WO2012112627A2 - Method and apparatus of cone beam breast ct image-based computer-aided detection and diagnosis - Google Patents
Method and apparatus of cone beam breast ct image-based computer-aided detection and diagnosis Download PDFInfo
- Publication number
- WO2012112627A2 WO2012112627A2 PCT/US2012/025141 US2012025141W WO2012112627A2 WO 2012112627 A2 WO2012112627 A2 WO 2012112627A2 US 2012025141 W US2012025141 W US 2012025141W WO 2012112627 A2 WO2012112627 A2 WO 2012112627A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- breast
- image data
- fat
- cbbct
- calcifications
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/50—Clinical applications
- A61B6/502—Clinical applications involving diagnosis of breast, i.e. mammography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computerised tomographs
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/04—Positioning of patients; Tiltable beds or the like
- A61B6/0407—Supports, e.g. tables or beds, for the body or parts of the body
- A61B6/0414—Supports, e.g. tables or beds, for the body or parts of the body with compression means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/40—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment with arrangements for generating radiation specially adapted for radiation diagnosis
- A61B6/4064—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment with arrangements for generating radiation specially adapted for radiation diagnosis specially adapted for producing a particular type of beam
- A61B6/4085—Cone-beams
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/44—Constructional features of apparatus for radiation diagnosis
- A61B6/4429—Constructional features of apparatus for radiation diagnosis related to the mounting of source units and detector units
- A61B6/4435—Constructional features of apparatus for radiation diagnosis related to the mounting of source units and detector units the source unit and the detector unit being coupled by a rigid structure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/46—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment with special arrangements for interfacing with the operator or the patient
- A61B6/461—Displaying means of special interest
- A61B6/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/48—Diagnostic techniques
- A61B6/481—Diagnostic techniques involving the use of contrast agents
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. 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
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30068—Mammography; Breast
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
Definitions
- the present invention is directed to breast imaging and more particularly to the provision of three-dimensional (3D) breast information, including 3D location and measurement of mass and calcifications, 3D duct structure, 3D vascular structure, and volumetric breast density.
- 3D three-dimensional
- BMRI cannot detect calcifications, which are important signs for early breast cancer and DCIS, and are evident in up to 50% of breast cancers not associated with a mass. Although it is a three-dimensional (3D) visualization of the breast, BMRI has limited spatial resolution (in-plane resolution of ⁇ 1 mm and slice thickness of 2-3 mm). Small lesions may be missed or incorrectly characterized due to the resolution limitation.
- BMRI-based CAD has had some success in distinguishing benign from malignant masses
- acknowledged limitations of the system include an inability to consider T2-weighted images.
- the system potentially may miss useful additional morphology information available in those sequences.
- current BMRI-based CAD cannot improve radiologist accuracy in distinguishing malignant from benign MRI screen-detected lesions because of its poor DCIS detection sensitivity.
- DBT digital breast tomosynthesis
- Ultrasound-based CAD (US -CAD) has also been explored. Though ultrasound has considerable potential, it also has well known limitations. The technique is difficult to teach and perform. Also, differentiating between benign and malignant lesions can be challenging. The addition of ultrasound could also lead to unnecessary biopsies of benign lesions. Another major limitation of US-CAD is the fact that microcalcifications are difficult to image with ultrasound. In addition, US -CAD is limited by the relatively poor spatial resolution of ultrasound. In summary, different breast imaging modalities have different characteristics that require the development of the modality-based CAD to further improve radiologists' accuracy and efficiency.
- Radiographic breast parenchymal pattern also referred to as breast density
- breast density is an important factor associated with the development of breast cancer.
- Most breast density research is based on mammography technology.
- Most breast density description uses the BI-RADS breast density terminology.
- BI-RADS four categories of breast density are defined:
- Type 1 Almost entirely fat: glandular tissue ⁇ 25%;
- Type 2 Scattered fibroglandular tissues: glandular tissue 25%-50%;
- Type 3 Heterogeneously dense: glandular tissue 51%-75%;
- Type 4 Extremely dense: glandular tissue > 75%.
- breast tissue overlaps in two-dimensional mammography projection images.
- the breast density measurement may be inaccurate using mammograms.
- Cone Beam Breast CT is a three-dimensional breast imaging modality with soft tissue contrast superior to that of mammography, high contrast resolution and no tissue overlap. With those advantages, it is possible to measure volumetric breast density accurately and quantitatively with CBBCT 3D images.
- Cone Beam Breast CT is a novel breast imaging technology, using cone beam CT technology and an ergonomically designed imaging system. CBBCT delivers true three- dimensional breast images without tissue overlap.
- CBBCT images The resolution of CBBCT images is 3D isotropic, with the voxel size as small as 155 ⁇ . Even without intravenous contrast injection, the CBBCT soft tissue contrast-to-noise ratio is as high as 8.
- the breast coverage of CBBCT is comparable to and even larger than that of mammography. With those novel features, CBBCT images of the breast can be an ideal tool to quantitatively measure volumetric density of the breast.
- CBBCT-based computer aided diagnosis (CBBCT-CAD) technology is a clinically useful tool for breast cancer detection and diagnosis that will help radiologists to make more efficient and accurate decisions.
- the CBBCT-CAD is able to: 1) use 3D algorithms for image artifact correction, mass and calcification detection and characterization, duct imaging and segmentation, vessel imaging and segmentation, and breast density measurement, 2) present composite information of the breast including mass and calcifications location and characteristics, duct structure, vascular structure and breast density to the radiologists to aid them in determining the probability of malignancy of a breast lesion.
- the novelties of the CBBCT-CAD system include: 1) The first 3D CAD system based on CBBCT technology; 2) The first CAD system to provide composite breast information that is not available from other modalities-based CAD systems; 3) Prominent accuracy and efficiency improvements in radiologists' diagnostic performance.
- Publications related to the present invention include:
- Figure 1 is a set of images showing a comparison between mammography and CBBCT images
- Figure 2 is a set of images showing skin removal results
- Figure 3 is a set of images showing the auto-segmentation of an image
- Figure 4 is a set of images showing mass detection
- Figure 5 is a set of images showing calcification detection
- Figure 6 is a schematic diagram showing an imaging system on which the preferred or another embodiment can be implemented.
- Figure 7 is a block diagram of a software system for use in the preferred embodiment.
- Figure 8 is a block diagram of a hardware system for use in the preferred embodiment.
- the first step is skin removal.
- the skin in CBBCT images has higher intensity than the fatty stroma, its intensity is only slightly higher than that of the glandular tissue.
- a simple thresholding cannot segment the skin from other tissue.
- a morphological process is proposed to remove the skin from the breast in CBBCT images.
- a histogram thresholding method is applied to the whole CBBCT image volume to separate the image into three distinct parts which have significant different intensities: air, fat and tissues (including skin and glands).
- 3D erosion operation is applied to erode the tissue between air and fat.
- the skin removal process stops.
- FCM fuzzy c-means
- x t is the data vector to be clustered
- Cj is the center vector of the jth cluster
- u t j is the degree of the vector x t in the jth cluster
- m is the fuzziness exponent
- N is the number of total data vectors
- C is the number of total clusters.
- 11*11 is a distance function measuring the similarity between any data vector and cluster center.
- the fuzzy c-means clustering algorithm iteratively optimizes the objective function J m by updating ui j and with
- the algorithm stops when max ⁇ . ⁇
- the cluster number C is set to 3. Each cluster represents air, fat, and glands.
- Bias areas include low density glandular tissue with attenuation (as measured in Hounsfeld units, or HU) close to the fat and non-uniform areas caused by imaging artifacts. To achieve better accuracy of tissue segmentation, the bias areas need to be handled. In addition to the clusters for air, fat and glands, an extra cluster is used for bias areas.
- f(x, y, z) f(x, y, z) - min f(p, q, r)
- f(x,y,z) is the HU of a voxel at a position (x,y,z), and R is a local cube with size
- Voxels in the bias area are extracted to go through a second clustering using the images from step 1.
- the cluster number here is set to 3.
- the cluster with the highest center value is considered to be glands, and the rest of clusters are considered to be fat.
- the percentage of each tissue with respect to the whole breast volume can be calculated.
- FIG. 1 shows the mammograms and the CBBCT slices of 4 cases used in this study, corresponding to the 4 BI-RADS breast density categories. More specifically, that figure shows four clinical cases with MLO mammogram images and CBBCT slice images. Top row: mammography images; Bottom row: corresponding CBBCT slices.
- FIG. 2 shows the skin removal results
- Figure 3 shows the auto- segmentation results. More specifically, Figure 2 shows a) original CBBCT image, b) CBBCT image with skin removed, and c) skin image. Figure 3 shows a) original CBBCT image with skin removed, b) fat tissue area, and c) glandular tissue area.
- the preferred embodiment is not limited to measuring breast density. Mass detection and calcification detection will now be disclosed. The algorithm is taught in Xiaohua Zhang, Ruola Ning and Dong Yang, "Three dimensional breast masses auto detection in cone beam breast CT," Proc. SPIE 2009; 7260: 726027.
- CBBCT high contrast resolution reveals the contrast changes of tissue components across voxels.
- the 3D detection algorithm is able to measure these changes and uses the difference between masses and normal tissues for suspicious region detection.
- the average contrast between masses and their surrounding tissues ranged from 10 to 80 HU.
- Other characteristics, such as the gradient congregation of the mass were also used to distinguish mass from normal tissue.
- a 3D weighted average algorithm was applied, followed by a 3D iris filtering to CBBCT volume images to highlight the congregate tissue volume. The highlighted areas are selected as candidates of breast masses.
- 12 of the 14 masses were correctly detected.
- the corresponding measurements of each region are calculated. The measurements include density, size, volume and shape descriptors. The marked results and corresponding measurements will be provided as output results.
- Figure 4 shows the results of preliminary studies on mass detection. Images (a) and (c) show pathology-proven masses. Images (b) and (d) show the results of automatic mass detection.
- Calcification detection will now be disclosed.
- the algorithm is taught in Xiaohua Zhang, Ruola Ning and Jiangkun Liu, "Computer aided breast calcification auto-detection in cone beam breast CT," Proc. SPIE 2010; 7624: 76242M.
- CBBCT images calcifications have high contrast to the surrounding tissues and high HU variations both inside the calcification area and at the edges.
- the contrast between calcification and background material is from -200 HU to -800 HU, and the HU standard deviation can be more than 200 HU.
- a calcification auto-detection scheme has been developed to locate the calcifications within CBBCT images.
- a 3D local thresholding process and a histogram thresholding process are first applied to the CBBCT images to select all voxels with relatively high HU value and HU variation with respect to the neighborhood voxels.
- six features are extracted from each remaining connected voxel object.
- the features are fed into an artificial neural network (ANN) which is trained with known calcification features.
- the ANN output values are used as criteria to differentiate calcification objects from false positive objects.
- ANN artificial neural network
- Figure 5 illustrates one example of CBBCT calcification auto-detection, in which image (a) indicates known calcifications and image (b) indicates eth results of the calcification algorithm. After the detection, measurements of the calcifications will be provided, including cluster size, number of calcifications in clusters and shape descriptors.
- Scattering is one of the major problems that are associated with CBBCT because the large-area flat-panel detector in a CBBCT system receives scattered x-rays as well as primary x-rays.
- the scatter-to-primary ratio can be as high as 0.5 for an average-sized breast. Scattering produces inaccurate CT numbers, reduces tissue contrast and causes cupping artifact in the reconstructed CBBCT images.
- the scattered radiation is estimated based on the breast shape in a projection image, and the projection image is corrected by subtracting the scattered radiation. As the shape and position and breast shadow are different across different projection images, such a correction is performed for all projections.
- the axial and longitude uniformity can be improved to 20 HU and 40 HU respectively.
- Motion artifacts are associated with patient movement and breathing during the scan, appearing as blurs in the reconstruction images.
- the moment of motion can be identified by examining projection images.
- the data before or after this moment can be considered as motion-free data which can be used for reconstruction with half scan algorithms.
- a suitable algorithm is taught in Dong Yang, Ruola Ning, Yong Yu, David Conover and Xianghua Lu, "Implementation and evaluation of the half-scan scheme based on CBCT (cone-beam CT) system" Proc. SPIE 5368, 542 (2004). This method can efficiently remove motion artifacts.
- FIG. 6A of that patent which is reproduced herein as Figure 6, shows an exemplary device.
- the patient P rests on an ergonomically formed table 202 so that the breast B to be scanned descends through a hole 204 in the table 202 into a safety cover 205.
- a gantry 206 supports a detector 208 and an x-ray tube 210, one on either side of the safety cover 205.
- the gantry is turned by a motor 212 to be rotatable around an axis A passing through the safety cover 205, so that as the x-ray tube travels along an orbit O, the breast B remains in the path of a cone beam C emitted by the x-ray tube 210.
- the gantry is also movable by a motor 214 to go up and down along a vertical path V.
- the table 202 can be moved up and down along a vertical path V.
- the detector 208 can be moved toward and away from the axis A by a motor 216 to change the magnification factor if necessary.
- a piston 218 may be used to push the nipple toward the chest wall to reduce z-direction coverage by a couple of centimeters, although usually, the breast does not have to be re- shaped.
- a contrast injector 220 can be provided for contrast enhanced tomographic imaging, angiogenesis studies and some other dynamic contrast studies.
- Various contrast injection media such as iodine, are known in the art. It is not always necessary to inject a contrast medium into the patient.
- the CBBCT-CAD software/hardware includes the modules shown in Figure 7:
- Image Artifact Correction Modules The image artifact correction modules are executed either before or after the CBBCT reconstruction. As shown, the modules include pre-correction 704 and post-correction 708. The pre-correction is performed on the projections acquired from the CBBCT scan. A suitable method is taught in Ning R: Apparatus and Method for X-ray Scatter Reduction and Correction for Fan Beam and Cone Beam Volume CT. U.S. 6,618466 issued on September 9, 2003 and PCT/US03/04871. The post-correction is performed on the isotropic 3D images from the CBBCT reconstruction.
- Detection and Segmentation Modules The four detection and segmentation modules are interconnected. Those modules are density assessment 710, duct segment detection 712, calcification detection 714, and mass detection 716.
- the density assessment algorithm has been described above.
- a suitable calcification detection algorithm is taught in Xiaohua Zhang, Ruola Ning and Jiangkun Liu, "Computer aided breast calcification auto- detection in cone beam breast CT," Proc. SPIE 2010; 7624: 76242M.
- a suitable mass detection algorithm is taught in Xiaohua Zhang, Ruola Ning and Dong Yang, "Three dimensional breast masses auto detection in cone beam breast CT," Proc. SPIE 2009; 7260: 726027.
- the users are able to choose one or multiple modules for better diagnostic assistance.
- Each of the modules is designed to run on both the CPU and the GPU to reduce the processing time. The output results of each module can be superimposed so that radiologists can combine different information to make an
- the Task Manager 718 is the main interface of the CAD system between the users and the CAD modules. System connections, data send/receive configurations and task scheduling/queuing are defined through the task manager.
- the task manager organizes all applicable cases and dispatches the tasks to the detection and segmentation modules based on the specific requirements for each case.
- the task manager also plans all possible resources in the system and assigns the resource to the appropriate modules.
- Data Access Interface 720 This is a DICOM interface to PACS/Image Archive system 722 for image data retrieve/store and the radiologists' feedback, annotation or report, for further processing. Multiple DICOM outputs, including DICOM printers, Structured Reporting, DICOM 6000 Overlay, Secondary Image Capture and RTSS are supported.
- Figure 8 shows the hardware structure of the CBBCT CAD system, based on the system of the above-cited '565 patent or any other suitable system. Three major hardware components will be included in the CAD system:
- CAD Server 802 The CAD Server provides the interface for all clients and external PACS 722 or image archive systems 804, as well as DICOM printers 806. It is equipped with highly configured parts to provide fast and reliable services.
- the CAD server accepts the schedules from pre-configured tasks or the user inputs, read data from the PACS/Archive system, dispatches the computation tasks to the CAD workstations, receives the result from the workstations and writes the CAD reports back to the PACS/Archive system or prints the reports.
- CAD Workstation 808 The major functional modules of the CAD system are running on the high performance workstation. It provides fast and reliable computation to satisfy the practical requirements.
- the workstation is attached to the server by hi-speed connection. Multiple workstations can be installed and connected in each system to perform the tasks parallelly to provide enough computation capability.
- Thin Client 810 The thin client gives users easy access to the system. It can be browser-based application or stand-alone GUI application. It communicates with the CAD server within the intranet or over the internet to provide the services from anywhere with internet connection. The users setup the configurations and schedule tasks on the CAD server through the intuitive GUI provided by the thin client.
- the total processing time of the CBBCT-CAD system is expected to be within 5 minutes.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- High Energy & Nuclear Physics (AREA)
- Veterinary Medicine (AREA)
- Optics & Photonics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Cone Beam Breast CT (CBBCT) is a three-dimensional breast imaging modality with high soft tissue contrast, high spatial resolution and no tissue overlap. CBBCT-based computer aided diagnosis (CBBCT-CAD) technology is a clinically useful tool for breast cancer detection and diagnosis that will help radiologists to make more efficient and accurate decisions. The CBBCT-CAD is able to: 1) use 3D algorithms for image artifact correction, mass and calcification detection and characterization, duct imaging and segmentation, vessel imaging and segmentation, and breast density measurement, 2) present composite information of the breast including mass and calcifications, duct structure, vascular structure and breast density to the radiologists to aid them in determining the probability of malignancy of a breast lesion.
Description
METHOD AND APPARATUS FOR CONE BEAM BREAST CT IMAGE-BASED COMPUTER-AIDED DETECTION AND DIAGNOSIS
Reference to Related Application
[0001] The present application claims the benefit of U.S. Provisional Patent Application No.
61/442,559, filed February 14, 2011, whose disclosure is hereby incorporated by reference in its entirety into the present disclosure.
Statement of Government Interest
[0002] This invention was made with government support under Grant Nos. ROl 9 HL078181 and 4 R33 CA94300 awarded by National Institutes of Health. The government has certain rights in the invention.
Field of the Invention
[0003] The present invention is directed to breast imaging and more particularly to the provision of three-dimensional (3D) breast information, including 3D location and measurement of mass and calcifications, 3D duct structure, 3D vascular structure, and volumetric breast density.
Description of Related Art
[0004] Many researchers have made significant progress in breast lesion auto detection on mammograms and Breast MRI (BMRI). Computer-aided auto-detection technology in those two imaging modalities has achieved good results. However, mammography and MRI have their inherent limitations. Due to breast tissue overlap, even large tumors and some calcification clusters are obscured in mammograms.
[0005] Although it is reported that CAD (computer-aided detection and diagnosis) on mammography increases sensitivity, it is also reported that there is no significant
improvement with the CAD applied to the mammograms. The effectiveness of the CAD application to mammography seems unclear.
[0006] BMRI cannot detect calcifications, which are important signs for early breast cancer and DCIS, and are evident in up to 50% of breast cancers not associated with a mass. Although it is a three-dimensional (3D) visualization of the breast, BMRI has limited spatial resolution (in-plane resolution of ~ 1 mm and slice thickness of 2-3 mm). Small lesions may be missed or incorrectly characterized due to the resolution limitation.
[0007] Although BMRI-based CAD has had some success in distinguishing benign from malignant masses, acknowledged limitations of the system include an inability to consider T2-weighted images. Thus, the system potentially may miss useful additional morphology information available in those sequences. In addition, current BMRI-based CAD cannot improve radiologist accuracy in distinguishing malignant from benign MRI screen-detected lesions because of its poor DCIS detection sensitivity.
[0008] Another breast imaging modality is digital breast tomosynthesis (DBT), which has a sensitivity of up to 85%. However, DBT collects projections over limited angles, resulting in spatial resolution loss in the direction perpendicular to the detector. Although CAD in DBT can help radiologists to handle a large amount of data, the resolution loss limits its ability to detect subtle breast lesions and calcification clusters, so that it is likely that DBT must be used with digital mammography for breast cancer screening and diagnosis.
[0009] Ultrasound-based CAD (US -CAD) has also been explored. Though ultrasound has considerable potential, it also has well known limitations. The technique is difficult to teach and perform. Also, differentiating between benign and malignant lesions can be challenging. The addition of ultrasound could also lead to unnecessary biopsies of benign lesions. Another
major limitation of US-CAD is the fact that microcalcifications are difficult to image with ultrasound. In addition, US -CAD is limited by the relatively poor spatial resolution of ultrasound. In summary, different breast imaging modalities have different characteristics that require the development of the modality-based CAD to further improve radiologists' accuracy and efficiency.
[0010] Radiographic breast parenchymal pattern, also referred to as breast density, is an important factor associated with the development of breast cancer. Currently, most breast density research is based on mammography technology. Most breast density description uses the BI-RADS breast density terminology. In BI-RADS, four categories of breast density are defined:
[0011] Type 1. Almost entirely fat: glandular tissue <25%;
[0012] Type 2. Scattered fibroglandular tissues: glandular tissue 25%-50%;
[0013] Type 3. Heterogeneously dense: glandular tissue 51%-75%; and
[0014] Type 4. Extremely dense: glandular tissue > 75%.
[0015] However, breast tissue overlaps in two-dimensional mammography projection images.
The breast density measurement may be inaccurate using mammograms.
[0016] In summary, different breast imaging modalities have different characteristics that require the development of the modality-based CAD to further improve radiologists' accuracy and efficiency.
Summary of the Invention
[0017] There is thus a need in the art for a CAD system working with CBBCT images to provide
3D composite breast information.
[0018] There is also a need in the art to improve accuracy and efficiency in radiologists' diagnostic performance.
[0019] It is therefore an object of the invention to meet those needs.
[0020] It is therefore a primary object of the invention to provide 3D composite breast information, which includes breast density evaluation, mass and calcification detection and measurement, breast vascular structure segmentation, and breast duct segmentation.
[0021] It is another object of the invention to provide method to accurately evaluate breast density with CBBCT images.
[0022] It is yet another object of the invention to provide three-dimensional location information of breast masses with CBBCT images.
[0023] It is yet another object of the invention to provide three-dimensional characteristics of breast masses with CBBCT images.
[0024] It is yet another object of the invention to provide three-dimensional location information of breast calcifications with CBBCT images.
[0025] It is yet another object of the invention to provide three-dimensional characteristics of breast calcifications with CBBCT images.
[0026] It is yet another object of the invention to provide three-dimensional characteristics of breast vascular system with CBBCT images.
[0027] It is yet another object of the invention to provide three-dimensional characteristics of breast ducts with CBBCT images.
[0028] To achieve the above and other objects, the present invention is directed to a CAD technique based on cone -beam breast computed tomography (CBBCT). Cone Beam Breast CT is a three-dimensional breast imaging modality with soft tissue contrast superior to that of mammography, high contrast resolution and no tissue overlap. With those advantages, it is possible to measure volumetric breast density accurately and quantitatively with CBBCT 3D images. Cone Beam Breast CT is a novel breast imaging technology, using cone beam CT technology and an ergonomically designed imaging system. CBBCT delivers true three- dimensional breast images without tissue overlap. The resolution of CBBCT images is 3D isotropic, with the voxel size as small as 155 μιη. Even without intravenous contrast injection, the CBBCT soft tissue contrast-to-noise ratio is as high as 8. The breast coverage of CBBCT is comparable to and even larger than that of mammography. With those novel features, CBBCT images of the breast can be an ideal tool to quantitatively measure volumetric density of the breast.
[0029] CBBCT-based computer aided diagnosis (CBBCT-CAD) technology is a clinically useful tool for breast cancer detection and diagnosis that will help radiologists to make more efficient and accurate decisions. The CBBCT-CAD is able to: 1) use 3D algorithms for image artifact correction, mass and calcification detection and characterization, duct imaging and segmentation, vessel imaging and segmentation, and breast density measurement, 2) present composite information of the breast including mass and calcifications location and characteristics, duct structure, vascular structure and breast density to the radiologists to aid them in determining the probability of malignancy of a breast lesion.
[0030] The novelties of the CBBCT-CAD system include: 1) The first 3D CAD system based on CBBCT technology; 2) The first CAD system to provide composite breast information that is
not available from other modalities-based CAD systems; 3) Prominent accuracy and efficiency improvements in radiologists' diagnostic performance.
[0031] Publications related to the present invention include:
[0032] James C. Bezdek, "Pattern Recognition with Fuzzy Objective Function Algorithms", Kluwer Academic Publishers, Norwell, MA, 1981
[0033] Xiaohua Zhang, Ruola Ning and Dong Yang, "Three dimensional breast masses auto detection in cone beam breast CT," Proc. SPIE 2009; 7260: 726027.
[0034] Xiaohua Zhang, Ruola Ning and Jiangkun Liu, "Computer aided breast calcification auto- detection in cone beam breast CT," Proc. SPIE 2010; 7624: 76242M.
[0035] D Chen, R Fahmi, AA Farag, RL Falk, GW Dryden, "Accurate and fast 3D colon segmentation in CT colonography," Proc. of ISBI 2009; 490-493.
[0036] Dong Yang, Ruola Ning, Yong Yu, David Conover and Xianghua Lu, "Implementation and evaluation of the half-scan scheme based on CBCT (cone-beam CT) system" Proc. SPIE 5368, 542 (2004).
[0037] The following related patents are hereby incorporated by reference into the present disclosure:
[0038] 1. 8,023,767 Method and apparatus for 3D metal and high-density artifact correction for cone-beam and fan-beam CT imaging
[0039] 2. 7,949,095 Methods and apparatus for differential phase-contrast fan beam CT, cone- beam CT and hybrid cone-beam CT
[0040] 3. 7,697,660 Apparatus and method for cone beam computed tomography breast imaging
[0041] 4. 7,643,605 Method and apparatus for cone beam CT dynamic imaging
[0042] 5. 7,362,845 Method and apparatus of global de-noising for cone beam and fan beam CT imaging
[0043] 6. 6,987,831 Apparatus and method for cone beam volume computed tomography breast imaging
[0044] 7. 6,618,466 Apparatus and method for x-ray scatter reduction and correction for fan beam CT and cone beam volume CT
[0045] 8. 6,504,892 System and method for cone beam volume computed tomography using circle-plus-multiple-arc orbit
[0046] 9. 6,480,565 Apparatus and method for cone beam volume computed tomography breast imaging
[0047] 10. 6,477,221 System and method for fast parallel cone-beam reconstruction using one or more microprocessors
[0048] 11. 6,298,110 Cone beam volume CT angiography imaging system and method
[0049] 12. 6,075,836 Method of and system for intravenous volume tomographic digital angiography imaging
[0050] 13. 5,999,587 Method of and system for cone-beam tomography reconstruction
Brief Description of the Drawings
[0051] A preferred embodiment of the present invention will be set forth in detail with reference to the drawings, in which:
[0052] Figure 1 is a set of images showing a comparison between mammography and CBBCT images;
[0053] Figure 2 is a set of images showing skin removal results;
[0054] Figure 3 is a set of images showing the auto-segmentation of an image;
[0055] Figure 4 is a set of images showing mass detection;
[0056] Figure 5 is a set of images showing calcification detection;
[0057] Figure 6 is a schematic diagram showing an imaging system on which the preferred or another embodiment can be implemented;
[0058] Figure 7 is a block diagram of a software system for use in the preferred embodiment; and
[0059] Figure 8 is a block diagram of a hardware system for use in the preferred embodiment.
Detailed Description of the Preferred Embodiment
[0060] A preferred embodiment will be set forth in detail with reference to the drawings, in which like reference numerals refer to like elements or steps throughout.
[0061] The first step is skin removal. Although the skin in CBBCT images has higher intensity than the fatty stroma, its intensity is only slightly higher than that of the glandular tissue. A simple thresholding cannot segment the skin from other tissue. Based on the fact that the skin is on the outermost layer of the whole breast, a morphological process is proposed to remove the skin from the breast in CBBCT images.
[0062] 1. A histogram thresholding method is applied to the whole CBBCT image volume to separate the image into three distinct parts which have significant different intensities: air, fat and tissues (including skin and glands).
[0063] 2. Based on the fact that the skin is between the inner breast and the air, a morphological
3D erosion operation is applied to erode the tissue between air and fat.
[0064] 3. When the erosion kernel reaches the fat area in the inner breast, the erosion stops.
[0065] 4. In case the glandular tissue is connected to the skin in CBBCT images, during the erosion, a global ratio of fat area vs. total edge area is recorded along the edge of the breast.
When the ratio reaches 80% (or another suitably chosen value), the skin removal process stops.
[0066] Glandular tissue segmentation will now be explained. The fuzzy c-means (FCM) algorithm is widely used for image segmentation. It is also used for breast density assessment in both mammography and breast MRI. In CBBCT images, due to the high soft tissue contrast, FCM is also an effective algorithm to segment glandular tissue from fat. The FCM
is taught in James C. Bezdek, "Pattern Recognition with Fuzzy Objective Function Algorithms", Kluwer Academic Publishers, Norwell, MA, 1981.
[0067] In the fuzzy c-means clustering algorithm, an objective function is defined as:
[0068] Jm =∑∑
i=l j=l
[0069] where xt is the data vector to be clustered, Cj is the center vector of the jth cluster, utj is the degree of the vector xt in the jth cluster, m is the fuzziness exponent, N is the number of total data vectors, and C is the number of total clusters. 11*11 is a distance function measuring the similarity between any data vector and cluster center.
[0070] The fuzzy c-means clustering algorithm iteratively optimizes the objective function Jm by updating uij and with
[0072] The algorithm stops when max^. {|w^+1) - M| |}< ε , where ε is the termination parameter between 0 and 1. The cluster number C is set to 3. Each cluster represents air, fat, and glands.
[0073] Bias areas include low density glandular tissue with attenuation (as measured in Hounsfeld units, or HU) close to the fat and non-uniform areas caused by imaging artifacts. To achieve better accuracy of tissue segmentation, the bias areas need to be handled. In addition to the clusters for air, fat and glands, an extra cluster is used for bias areas.
[0074] To further assign voxels in a bias area into the three clusters, the following process is used:
[0075] 1. A local contrast process is applied to the CBBCT images after skin removal. The local contrast is based on the following equation:
[0076] f(x, y, z) = f(x, y, z) - min f(p, q, r)
(p.q,r)e R
[0077] Here, f(x,y,z) is the HU of a voxel at a position (x,y,z), and R is a local cube with size
NxNxN. By this process, the non-uniform artifact is reduced.
[0078] 2. Voxels in the bias area are extracted to go through a second clustering using the images from step 1. The cluster number here is set to 3. The cluster with the highest center value is considered to be glands, and the rest of clusters are considered to be fat.
[0079] 3. Combine the clustering results from first clustering and second clustering to yield a final result of air, fat and gland segmentation.
[0080] After the CBBCT images are segmented into skin, fat and glands, the percentage of each tissue with respect to the whole breast volume can be calculated.
[0081] Experimental results will now be discussed.
[0082] From the CBBCT clinical database, 5 patient data sets were selected for a preliminary experiment. Each patient data set had its mammography records reviewed by a radiologist, and its breast density category was assigned based on the mammograms. The computer aided breast density evaluation was applied to the CBBCT images of each patient. Figure 1 shows the mammograms and the CBBCT slices of 4 cases used in this study, corresponding to the 4 BI-RADS breast density categories. More specifically, that figure shows four clinical cases with MLO mammogram images and CBBCT slice images. Top row: mammography images; Bottom row: corresponding CBBCT slices. Left column: BIRADS-1 (fatty) breast; Middle left column: BIRADS-2 (scattered) breast; Middle right column: BIRADS-3 (Hetero dense) breast; Right column: BIRADS-4 (Extreme dense) breast.
[0083] The CBBCT breast density auto-evaluation process is applied to each of the clinical cases. Figure 2 shows the skin removal results, and Figure 3 shows the auto- segmentation results. More specifically, Figure 2 shows a) original CBBCT image, b) CBBCT image with skin removed, and c) skin image. Figure 3 shows a) original CBBCT image with skin removed, b) fat tissue area, and c) glandular tissue area.
[0084] Based on the segmented image, the percentages of skin, fat, and glands could be acquired. Table I lists the density measurement and compares it with the BI-RADS category of each case.
Mammography CB BCT Measurement
Case Number BI-RADS Gland (%) Fat (%) Skin (%)
Category
I Fatty 5.23 81.52 13.25
2 Scattered 24.91 63.42 11.67
Hetero Dense 23.79 63.50 12.71
4 Hetero Dense 8.97 79.23 11.79
5 Extreme Dense 13.21 65.03 21.75
[0085] Breast density changes over time. An increase in breast density is associated with greater risk of breast cancer, regardless of the original breast density measurement. Accurate measurement over time is important for active surveillance of the breast density change. The breast density auto-evaluation provides accurate volumetric measurement to detect the changes of density; hence timely cancer risk assessment can be possible.
[0086] Table I above gives the comparison result between CBBCT breast density measurement and the mammography based BI-RADS category. As can be seen from the table, there are obvious disagreements between those two systems, especially within breasts with higher density categories in BI-RADS. Measuring breast density with two-dimensional mammograms and true three-dimensional CBBCT images can yield different results for the same breast. A new breast density measurement system may be defined based on CBBCT images.
[0087] The preferred embodiment is not limited to measuring breast density. Mass detection and calcification detection will now be disclosed. The algorithm is taught in Xiaohua Zhang, Ruola Ning and Dong Yang, "Three dimensional breast masses auto detection in cone beam breast CT," Proc. SPIE 2009; 7260: 726027.
[0088] Abnormal density and structural distortion are radiographic signs for radiologists to detect masses. In 3D CBBCT images, breast masses are observed as congregated volumetric regions which have a denser structure than the surrounding normal tissues. Malignant masses have irregular or spiculated margins, while benign masses usually have smooth margins. The high contrast of CBBCT images reveals the density difference between tissues. A 3D mass detection algorithm takes advantage of high contrast resolution and the 3D characteristic of the CBBCT images.
[0089] In CBBCT, high contrast resolution reveals the contrast changes of tissue components across voxels. The 3D detection algorithm is able to measure these changes and uses the difference between masses and normal tissues for suspicious region detection. According to the preliminary study on 14 pathology-proven masses, after image calibration, the average contrast between masses and their surrounding tissues ranged from 10 to 80 HU. Other
characteristics, such as the gradient congregation of the mass, were also used to distinguish mass from normal tissue. In the preliminary studies, a 3D weighted average algorithm was applied, followed by a 3D iris filtering to CBBCT volume images to highlight the congregate tissue volume. The highlighted areas are selected as candidates of breast masses. In the preliminary result, 12 of the 14 masses were correctly detected. After the mass regions are detected, the corresponding measurements of each region are calculated. The measurements include density, size, volume and shape descriptors. The marked results and corresponding measurements will be provided as output results.
[0090] Figure 4 shows the results of preliminary studies on mass detection. Images (a) and (c) show pathology-proven masses. Images (b) and (d) show the results of automatic mass detection.
[0091] Calcification detection will now be disclosed. The algorithm is taught in Xiaohua Zhang, Ruola Ning and Jiangkun Liu, "Computer aided breast calcification auto-detection in cone beam breast CT," Proc. SPIE 2010; 7624: 76242M. In CBBCT images, calcifications have high contrast to the surrounding tissues and high HU variations both inside the calcification area and at the edges. The contrast between calcification and background material is from -200 HU to -800 HU, and the HU standard deviation can be more than 200 HU. A calcification auto-detection scheme has been developed to locate the calcifications within CBBCT images. A 3D local thresholding process and a histogram thresholding process are first applied to the CBBCT images to select all voxels with relatively high HU value and HU variation with respect to the neighborhood voxels. To further reduce false positives, six features are extracted from each remaining connected voxel object. The features are fed into an artificial neural network (ANN) which is trained with known calcification features. The
ANN output values are used as criteria to differentiate calcification objects from false positive objects. A preliminary study achieves sensitivity of 95% with average 10 false positives calcifications per case. Figure 5 illustrates one example of CBBCT calcification auto-detection, in which image (a) indicates known calcifications and image (b) indicates eth results of the calcification algorithm. After the detection, measurements of the calcifications will be provided, including cluster size, number of calcifications in clusters and shape descriptors.
[0092] Breast ducts and blood vessels can be segmented. Segmenting algorithms are known in the art, e.g., for segmenting colons. A suitable algorithm is taught in D Chen, R Fahmi, AA Farag, RL Falk, GW Dryden, "Accurate and fast 3D colon segmentation in CT colonography," Proc. of ISBI 2009; 490-493. Such segmentation can be used for active surveillance of duct carcinoma in situ (DICS) and abnormal vasculature relating to tumors.
[0093] Artifact correction will now be disclosed. A suitable method is taught in Ning R:
Apparatus and Method for X-ray Scatter Reduction and Correction for Fan Beam and Cone Beam Volume CT. U.S. 6,618466 issued on September 9, 2003 and PCT/US03/04871.
[0094] Scattering is one of the major problems that are associated with CBBCT because the large-area flat-panel detector in a CBBCT system receives scattered x-rays as well as primary x-rays. At 49kVp, the scatter-to-primary ratio can be as high as 0.5 for an average-sized breast. Scattering produces inaccurate CT numbers, reduces tissue contrast and causes cupping artifact in the reconstructed CBBCT images. Given the roughly symmetric geometry of a breast and the slowly varying nature of scattered radiation, the scattered radiation is estimated based on the breast shape in a projection image, and the projection image is corrected by subtracting the scattered radiation. As the shape and position and breast shadow
are different across different projection images, such a correction is performed for all projections. The axial and longitude uniformity can be improved to 20 HU and 40 HU respectively.
[0095] Motion artifacts are associated with patient movement and breathing during the scan, appearing as blurs in the reconstruction images. Usually, the moment of motion can be identified by examining projection images. The data before or after this moment can be considered as motion-free data which can be used for reconstruction with half scan algorithms. A suitable algorithm is taught in Dong Yang, Ruola Ning, Yong Yu, David Conover and Xianghua Lu, "Implementation and evaluation of the half-scan scheme based on CBCT (cone-beam CT) system" Proc. SPIE 5368, 542 (2004). This method can efficiently remove motion artifacts.
[0096] A system on which the preferred or another embodiment can be implemented is set forth in U.S. Patent No. 6,480,565, whose disclosure is hereby incorporated by reference in its entirety into the present disclosure. Figure 2A of that patent, which is reproduced herein as Figure 6, shows an exemplary device. In the scanner 200, the patient P rests on an ergonomically formed table 202 so that the breast B to be scanned descends through a hole 204 in the table 202 into a safety cover 205.
[0097] Below the table 202, a gantry 206 supports a detector 208 and an x-ray tube 210, one on either side of the safety cover 205. The gantry is turned by a motor 212 to be rotatable around an axis A passing through the safety cover 205, so that as the x-ray tube travels along an orbit O, the breast B remains in the path of a cone beam C emitted by the x-ray tube 210. The gantry is also movable by a motor 214 to go up and down along a vertical path V. Alternatively, the table 202 can be moved up and down along a vertical path V. The detector
208 can be moved toward and away from the axis A by a motor 216 to change the magnification factor if necessary.
[0098] In some embodiments, a piston 218 may be used to push the nipple toward the chest wall to reduce z-direction coverage by a couple of centimeters, although usually, the breast does not have to be re- shaped.
[0099] A contrast injector 220 can be provided for contrast enhanced tomographic imaging, angiogenesis studies and some other dynamic contrast studies. Various contrast injection media, such as iodine, are known in the art. It is not always necessary to inject a contrast medium into the patient.
[00100] The CBBCT-CAD software/hardware includes the modules shown in Figure 7:
[00101] Image Artifact Correction Modules: The image artifact correction modules are executed either before or after the CBBCT reconstruction. As shown, the modules include pre-correction 704 and post-correction 708. The pre-correction is performed on the projections acquired from the CBBCT scan. A suitable method is taught in Ning R: Apparatus and Method for X-ray Scatter Reduction and Correction for Fan Beam and Cone Beam Volume CT. U.S. 6,618466 issued on September 9, 2003 and PCT/US03/04871. The post-correction is performed on the isotropic 3D images from the CBBCT reconstruction.
[00102] Detection and Segmentation Modules: The four detection and segmentation modules are interconnected. Those modules are density assessment 710, duct segment detection 712, calcification detection 714, and mass detection 716. The density assessment algorithm has been described above. A suitable calcification detection algorithm is taught in Xiaohua Zhang, Ruola Ning and Jiangkun Liu, "Computer aided breast calcification auto- detection in cone beam breast CT," Proc. SPIE 2010; 7624: 76242M. A suitable mass
detection algorithm is taught in Xiaohua Zhang, Ruola Ning and Dong Yang, "Three dimensional breast masses auto detection in cone beam breast CT," Proc. SPIE 2009; 7260: 726027. The users are able to choose one or multiple modules for better diagnostic assistance. Each of the modules is designed to run on both the CPU and the GPU to reduce the processing time. The output results of each module can be superimposed so that radiologists can combine different information to make an accurate decision.
[00103] The Task Manager 718 is the main interface of the CAD system between the users and the CAD modules. System connections, data send/receive configurations and task scheduling/queuing are defined through the task manager. The task manager organizes all applicable cases and dispatches the tasks to the detection and segmentation modules based on the specific requirements for each case. The task manager also plans all possible resources in the system and assigns the resource to the appropriate modules.
[00104] Data Access Interface 720: This is a DICOM interface to PACS/Image Archive system 722 for image data retrieve/store and the radiologists' feedback, annotation or report, for further processing. Multiple DICOM outputs, including DICOM printers, Structured Reporting, DICOM 6000 Overlay, Secondary Image Capture and RTSS are supported.
[00105] Figure 8 shows the hardware structure of the CBBCT CAD system, based on the system of the above-cited '565 patent or any other suitable system. Three major hardware components will be included in the CAD system:
[00106] CAD Server 802: The CAD Server provides the interface for all clients and external PACS 722 or image archive systems 804, as well as DICOM printers 806. It is equipped with highly configured parts to provide fast and reliable services. The CAD server accepts the schedules from pre-configured tasks or the user inputs, read data from the
PACS/Archive system, dispatches the computation tasks to the CAD workstations, receives the result from the workstations and writes the CAD reports back to the PACS/Archive system or prints the reports.
[00107] CAD Workstation 808: The major functional modules of the CAD system are running on the high performance workstation. It provides fast and reliable computation to satisfy the practical requirements. The workstation is attached to the server by hi-speed connection. Multiple workstations can be installed and connected in each system to perform the tasks parallelly to provide enough computation capability.
[00108] Thin Client 810: The thin client gives users easy access to the system. It can be browser-based application or stand-alone GUI application. It communicates with the CAD server within the intranet or over the internet to provide the services from anywhere with internet connection. The users setup the configurations and schedule tasks on the CAD server through the intuitive GUI provided by the thin client.
[00109] With the parallel processing capability of the hardware and software design, the total processing time of the CBBCT-CAD system is expected to be within 5 minutes.
[00110] While a preferred embodiment has been set forth in detail above, those skilled in the art who have reviewed the present disclosure will readily appreciate that other embodiments can be realized within the scope of the invention. For example, recitations of specific hardware and of numerical values are illustrative rather than limiting. In addition, the disclosed cone beam CT image-based CAD method and system can be used for other cone beam CT imaging applications, such as angiography imaging and lung imaging. Therefore, the present invention should be construed as limited only by the appended claims.
Claims
1. A method for imaging a breast of a patient, the method comprising:
(a) taking three-dimensional (3D) cone-beam breast computed tomography (CBBCT) projection image data of the breast;
(b) processing the projection image data taken in step (a) in a computing device for pre- reconstruction correction of the projection image data;
(c) performing cone beam reconstruction of a matrix of 3D distribution of a linear attenuation coefficient of the breast in the computer device;
(d) performing correction and processing after the reconstruction of the matrix of the breast in the computer device;
(e) storing the corrected reconstruction matrix into an image archive device;
(f) using a CPU-based computer device and a GPU-based computer device to perform the following plurality of tasks: detecting and characterizing mass, detecting calcifications, assessing breast density and detecting and characterizing duct system of the breast, based the reconstructed 3D data;
, (g) outputting the composite breast information including locations, shapes and size(s) of mass(es) and calcifications, number of calcifications in volume of interest, breast density measurement and shapes of duct system of the breast; and
(h) outputting the probability of malignancy of the breast based on the composite breast information determined in (g).
2. The method of claim 1, wherein step (d) comprises:
(a) detecting the skin of the breast and to remove the skin of the breast from the image data; (b) applying a stepwise fuzzy clustering algorithm in the computing device to the image data with the skin removed to adaptively cluster image voxels in the image data;
(c) dividing the image data in the computing device into a plurality of categories; and
(d) forming a three-dimensional image in the computing device from the image data divided into the plurality of categories.
3. The method of claim 2, wherein the plurality of categories comprise skin, fat, and glands.
4. The method of claim 2, wherein step (b) comprises:
(i) separating the image data into air, fat, and tissues, using a histogram thresholding method;
(ii) eroding the tissue between the air and the fat, using a morphological three- dimensional erosion operation with an erosion kernel; and
(iii) stopping step (b)(ii) when the erosion kernel reaches a fat area in an inner portion of the breast
5. The method of claim 2 4, wherein step (c) comprises:
(A) separating the image data into air, fat, tissues, and a bias area; and
(B) re-clustering the bias area to classify the bias area as air, fat, or tissues.
6. The method of claim 5, wherein the bias area arises from at least one of low-density glandular tissue and imaging artifacts.
7. The method of claim 2, wherein step (b) comprises:
(i) recording a global ratio of a fat area to a total edge area along the edge of the breast; and
(ii) stopping step (b) when the ratio reaches a predetermined value.
8. The method of claim 2, wherein the fuzzy clustering algorithm is a fuzzy c-means algorithm.
9. The method of claim 1, wherein (f), breast density is measured.
10. The method of claim 1, wherein (f) breast masses are detected.
11. The method of claim 1, wherein (f), breast calcifications are detected.
12. The method of claim 1, wherein (f) further comprising automatically or semi- automatically detecting and characterizing at least one of mass, calcifications, duct structure, vascular structure, and breast density.
13. A system for imaging a breast of a patient, the system comprising:
an imaging apparatus for taking three-dimensional (3D) cone-beam breast computed tomography (CBBCT) projection image data of the breast;
at least a computer device configured to process the projection image data taken in step (a) in a computing device for pre -reconstruction correction of the projection image data;
to perform cone beam reconstruction of a matrix of 3D distribution of linear attenuation coefficient of the breast;
to perform correction and processing after the reconstruction of the matrix of the breast in the computer device;
a massive data storage/archive device to store the corrected reconstruction matrix into image archive device;
at least a computer device comprising a CPU-based computer device and a GPU-based computer device to perform following plurality of tasks: detecting and characterizing mass, detecting calcifications, assessing breast density and detecting and characterizing duct system of the breast, based the reconstructed 3D data; , outputting the composite breast information including locations, shapes and size (s) of mass(es) and calcifications, number of calcifications in volume of interest, breast density measurement and shapes of duct system of the breast;
outputting the probability of malignancy of the breast based on the composite breast information determined in previous step.
14. The system of claim 13, the system comprising:
a processor, in communication with the imaging apparatus, configured for processing the image data taken by the imaging apparatus to detect the skin of the breast and to remove the skin of the breast from the image data; applying a stepwise fuzzy clustering algorithm to the image data with the skin removed to adaptively cluster image voxels in the image data; dividing the image data into a plurality of categories; and forming a three-dimensional image from the image data divided into the three categories; and
an output, in communication with the processor, for outputting the image.
15. The system of claim 14, wherein the plurality of categories comprise skin, fat, and glands.
16. The system of claim 15, wherein the processor is configured for:
(i) separating the image data into air, fat, and tissues, using a histogram thresholding method;
(ii) eroding the tissue between the air and the fat, using a morphological three- dimensional erosion operation with an erosion kernel; and
(iii) stopping step (ii) when the erosion kernel reaches a fat area in an inner portion of the breast
17. The system of claim 16, wherein the processor is configured such that step (i) comprises:
(A) separating the image data into air, fat, tissues, and a bias area; and
(B) re-clustering the bias area to classify the bias area as air, fat, or tissues.
18. The system of claim 14, wherein the processor is configured for a situation in which the bias area arises from at least one of low-density glandular tissue and imaging artifacts.
19. The system of claim 14, wherein the processor is configured for:
(i) recording a global ratio of a fat area to a total edge area along the edge of the breast; and
(ii) stopping step (b) when the ratio reaches a predetermined value.
20. The system of claim 14, wherein the processor is configured such that the fuzzy clustering algorithm is a fuzzy c-means algorithm.
21. The system of claim 14, wherein the processor is configured to measure breast density.
22. The system of claim 14, wherein the processor is configured to detect breast masses.
23. The system of claim 14, wherein the processor is configured to detect breast calcifications.
24. The system of claim 14, wherein the processor is configured for automatically or semi-automatically detecting and characterizing at least one of mass, calcifications, duct structure, vascular structure, and breast density.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/985,517 US9392986B2 (en) | 2011-02-14 | 2012-02-14 | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
CN201280013089.4A CN103582455B (en) | 2011-02-14 | 2012-02-14 | Computer aided detection based on cone beam breast CT image and the method and apparatus of diagnosis |
EP12747439.3A EP2675360B1 (en) | 2011-02-14 | 2012-02-14 | Method and apparatus of cone beam breast ct image-based computer-aided detection and diagnosis |
US15/177,949 US10098600B2 (en) | 2011-02-14 | 2016-06-09 | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201161442559P | 2011-02-14 | 2011-02-14 | |
US61/442,559 | 2011-02-14 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/985,517 A-371-Of-International US9392986B2 (en) | 2011-02-14 | 2012-02-14 | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
US15/177,949 Continuation US10098600B2 (en) | 2011-02-14 | 2016-06-09 | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
Publications (3)
Publication Number | Publication Date |
---|---|
WO2012112627A2 true WO2012112627A2 (en) | 2012-08-23 |
WO2012112627A3 WO2012112627A3 (en) | 2012-11-08 |
WO2012112627A4 WO2012112627A4 (en) | 2013-02-21 |
Family
ID=46673140
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2012/025141 WO2012112627A2 (en) | 2011-02-14 | 2012-02-14 | Method and apparatus of cone beam breast ct image-based computer-aided detection and diagnosis |
Country Status (4)
Country | Link |
---|---|
US (2) | US9392986B2 (en) |
EP (1) | EP2675360B1 (en) |
CN (1) | CN103582455B (en) |
WO (1) | WO2012112627A2 (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9999402B2 (en) | 2014-07-21 | 2018-06-19 | International Business Machines Corporation | Automatic image segmentation |
EP3366217A1 (en) | 2013-03-15 | 2018-08-29 | Hologic Inc. | Tomosynthesis-guided biopsy in prone |
CN111081380A (en) * | 2019-12-26 | 2020-04-28 | 天津大学 | Method for optimizing microwave breast image based on image quality index and simulated annealing |
CN111937079A (en) * | 2018-01-25 | 2020-11-13 | 珀尔·霍尔 | Compositions and methods for monitoring treatment of breast conditions |
US11364005B2 (en) | 2013-10-24 | 2022-06-21 | Hologic, Inc. | System and method for navigating x-ray guided breast biopsy |
US11403483B2 (en) | 2017-06-20 | 2022-08-02 | Hologic, Inc. | Dynamic self-learning medical image method and system |
US11406332B2 (en) | 2011-03-08 | 2022-08-09 | Hologic, Inc. | System and method for dual energy and/or contrast enhanced breast imaging for screening, diagnosis and biopsy |
US11419565B2 (en) | 2014-02-28 | 2022-08-23 | IIologic, Inc. | System and method for generating and displaying tomosynthesis image slabs |
US11445993B2 (en) | 2017-03-30 | 2022-09-20 | Hologic, Inc. | System and method for targeted object enhancement to generate synthetic breast tissue images |
US11452486B2 (en) | 2006-02-15 | 2022-09-27 | Hologic, Inc. | Breast biopsy and needle localization using tomosynthesis systems |
US11455754B2 (en) | 2017-03-30 | 2022-09-27 | Hologic, Inc. | System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement |
US11481038B2 (en) | 2020-03-27 | 2022-10-25 | Hologic, Inc. | Gesture recognition in controlling medical hardware or software |
US11508340B2 (en) | 2011-11-27 | 2022-11-22 | Hologic, Inc. | System and method for generating a 2D image using mammography and/or tomosynthesis image data |
US11663780B2 (en) | 2012-02-13 | 2023-05-30 | Hologic Inc. | System and method for navigating a tomosynthesis stack using synthesized image data |
US11694792B2 (en) | 2019-09-27 | 2023-07-04 | Hologic, Inc. | AI system for predicting reading time and reading complexity for reviewing 2D/3D breast images |
US11701199B2 (en) | 2009-10-08 | 2023-07-18 | Hologic, Inc. | Needle breast biopsy system and method of use |
US11775156B2 (en) | 2010-11-26 | 2023-10-03 | Hologic, Inc. | User interface for medical image review workstation |
US11883206B2 (en) | 2019-07-29 | 2024-01-30 | Hologic, Inc. | Personalized breast imaging system |
US11957497B2 (en) | 2017-03-30 | 2024-04-16 | Hologic, Inc | System and method for hierarchical multi-level feature image synthesis and representation |
US11983799B2 (en) | 2022-07-22 | 2024-05-14 | Hologic, Inc. | System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement |
Families Citing this family (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9247926B2 (en) | 2010-04-14 | 2016-02-02 | Maui Imaging, Inc. | Concave ultrasound transducers and 3D arrays |
ES2663617T3 (en) * | 2010-11-18 | 2018-04-16 | Hologic Inc. | Table for medical procedures |
US8989469B2 (en) * | 2010-12-20 | 2015-03-24 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for simultaneous acquisition of scatter and image projection data in computed tomography |
US9392986B2 (en) * | 2011-02-14 | 2016-07-19 | University Of Rochester | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
US8818065B2 (en) * | 2011-07-01 | 2014-08-26 | Carestream Health, Inc. | Methods and apparatus for scatter correction for CBCT system and cone-beam image reconstruction |
WO2013101988A1 (en) | 2011-12-29 | 2013-07-04 | Maui Imaging, Inc. | M-mode ultrasound imaging of arbitrary paths |
CN104135937B (en) | 2012-02-21 | 2017-03-29 | 毛伊图像公司 | Material stiffness is determined using porous ultrasound |
CN104620128B (en) | 2012-08-10 | 2017-06-23 | 毛伊图像公司 | The calibration of multiple aperture ultrasonic probe |
US9883848B2 (en) | 2013-09-13 | 2018-02-06 | Maui Imaging, Inc. | Ultrasound imaging using apparent point-source transmit transducer |
DE102014208411A1 (en) * | 2014-05-06 | 2015-11-12 | Siemens Aktiengesellschaft | Evaluation of an X-ray image of a breast produced during mammography |
JP6611428B2 (en) * | 2014-12-09 | 2019-11-27 | キヤノン株式会社 | Mammography system |
KR20170007181A (en) | 2015-07-10 | 2017-01-18 | 3스캔 인크. | Spatial multiplexing of histological stains |
WO2017045618A1 (en) | 2015-09-15 | 2017-03-23 | Shanghai United Imaging Healthcare Co., Ltd. | Image reconstruction system and method |
US9697623B1 (en) * | 2015-09-15 | 2017-07-04 | Shanghai United Imaging Healthcare Co., Ltd. | Image reconstruction system and method |
EP3408037A4 (en) | 2016-01-27 | 2019-10-23 | Maui Imaging, Inc. | Ultrasound imaging with sparse array probes |
US9943280B2 (en) | 2016-03-07 | 2018-04-17 | General Electric Company | Breast tomosynthesis with flexible compression paddle |
EP3639242B1 (en) * | 2017-06-16 | 2023-07-26 | Volpara Health Technologies Limited | Method for detection and quantification of arterial calcification |
JP2019037576A (en) * | 2017-08-25 | 2019-03-14 | キヤノン株式会社 | Breast imaging device, image processor and image processing method |
US10993689B2 (en) | 2017-08-31 | 2021-05-04 | General Electric Company | Method and system for motion assessment and correction in digital breast tomosynthesis |
EP3457360B1 (en) * | 2017-09-13 | 2019-10-30 | Siemens Healthcare GmbH | Reduction of motion artefacts in computer tomography image data |
JP6757303B2 (en) * | 2017-09-28 | 2020-09-16 | 富士フイルム株式会社 | Breast type identification friend, method and program |
CA3090672A1 (en) * | 2018-02-06 | 2019-08-15 | The Regents Of The University Of Michigan | Systems and methods for analysis and remote interpretation of optical histologic images |
CN108734705A (en) * | 2018-05-17 | 2018-11-02 | 杭州电子科技大学 | Digital galactophore fault image calcification clusters automatic testing method based on deep learning |
WO2019222606A1 (en) * | 2018-05-18 | 2019-11-21 | The Johns Hopkins University | Multi-motion compensation for high-quality cone-beam ct of the head |
KR102068326B1 (en) * | 2018-06-27 | 2020-01-20 | 한국원자력의학원 | Radiation therapy apparatus for animals |
CN109087713A (en) * | 2018-08-02 | 2018-12-25 | 山东省计算中心(国家超级计算济南中心) | A kind of slow sick Added Management decision support method based on fuzzy C-means clustering |
CN109288536B (en) * | 2018-09-30 | 2021-01-29 | 数坤(北京)网络科技有限公司 | Method, device and system for obtaining classification of coronary artery calcification area |
CN109872307B (en) * | 2019-01-30 | 2022-01-07 | 腾讯科技(深圳)有限公司 | Method for detecting tumor in biological tissue image, corresponding device and medium |
JP7349345B2 (en) * | 2019-12-23 | 2023-09-22 | 富士フイルムヘルスケア株式会社 | Image diagnosis support device, image diagnosis support program, and medical image acquisition device equipped with the same |
CN111028310B (en) * | 2019-12-31 | 2023-10-03 | 上海联影医疗科技股份有限公司 | Method, device, terminal and medium for determining scanning parameters of breast tomography |
WO2021155340A1 (en) * | 2020-01-31 | 2021-08-05 | The General Hospital Corporation | Systems and methods for artifact reduction in tomosynthesis with multi-scale deep learning image processing |
US11540789B1 (en) | 2022-04-22 | 2023-01-03 | Izotropic Corporation | Self-shielded x-ray computed tomography system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090171244A1 (en) | 2007-12-21 | 2009-07-02 | Koning Corporation | Methods and apparatus of cone beam ct imaging and image-guided procedures |
Family Cites Families (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2014918A1 (en) * | 1989-09-06 | 1991-03-06 | James A. Mcfaul | Scanning mammography system with improved skin line viewing |
US4998270A (en) * | 1989-09-06 | 1991-03-05 | General Electric Company | Mammographic apparatus with collimated controllable X-ray intensity and plurality filters |
US4969174A (en) * | 1989-09-06 | 1990-11-06 | General Electric Company | Scanning mammography system with reduced scatter radiation |
US5857030A (en) * | 1995-08-18 | 1999-01-05 | Eastman Kodak Company | Automated method and system for digital image processing of radiologic images utilizing artificial neural networks |
US5889882A (en) * | 1996-03-21 | 1999-03-30 | Eastman Kodak Company | Detection of skin-line transition in digital medical imaging |
US5799100A (en) * | 1996-06-03 | 1998-08-25 | University Of South Florida | Computer-assisted method and apparatus for analysis of x-ray images using wavelet transforms |
US6310967B1 (en) * | 1998-04-29 | 2001-10-30 | University Of South Florida | Normal and abnormal tissue identification system and method for medical images such as digital mammograms |
US6480565B1 (en) * | 1999-11-18 | 2002-11-12 | University Of Rochester | Apparatus and method for cone beam volume computed tomography breast imaging |
US6987831B2 (en) | 1999-11-18 | 2006-01-17 | University Of Rochester | Apparatus and method for cone beam volume computed tomography breast imaging |
JP2001299733A (en) * | 2000-04-27 | 2001-10-30 | Konica Corp | Pci radiation beam image processing apparatus, pci radiation beam image detecting and processing apparatus, pci radiation beam image outputting apparatus and pci radiation beam image diagnosis supporting apparatus |
US6956975B2 (en) * | 2001-04-02 | 2005-10-18 | Eastman Kodak Company | Method for improving breast cancer diagnosis using mountain-view and contrast-enhancement presentation of mammography |
US7298877B1 (en) * | 2001-11-20 | 2007-11-20 | Icad, Inc. | Information fusion with Bayes networks in computer-aided detection systems |
FI113897B (en) * | 2001-11-23 | 2004-06-30 | Planmed Oy | Automatic exposure procedure and automatic exposure system |
US7295691B2 (en) * | 2002-05-15 | 2007-11-13 | Ge Medical Systems Global Technology Company, Llc | Computer aided diagnosis of an image set |
US20050053270A1 (en) * | 2003-09-05 | 2005-03-10 | Konica Minolta Medical & Graphic, Inc. | Image processing apparatus and signal processing apparatus |
US7693318B1 (en) | 2004-01-12 | 2010-04-06 | Pme Ip Australia Pty Ltd | Method and apparatus for reconstruction of 3D image volumes from projection images |
JP4549093B2 (en) * | 2004-04-12 | 2010-09-22 | キヤノン株式会社 | Image processing apparatus and method, and program |
DE102004034239A1 (en) * | 2004-07-15 | 2006-02-02 | Siemens Ag | Medical imaging device |
US20060074287A1 (en) * | 2004-09-30 | 2006-04-06 | General Electric Company | Systems, methods and apparatus for dual mammography image detection |
CA2605836A1 (en) * | 2005-04-25 | 2006-11-02 | University Of Rochester | Method and apparatus of global de-noising for ct imaging |
WO2006119426A2 (en) * | 2005-05-03 | 2006-11-09 | Regents Of The University Of California | Biopsy systems for breast computed tomography |
US20070206844A1 (en) * | 2006-03-03 | 2007-09-06 | Fuji Photo Film Co., Ltd. | Method and apparatus for breast border detection |
US20070211930A1 (en) | 2006-03-09 | 2007-09-13 | Terry Dolwick | Attribute based image enhancement and display for medical imaging applications |
US8000435B2 (en) * | 2006-06-22 | 2011-08-16 | Koninklijke Philips Electronics N.V. | Method and system for error compensation |
JP4833785B2 (en) * | 2006-09-29 | 2011-12-07 | 富士フイルム株式会社 | Radiographic apparatus and radiographic method |
US7429737B2 (en) * | 2006-11-09 | 2008-09-30 | Carestream Health, Inc. | Retrofit digital mammography detector |
US7903861B2 (en) * | 2006-12-28 | 2011-03-08 | Carestream Health, Inc. | Method for classifying breast tissue density using computed image features |
JP5032229B2 (en) * | 2007-07-20 | 2012-09-26 | 富士フイルム株式会社 | Radiographic imaging apparatus and imaging method |
US7929743B2 (en) * | 2007-10-02 | 2011-04-19 | Hologic, Inc. | Displaying breast tomosynthesis computer-aided detection results |
ATE550742T1 (en) * | 2008-04-16 | 2012-04-15 | Univ Lausanne | AUTOMATIC DETECTION AND ACCURATE SEGMENTATION OF THE ABDOMINAL AORTIC ANEURYSMA |
US8233690B2 (en) * | 2008-04-30 | 2012-07-31 | Real-Time Tomography, Llc | Dynamic tomographic image reconstruction and rendering on-demand |
US20100158332A1 (en) * | 2008-12-22 | 2010-06-24 | Dan Rico | Method and system of automated detection of lesions in medical images |
US8184890B2 (en) * | 2008-12-26 | 2012-05-22 | Three Palm Software | Computer-aided diagnosis and visualization of tomosynthesis mammography data |
JP5399278B2 (en) * | 2009-03-31 | 2014-01-29 | 富士フイルム株式会社 | Breast content estimation apparatus and method |
US20110052025A1 (en) * | 2009-08-03 | 2011-03-03 | Matakina Technology Limited | System for imaging pathway verification |
EP2462561B1 (en) * | 2009-08-03 | 2018-10-31 | Volpara Health Technologies Limited | A method and system for analysing tissue from images |
US8582858B2 (en) * | 2009-12-17 | 2013-11-12 | The Regents Of The University Of California | Method and apparatus for quantitative analysis of breast density morphology based on MRI |
DE202011110476U1 (en) * | 2010-09-09 | 2014-03-27 | Hologic Inc. | System for dynamic modification of recording parameters during image acquisition |
US9208556B2 (en) * | 2010-11-26 | 2015-12-08 | Quantitative Insights, Inc. | Method, system, software and medium for advanced intelligent image analysis and display of medical images and information |
WO2012082994A2 (en) * | 2010-12-15 | 2012-06-21 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Method for assessing breast density |
US9392986B2 (en) * | 2011-02-14 | 2016-07-19 | University Of Rochester | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis |
-
2012
- 2012-02-14 US US13/985,517 patent/US9392986B2/en active Active
- 2012-02-14 WO PCT/US2012/025141 patent/WO2012112627A2/en active Application Filing
- 2012-02-14 EP EP12747439.3A patent/EP2675360B1/en active Active
- 2012-02-14 CN CN201280013089.4A patent/CN103582455B/en active Active
-
2016
- 2016-06-09 US US15/177,949 patent/US10098600B2/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090171244A1 (en) | 2007-12-21 | 2009-07-02 | Koning Corporation | Methods and apparatus of cone beam ct imaging and image-guided procedures |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11452486B2 (en) | 2006-02-15 | 2022-09-27 | Hologic, Inc. | Breast biopsy and needle localization using tomosynthesis systems |
US11918389B2 (en) | 2006-02-15 | 2024-03-05 | Hologic, Inc. | Breast biopsy and needle localization using tomosynthesis systems |
US11701199B2 (en) | 2009-10-08 | 2023-07-18 | Hologic, Inc. | Needle breast biopsy system and method of use |
US11775156B2 (en) | 2010-11-26 | 2023-10-03 | Hologic, Inc. | User interface for medical image review workstation |
US11406332B2 (en) | 2011-03-08 | 2022-08-09 | Hologic, Inc. | System and method for dual energy and/or contrast enhanced breast imaging for screening, diagnosis and biopsy |
US11508340B2 (en) | 2011-11-27 | 2022-11-22 | Hologic, Inc. | System and method for generating a 2D image using mammography and/or tomosynthesis image data |
US11837197B2 (en) | 2011-11-27 | 2023-12-05 | Hologic, Inc. | System and method for generating a 2D image using mammography and/or tomosynthesis image data |
US11663780B2 (en) | 2012-02-13 | 2023-05-30 | Hologic Inc. | System and method for navigating a tomosynthesis stack using synthesized image data |
US10456213B2 (en) | 2013-03-15 | 2019-10-29 | Hologic, Inc. | Tomosynthesis-guided biopsy apparatus and method |
US10092358B2 (en) | 2013-03-15 | 2018-10-09 | Hologic, Inc. | Tomosynthesis-guided biopsy apparatus and method |
EP3366217A1 (en) | 2013-03-15 | 2018-08-29 | Hologic Inc. | Tomosynthesis-guided biopsy in prone |
US11589944B2 (en) | 2013-03-15 | 2023-02-28 | Hologic, Inc. | Tomosynthesis-guided biopsy apparatus and method |
US11364005B2 (en) | 2013-10-24 | 2022-06-21 | Hologic, Inc. | System and method for navigating x-ray guided breast biopsy |
US11801025B2 (en) | 2014-02-28 | 2023-10-31 | Hologic, Inc. | System and method for generating and displaying tomosynthesis image slabs |
US11419565B2 (en) | 2014-02-28 | 2022-08-23 | IIologic, Inc. | System and method for generating and displaying tomosynthesis image slabs |
US9999402B2 (en) | 2014-07-21 | 2018-06-19 | International Business Machines Corporation | Automatic image segmentation |
US11455754B2 (en) | 2017-03-30 | 2022-09-27 | Hologic, Inc. | System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement |
US11957497B2 (en) | 2017-03-30 | 2024-04-16 | Hologic, Inc | System and method for hierarchical multi-level feature image synthesis and representation |
US11445993B2 (en) | 2017-03-30 | 2022-09-20 | Hologic, Inc. | System and method for targeted object enhancement to generate synthetic breast tissue images |
US11403483B2 (en) | 2017-06-20 | 2022-08-02 | Hologic, Inc. | Dynamic self-learning medical image method and system |
US11850021B2 (en) | 2017-06-20 | 2023-12-26 | Hologic, Inc. | Dynamic self-learning medical image method and system |
CN111937079A (en) * | 2018-01-25 | 2020-11-13 | 珀尔·霍尔 | Compositions and methods for monitoring treatment of breast conditions |
US11883206B2 (en) | 2019-07-29 | 2024-01-30 | Hologic, Inc. | Personalized breast imaging system |
US11694792B2 (en) | 2019-09-27 | 2023-07-04 | Hologic, Inc. | AI system for predicting reading time and reading complexity for reviewing 2D/3D breast images |
CN111081380A (en) * | 2019-12-26 | 2020-04-28 | 天津大学 | Method for optimizing microwave breast image based on image quality index and simulated annealing |
CN111081380B (en) * | 2019-12-26 | 2023-04-07 | 天津大学 | Method for optimizing microwave breast image based on image quality index and simulated annealing |
US11481038B2 (en) | 2020-03-27 | 2022-10-25 | Hologic, Inc. | Gesture recognition in controlling medical hardware or software |
US11983799B2 (en) | 2022-07-22 | 2024-05-14 | Hologic, Inc. | System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement |
Also Published As
Publication number | Publication date |
---|---|
US10098600B2 (en) | 2018-10-16 |
CN103582455A (en) | 2014-02-12 |
US20140037044A1 (en) | 2014-02-06 |
US9392986B2 (en) | 2016-07-19 |
EP2675360B1 (en) | 2022-08-10 |
WO2012112627A4 (en) | 2013-02-21 |
EP2675360A4 (en) | 2016-12-28 |
WO2012112627A3 (en) | 2012-11-08 |
CN103582455B (en) | 2016-12-28 |
EP2675360A2 (en) | 2013-12-25 |
US20170020474A1 (en) | 2017-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10098600B2 (en) | Method and apparatus for cone beam breast CT image-based computer-aided detection and diagnosis | |
US7218766B2 (en) | Computer aided detection (CAD) for 3D digital mammography | |
Chen et al. | Computer-aided diagnosis applied to US of solid breast nodules by using neural networks | |
US7646902B2 (en) | Computerized detection of breast cancer on digital tomosynthesis mammograms | |
US7903861B2 (en) | Method for classifying breast tissue density using computed image features | |
JP5138910B2 (en) | 3D CAD system and method using projected images | |
US7865002B2 (en) | Methods and apparatus for computer automated diagnosis of mammogram images | |
US8634622B2 (en) | Computer-aided detection of regions of interest in tomographic breast imagery | |
US7840046B2 (en) | System and method for detection of breast masses and calcifications using the tomosynthesis projection and reconstructed images | |
Reiser et al. | Computerized mass detection for digital breast tomosynthesis directly from the projection images | |
Yam et al. | Three-dimensional reconstruction of microcalcification clusters from two mammographic views | |
US8223916B2 (en) | Computer-aided detection of anatomical abnormalities in x-ray tomosynthesis images | |
JP2002523123A (en) | Method and system for lesion segmentation and classification | |
Qian et al. | Computer-aided mass detection based on ipsilateral multiview mammograms | |
JP5048233B2 (en) | Method and system for anatomical shape detection in a CAD system | |
Caroline et al. | Computer aided detection of masses in digital breast tomosynthesis: A review | |
Thangaraju et al. | Detection of microcalcification clusters using hessian matrix and foveal segmentation method on multiscale analysis in digital mammograms | |
Wienbeck et al. | Comparison between cone-beam breast-CT and full-field digital mammography for microcalcification detection depending on breast density | |
Chan | Computer-aided diagnosis in breast tomosynthesis and chest CT | |
Olsén | Towards automatic image analysis for computerised mammography | |
Li et al. | Intelligent system for predicting breast tumors using machine learning | |
Jeong et al. | Simplified computer-aided detection scheme of microcalcification clusters in digital breast tomosynthesis images | |
Zhang et al. | Computer aided breast density evaluation in cone beam breast CT | |
Chan et al. | Comparison of computerized mass detection in digital breast tomosynthesis (DBT) mammograms and conventional mammograms | |
Zhang | Computer aided diagnosis for cone beam breast CT |
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: 12747439 Country of ref document: EP Kind code of ref document: A2 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012747439 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13985517 Country of ref document: US |