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

Abstract 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 spat...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Priya Lakshmi Narayanan, Shan E. Ahmed Raza, Allison H. Hall, Jeffrey R. Marks, Lorraine King, Robert B. West, Lucia Hernandez, Naomi Guppy, Mitch Dowsett, Barry Gusterson, Carlo Maley, E. Shelley Hwang, Yinyin Yuan
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/933aafb5df734dabbcabf44349806765
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:933aafb5df734dabbcabf44349806765
record_format dspace
spelling oai:doaj.org-article:933aafb5df734dabbcabf443498067652021-12-02T18:01:26ZUnmasking the immune microecology of ductal carcinoma in situ with deep learning10.1038/s41523-020-00205-52374-4677https://doaj.org/article/933aafb5df734dabbcabf443498067652021-03-01T00:00:00Zhttps://doi.org/10.1038/s41523-020-00205-5https://doaj.org/toc/2374-4677Abstract 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.Priya Lakshmi NarayananShan E. Ahmed RazaAllison H. HallJeffrey R. MarksLorraine KingRobert B. WestLucia HernandezNaomi GuppyMitch DowsettBarry GustersonCarlo MaleyE. Shelley HwangYinyin YuanNature PortfolioarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENnpj Breast Cancer, Vol 7, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
spellingShingle Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
Priya Lakshmi Narayanan
Shan E. Ahmed Raza
Allison H. Hall
Jeffrey R. Marks
Lorraine King
Robert B. West
Lucia Hernandez
Naomi Guppy
Mitch Dowsett
Barry Gusterson
Carlo Maley
E. Shelley Hwang
Yinyin Yuan
Unmasking the immune microecology of ductal carcinoma in situ with deep learning
description Abstract 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.
format article
author Priya Lakshmi Narayanan
Shan E. Ahmed Raza
Allison H. Hall
Jeffrey R. Marks
Lorraine King
Robert B. West
Lucia Hernandez
Naomi Guppy
Mitch Dowsett
Barry Gusterson
Carlo Maley
E. Shelley Hwang
Yinyin Yuan
author_facet Priya Lakshmi Narayanan
Shan E. Ahmed Raza
Allison H. Hall
Jeffrey R. Marks
Lorraine King
Robert B. West
Lucia Hernandez
Naomi Guppy
Mitch Dowsett
Barry Gusterson
Carlo Maley
E. Shelley Hwang
Yinyin Yuan
author_sort Priya Lakshmi Narayanan
title Unmasking the immune microecology of ductal carcinoma in situ with deep learning
title_short Unmasking the immune microecology of ductal carcinoma in situ with deep learning
title_full Unmasking the immune microecology of ductal carcinoma in situ with deep learning
title_fullStr Unmasking the immune microecology of ductal carcinoma in situ with deep learning
title_full_unstemmed Unmasking the immune microecology of ductal carcinoma in situ with deep learning
title_sort unmasking the immune microecology of ductal carcinoma in situ with deep learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/933aafb5df734dabbcabf44349806765
work_keys_str_mv AT priyalakshminarayanan unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT shaneahmedraza unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT allisonhhall unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT jeffreyrmarks unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT lorraineking unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT robertbwest unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT luciahernandez unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT naomiguppy unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT mitchdowsett unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT barrygusterson unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT carlomaley unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT eshelleyhwang unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
AT yinyinyuan unmaskingtheimmunemicroecologyofductalcarcinomainsituwithdeeplearning
_version_ 1718379004760686592