/JP6544648B2/ja active Active
- 2014-11-25 WO PCT/JP2014/081056 patent/WO2015076406A1/ja active Application Filing
- 2014-11-25 DE DE112014005372.4T patent/DE112014005372B4/de active Active
-
2016
- 2016-05-23 US US15/162,447 patent/US10004448B2/en active Active
-
2018
- 2018-06-25 US US16/017,066 patent/US11672471B2/en active Active
-
2023
- 2023-04-30 US US18/309,815 patent/US20230263463A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006043523A1 (ja) * | 2004-10-19 | 2006-04-27 | Hiroshima University Independent Administrative Agency | 骨粗鬆症診断支援装置 |
JP2012143387A (ja) * | 2011-01-12 | 2012-08-02 | Hiroshima Univ | 骨粗鬆症診断支援装置及び骨粗鬆症診断支援プログラム |
JP2013116293A (ja) * | 2011-12-05 | 2013-06-13 | Hiroshima Univ | 骨粗鬆症診断支援装置、骨粗鬆症診断支援プログラム、及び骨密度変化部位特定方法 |
Non-Patent Citations (2)
Title |
---|
KAZUKI HORIBA ET AL.: "Automated Measurement of Mandibular Cortical Width on Dental Panoramic Radiographs for Early Detection of Osteoporosis: Extraction of Linear Structures", MEDICAL IMAGING TECHNOLOGY, vol. 32, no. 5, 18 November 2014 (2014-11-18), pages 342 - 346 * |
TAKUYA MATSUMOTO ET AL.: "Osteoporosis screening by use of automated scheme for measuring mandibular cortical thickness on dental panoramic radiographs", IEICE TECHNICAL REPORT, vol. 111, no. 389, 12 January 2012 (2012-01-12), pages 325 - 329 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108463172A (zh) * | 2015-11-13 | 2018-08-28 | 新泽西州立拉特格斯大学 | 基于图像分析结果对根尖周疾病的鉴别诊断 |
JP2019502423A (ja) * | 2015-11-13 | 2019-01-31 | ラトガース, ザ ステイト ユニバーシティー オブ ニュージャージー | 画像解析の結果に基づく歯根尖周囲疾患の鑑別診断 |
JP2017164412A (ja) * | 2016-03-18 | 2017-09-21 | メディア株式会社 | 骨粗鬆症診断支援装置 |
US20210104048A1 (en) * | 2019-10-07 | 2021-04-08 | J. Morita Manufacturing Corporation | Segmentation device and method of generating learning model |
JP2021058594A (ja) * | 2019-10-07 | 2021-04-15 | 株式会社モリタ製作所 | セグメンテーション装置および学習モデルの生成方法 |
JP7152455B2 (ja) | 2019-10-07 | 2022-10-12 | 株式会社モリタ製作所 | セグメンテーション装置および学習モデルの生成方法 |
US11734825B2 (en) | 2019-10-07 | 2023-08-22 | J. Morita Mfg. Corp. | Segmentation device and method of generating learning model |
Also Published As
Publication number | Publication date |
---|---|
US11672471B2 (en) | 2023-06-13 |
US20160262686A1 (en) | 2016-09-15 |
US20230263463A1 (en) | 2023-08-24 |
DE112014005372B4 (de) | 2022-07-14 |
JP5722414B1 (ja) | 2015-05-20 |
JPWO2015076406A1 (ja) | 2017-03-16 |
US10004448B2 (en) | 2018-06-26 |
JP6544648B2 (ja) | 2019-07-17 |
US20180303409A1 (en) | 2018-10-25 |
DE112014005372T5 (de) | 2016-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015076406A1 (ja) | 骨粗鬆症診断支援装置 | |
Kumar et al. | Sharpness estimation for document and scene images | |
US8724865B2 (en) | Method, computer software, and system for tracking, stabilizing, and reporting motion between vertebrae | |
JP5231007B2 (ja) | 自動セグメント化方法及び装置 | |
JP7188514B2 (ja) | 診断支援装置、及び診断支援装置における画像処理方法、並びにプログラム | |
CN110772286B (zh) | 一种基于超声造影识别肝脏局灶性病变的系统 | |
JP2017515106A (ja) | 液体キャニスタ内の血液成分量の推定方法 | |
US20030086596A1 (en) | Method, computer software, and system for tracking, stabilizing, and reporting motion between vertebrae | |
JP6273291B2 (ja) | 画像処理装置および方法 | |
KR20160009435A (ko) | 프로브 속도에 기초한 컴퓨터 보조 진단 지원 장치 및 방법 | |
US7840055B2 (en) | Computer aided tube and tip detection | |
CN107529963B (zh) | 图像处理装置、图像处理方法和存储介质 | |
JP6810395B2 (ja) | 骨粗鬆症診断支援装置 | |
JP2007105264A (ja) | 医用画像判定装置、医用画像判定方法およびそのプログラム | |
JP6877109B2 (ja) | 画像処理装置、画像処理方法、及びプログラム | |
JP6603709B2 (ja) | 画像処理装置、画像処理方法および画像処理プログラム | |
JP5935061B2 (ja) | 骨粗鬆症診断支援装置、骨粗鬆症診断支援プログラム、及び骨密度変化部位特定方法 | |
JP6082337B2 (ja) | 心胸郭比算出装置 | |
KR101494975B1 (ko) | 3차원 자동 유방 초음파 영상의 유두 자동 검출 시스템 및 그 검출 방법 | |
KR101334029B1 (ko) | 두경부 근육 추출 방법 및 roi분석 방법 | |
CN113469942A (zh) | 一种ct图像病变检测方法 | |
JP5419925B2 (ja) | 通過物体数計測方法、通過物体数計測装置、及びプログラム | |
JP2006175036A (ja) | 肋骨形状推定装置、肋骨形状推定方法およびそのプログラム | |
JP2019180748A (ja) | 画像処理プログラム、画像処理装置、および画像処理方法 | |
CN116977411B (zh) | 内镜移动速度估计方法及装置、电子设备及存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14863697 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015549222 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112014005372 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14863697 Country of ref document: EP Kind code of ref document: A1 |