Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density

Maeve Mullooly, Babak Ehteshami Bejnordi, Ruth M. Pfeiffer, Shaoqi Fan, Maya Palakal, Manila Hada, Pamela M. Vacek, Donald L. Weaver, John A. Shepherd, Bo Fan, Amir Pasha Mahmoudzadeh, Jeff Wang, Serghei Malkov, Jason M. Johnson, Sally D. Herschorn, Brian L. Sprague, Stephen Hewitt, Louise A. Brinton, Nico Karssemeijer, Jeroen van der LaakAndrew Beck, Mark E. Sherman, Gretchen L. Gierach

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Breast density, a breast cancer risk factor, is a radiologic feature that reflects fibroglandular tissue content relative to breast area or volume. Its histology is incompletely characterized. Here we use deep learning approaches to identify histologic correlates in radiologically-guided biopsies that may underlie breast density and distinguish cancer among women with elevated and low density. We evaluated hematoxylin and eosin (H&E)-stained digitized images from image-guided breast biopsies (n = 852 patients). Breast density was assessed as global and localized fibroglandular volume (%). A convolutional neural network characterized H&E composition. In total 37 features were extracted from the network output, describing tissue quantities and morphological structure. A random forest regression model was trained to identify correlates most predictive of fibroglandular volume (n = 588). Correlations between predicted and radiologically quantified fibroglandular volume were assessed in 264 independent patients. A second random forest classifier was trained to predict diagnosis (invasive vs. benign); performance was assessed using area under receiver-operating characteristics curves (AUC). Using extracted features, regression models predicted global (r = 0.94) and localized (r = 0.93) fibroglandular volume, with fat and non-fatty stromal content representing the strongest correlates, followed by epithelial organization rather than quantity. For predicting cancer among high and low fibroglandular volume, the classifier achieved AUCs of 0.92 and 0.84, respectively, with epithelial organizational features ranking most important. These results suggest non-fatty stroma, fat tissue quantities and epithelial region organization predict fibroglandular volume. The model holds promise for identifying histological correlates of cancer risk in patients with high and low density and warrants further evaluation.

Original languageEnglish (US)
Article number43
Journalnpj Breast Cancer
Volume5
Issue number1
DOIs
StatePublished - Dec 1 2019

ASJC Scopus subject areas

  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Pharmacology (medical)

Fingerprint Dive into the research topics of 'Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density'. Together they form a unique fingerprint.

Cite this