Spiculated malignant mass detection and classification in radiographic image
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/00
G06K-009/62
G06T-007/00
출원번호
US-0695369
(2011-04-29)
등록번호
US-8923594
(2014-12-30)
국제출원번호
PCT/US2011/034699
(2011-04-29)
§371/§102 date
20121126
(20121126)
국제공개번호
WO2011/137410
(2011-11-03)
발명자
/ 주소
Wehnes, Jeffrey C.
Harding, David S.
출원인 / 주소
vuCOMP, Inc.
대리인 / 주소
Slater & Matsil, L.L.P.
인용정보
피인용 횟수 :
2인용 특허 :
71
초록▼
An image analysis embodiment comprises generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies, detecting ridges in the digital image to generate a detected ridges map, projecting the detected ridges map onto a set of direction maps
An image analysis embodiment comprises generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies, detecting ridges in the digital image to generate a detected ridges map, projecting the detected ridges map onto a set of direction maps having different directional vectors to generate a set of ridge direction) projection maps, determining wedge features for the potential convergence hubs from the set of ridge direction projection maps, selecting ridge convergence hubs from the potential convergence hubs having strongest wedge features, extracting classification features for each of the selected ridge convergence hubs, and classifying the selected ridge convergence hubs based on the extracted classification features.
대표청구항▼
1. A method for identifying spiculated anomalies in an image comprising pixels, the method comprising: generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies;detecting ridges in the digital image to generate a detected ridges map;p
1. A method for identifying spiculated anomalies in an image comprising pixels, the method comprising: generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies;detecting ridges in the digital image to generate a detected ridges map;projecting the detected ridges map onto a set of direction maps having different directional vectors to generate a set of ridge direction projection maps;determining wedge features for the potential convergence hubs from the set of ridge direction projection maps;selecting ridge convergence hubs from the potential convergence hubs having strongest wedge features;extracting classification features for each of the selected ridge convergence hubs; andclassifying the selected ridge convergence hubs based on the extracted classification features,wherein projecting the detected ridges map onto the set of direction maps comprises:separating the detected ridges map into a line mask image, a row component image, and a column component image; anddetermining a dot product of the line mask image, the row component image, and the column component image with the directional vectors. 2. The method of claim 1, wherein the image is a mammogram, the bulges are potentially-malignant masses, the spiculated anomalies are potentially-malignant spiculated masses, and the one or more classification features are selected from the group consisting of: wedge width, radius, signal-to-noise ratio (SNR), minimum hub contrast, nipple distance and y position, and combinations thereof. 3. The method of claim 1, wherein detecting the ridges is performed for multiple ridge widths, multiple ridge orientations, and multiple ridge aspect ratios. 4. The method of claim 3, wherein detecting the ridges comprises: determining an image noise map for each ridge width;calculating second derivative measurements at each ridge width, orientation and aspect ratio;determining an average contrast and contrast standard deviation from the second derivative measurements;determining the SNR from the average contrast and the noise map; andselecting the ridges to include in the detected ridges map based on relative values of at least one of SNR, contrast density, and contrast standard deviation. 5. The method of claim 4, further comprising thinning the selected ridges. 6. The method of claim 1, wherein determining the wedge features comprises: measuring the wedge features for multiple wedge widths, multiple wedge offsets, and multiple wedge radii; andgenerating a set of radius/wedge width maps comprising a highest SNR and respective offset for each potential convergence hub. 7. The method of claim 6, wherein selecting ridge convergence hubs comprises: thresholding each radius/wedge width map to a minimum significant SNR; andthinning contiguous groups of ridge convergence hubs to one ridge convergence hub having maximum relative SNR. 8. The method of claim 1, further comprising, before generating the bulge mask, removing bright areas from and flattening an intensity of the digital image. 9. The method of claim 1, further comprising, after classifying the selected ridge convergence hubs, marking on an output image ones of the selected ridge convergence hubs having extracted classification features exceeding a threshold. 10. A system for identifying spiculated anomalies in an image comprising pixels, the method comprising: a bulge mask generator generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies;a ridge detector detecting ridges in the digital image to generate a detected ridges map;a convergence projector projecting the detected ridges map onto a set of direction maps having different directional vectors to generate a set of ridge direction projection maps;a wedge feature calculator determining wedge features for the potential convergence hubs from the set of ridge direction projection maps;a convergence hub selector selecting ridge convergence hubs from the potential convergence hubs having strongest wedge features;a feature extractor extracting classification features for each of the selected ridge convergence hubs; anda classifier classifying the selected ridge convergence hubs based on the extracted classification features,wherein the convergence projector separates the detected ridges map into a line mask image, a row component image, and a column component image, and determines a dot product of the line mask image, the row component image, and the column component image with the directional vectors. 11. The system of claim 10, wherein the image is a mammogram, the bulges are potentially-malignant masses, the spiculated anomalies are potentially-malignant spiculated masses, and the one or more classification features are selected from the group consisting of: wedge width, radius, signal-to-noise ratio (SNR), minimum hub contrast, nipple distance and y position, and combinations thereof. 12. The system of claim 10, wherein the ridge detector detects ridges for multiple ridge widths, multiple ridge orientations, and multiple ridge aspect ratios. 13. The system of claim 10, wherein the wedge feature calculator measures the wedge features for multiple wedge widths, multiple wedge offsets, and multiple wedge radii, and generates a set of radius/wedge width maps comprising a highest SNR and respective offset for each potential convergence hub. 14. A computer program product for identifying spiculated anomalies in an image comprising pixels, the computer program product having a non-transitory computer-readable medium with a computer program embodied thereon, the computer program comprising: computer program code for generating a bulge mask from a digital image, the bulge mask comprising potential convergence hubs for spiculated anomalies;computer program code for detecting ridges in the digital image to generate a detected ridges map;computer program code for projecting the detected ridges map onto a set of direction maps having different directional vectors to generate a set of ridge direction projection maps;computer program code for determining wedge features for the potential convergence hubs from the set of ridge direction projection maps;computer program code for selecting ridge convergence hubs from the potential convergence hubs having strongest wedge features;computer program code for extracting classification features for each of the selected ridge convergence hubs; andcomputer program code for classifying the selected ridge convergence hubs based on the extracted classification features,wherein projecting the detected ridges map onto the set of direction maps comprises:separating the detected ridges map into a line mask image, a row component image, and a column component image; anddetermining a dot product of the line mask image, the row component image, and the column component image with the directional vectors. 15. The computer program product of claim 14, wherein the image is a mammogram, the bulges are potentially-malignant masses, the spiculated anomalies are potentially-malignant spiculated masses, and the one or more classification features are selected from the group consisting of: wedge width, radius, signal-to-noise ratio (SNR), minimum hub contrast, nipple distance and y position, and combinations thereof. 16. The computer program product of claim 14, wherein the computer program code for detecting the ridges comprises: computer program code for detecting the ridges at multiple ridge widths, multiple ridge orientations, and multiple ridge aspect ratios;computer program code for determining an image noise map for each ridge width;computer program code for calculating second derivative measurements at each ridge width, orientation and aspect ratio;computer program code for determining an average contrast and contrast standard deviation from the second derivative measurements;computer program code for determining the SNR from the average contrast and the noise map; andcomputer program code for selecting the ridges to include in the detected ridges map based on relative values of at least one of SNR, contrast density, and contrast standard deviation. 17. The computer program product of claim 14, wherein the computer program code for determining the wedge features comprises: computer program code for measuring the wedge features for multiple wedge widths, multiple wedge offsets, and multiple wedge radii; andcomputer program code for generating a set of radius/wedge width maps comprising a highest SNR and respective offset for each potential convergence hub. 18. The computer program product of claim 17, wherein the computer program code for selecting ridge convergence hubs comprises: computer program code for thresholding each radius/wedge width map to a minimum significant SNR; andcomputer program code for thinning contiguous groups of ridge convergence hubs to one ridge convergence hub having maximum relative SNR.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (71)
Doi, Kunio; Aoyama, Masahito, Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images.
Armato III, Samuel G.; MacMahon, Heber; Oxnard, Geoffrey R., Automated method and system for the delineation of the chest wall in computed tomography scans for the assessment of pleural disease.
Armato, III, Samuel G.; MacMahon, Heber, Automated method and system for the delineation of the chest wall in computed tomography scans for the assessment of pleural disease.
Giger Maryellen L. (Elmhurst IL) Doi Kunio (Hinsdale IL) Metz Charles E. (Willowbrook IL) Yin Fang-Fang (Chicago IL), Automated method and system for the detection and classification of abnormal lesions and parenchymal distortions in digi.
Giger Maryellen L. (Elmhurst IL) Armato Samuel (Chicago IL) MacMahon Heber (Chicago IL), Automated method and system for the detection of gross abnormalities and asymmetries in chest images.
Boucheron, Laura E., Combinational pixel-by-pixel and object-level classifying, segmenting, and agglomerating in performing quantitative image analysis that distinguishes between healthy non-cancerous and cancerous cell nuclei and delineates nuclear, cytoplasm, and stromal material objects from stained biological tissue materials.
Collins, Michael J.; Rogers, Steven K.; Mitchell, Richard A., Computer aided detection of masses and clustered microcalcifications with single and multiple input image context classification strategies.
Doi Kunio ; Xu Xin-Wei ; Katsuragawa Shigehiko,JPX ; Morishita Junji,JPX, Computer-aided method for automated image feature analysis and diagnosis of digitized medical images.
Doi Kunio ; Xu Xin-Wei ; Katsuragawa Shigehiko,JPX ; Morishita Junji,JPX, Computer-aided method for automated image feature analysis and diagnosis of medical images.
Gur David (Pittsburgh PA) Zheng Bin (Pittsburgh PA) Chang Yuang-Hsiang (Pittsburgh PA), Computerized detection of masses and microcalcifications in digital mammograms.
Yeh, Hwa-Young Michael; Lin, Jyh-Shyan; Lure, Yuan-Ming Fleming; Xu, Xin-Wei; Li, Ruiping; Zhuang, Rong Feng, Divide-and-conquer method and system for the detection of lung nodule in radiological images.
Sato,Makoto, Image processing apparatus, image processing method, program, and recording medium for generating a difference image from a first radiographic image and second radiographic image.
Xu Xin-Wei ; Doi Kunio, Method and computer readable medium for automated analysis of chest radiograph images using histograms of edge gradients for false positive reduction in lung nodule detection.
Rogers Steven K. ; Amburn Philip ; Berkey Telford S. ; Broussard Randy P. ; DeSimio Martin P. ; Hoffmeister Jeffrey W. ; Ochoa Edward M. ; Rathbun Thomas P. ; Rosenstengel John E., Method and system for automated detection of clustered microcalcifications from digital mammograms.
Roehrig Jimmy R. ; Schneider Alexander C. ; Wang Shih-Ping, Method and system for computer-aided lesion detection using information from multiple images.
Roehrig Jimmy R. ; Doi Takeshi ; Karssemeijer Nico,NLX ; Te Brake Guido M.,NLX, Method and system for detection of suspicious lesions in digital mammograms using a combination of spiculation and density signals.
Doi Kunio (Willowbrook IL) Chan Heang-Ping (Chicago IL) Giger Maryellen L. (Elmhurst IL), Method and system for enhancement and detection of abnormal anatomic regions in a digital image.
Yeh Hwa-Young M ; Lure Yuan-Ming F ; Lin Jyh-Shyan, Method and system for re-screening nodules in radiological images using multi-resolution processing, neural network, and image processing.
Armato ; III Samuel G. ; Giger Maryellen L. ; MacMahon Heber, Method and system for the automated delineation of lung regions and costophrenic angles in chest radiographs.
Armato, III, Samuel G.; Giger, Maryellen L.; MacMahon, Heber, Method and system for the automated delineation of lung regions and costophrenic angles in chest radiographs.
Yeh, Hwa-Young Michael; Lure, Yuan-Ming Fleming; Lin, Jyh-Shyan, Method and system for the detection of lung nodule in radiological images using digital image processing and artificial neural network.
Zhang Wei ; Romsdahl Harlan M. ; Roehrig Jimmy R., Method and system for using local attention in the detection of abnormalities in digitized medical images.
Rogers, Steven K.; Bauer, Kenneth W.; Collins, Michael J.; DeSimio, Martin P.; Mitchell, Richard A., Method for determining features from detections in a digital image using a bauer-fisher ratio.
Li, Qiang; Doi, Kunio, Method, system, and computer program product for computer-aided detection of nodules with three dimensional shape enhancement filters.
Li, Qiang; Katsuragawa, Shigehiko; Doi, Kunio, Process, system and computer readable medium for pulmonary nodule detection using multiple-templates matching.
Wei,Guo Qing; Qian,Jian Zhong; Fan,Li; Liang,Cheng Chung, Spatial-temporal lesion detection, segmentation, and diagnostic information extraction system and method.
Jerebko,Anna; Bogoni,Luca; Lakare,Sarang, System and method for segmenting a structure of interest using an interpolation of a separating surface in an area of attachment to a structure having similar properties.
McKaughan Stephen V. (Arlington MA) Nevers Gary F. (Lynn MA) Landry Joseph W. (Saugus MA) Fallon John P. (Andover MA) Adomaitis Paul R. (Trafford PA), Video web inspection system employing filtering and thresholding to determine surface anomalies.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.