1
|
Strandberg R, Illipse M, Czene K, Hall P, Humphreys K. Influence of mammographic density and compressed breast thickness on true mammographic sensitivity: a cohort study. Sci Rep 2023; 13:14194. [PMID: 37648804 PMCID: PMC10468499 DOI: 10.1038/s41598-023-41356-2] [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: 05/16/2023] [Accepted: 08/24/2023] [Indexed: 09/01/2023] Open
Abstract
Understanding the detectability of breast cancer using mammography is important when considering nation-wide screening programmes. Although the role of imaging settings on image quality has been studied extensively, their role in detectability of cancer at a population level is less well studied. We wish to quantify the association between mammographic screening sensitivity and various imaging parameters. Using a novel approach applied to a population-based breast cancer screening cohort, we specifically focus on sensitivity as defined in the classical diagnostic testing literature, as opposed to the screen-detected cancer rate, which is often used as a measure of sensitivity for monitoring and evaluating breast cancer screening. We use a natural history approach to model the presence and size of latent tumors at risk of detection at mammography screening, and the screening sensitivity is modeled as a logistic function of tumor size. With this approach we study the influence of compressed breast thickness, x-ray exposure, and compression pressure, in addition to (percent) breast density, on the screening test sensitivity. When adjusting for all screening parameters in addition to latent tumor size, we find that percent breast density and compressed breast thickness are statistically significant factors for the detectability of breast cancer. A change in breast density from 6.6 to 33.5% (the inter-quartile range) reduced the odds of detection by 61% (95% CI 48-71). Similarly, a change in compressed breast thickness from 46 to 66 mm reduced the odds by 42% (95% CI 21-57). The true sensitivity of mammography, defined as the probability that an examination leads to a positive result if a tumour is present in the breast, is associated with compressed breast thickness after accounting for mammographic density and tumour size. This can be used to guide studies of setups aimed at improving lesion detection. Compressed breast thickness-in addition to breast density-should be considered when assigning complementary screening modalities and personalized screening intervals.
Collapse
Affiliation(s)
- Rickard Strandberg
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
- Swedish eScience Research Centre (SeRC), Karolinska Institutet, Stockholm, Sweden.
| | - Maya Illipse
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
- Swedish eScience Research Centre (SeRC), Karolinska Institutet, Stockholm, Sweden
| | - Kamila Czene
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
| | - Per Hall
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
| | - Keith Humphreys
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
- Swedish eScience Research Centre (SeRC), Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
2
|
Kim YS, Cho HG, Kim J, Park SJ, Kim HJ, Lee SE, Yang JD, Kim WH, Lee JS. Prediction of Implant Size Based on Breast Volume Using Mammography with Fully Automated Measurements and Breast MRI. Ann Surg Oncol 2022; 29:7845-7854. [PMID: 35723790 DOI: 10.1245/s10434-022-11972-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Accepted: 05/17/2022] [Indexed: 11/18/2022]
Abstract
BACKGROUND Determination of implant size is crucial for patients with breast cancer undergoing one-stage breast reconstruction. The purpose of this study is to predict the implant size based on the breast volume measured by mammography (MG) with a fully automated method, and by breast magnetic resonance imaging (MRI) with a semi-automated method, in breast cancer patients with direct-to-implant reconstruction. PATIENTS AND METHODS This retrospective study included 84 patients with breast cancer who underwent direct-to-implant reconstruction after nipple-sparing or skin-sparing mastectomy and preoperative MG and MRI between April 2015 and April 2019. Breast volume was measured using (a) MG with a fully automated commercial software and (b) MRI with an in-house semi-automated software program. Multivariable regression analyses including breast volume and patient weight (P < 0.05 in univariable analysis) were conducted to predict implant size. RESULTS MG and MRI breast volume was highly correlated with both implant size (correlation coefficient 0.862 and 0.867, respectively; P values < 0.001) and specimen weight (correlation coefficient 0.802 and 0.852, respectively; P values < 0.001). Mean absolute difference between the MR breast volume and implant size was 160 cc, which was significantly higher than that between the MG breast volume and implant size of 118 cc (P < 0.001). On multivariable analyses, only breast volume measured by both MG and MRI was significantly associated with implant size in any implant type (all P values < 0.001). CONCLUSION Breast volume measured by MG and MRI can be used to predict appropriate implant size in breast cancer patients undergoing direct-to-implant reconstruction in an efficient and objective manner.
Collapse
Affiliation(s)
- Young Seon Kim
- Department of Radiology, Yeungnam University Hospital, Yeungnam University College of Medicine, Daegu, Republic of Korea
| | - Hyun Geun Cho
- Department of Plastic and Reconstructive Surgery, School of Medicine, Kyungpook National University, Daegu, Republic of Korea
| | - Jaeil Kim
- School of Computer Science and Engineering, Kyungpook National University, Daegu, Republic of Korea
| | - Sung Joon Park
- School of Computer Science and Engineering, Kyungpook National University, Daegu, Republic of Korea
| | - Hye Jung Kim
- Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, Republic of Korea
| | - Seung Eun Lee
- Department of Radiology, Yeungnam University Hospital, Yeungnam University College of Medicine, Daegu, Republic of Korea
| | - Jung Dug Yang
- Department of Plastic and Reconstructive Surgery, School of Medicine, Kyungpook National University, Daegu, Republic of Korea
| | - Won Hwa Kim
- Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital, Daegu, Republic of Korea.
| | - Joon Seok Lee
- Department of Plastic and Reconstructive Surgery, School of Medicine, Kyungpook National University, Daegu, Republic of Korea.
| |
Collapse
|
3
|
Hejduk P, Marcon M, Unkelbach J, Ciritsis A, Rossi C, Borkowski K, Boss A. Fully automatic classification of automated breast ultrasound (ABUS) imaging according to BI-RADS using a deep convolutional neural network. Eur Radiol 2022; 32:4868-4878. [PMID: 35147776 PMCID: PMC9213284 DOI: 10.1007/s00330-022-08558-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Revised: 12/14/2021] [Accepted: 12/26/2021] [Indexed: 12/15/2022]
Abstract
Purpose The aim of this study was to develop and test a post-processing technique for detection and classification of lesions according to the BI-RADS atlas in automated breast ultrasound (ABUS) based on deep convolutional neural networks (dCNNs). Methods and materials In this retrospective study, 645 ABUS datasets from 113 patients were included; 55 patients had lesions classified as high malignancy probability. Lesions were categorized in BI-RADS 2 (no suspicion of malignancy), BI-RADS 3 (probability of malignancy < 3%), and BI-RADS 4/5 (probability of malignancy > 3%). A deep convolutional neural network was trained after data augmentation with images of lesions and normal breast tissue, and a sliding-window approach for lesion detection was implemented. The algorithm was applied to a test dataset containing 128 images and performance was compared with readings of 2 experienced radiologists. Results Results of calculations performed on single images showed accuracy of 79.7% and AUC of 0.91 [95% CI: 0.85–0.96] in categorization according to BI-RADS. Moderate agreement between dCNN and ground truth has been achieved (κ: 0.57 [95% CI: 0.50–0.64]) what is comparable with human readers. Analysis of whole dataset improved categorization accuracy to 90.9% and AUC of 0.91 [95% CI: 0.77–1.00], while achieving almost perfect agreement with ground truth (κ: 0.82 [95% CI: 0.69–0.95]), performing on par with human readers. Furthermore, the object localization technique allowed the detection of lesion position slice-wise. Conclusions Our results show that a dCNN can be trained to detect and distinguish lesions in ABUS according to the BI-RADS classification with similar accuracy as experienced radiologists. Key Points • A deep convolutional neural network (dCNN) was trained for classification of ABUS lesions according to the BI-RADS atlas. • A sliding-window approach allows accurate automatic detection and classification of lesions in ABUS examinations.
Collapse
Affiliation(s)
- Patryk Hejduk
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland.
| | - Magda Marcon
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| | - Jan Unkelbach
- Department of Radiation Oncology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| | - Alexander Ciritsis
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| | - Cristina Rossi
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| | - Karol Borkowski
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| | - Andreas Boss
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Rämistr. 100, 8091, Zurich, Switzerland
| |
Collapse
|
4
|
Vairavan R, Abdullah O, Retnasamy PB, Sauli Z, Shahimin MM, Retnasamy V. A Brief Review on Breast Carcinoma and Deliberation on Current Non Invasive Imaging Techniques for Detection. Curr Med Imaging 2020; 15:85-121. [PMID: 31975658 DOI: 10.2174/1573405613666170912115617] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2017] [Revised: 08/27/2017] [Accepted: 08/29/2017] [Indexed: 12/22/2022]
Abstract
BACKGROUND Breast carcinoma is a life threatening disease that accounts for 25.1% of all carcinoma among women worldwide. Early detection of the disease enhances the chance for survival. DISCUSSION This paper presents comprehensive report on breast carcinoma disease and its modalities available for detection and diagnosis, as it delves into the screening and detection modalities with special focus placed on the non-invasive techniques and its recent advancement work done, as well as a proposal on a novel method for the application of early breast carcinoma detection. CONCLUSION This paper aims to serve as a foundation guidance for the reader to attain bird's eye understanding on breast carcinoma disease and its current non-invasive modalities.
Collapse
Affiliation(s)
- Rajendaran Vairavan
- School of Microelectronic Engineering, Universiti Malaysia Perlis, Pauh Putra Campus, 02600 Arau, Perlis, Malaysia
| | - Othman Abdullah
- Hospital Sultan Abdul Halim, 08000 Sg. Petani, Kedah, Malaysia
| | | | - Zaliman Sauli
- School of Microelectronic Engineering, Universiti Malaysia Perlis, Pauh Putra Campus, 02600 Arau, Perlis, Malaysia
| | - Mukhzeer Mohamad Shahimin
- Department of Electrical and Electronic Engineering, Faculty of Engineering, National Defence University of Malaysia (UPNM), Kem Sungai Besi, 57000 Kuala Lumpur, Malaysia
| | - Vithyacharan Retnasamy
- School of Microelectronic Engineering, Universiti Malaysia Perlis, Pauh Putra Campus, 02600 Arau, Perlis, Malaysia
| |
Collapse
|
5
|
Effect of neoadjuvant chemotherapy on breast tissue composition: a longitudinal mammographic study with automated volumetric measurement. Eur Radiol 2020; 30:4785-4794. [PMID: 32314056 DOI: 10.1007/s00330-020-06830-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2019] [Revised: 03/05/2020] [Accepted: 03/23/2020] [Indexed: 10/24/2022]
Abstract
OBJECTIVES To investigate the effect of neoadjuvant chemotherapy (NAC) on breast tissue composition with mammographic automated volumetric measurement. METHODS This retrospective study included 168 breast cancer patients who were treated with NAC and underwent serial mammography (pre-treatment, mid-treatment, and post-treatment) between January 2015 and October 2018. Automated volumetric measurements of the contralateral breast volume (BV), fibroglandular volume (FGV), and breast density (BD) were performed using Volpara software. BD grades were divided into 4 groups by Volpara density grade (VDG). The longitudinal changes in BV, FGV, BD, and their associated factors were evaluated. RESULTS Repeated-measures analysis of variance demonstrated a significant reduction in BV, FGV, and BD over time (p < 0.001, p < 0.001, and p = 0.002, respectively). BV showed a greater reduction in the second half than in the first half (- 28.6 cm3 vs. - 15.2 cm3), BD showed a greater reduction in the first half than in the second half (- 0.8% vs. - 0.1%), and FGV steadily decreased (- 4.6 cm3 and - 3.9 cm3 in the first and second halves). On multivariable linear regression analysis, chemotherapy regimen was associated with BV change between pre- and post-treatment (p = 0.002); age (p = 0.024) and VDG (p = 0.027) were associated with FGV change; age (p = 0.037), VDG (p = 0.002), and chemotherapy regimen (p = 0.003) were associated with BD change. CONCLUSIONS NAC affects breast tissue composition, reflected as reductions in BV, FGV, and BD. Mammography with automated volumetric measurement can capture quantitative changes in these breast tissue parameters during NAC. KEY POINTS • Neoadjuvant chemotherapy (NAC) affects breast tissue composition with different patterns of reduction in breast volume, fibroglandular volume, and breast density. • Age, Volpara density grades, and NAC regimen were independent factors associated with breast density change between pre-treatment and post-treatment. • Mammography with automated volumetric measurement enables identification of longitudinal changes in breast tissue composition.
Collapse
|
6
|
Vinnicombe SJ. Breast density: why all the fuss? Clin Radiol 2017; 73:334-357. [PMID: 29273225 DOI: 10.1016/j.crad.2017.11.018] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2017] [Accepted: 11/17/2017] [Indexed: 01/06/2023]
Abstract
The term "breast density" or mammographic density (MD) denotes those components of breast parenchyma visualised at mammography that are denser than adipose tissue. MD is composed of a mixture of epithelial and stromal components, notably collagen, in variable proportions. MD is most commonly assessed in clinical practice with the time-honoured method of visual estimation of area-based percent density (PMD) on a mammogram, with categorisation into quartiles. The computerised semi-automated thresholding method, Cumulus, also yielding area-based percent density, is widely used for research purposes; however, the advent of fully automated volumetric methods developed as a consequence of the widespread use of digital mammography (DM) and yielding both absolute and percent dense volumes, has resulted in an explosion of interest in MD recently. Broadly, the importance of MD is twofold: firstly, the presence of marked MD significantly reduces mammographic sensitivity for breast cancer, even with state-of-the-art DM. Recognition of this led to the formation of a powerful lobby group ('Are You Dense') in the US, as a consequence of which 32 states have legislated for mandatory disclosure of MD to women undergoing mammography. Secondly, it is now widely accepted that MD is in itself a risk factor for breast cancer, with a four-to sixfold increased relative risk in women with PMD in the highest quintile compared to those with PMD in the lowest quintile. Consequently, major research efforts are underway to assess whether use of MD could provide a major step forward towards risk-adapted, personalised breast cancer prevention, imaging, and treatment.
Collapse
Affiliation(s)
- S J Vinnicombe
- Cancer Research, School of Medicine, Level 7, Mailbox 4, Ninewells Hospital and Medical School, University of Dundee, Dundee DD1 9SY, UK.
| |
Collapse
|
7
|
Brisson J, Bérubé S, Diorio C, Mâsse B, Lemieux J, Duchesne T, Delvin E, Vieth R, Yaffe MJ, Chiquette J. A Randomized Double-Blind Placebo-Controlled Trial of the Effect of Vitamin D 3 Supplementation on Breast Density in Premenopausal Women. Cancer Epidemiol Biomarkers Prev 2017; 26:1233-1241. [PMID: 28515107 DOI: 10.1158/1055-9965.epi-17-0249] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2017] [Revised: 04/28/2017] [Accepted: 05/09/2017] [Indexed: 11/16/2022] Open
Abstract
Background: This double-blind, placebo-controlled parallel group trial assessed whether oral supplementation with 1,000, 2,000, or 3,000 IU/day vitamin D3 over one year reduces percent mammographic breast density in premenopausal women.Methods: The trial was conducted between October 2012 and June 2015, among premenopausal female volunteers from Quebec City (Quebec, Canada). Women were randomized with ratio 1:1:1:1 to one of four study arms (1,000, 2,000, or 3,000 IU/day vitamin D3 or placebo). The primary outcome was mean change in percent mammographic breast density. Participants and research team were blinded to study arm assignment.Results: Participants (n = 405) were randomized to receive 1,000 (n = 101), 2,000 (n = 104), or 3,000 IU/day (n = 101) vitamin D3, or a placebo (n = 99). The primary analysis included 391 participants (96, 99, 100, and 96, respectively). After the one-year intervention, mean ± SE change in percent breast density in the arms 1,000 IU/day (-5.5% ± 0.5%) and 2,000 IU/day (-5.9% ± 0.5%) vitamin D3 was similar to that in the placebo arm (-5.7% ± 0.5%) (P values = 1.0). In the 3,000 IU/day vitamin D3 arm, percent breast density also declined but slightly less (-3.8% ± 0.5%) compared with placebo arm (P = 0.03). Adherence to intervention was excellent (92.8%), and reporting of health problems was comparable among study arms (P ≥ 0.95). All participants had normal serum calcium.Conclusions: In premenopausal women, one-year supplementation with 1,000, 2,000, or 3,000 IU/day vitamin D3 resulted in a reduction of percent breast density no greater than that seen with the placebo.Impact: At doses of 1,000-3,000 IU/day, vitamin D supplementation will not reduce breast cancer risk through changes in breast density. Cancer Epidemiol Biomarkers Prev; 26(8); 1233-41. ©2017 AACR.
Collapse
Affiliation(s)
- Jacques Brisson
- Centre de Recherche du CHU de Québec-Université Laval, Québec, Canada. .,Département de Médecine Sociale et Préventive, Centre de Recherche sur le Cancer, Université Laval, Québec, Canada.,Centre des Maladies du sein Deschênes-Fabia, Hôpital du St-Sacrement, Québec, Canada
| | - Sylvie Bérubé
- Centre de Recherche du CHU de Québec-Université Laval, Québec, Canada
| | - Caroline Diorio
- Centre de Recherche du CHU de Québec-Université Laval, Québec, Canada.,Département de Médecine Sociale et Préventive, Centre de Recherche sur le Cancer, Université Laval, Québec, Canada.,Centre des Maladies du sein Deschênes-Fabia, Hôpital du St-Sacrement, Québec, Canada
| | - Benoît Mâsse
- Département de Médecine Sociale et Préventive, Université de Montréal, Montréal, Québec, Canada.,Centre de Recherche du CHU Sainte-Justine, Montréal, Québec, Canada
| | - Julie Lemieux
- Centre de Recherche du CHU de Québec-Université Laval, Québec, Canada.,Centre des Maladies du sein Deschênes-Fabia, Hôpital du St-Sacrement, Québec, Canada
| | - Thierry Duchesne
- Département de Mathématiques et de Statistique, Université Laval, Québec, Canada
| | - Edgar Delvin
- Centre de Recherche du CHU Sainte-Justine, Montréal, Québec, Canada
| | - Reinhold Vieth
- Departments of Laboratory Medicine and Pathobiology and Nutritional Sciences, University of Toronto, Toronto, Ontario, Canada
| | - Martin J Yaffe
- Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada
| | - Jocelyne Chiquette
- Centre de Recherche du CHU de Québec-Université Laval, Québec, Canada.,Centre des Maladies du sein Deschênes-Fabia, Hôpital du St-Sacrement, Québec, Canada
| |
Collapse
|
8
|
Imaging Breast Density: Established and Emerging Modalities. Transl Oncol 2015; 8:435-45. [PMID: 26692524 PMCID: PMC4700291 DOI: 10.1016/j.tranon.2015.10.002] [Citation(s) in RCA: 21] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2015] [Revised: 09/30/2015] [Accepted: 10/06/2015] [Indexed: 11/23/2022] Open
Abstract
Mammographic density has been proven as an independent risk factor for breast cancer. Women with dense breast tissue visible on a mammogram have a much higher cancer risk than women with little density. A great research effort has been devoted to incorporate breast density into risk prediction models to better estimate each individual’s cancer risk. In recent years, the passage of breast density notification legislation in many states in USA requires that every mammography report should provide information regarding the patient’s breast density. Accurate definition and measurement of breast density are thus important, which may allow all the potential clinical applications of breast density to be implemented. Because the two-dimensional mammography-based measurement is subject to tissue overlapping and thus not able to provide volumetric information, there is an urgent need to develop reliable quantitative measurements of breast density. Various new imaging technologies are being developed. Among these new modalities, volumetric mammographic density methods and three-dimensional magnetic resonance imaging are the most well studied. Besides, emerging modalities, including different x-ray–based, optical imaging, and ultrasound-based methods, have also been investigated. All these modalities may either overcome some fundamental problems related to mammographic density or provide additional density and/or compositional information. The present review article aimed to summarize the current established and emerging imaging techniques for the measurement of breast density and the evidence of the clinical use of these density methods from the literature.
Collapse
|
9
|
Reproducibility of automated volumetric breast density assessment in short-term digital mammography reimaging. Clin Imaging 2015; 39:582-6. [DOI: 10.1016/j.clinimag.2015.02.011] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2014] [Revised: 01/21/2015] [Accepted: 02/16/2015] [Indexed: 11/22/2022]
|
10
|
Keller BM, Oustimov A, Wang Y, Chen J, Acciavatti RJ, Zheng Y, Ray S, Gee JC, Maidment ADA, Kontos D. Parenchymal texture analysis in digital mammography: robust texture feature identification and equivalence across devices. J Med Imaging (Bellingham) 2015; 2:024501. [PMID: 26158105 DOI: 10.1117/1.jmi.2.2.024501] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2014] [Accepted: 03/13/2015] [Indexed: 11/14/2022] Open
Abstract
An analytical framework is presented for evaluating the equivalence of parenchymal texture features across different full-field digital mammography (FFDM) systems using a physical breast phantom. Phantom images (FOR PROCESSING) are acquired from three FFDM systems using their automated exposure control setting. A panel of texture features, including gray-level histogram, co-occurrence, run length, and structural descriptors, are extracted. To identify features that are robust across imaging systems, a series of equivalence tests are performed on the feature distributions, in which the extent of their intersystem variation is compared to their intrasystem variation via the Hodges-Lehmann test statistic. Overall, histogram and structural features tend to be most robust across all systems, and certain features, such as edge enhancement, tend to be more robust to intergenerational differences between detectors of a single vendor than to intervendor differences. Texture features extracted from larger regions of interest (i.e., [Formula: see text]) and with a larger offset length (i.e., [Formula: see text]), when applicable, also appear to be more robust across imaging systems. This framework and observations from our experiments may benefit applications utilizing mammographic texture analysis on images acquired in multivendor settings, such as in multicenter studies of computer-aided detection and breast cancer risk assessment.
Collapse
Affiliation(s)
- Brad M Keller
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Andrew Oustimov
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Yan Wang
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Jinbo Chen
- University of Pennsylvania , Perelman School of Medicine, Department of Biostatistics and Epidemiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Raymond J Acciavatti
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Yuanjie Zheng
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Shonket Ray
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - James C Gee
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Andrew D A Maidment
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| | - Despina Kontos
- University of Pennsylvania , Perelman School of Medicine, Department of Radiology, 3600 Market Street, Suite 360, Philadelphia, Pennsylvania 19104, United States
| |
Collapse
|