IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0487729
(2009-06-19)
|
등록번호 |
US-8768016
(2014-07-01)
|
발명자
/ 주소 |
- Pan, Liangliang
- Yan, Jiayong
- Wang, Wei
- Shi, Lixing
- Wong, Victor C.
|
출원인 / 주소 |
|
인용정보 |
피인용 횟수 :
5 인용 특허 :
10 |
초록
▼
A method for quantifying caries, executed at least in part on data processing hardware, the method comprising generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background; extracting a lesion area from sound tooth
A method for quantifying caries, executed at least in part on data processing hardware, the method comprising generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background; extracting a lesion area from sound tooth regions by identifying tooth regions, extracting suspicious lesion areas, and removing false positives; identifying an adjacent sound region that is adjacent to the extracted lesion area; reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; and quantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area.
대표청구항
▼
1. A method for quantifying caries, executed at least in part on data processing hardware, the method comprising: generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;automatically extracting a lesion area
1. A method for quantifying caries, executed at least in part on data processing hardware, the method comprising: generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;automatically extracting a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives;identifying an adjacent sound region that is adjacent to the extracted lesion area;reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area;wherein identifying tooth regions comprises sub-steps of: generating a first threshold image from a grayscale fluorescence image of the tooth by selecting intensity data values higher than a first predetermined threshold value c1;generating a second threshold image from a grayscale reflectance image of the tooth by selecting intensity data values higher than a second predetermined threshold value c2;generating a preliminary tooth regions image from the intersection of the first and second threshold images;generating a reference binary image from the grayscale fluorescence image by selecting intensity data values higher than a third predetermined threshold value c3, wherein threshold value c3 exceeds threshold value c1; andgenerating a refined tooth regions image from regions that are in the preliminary tooth regions image and are connected to objects in the reference binary image. 2. A method for quantifying caries, executed at least in part on data processing hardware, the method comprising: generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;automatically area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives;identifying an adjacent sound region that is adjacent to the extracted lesion area;reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area;wherein extracting the suspicious lesion area comprises using a morphological bottom-hat based method along with multi-resolution and surface reconstruction techniques. 3. A method for quantifying caries, executed at least in part on data processing hardware, the method comprising: generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;extracting a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives;identifying an adjacent sound region that is adjacent to the extracted lesion area;reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region;quantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area; andwherein identifying tooth regions comprises sub-steps of:generating a first threshold image from a grayscale fluorescence image of the tooth by selecting intensity data values higher than a first predetermined threshold value c1;generating a second threshold image from a grayscale reflectance image of the tooth by selecting intensity data values higher than a second predetermined threshold value c2;generating a preliminary tooth regions image from the intersection of the first and second threshold images;generating a reference binary image from the grayscale fluorescence image by selecting intensity data values higher than a third predetermined threshold value c3, wherein threshold value c3 exceeds threshold value c1; andgenerating a refined tooth regions image from regions that are in the preliminary tooth regions image and are connected to objects in the reference binary image. 4. The method of claim 3, wherein one or both of the grayscale fluorescence image and the grayscale reflectance image are obtained from the green channels of the fluorescence image and reflectance image, respectively. 5. A method for quantifying caries, executed at least in part on data processing hardware, the method comprising: generating a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;extracting a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives, wherein extracting the suspicious lesion area comprises using a morphological bottom-hat based method along with multi-resolution and surface reconstruction techniques;identifying an adjacent sound region that is adjacent to the extracted lesion area;reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area. 6. A method for quantifying caries, executed at least in part on data processing hardware, comprising steps of:obtaining fluorescence image data from the tooth,obtaining reflectance image data from the tooth, andcombining the fluorescence image data with the reflectance image data to form a digital image of the tooth;extracting a lesion area from sound tooth regions, wherein extracting the lesion area comprises identifying tooth regions, extracting a suspicious lesion area using a morphological bottom-hat based method along with the multi-resolution and surface reconstruction techniques, and removing false positives;identifying an adjacent sound region that is adjacent to the extracted lesion area;reconstructing intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantifying the condition of the caries using the reconstructed intensity values and intensity values from the lesion area. 7. The method of claim 6, wherein extracting the lesion area comprises identifying tooth regions, extracting a suspicious lesion area using a marker-controlled watershed algorithm and removing false positives. 8. The method of claim 7 further comprising removing false positives by locating interproximal regions and removing interproximal false positives. 9. A computer program embodied on a non-transitory computer readable medium for use in quantifying caries, the program comprising executable instructions that when loaded on a computer, causes the computer to: generate a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;automatically extract a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas and removing false positives;identify an adjacent sound region that is adjacent to the extracted lesion area;reconstruct intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantify the condition of the caries using the reconstructed intensity values and intensity values from the lesion area,wherein identifying tooth regions comprises sub-steps of: generating a first threshold image from a grayscale fluorescence image of the tooth by selecting intensity data values higher than a first predetermined threshold value c1;generating a second threshold image from a grayscale reflectance image of the tooth by selecting intensity data values higher than a second predetermined threshold value c2;generating a preliminary tooth regions image from the intersection of the first and second threshold images;generating a reference binary image from the grayscale fluorescence image by selecting intensity data values higher than a third predetermined threshold value c3, wherein threshold value c3 exceeds threshold value c1; andgenerating a refined tooth regions image from regions that are in the preliminary tooth regions image and are connected to objects in the reference binary image. 10. The computer program of claim 9, wherein one or both of the grayscale fluorescence image and the grayscale reflectance image are obtained from the green channels of the fluorescence image and reflectance image, respectively. 11. A computer program embodied on a non-transitory computer readable medium for use in quantifying caries, the program comprising executable instructions that when loaded on a computer, causes the computer to: generate a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background;automatically extract a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives;identify an adjacent sound region that is adjacent to the extracted lesion area;reconstruct intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantify the condition of the caries using the reconstructed intensity values and intensity values from the lesion area,wherein extracting the suspicious lesion area comprises using a morphological bottom-hat based method along with multi-resolution and surface reconstruction techniques. 12. The computer program of claim 11, wherein removing false positives comprises locating interproximal regions and removing interproximal false positives. 13. The computer program of claim 11, wherein extracting the suspicious lesion area comprises: identifying one or more internal markers;identifying one or more external markers;forming a gradient image; andapplying a marker-controlled watershed transformation to the gradient image. 14. The computer program of claim 11, wherein extracting the suspicious lesion area further comprises: applying a bottom-hat operation to the digital image at full resolution to produce an original bottom-hat image;down-sampling the original bottom-hat image to form one or more reduced-resolution bottom-hat images;applying the morphological bottom hat operation to the original bottom-hat image and to the one or more reduced-resolution bottom-hat images to form a plurality of morphological bottom-hat processed images;applying a threshold operation to each of the plurality of morphological bottom-hat processed images to form a plurality of binary bottom-hat processed images;interpolating each of the plurality of binary bottom-hat processed images to the full resolution to form a plurality of interpolated images; andidentifying one or more suspicious lesion areas as a union of the plurality of interpolated images. 15. A computer program embodied on a non-transitory computer readable medium for use in quantifying caries, the program comprising executable instructions that when loaded on a computer, causes the computer to: generate a digital image of a tooth, the image comprising intensity values for a region of pixels corresponding to the tooth, gum, and background,automatically extract a lesion area from sound regions of a tooth by identifying tooth regions, extracting suspicious lesion areas, and removing false positives,identify an adjacent sound region that is adjacent to the extracted lesion area;reconstruct intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantify the condition of the caries using the reconstructed intensity values and intensity values from the lesion area,wherein removing false positives comprises locating interproximal regions and removing interproximal false positives, andwherein locating interproximal regions comprises locating interproximal regions that have clear demarcation with the steps of: applying a distance transformation to a binary image of the digital image of the tooth to locate the pixel with the largest distance measured from the boundaries of the identified tooth regions in the binary image;assigning the identified tooth region that is connected to the located pixel as a first object;assigning the identified tooth region that is not connected to the located pixel as a second object; anddefining the interproximal regions to be the pixels in the background having the same distance to the first and second objects. 16. The computer program of claim 12, wherein locating interproximal regions comprises locating interproximal regions that have no clear demarcation with the steps of: defining an origin point in a binary image of the tooth;casting a fan of ray lines from the origin point in a plurality of angles;defining a contour line at points at which each ray line first encounters the boundary between tooth and background areas,determining internal and external markers;applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital image with the internal and external markers to form first and second groups of water basins; andtaking the pixels having the same distance to the first and second groups of water basins as interproximal regions. 17. The computer program of claim 12, wherein locating interproximal regions comprises locating interproximal regions that have no clear demarcation with the steps of: applying a distance transformation to a binary image of the digital image of the tooth, to form a distance image in which each pixel value represents the closest distance of that pixel to the background of the teeth;determining internal and external markers using the distance image;applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital image with the internal and external markers to form two groups of water basins; andtaking the pixels having the same distance to the two groups of basins as interproximal regions. 18. The computer program of claim 11, wherein the step of reconstructing intensity values is performed by a process consisting of one or more of bilinear interpolation, surface fit, and interpolation by solving Laplace's equation. 19. The computer program of claim 11, wherein quantifying the condition of the caries comprises calculating the fluorescence loss of the lesion area or calculating the area of the lesion area. 20. A computer program embodied on a non-transitory computer readable medium for use in quantifying caries, the program comprising executable instructions that when loaded on a computer, causes the computer to: obtain a fluorescence image data from the tooth,obtain a reflectance image data from the tooth, andcombine the fluorescence image data with the reflectance image data to form a digital image of the tooth;extract a lesion area from sound tooth regions, wherein extracting the lesion area comprises identifying tooth regions, extracting a suspicious lesion area using a morphological bottom-hat based method along with the multi-resolution and surface reconstruction techniques, and removing false positives;identify an adjacent sound region that is adjacent to the extracted lesion area;reconstruct intensity values for tooth tissue within the lesion area according to values in the adjacent sound region; andquantify the condition of the caries using the reconstructed intensity values and intensity values from the lesion area. 21. The computer program of claim 20, wherein extracting the lesion area comprises identifying tooth regions, extracting a suspicious lesion area using a marker-controlled watershed algorithm and removing false positives. 22. The computer program of claim 21 wherein removing false positives comprises locating interproximal regions. 23. The method of claim 5, wherein extracting the suspicious lesion area further comprises: applying a bottom-hat operation to the digital image at full resolution to produce an original bottom-hat image;down-sampling the original bottom-hat image to form one or more reduced-resolution bottom-hat images;applying the morphological bottom hat operation to the original bottom-hat image and to the one or more reduced-resolution bottom-hat images to form a plurality of morphological bottom-hat processed images;applying a threshold operation to each of the plurality of morphological bottom-hat processed images to form a plurality of binary bottom-hat processed images;interpolating each of the plurality of binary bottom-hat processed images to the full resolution to form a plurality of interpolated images; andidentifying one or more suspicious lesion areas as a union of the plurality of interpolated images.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.