scholarly journals Statistical Evaluation of a Fully Automated Mammographic Breast Density Algorithm

2013 ◽  
Vol 2013 ◽  
pp. 1-6 ◽  
Author(s):  
Mohamed Abdolell ◽  
Kaitlyn Tsuruda ◽  
Gerry Schaller ◽  
Judy Caines
Keyword(s):  
Clinical Practice ◽  
Mammographic Density ◽  
Breast Density ◽  
Quantitative Methods ◽  
Statistical Evaluation ◽  
Comprehensive Evaluation ◽  
Density Measurement ◽  
Mammographic Breast Density ◽  
Reference Standard ◽  
Effective Use

Visual assessments of mammographic breast density by radiologists are used in clinical practice; however, these assessments have shown weaker associations with breast cancer risk than area-based, quantitative methods. The purpose of this study is to present a statistical evaluation of a fully automated, area-based mammographic density measurement algorithm. Five radiologists estimated density in 5% increments for 138 “For Presentation” single MLO views; the median of the radiologists’ estimates was used as the reference standard. Agreement amongst radiologists was excellent, ICC = 0.884, 95% CI (0.854, 0.910). Similarly, the agreement between the algorithm and the reference standard was excellent, ICC = 0.862, falling within the 95% CI of the radiologists’ estimates. The Bland-Altman plot showed that the reference standard was slightly positively biased (+1.86%) compared to the algorithm-generated densities. A scatter plot showed that the algorithm moderately overestimated low densities and underestimated high densities. A box plot showed that 95% of the algorithm-generated assessments fell within one BI-RADS category of the reference standard. This study demonstrates the effective use of several statistical techniques that collectively produce a comprehensive evaluation of the algorithm and its potential to provide mammographic density measures that can be used to inform clinical practice.

scholarly journals Subjective Versus Quantitative Methods of Assessing Breast Density

Diagnostics ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 331 ◽  
Author(s):  
Wijdan Alomaim ◽  
Desiree O’Leary ◽  
John Ryan ◽  
Louise Rainford ◽  
Michael Evanoff ◽  
...  
Keyword(s):  
Breast Density ◽  
Quantitative Methods ◽  
Weighted Kappa ◽  
Subjective Assessment ◽  
Evidence Base ◽  
Assessment Methods ◽  
Digital Data ◽  
Mammographic Breast Density ◽  
National Breast ◽  
Busy Clinical Setting

In order to find a consistent, simple and time-efficient method of assessing mammographic breast density (MBD), different methods of assessing density comparing subjective, quantitative, semi-subjective and semi-quantitative methods were investigated. Subjective MBD of anonymized mammographic cases (n = 250) from a national breast-screening programme was rated by 49 radiologists from two countries (UK and USA) who were voluntarily recruited. Quantitatively, three measurement methods, namely VOLPARA, Hand Delineation (HD) and ImageJ (IJ) were used to calculate breast density using the same set of cases, however, for VOLPARA only mammographic cases (n = 122) with full raw digital data were included. The agreement level between methods was analysed using weighted kappa test. Agreement between UK and USA radiologists and VOLPARA varied from moderate (κw = 0.589) to substantial (κw = 0.639), respectively. The levels of agreement between USA, UK radiologists, VOLPARA with IJ were substantial (κw = 0.752, 0.768, 0.603), and with HD the levels of agreement varied from moderate to substantial (κw = 0.632, 0.680, 0.597), respectively. This study found that there is variability between subjective and objective MBD assessment methods, internationally. These results will add to the evidence base, emphasising the need for consistent, simple and time-efficient MBD assessment methods. Additionally, the quickest method to assess density is the subjective assessment, followed by VOLPARA, which is compatible with a busy clinical setting. Moreover, the use of a more limited two-scale system improves agreement levels and could help minimise any potential country bias.

Impact of a deep learning model to reduce variation and costs of federally mandated breast density legislation.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 1550-1550
Author(s):  
Katherine Cavallo Hom ◽  
Brian Nicholas Dontchos ◽  
Sarah Mercaldo ◽  
Pragya Dang ◽  
Leslie Lamb ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Practice ◽  
Breast Density ◽  
Routine Clinical Practice ◽  
Dense Breast ◽  
Wilcoxon Test ◽  
Screening Tests ◽  
Mammographic Breast Density ◽  
Community Practice ◽  
Screening Mammograms

1550 Background: Dense breast tissue is an independent risk factor for malignancy and can mask cancers on mammography. Yet, radiologist-assessed mammographic breast density is subjective and varies widely between and within radiologists. Our deep learning (DL) model was implemented into routine clinical practice at an academic breast imaging center and was externally validated at a separate community practice, with both sites demonstrating high clinical acceptance of the model’s density predictions. The aim of this study is to demonstrate the influence our DL model has on prospective radiologist density assessments in routine clinical practice. Methods: This IRB-approved, HIPAA-compliant retrospective study identified consecutive screening mammograms without exclusion performed across three clinical sites, over two time periods: pre-DL model implementation (January 1, 2017 through September 30, 2017) and post-DL model implementation (January 1, 2019 through September 30, 2019). Clinical sites were as follows: Site A (the academic practice where the DL model was developed and was implemented in late 2017); Site B (an affiliated community practice which implemented the DL model in late 2017 and was used for external validation); and Site C (an affiliated community practice which was never exposed to the DL model). Patient demographics and radiologist-assessed mammographic breast densities were compared over time and across sites. Patient characteristics were evaluated using Wilcoxon test and Pearson’s chi-squared test. Multivariable logistic regression models evaluated the odds of a dense breast classification as a function of time period (pre-DL vs post-DL), race (White vs non-White) and site. Results: A total of 85,865 consecutive screening mammograms across the three clinical sites were identified. After controlling for age and race, adjusted odds ratios (aOR) of a mammogram being classified as dense at Site C compared to Site B before the DL model was implemented was 2.01 (95% CI 1.873, 2.157, p<0.001). This increased to 2.827 (95% CI 2.636, 3.032, p< 0.001) after DL implementation. The aOR of a mammogram being classified as dense at Site A after implementation compared to before implementation was 0.924 (95% CI 0.885, 0.964, p<0.001). Conclusions: Our findings suggest implementation of the DL model influences radiologist’s prospective density assessments in routine clinical practice by reducing the odds of a screening exam being categorized as dense. As a result, clinical use of our model could reduce downstream costs of supplemental screening tests and limit unnecessary high-risk clinic evaluations.[Table: see text]

Correlation of mammographic breast density with Ki-67 expression in benign breast epithelial cells obtained by random periareolar fine needle aspiration of high risk women

2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 1011-1011
Author(s):  
Q. J. Khan ◽  
B. F. Kimler ◽  
E. J. Smith ◽  
A. P. O’Dea ◽  
P. Sharma ◽  
...  
Keyword(s):  
Breast Cancer ◽  
High Risk ◽  
Mammographic Density ◽  
Breast Density ◽  
Fine Needle Aspiration ◽  
Needle Aspiration ◽  
Mammographic Breast Density ◽  
Ki 67 ◽  
Fine Needle ◽  
Cytologic Atypia

1011 
 >Background: Known risk factors for breast cancer development include elements incorporated into the Gail risk model, mammographic breast density and cytologic atypia detected by Random Periareolar Fine Needle Aspiration (RPFNA). Ki-67 expression is a possible risk biomarker and is currently being used as a response biomarker in chemoprevention trials. We have previously shown that Ki-67 expression is higher in RPFNA specimens of benign breast cells exhibiting cytologic atypia. It is not known whether there is a correlation between mammographic density and Ki-67 expression in benign breast ductal cells obtained by RPFNA. Methods: 344 women at high risk of developing breast cancer (based on personal or family history) seen at The University of Kansas Medical Center high risk breast clinic, who underwent RPFNA with cytomorphology and Ki-67 assessment, plus a mammogram were included in the study. Mammographic breast density was assessed using the Cumulus program. Categorical variables were analyzed by Chi-square test and continuous variables were analyzed by non-parametric test and linear regression. Results: 40% of women were premenopausal, 7% perimenopausal and 53% were postmenopausal. Median age was 49 years, median 5 year Gail Risk was 2.2%, and median Ki-67 was 1.9%. Median mammographic breast density was 37%. Ki-67 expression increased with cytologic abnormality and number of cells collected, but was unrelated to Gail risk (as observed previously). Breast density was higher in pre-menopausal women (p=0.001), those with lower BMI (p< 0.001), and lower 5-year Gail risk (p=0.012); Breast density showed no correlation with Ki-67 expression or cytomorphology. Conclusion: Given the lack of correlation of mammographic breast density with either cytomorphology or Ki-67 expression in RPFNA specimens, mammographic density and Ki-67 expression should be considered as potentially complementary response biomarkers for breast cancer chemoprevention trials. No significant financial relationships to disclose.

scholarly journals An Evaluation and Dissemination Model for the Machine Learning Embedded System Lifecycle in Clinical Practice Settings

2021 ◽  
Author(s):  
melanie besculides ◽  
Ksenia Gorbenko ◽  
Cardinale Smith ◽  
Robert Freeman ◽  
David Reich ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Practice ◽  
Embedded System ◽  
Quantitative Methods ◽  
Clinical Decision Making ◽  
Comprehensive Evaluation ◽  
Healthcare Setting ◽  
Clinical Decision ◽  
Qualitative And Quantitative Methods ◽  
Better Than

Machine learning (ML) algorithms are gaining popularity in clinical practice settings due to their ability to process information in ways that augment human reasoning. While tools that rely on output from ML algorithms in the healthcare setting are appealing for their ability to aid in clinical decision making and streamline workflows, their implementation and effectiveness are not well documented. There is an abundance of published ML literature that focuses on whether algorithms can predict an outcome or predict it better than previous algorithms, but a dearth of effort evaluating their implementation or impact on patient outcomes. While developing and validating algorithms is an important first step in research, comprehensive evaluation is needed before application of ML algorithms in new settings is considered. Evaluation should examine both the process of implementation and the outcomes using a mix of qualitative and quantitative methods. This commentary describes a model we developed to guide our institutional ML evaluation efforts.

scholarly journals Mammographic Breast Density and Urbanization: Interactions with BMI, Environmental, Lifestyle, and Other Patient Factors

Diagnostics ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 418
Author(s):  
Nick Perry ◽  
Sue Moss ◽  
Steve Dixon ◽  
Sue Milner ◽  
Kefah Mokbel ◽  
...  
Keyword(s):  
Breast Density ◽  
Density Measurement ◽  
Urban Setting ◽  
Imaging Biomarker ◽  
Mammographic Breast Density ◽  
Contributing Factors ◽  
Urban Residence ◽  
Patient Factors ◽  
Breast Density Measurement ◽  
The Relationship

Mammographic breast density (MBD) is an important imaging biomarker of breast cancer risk, but it has been suggested that increased MBD is not a genuine finding once corrected for age and body mass index (BMI). This study examined the association of various factors, including both residing in and working in the urban setting, with MBD. Questionnaires were completed by 1144 women attending for mammography at the London Breast Institute in 2012–2013. Breast density was assessed with an automated volumetric breast density measurement system (Volpara) and compared with subjective radiologist assessment. Multivariable linear regression was used to model the relationship between MBD and residence in the urban setting as well as working in the urban setting, adjusting for both age and BMI and other menstrual, reproductive, and lifestyle factors. Urban residence was significantly associated with an increasing percent of MBD, but this association became non-significant when adjusted for age and BMI. This was not the case for women who were both residents in the urban setting and still working. Our results suggest that the association between urban women and increased MBD can be partially explained by their lower BMI, but for women still working, there appear to be other contributing factors.

scholarly journals Increased mammographic breast density in acromegaly: quantitative and qualitative assessment

2011 ◽  
Vol 164 (3) ◽  
pp. 335-340 ◽  
Author(s):  
Alberto Tagliafico ◽  
Massimo Calabrese ◽  
Giulio Tagliafico ◽  
Eugenia Resmini ◽  
Carlo Martinoli ◽  
...  
Keyword(s):  
Mammographic Density ◽  
Breast Density ◽  
Breast Imaging ◽  
Independent Risk Factor ◽  
Disease Duration ◽  
Observer Agreement ◽  
Qualitative Assessment ◽  
Mammographic Breast Density ◽  
Computer Aided ◽  
A Prospective Study

ContextMammographic density is a strong independent risk factor for breast cancer, whose prevalence in acromegaly is still controversial.ObjectiveTo compare breast density in premenopausal acromegalic patients and controls and to determine whether density correlated with disease duration, GH, and IGF1 levels.Design, setting and participantsA prospective study involving 30 patients and 60 controls matched for age and body mass index.InterventionsA quantitative computer-aided mammographic density estimation (MDEST) and a qualitative blind evaluation by two experienced radiologists using the breast imaging reporting and data system (BI-RADS) was performed. Totally, 60 (acromegaly) and 120 (controls) craniocaudal and mediolateral oblique mammograms were evaluated in both patients and controls.Main outcome measuresBreast density.ResultsPatients showed a significantly (P<0.01) increased mammographic breast density with both methods (MDEST: 0.33±0.21% and BI-RADS category: 2.81±0.78) in comparison with controls (MDEST: 0.26±0.19% and BI-RADS category: 2.35±0.61). The agreement between the two methods and inter-observer agreement between the two radiologists were excellent (k=0.63 and k=0.85). In patients grouped according to disease activity (17 controlled and 13 uncontrolled) and medical therapy (15 treated and 15 untreated), no differences were found. All these groups had significantly increased mammographic breast density compared with controls (P<0.01).A positive correlation was found between mammographic breast density, IGF1 values and disease duration (r=0.29 and r=0.39), whereas it was not found with GH (r=−0.02).ConclusionsMammographic breast density in premenopausal acromegalic patients is significantly higher than controls and positively correlated with IGF1 and disease duration.

Dehydroepiandrosterone and/or its metabolites: possible androgen receptor antagonistic effects on digitized mammographic breast density in normal breast tissue of postmenopausal women

2018 ◽  
Vol 35 (1) ◽  
Author(s):  
Eva Lundström ◽  
Kjell Carlström ◽  
Sabine Naessen ◽  
Gunnar Söderqvist
Keyword(s):  
Cell Proliferation ◽  
Postmenopausal Women ◽  
Mammographic Density ◽  
Breast Density ◽  
Free Testosterone ◽  
Serum Levels ◽  
Sex Hormone Binding Globulin ◽  
Mammographic Breast Density

Abstract Background Androgens, notably testosterone inhibit breast cell proliferation and negative correlations between free testosterone (fT) and breast cell proliferation as well as mammographic density have been described. Dehydroepiandrosterone (DHEA) is reported to be a partial androgen antagonist in breast tumor cells in vitro. Our aim was to investigate if circulating DHEA had any effects on the association between circulating fT and mammographic density in vivo in the normal postmenopausal breast. Methods We measured visual and digitized mammographic density and serum DHEA, testosterone, sex-hormone-binding globulin and calculated fT in 84 healthy untreated postmenopausal women. Results Significant negative correlations between fT and both visual and digitized mammographic density were strengthened when the median DHEA level decreased from 10.2 to 8.6 nmol/L. Thereafter, correlations became weaker again probably due to decreasing fT levels and/or sample size. There were no correlations between mammographic density and DHEA, at any of the DHEA concentration ranges studied. Serum levels of fT and DHEA were positively correlated. Conclusion Our findings demonstrate that circulating DHEA and/or its metabolites counteract the inhibitory action of fT on mammographic breast density.

scholarly journals Development of a Quantitative Estimation of Mammographically Breast Density

2017 ◽  
Vol 18 (1) ◽  
pp. 16-20
Author(s):  
Meherun Nahar ◽  
Abdus Sattar Mollah ◽  
Mir Mohammad Akramuzzaman
Keyword(s):  
Breast Cancer ◽  
Mammographic Density ◽  
Breast Density ◽  
Quantitative Estimation ◽  
Mammographic Breast Density ◽  
Computer Assisted ◽  
Image Analyzer ◽  
Oblique View ◽  
Language Version ◽  
Dense Tissue

Objective: Increased mammographic breast density is a moderate independent risk factor for breast cancer. Assessment of breast density may become useful in risk assessment and prevention decisions. To evaluate the association between mammographic density and breast cancer risk, a simple observer-assisted technique called interactive thresholding was developed.Methods: For providing, a quantitative estimation of mammographically dense tissue, in this study computer assisted measurements were carried out using Adobe AIR software. For thresholding technique, software named ‘Xray Image Analyzer’ was programmed in Adobe AIR language version - Action script 3.0. runtime version- Flash player 9, AIR 1.0, and flash Lite-4. Interactive thresholding technique was applied to digitized film screen mammograms, which assesses the proportion of radio graphically dense tissue in the mammographic image representing mammographic density. The technique evaluated for 36 mammograms of 18 women who underwent referral mammography in a hospital at Dhaka city from October 2010 to October 2011.Results: The women in the selected group were in age range of 20 to 60 years, with a mean age of 44±9 and median age is 45 yrs. The technique was found to be very reliable with an intra-class correlation coefficient between observers typically R = 0.887. This technique may have a role in routine mammographic analysis for the purpose of assessing risk categories and as a tool in studies of the etiology of breast cancer, in particular for monitoring changes in breast parenchyma during potential preventive interventions. Conclusion: It is possible to use the interactive segmentation technique for other projections of the breast, such as the medio-lateral oblique view. In this case, however, it is necessary to perform a manual segmentation to remove the image of the pectoral muscle from the analysis. This technique can be employ as a tool in many clinical studies.Bangladesh J. Nuclear Med. 18(1): 16-20, January 2015

scholarly journals Mammographic density in asymptomatic menopausal women: correlation with clinical and sonographic findings

2012 ◽  
Vol 45 (3) ◽  
pp. 149-154 ◽  
Author(s):  
Beatriz Regina Alvares ◽  
Christian Henrique de Andrade Freitas ◽  
Rodrigo Menezes Jales ◽  
Orlando José de Almeida ◽  
Emílio Francisco Marussi
Keyword(s):  
Body Mass Index ◽  
Hormone Replacement Therapy ◽  
Replacement Therapy ◽  
Body Mass ◽  
Mammographic Density ◽  
Breast Density ◽  
Hormone Replacement ◽  
Mammographic Breast Density ◽  
Asymptomatic Patients ◽  
Menopausal Women

OBJECTIVE: To evaluate mammographic breast density in asymptomatic menopausal women in correlation with clinical and sonographic findings. MATERIALS AND METHODS: Mammograms and clinical and sonographic findings of 238 asymptomatic patients were retrospectively reviewed in the period from February/2022 to June/2006. The following variables were analyzed: mammographic density patterns, sonographic findings, patients' age, parity, body mass index and use of hormone replacement therapy. RESULTS: Age, parity and body mass index showed a negative correlation with breast density pattern, while use of hormone replacement therapy showed a positive correlation. Supplementary breast ultrasonography was performed in 103 (43.2%) patients. Alterations which could not be visualized at mammography were found in 34 (33%) of them, most frequently in women with breast density patterns 3 and 4. CONCLUSION: The authors concluded that breast density patterns were influenced by age, parity, body mass index and time of hormone replacement therapy. Despite not having found any malignant abnormality in the studied cases, the authors have observed a predominance of benign sonographic abnormalities in women with high breast density patterns and without mammographic abnormalities, proving the relevance of supplementary ultrasonography to identify breast lesions in such patients.

Sign in / Sign up

Export Citation Format

Share Document