Unmasking the immune microecology of ductal carcinoma in situ with deep learning.


Despite increasing evidence supporting the clinical relevance of tumour infiltrating lymphocytes (TILs) in invasive breast cancer, TIL spatial variability within ductal carcinoma in situ (DCIS) samples and its association with progression are not well understood. To characterise tissue spatial architecture and the microenvironment of DCIS, we designed and validated a new deep learning pipeline, UNMaSk. Following automated detection of individual DCIS ducts using a new method IM-Net, we applied spatial tessellation to create virtual boundaries for each duct. To study local TIL infiltration for each duct, DRDIN was developed for mapping the distribution of TILs. In a dataset comprising grade 2-3 pure DCIS and DCIS adjacent to invasive cancer (adjacent DCIS), we found that pure DCIS cases had more TILs compared to adjacent DCIS. However, the colocalisation of TILs with DCIS ducts was significantly lower in pure DCIS compared to adjacent DCIS, which may suggest a more inflamed tissue ecology local to DCIS ducts in adjacent DCIS cases. Our study demonstrates that technological developments in deep convolutional neural networks and digital pathology can enable an automated morphological and microenvironmental analysis of DCIS, providing a new way to study differential immune ecology for individual ducts and identify new markers of progression.






Published Version (Please cite this version)


Publication Info

Narayanan, Priya Lakshmi, Shan E Ahmed Raza, Allison H Hall, Jeffrey R Marks, Lorraine King, Robert B West, Lucia Hernandez, Naomi Guppy, et al. (2021). Unmasking the immune microecology of ductal carcinoma in situ with deep learning. NPJ breast cancer, 7(1). p. 19. 10.1038/s41523-020-00205-5 Retrieved from https://hdl.handle.net/10161/26594.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.



Allison Haberstroh Sandler Hall

Adjunct Associate Professor in the Department of Pathology

Jeffrey R. Marks

Joseph W. and Dorothy W. Beard Distinguished Professor of Experimental Surgery

I have been engaged in basic and applied cancer research for over 28 years beginning with my post-doctoral fellowship under Arnold Levine at Princeton. Since being appointed to the faculty in the Department of Surgery at Duke, my primary interest has been towards understanding breast and ovarian cancer. I am a charter member of the NCI-Early Detection Research Network (EDRN) and have been an integral scientist in the breast and gynecologic collaborative group for 15 years including leading this group for a 5 year period. I am also a major contributor to the Cancer Genome Atlas and have worked in this context for the past 4 years. My research interests are in the molecular etiology of these diseases and understanding how key genetic events contribute to their onset and progression. My work has been very multi-disciplinary incorporating quantitative, population, genetic, and behavioral approaches.  I consider my specialty to be in the area of using human breast and ovarian cancer as the primary and only authentic model system to understand these diseases.  


Eun-Sil Shelley Hwang

Mary and Deryl Hart Distinguished Professor of Surgery, in the School of Medicine

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.