Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk

Suzanne C. Wetstein (Corresponding author), Allison M. Onken, Christina Luffman, Gabrielle M. Baker, Michael E. Pyle, Kevin H. Kensler, Ying Liu, Bart Bakker, Ruud Vlutters, Marinus B. van Leeuwen, Laura C. Collins, Stuart J. Schnitt, Josien P.W. Pluim, Rulla M. Tamimi, Yujing J. Heng, Mitko Veta

Research output: Contribution to journalArticleAcademicpeer-review

14 Citations (Scopus)
109 Downloads (Pure)

Abstract

Terminal duct lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for labor-intensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures. Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses' Health Study. A set of 92 WSIs was annotated for acini, TDLUs and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area, median TDLU span and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures. Our CNN models detected acini with an F1 score of 0.73±0.07, and segmented TDLUs and adipose tissue with Dice scores of 0.84±0.13 and 0.87±0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 0.81 and 0.73, respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80 for number of TDLUs per tissue area, 0.57 for median TDLU span, and 0.80 for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status. We developed a computational pathology method to measure TDLU involution. This technology eliminates the labor-intensiveness and subjectivity of manual TDLU assessment, and can be applied to future breast cancer risk studies.

Original languageEnglish
Article numbere0231653
Number of pages16
JournalPLoS ONE
Volume15
Issue number4
DOIs
Publication statusPublished - 15 Apr 2020

Funding

This work was supported by the National Institute of Health/National Cancer Institute R21CA187642 (RMT), UM1CA186107, and U01CA176726, the Susan G. Komen Foundation (RMT), the Klarman Family Foundation (YJH), and the Deep Learning for Medical Image Analysis research program by Netherlands Organization for Scientific Research and Philips Research Europe P15-26 (SCW, MV and JPWP). Philips Research Europe provided support in the form of salaries for authors (BB, RV and MBL), but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.

FundersFunder number
Nederlandse Organisatie voor Wetenschappelijk Onderzoek
National Cancer InstituteU01CA176726, K99CA245900

    Fingerprint

    Dive into the research topics of 'Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk'. Together they form a unique fingerprint.

    Cite this