Comparison of the clinical performance of three digital mammography systems in a breast cancer screening programme

Keavey, Elizabeth; Phelan, Niamh; O’Connell, Avice M; Flanagan, Fidelma; O’Doherty, Ann; Larke, A.; Connors, A M

doi:10.1259/bjr/29747759

Cited by 15 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, several deep learning studies for mammographic breast density assessment were only validated on patient cohorts from a single institution or digital mammography system [6,35,36]. Some possible differences between different digital mammography systems or versions of systems include the x-ray tube target, filter, digital detector technology, and control of automatic exposure [37]. Our results add to the growing body of literature that states that deep learning models do not necessarily generalize when applied to data that differs from that which the model was trained with.…”

Section: Discussionmentioning

confidence: 99%

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

Chang

Beers

Brink

et al. 2020

Journal of the American College of Radiology

View full text Add to dashboard Cite

Objective: We developed deep learning algorithms to automatically assess BI-RADS breast density.Methods: Using a large multi-institution patient cohort of 108,230 digital screening mammograms from the Digital Mammographic Imaging Screening Trial, we investigated the effect of data, model, and training parameters on overall model performance and provided crowdsourcing evaluation from the attendees of the ACR 2019 Annual Meeting.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

Chang

Beers

Brink

et al. 2020

Journal of the American College of Radiology

View full text Add to dashboard Cite

show abstract

“…Indeed, it was found in a dose survey of the Irish breast-screening program that the lower dose resulted from the use of DM systems, and the photon-counting system accounted for 25% of mammography units in Ireland 27. Clinical performance for this system is comparable to other DM systems in screening,28 and has not been shown to be inferior in radiologist performance 25…”

Section: Conventional Mammographymentioning

confidence: 99%

Update on new technologies in digital mammography

Patterson¹,

Roubidoux²

2014

IJWH

View full text Add to dashboard Cite

Despite controversy regarding mammography’s efficacy, it continues to be the most commonly used breast cancer-screening modality. With the development of digital mammography, some improved benefit has been shown in women with dense breast tissue. However, the density of breast tissue continues to limit the sensitivity of conventional mammography. We discuss the development of some derivative digital technologies, primarily digital breast tomosynthesis, and their strengths, weaknesses, and potential patient impact.

show abstract

“…Our study addresses heterogeneity in digital mammography systems across different institutions (as depicted in Fig. 1a) that arises from variability in x-ray tube targets, filters, digital detector technology, and control of automatic exposure [14].…”

Section: Introductionmentioning

confidence: 99%

Addressing catastrophic forgetting for medical domain expansion

Gupta¹,

Singh²,

Chang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions. While pooling datasets from multiple institutions and re-training may provide a straightforward solution, it is often infeasible and may compromise patient privacy. An alternative approach is to fine-tune the model on subsequent institutions after training on the original institution. Notably, this approach degrades model performance at the original institution, a phenomenon known as catastrophic forgetting. In this paper, we develop an approach to address catastrophic forgetting based on elastic weight consolidation combined with modulation of batch normalization statistics under two scenarios: first, for expanding the domain from one imaging system's data to another imaging system's, and second, for expanding the domain from a large multi-institutional dataset to another single institution dataset. We show that our approach outperforms several other state-of-the-art approaches and provide theoretical justification for the efficacy of batch normalization modulation. The results of this study are generally applicable to the deployment of any clinical deep learning model which requires domain expansion.

show abstract

Comparison of the clinical performance of three digital mammography systems in a breast cancer screening programme

Cited by 15 publications

References 16 publications

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density

Update on new technologies in digital mammography

Addressing catastrophic forgetting for medical domain expansion

Contact Info

Product

Resources

About