1
|
Vedantham S, Tseng HW, Fu Z, Chow HHS. Dedicated Cone-Beam Breast CT: Reproducibility of Volumetric Glandular Fraction with Advanced Image Reconstruction Methods. Tomography 2023; 9:2039-2051. [PMID: 37987346 PMCID: PMC10661286 DOI: 10.3390/tomography9060160] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 10/06/2023] [Accepted: 10/20/2023] [Indexed: 11/22/2023] Open
Abstract
Dedicated cone-beam breast computed tomography (CBBCT) is an emerging modality and provides fully three-dimensional (3D) images of the uncompressed breast at an isotropic voxel resolution. In an effort to translate this modality to breast cancer screening, advanced image reconstruction methods are being pursued. Since radiographic breast density is an established risk factor for breast cancer and CBBCT provides volumetric data, this study investigates the reproducibility of the volumetric glandular fraction (VGF), defined as the proportion of fibroglandular tissue volume relative to the total breast volume excluding the skin. Four image reconstruction methods were investigated: the analytical Feldkamp-Davis-Kress (FDK), a compressed sensing-based fast, regularized, iterative statistical technique (FRIST), a fully supervised deep learning approach using a multi-scale residual dense network (MS-RDN), and a self-supervised approach based on Noise-to-Noise (N2N) learning. Projection datasets from 106 women who participated in a prior clinical trial were reconstructed using each of these algorithms at a fixed isotropic voxel size of (0.273 mm3). Each reconstructed breast volume was segmented into skin, adipose, and fibroglandular tissues, and the VGF was computed. The VGF did not differ among the four reconstruction methods (p = 0.167), and none of the three advanced image reconstruction algorithms differed from the standard FDK reconstruction (p > 0.862). Advanced reconstruction algorithms developed for low-dose CBBCT reproduce the VGF to provide quantitative breast density, which can be used for risk estimation.
Collapse
Affiliation(s)
- Srinivasan Vedantham
- Department of Medical Imaging, University of Arizona, Tucson, AZ 85724, USA; (H.W.T.); (Z.F.)
- Department of Biomedical Engineering, University of Arizona, Tucson, AZ 85724, USA
| | - Hsin Wu Tseng
- Department of Medical Imaging, University of Arizona, Tucson, AZ 85724, USA; (H.W.T.); (Z.F.)
| | - Zhiyang Fu
- Department of Medical Imaging, University of Arizona, Tucson, AZ 85724, USA; (H.W.T.); (Z.F.)
| | | |
Collapse
|
2
|
Vedantham S, Shazeeb MS, Chiang A, Vijayaraghavan GR. Artificial Intelligence in Breast X-Ray Imaging. Semin Ultrasound CT MR 2023; 44:2-7. [PMID: 36792270 PMCID: PMC9932302 DOI: 10.1053/j.sult.2022.12.002] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
This topical review is focused on the clinical breast x-ray imaging applications of the rapidly evolving field of artificial intelligence (AI). The range of AI applications is broad. AI can be used for breast cancer risk estimation that could allow for tailoring the screening interval and the protocol that are woman-specific and for triaging the screening exams. It also can serve as a tool to aid in the detection and diagnosis for improved sensitivity and specificity and as a tool to reduce radiologists' reading time. AI can also serve as a potential second 'reader' during screening interpretation. During the last decade, numerous studies have shown the potential of AI-assisted interpretation of mammography and to a lesser extent digital breast tomosynthesis; however, most of these studies are retrospective in nature. There is a need for prospective clinical studies to evaluate these technologies to better understand their real-world efficacy. Further, there are ethical, medicolegal, and liability concerns that need to be considered prior to the routine use of AI in the breast imaging clinic.
Collapse
Affiliation(s)
| | | | - Alan Chiang
- Department of Medical Imaging, University of Arizona, Tucson, AZ
| | | |
Collapse
|
3
|
Development of digital breast tomosynthesis and diffuse optical tomography fusion imaging for breast cancer detection. Sci Rep 2020; 10:13127. [PMID: 32753578 PMCID: PMC7403423 DOI: 10.1038/s41598-020-70103-0] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2020] [Accepted: 07/20/2020] [Indexed: 02/06/2023] Open
Abstract
Diffuse optical tomography (DOT) non-invasively measures the functional characteristics of breast lesions using near infrared light to probe tissue optical properties. This study aimed to evaluate a new digital breast tomosynthesis (DBT)/DOT fusion imaging technique and obtain preliminary data for breast cancer detection. Twenty-eight women were prospectively enrolled and underwent both DBT and DOT examinations. DBT/DOT fusion imaging was created after acquisition of both examinations. Two breast radiologists analyzed DBT and DOT images independently, and then finally evaluated the fusion images. The diagnostic performance of each reading session was compared and interobserver agreement was assessed. The technical success rate was 96.4%, with one failure due to an error during DOT data storage. Among the 27 women finally included in the analysis, 13 had breast cancer. The areas under the receiver operating characteristic curve (AUCs) for DBT were 0.783 and 0.854 for readers 1 and 2, respectively. DOT showed comparable diagnostic performance to DBT for both readers. The AUCs were significantly improved (P = 0.004) when the DBT/DOT fusion images were used. Interobserver agreements were highest for the DBT/DOT fusion images. In conclusion, this study suggests that DBT/DOT fusion imaging technique appears to be a promising tool for breast cancer diagnosis.
Collapse
|
4
|
Sujlana PS, Mahesh M, Vedantham S, Harvey SC, Mullen LA, Woods RW. Digital breast tomosynthesis: Image acquisition principles and artifacts. Clin Imaging 2018; 55:188-195. [PMID: 30236642 DOI: 10.1016/j.clinimag.2018.07.013] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2018] [Revised: 06/26/2018] [Accepted: 07/16/2018] [Indexed: 11/16/2022]
Abstract
Digital breast tomosynthesis (DBT) is a new technology that is being used more frequently for both breast cancer screening and diagnostic purposes and its utilization is likely to continue to increase over time. The major benefit of tomosynthesis over 2D-mammography is that it allows radiologists to view breast tissue using a three-dimensional dataset and improves diagnostic accuracy by facilitating differentiation of potentially malignant lesions from overlap of normal tissue. In addition, image processing techniques allow reconstruction of two dimensional synthesized mammograms (SM) from DBT data, which eliminates the need for acquiring two dimensional full field digital mammography (FFDM) in addition to tomosynthesis and thereby reduces the radiation dose. DBT systems incorporate a moveable x-ray tube, which moves in a prescribed way over a limited angular range to obtain three-dimensional data of patients' breasts, and utilize reconstruction algorithms. The limited angular range for DBT leads to incomplete sampling of the object, and a movable x-ray tube prolongs the imaging time, both of which make DBT and SM susceptible to artifacts. Understanding the etiology of these artifacts should help radiologists in reducing the number of artifacts and in differentiating a true finding from one related to an artifact, thus potentially decreasing recall rates and false positive rates. This is becoming especially important with increased incorporation of DBT in practices around the world. The goal of this article is to review the physics principles behind DBT systems and use these principles to explain the origin of artifacts that can limit diagnostic evaluation.
Collapse
Affiliation(s)
- Parvinder S Sujlana
- Johns Hopkins Medical Institutions, The Russell H. Morgan Department of Radiology and Radiological Science, 601 N. Wolfe Street, Baltimore, MD 21287, United States of America
| | - Mahadevappa Mahesh
- Johns Hopkins Medical Institutions, The Russell H. Morgan Department of Radiology and Radiological Science, 601 N. Wolfe Street, Baltimore, MD 21287, United States of America
| | - Srinivasan Vedantham
- University of Arizona - Banner University Medical Center, 1609 N. Warren Ave, Tucson, AZ 85719, United States of America
| | - Susan C Harvey
- Johns Hopkins Medical Institutions, The Russell H. Morgan Department of Radiology and Radiological Science, 601 N. Wolfe Street, Baltimore, MD 21287, United States of America
| | - Lisa A Mullen
- Johns Hopkins Medical Institutions, The Russell H. Morgan Department of Radiology and Radiological Science, 601 N. Wolfe Street, Baltimore, MD 21287, United States of America
| | - Ryan W Woods
- University of Wisconsin School of Medicine and Public Health, Department of Radiology, 600 Highland Avenue, Madison, WI 53792, United States of America.
| |
Collapse
|
5
|
Vedantham S, Karellas A. Emerging Breast Imaging Technologies on the Horizon. Semin Ultrasound CT MR 2018; 39:114-121. [PMID: 29317033 DOI: 10.1053/j.sult.2017.09.004] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
Early detection of breast cancers by mammography in conjunction with adjuvant therapy has contributed to reduction in breast cancer mortality. Mammography remains the "gold-standard" for breast cancer screening but is limited by tissue superposition. Digital breast tomosynthesis and more recently, dedicated breast computed tomography have been developed to alleviate the tissue superposition problem. However, all of these modalities rely upon x-ray attenuation contrast to provide anatomical images, and there are ongoing efforts to develop and clinically translate alternative modalities. These emerging modalities could provide for new contrast mechanisms and may potentially improve lesion detection and diagnosis. In this article, several of these emerging modalities are discussed with a focus on technologies that have advanced to the stage of in vivo clinical evaluation.
Collapse
Affiliation(s)
- Srinivasan Vedantham
- Department of Medical Imaging, University of Arizona College of Medicine, Banner University Medical Center, Tucson, AZ.
| | - Andrew Karellas
- Department of Medical Imaging, University of Arizona College of Medicine, Banner University Medical Center, Tucson, AZ
| |
Collapse
|
6
|
Zimmermann BB, Deng B, Singh B, Martino M, Selb J, Fang Q, Sajjadi AY, Cormier J, Moore RH, Kopans DB, Boas DA, Saksena MA, Carp SA. Multimodal breast cancer imaging using coregistered dynamic diffuse optical tomography and digital breast tomosynthesis. JOURNAL OF BIOMEDICAL OPTICS 2017; 22:46008. [PMID: 28447102 PMCID: PMC5406652 DOI: 10.1117/1.jbo.22.4.046008] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2016] [Accepted: 04/07/2017] [Indexed: 05/02/2023]
Abstract
Diffuse optical tomography (DOT) is emerging as a noninvasive functional imaging method for breast cancer diagnosis and neoadjuvant chemotherapy monitoring. In particular, the multimodal approach of combining DOT with x-ray digital breast tomosynthesis (DBT) is especially synergistic as DBT prior information can be used to enhance the DOT reconstruction. DOT, in turn, provides a functional information overlay onto the mammographic images, increasing sensitivity and specificity to cancer pathology. We describe a dynamic DOT apparatus designed for tight integration with commercial DBT scanners and providing a fast (up to 1 Hz) image acquisition rate to enable tracking hemodynamic changes induced by the mammographic breast compression. The system integrates 96 continuous-wave and 24 frequency-domain source locations as well as 32 continuous wave and 20 frequency-domain detection locations into low-profile plastic plates that can easily mate to the DBT compression paddle and x-ray detector cover, respectively. We demonstrate system performance using static and dynamic tissue-like phantoms as well as in vivo images acquired from the pool of patients recalled for breast biopsies at the Massachusetts General Hospital Breast Imaging Division.
Collapse
Affiliation(s)
- Bernhard B. Zimmermann
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States
| | - Bin Deng
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
| | - Bhawana Singh
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
| | - Mark Martino
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
| | - Juliette Selb
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
| | - Qianqian Fang
- Northeastern University, Department of Bioengineering, Boston, Massachusetts, United States
| | - Amir Y. Sajjadi
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
| | - Jayne Cormier
- Massachusetts General Hospital, Breast Imaging Division, Department of Radiology, Boston, Massachusetts, United States
| | - Richard H. Moore
- Massachusetts General Hospital, Breast Imaging Division, Department of Radiology, Boston, Massachusetts, United States
| | - Daniel B. Kopans
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
- Massachusetts General Hospital, Breast Imaging Division, Department of Radiology, Boston, Massachusetts, United States
| | - David A. Boas
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
| | - Mansi A. Saksena
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
- Massachusetts General Hospital, Breast Imaging Division, Department of Radiology, Boston, Massachusetts, United States
| | - Stefan A. Carp
- Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Charlestown, Massachusetts, United States
- Harvard Medical School, Department of Radiology, Boston, Massachusetts, United States
- Address all correspondence to: Stefan A. Carp, E-mail:
| |
Collapse
|
7
|
Michaelsen KE, Krishnaswamy V, Shi L, Vedantham S, Karellas A, Pogue BW, Paulsen KD, Poplack SP. Effects of breast density and compression on normal breast tissue hemodynamics through breast tomosynthesis guided near-infrared spectral tomography. JOURNAL OF BIOMEDICAL OPTICS 2016; 21:91316. [PMID: 27677170 PMCID: PMC5038925 DOI: 10.1117/1.jbo.21.9.091316] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/06/2016] [Accepted: 08/30/2016] [Indexed: 06/06/2023]
Abstract
Optically derived tissue properties across a range of breast densities and the effects of breast compression on estimates of hemoglobin, oxygen metabolism, and water and lipid concentrations were obtained from a coregistered imaging system that integrates near-infrared spectral tomography (NIRST) with digital breast tomosynthesis (DBT). Image data were analyzed from 27 women who underwent four IRB approved NIRST/DBT exams that included fully and mildly compressed breast acquisitions in two projections—craniocaudal (CC) and mediolateral-oblique (MLO)—and generated four data sets per patient (full and moderate compression in CC and MLO views). Breast density was correlated with HbT (r=0.64, p=0.001), water (r=0.62, p=0.003), and lipid concentrations (r=?0.74, p<0.001), but not oxygen saturation. CC and MLO views were correlated for individual subjects and demonstrated no statistically significant differences in grouped analysis. Comparison of compressed and uncompressed imaging demonstrated a significant decrease in oxygen saturation under compression (58% versus 50%, p=0.04). Mammographic breast density categorization was correlated with measured optically derived properties.
Collapse
Affiliation(s)
- Kelly E. Michaelsen
- Dartmouth College, Thayer School of Engineering, 14 Engineering Drive, Hanover, New Hampshire 03755, United States
| | - Venkataramanan Krishnaswamy
- Dartmouth College, Thayer School of Engineering, 14 Engineering Drive, Hanover, New Hampshire 03755, United States
| | - Linxi Shi
- Georgia Institute of Technology, School of Mechanical Engineering, 801 Ferst Drive, Atlanta, Georgia 30332, United States
| | - Srinivasan Vedantham
- University of Massachusetts Medical School, Department of Radiology, 55 Lake Avenue North, Worcester, Massachusetts 01655, United States
| | - Andrew Karellas
- University of Massachusetts Medical School, Department of Radiology, 55 Lake Avenue North, Worcester, Massachusetts 01655, United States
| | - Brian W. Pogue
- Dartmouth College, Thayer School of Engineering, 14 Engineering Drive, Hanover, New Hampshire 03755, United States
| | - Keith D. Paulsen
- Dartmouth College, Thayer School of Engineering, 14 Engineering Drive, Hanover, New Hampshire 03755, United States
| | - Steven P. Poplack
- Washington University School of Medicine, Mallinckrodt Institute of Radiology, 4921 Parkview Place, St. Louis, Missouri 63110, United States
| |
Collapse
|
8
|
Michaelsen KE, Krishnaswamy V, Shi L, Vedantham S, Poplack SP, Karellas A, Pogue BW, Paulsen KD. Calibration and optimization of 3D digital breast tomosynthesis guided near infrared spectral tomography. BIOMEDICAL OPTICS EXPRESS 2015; 6:4981-91. [PMID: 26713210 PMCID: PMC4679270 DOI: 10.1364/boe.6.004981] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/24/2015] [Revised: 10/30/2015] [Accepted: 11/01/2015] [Indexed: 05/18/2023]
Abstract
Calibration of a three-dimensional multimodal digital breast tomosynthesis (DBT) x-ray and non-fiber based near infrared spectral tomography (NIRST) system is challenging but essential for clinical studies. Phantom imaging results yielded linear contrast recovery of total hemoglobin (HbT) concentration for cylindrical inclusions of 15 mm, 10 mm and 7 mm with a 3.5% decrease in the HbT estimate for each 1 cm increase in inclusion depth. A clinical exam of a patient's breast containing both benign and malignant lesions was successfully imaged, with greater HbT was found in the malignancy relative to the benign abnormality and fibroglandular regions (11 μM vs. 9.5 μM). Tools developed improved imaging system characterization and optimization of signal quality, which will ultimately improve patient selection and subsequent clinical trial results.
Collapse
Affiliation(s)
| | | | - Linxi Shi
- Department of Radiology, University of Massachusetts Medical School, Worcester, MA 01655,
USA
- Currently at School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, 30332,
USA
| | - Srinivasan Vedantham
- Department of Radiology, University of Massachusetts Medical School, Worcester, MA 01655,
USA
| | - Steven P. Poplack
- Thayer School of Engineering, Dartmouth College, Hanover, NH 03755,
USA
- Currently at Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110,
USA
| | - Andrew Karellas
- Department of Radiology, University of Massachusetts Medical School, Worcester, MA 01655,
USA
| | - Brian W. Pogue
- Thayer School of Engineering, Dartmouth College, Hanover, NH 03755,
USA
| | - Keith D. Paulsen
- Thayer School of Engineering, Dartmouth College, Hanover, NH 03755,
USA
| |
Collapse
|