{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:33:30Z","timestamp":1793039610914,"version":"4.5.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Breast Cancer"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>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\u20133 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.<\/jats:p>","DOI":"10.1038\/s41523-020-00205-5","type":"journal-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T06:07:32Z","timestamp":1614578852000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Unmasking the immune microecology of ductal carcinoma in situ with deep learning"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6784-9226","authenticated-orcid":false,"given":"Priya Lakshmi","family":"Narayanan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-1738","authenticated-orcid":false,"given":"Shan E. Ahmed","family":"Raza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allison H.","family":"Hall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey R.","family":"Marks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorraine","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert B.","family":"West","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucia","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naomi","family":"Guppy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitch","family":"Dowsett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barry","family":"Gusterson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlo","family":"Maley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E. Shelley","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinyin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,1]]},"reference":[{"key":"205_CR1","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1093\/jncimonographs\/lgq035","volume":"2010","author":"DC Allred","year":"2010","unstructured":"Allred, D. C. et al. Ductal carcinoma in situ: terminology, classification, and natural history. J. Natl Cancer Inst. Monogr. 2010, 134\u2013138 (2010).","journal-title":"J. Natl Cancer Inst. Monogr."},{"key":"205_CR2","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1093\/jnci\/djh164","volume":"96","author":"GD Leonard","year":"2004","unstructured":"Leonard, G. D. & Swain, S. M. Ductal carcinoma in situ, complexities and challenges. J. Natl Cancer Inst. 96, 906\u2013920 (2004).","journal-title":"J. Natl Cancer Inst."},{"key":"205_CR3","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1016\/j.molonc.2013.07.005","volume":"7","author":"CF Cowell","year":"2013","unstructured":"Cowell, C. F. et al. Progression from ductal carcinoma in situ to invasive breast cancer: revisited. Mol. Oncol 7, 859\u2013869 (2013).","journal-title":"Mol. Oncol"},{"key":"205_CR4","doi-asserted-by":"crossref","unstructured":"van Seijen, M. et al. Ductal carcinoma in situ: to treat or not to treat, that is the question. Br. J. Cancer. 121, 285\u2013292 (2019).","DOI":"10.1038\/s41416-019-0478-6"},{"key":"205_CR5","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1002\/path.4840","volume":"241","author":"AK Casasent","year":"2017","unstructured":"Casasent, A. K., Edgerton, M. & Navin, N. E. Genome evolution in ductal carcinoma in situ: invasion of the clones. J. Pathol. 241, 208\u2013218 (2017).","journal-title":"J. Pathol."},{"key":"205_CR6","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1158\/2159-8290.CD-17-0222","volume":"7","author":"CR Del Alcazar","year":"2017","unstructured":"Del Alcazar, C. R. et al. Immune escape in breast cancer during in situ to invasive carcinoma transition. Cancer Discov 7, 1098\u20131115 (2017).","journal-title":"Cancer Discov"},{"key":"205_CR7","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/nrc.2017.69","volume":"17","author":"CC Maley","year":"2017","unstructured":"Maley, C. C. et al. Classifying the evolutionary and ecological features of neoplasms. Nat. Rev. Cancer 17, 605\u2013619 (2017).","journal-title":"Nat. Rev. Cancer"},{"key":"205_CR8","doi-asserted-by":"publisher","first-page":"248","DOI":"10.3389\/fonc.2017.00248","volume":"7","author":"KL Gorringe","year":"2017","unstructured":"Gorringe, K. L. & Fox, S. B. Ductal carcinoma in situ biology, biomarkers, and diagnosis. Front. Oncol 7, 248 (2017).","journal-title":"Front. Oncol"},{"key":"205_CR9","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1001\/jama.2015.1405","volume":"313","author":"JG Elmore","year":"2015","unstructured":"Elmore, J. G. et al. Diagnostic concordance among pathologists interpreting breast biopsy specimens. Jama 313, 1122\u20131132 (2015).","journal-title":"Jama"},{"key":"205_CR10","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1109\/TMI.2016.2550620","volume":"35","author":"BE Bejnordi","year":"2016","unstructured":"Bejnordi, B. E. et al. Automated detection of DCIS in whole-slide H&E stained breast histopathology images. IEEE Trans. Med. Imaging 35, 2141\u20132150 (2016).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"205_CR11","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s13058-019-1165-5","volume":"21","author":"S Klimov","year":"2019","unstructured":"Klimov, S. et al. A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk. Breast Cancer Res 21, 83 (2019).","journal-title":"Breast Cancer Res"},{"key":"205_CR12","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s10549-016-4036-0","volume":"161","author":"MJ Campbell","year":"2017","unstructured":"Campbell, M. J. et al. Characterizing the immune microenvironment in high-risk ductal carcinoma in situ of the breast. Breast Cancer Res 161, 17\u201328 (2017).","journal-title":"Breast Cancer Res"},{"key":"205_CR13","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1038\/nrclinonc.2015.215","volume":"13","author":"P Savas","year":"2016","unstructured":"Savas, P. et al. Clinical relevance of host immunity in breast cancer: from TILs to the clinic. Nat. Rev. Clin. Oncol 13, 228 (2016).","journal-title":"Nat. Rev. Clin. Oncol"},{"key":"205_CR14","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Ssd: Single shot multibox detector. In 14th European Conference on Computer Vision 21\u201337 (ECCV, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"205_CR15","doi-asserted-by":"crossref","unstructured":"Girshick, R. Fast r-cnn. IEEE International Conference on Computer Vision 1440\u20131448 (IEEE, 2015).","DOI":"10.1109\/ICCV.2015.169"},{"key":"205_CR16","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. in International Conference on Medical Image Computing and Computer-Assisted Intervention 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"205_CR17","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.media.2018.12.003","volume":"52","author":"SEA Raza","year":"2019","unstructured":"Raza, S. E. A. et al. Micro-Net: a unified model for segmentation of various objects in microscopy images. Med. Image Anal. 52, 160\u2013173 (2019).","journal-title":"Med. Image Anal."},{"key":"205_CR18","doi-asserted-by":"publisher","first-page":"46450","DOI":"10.1038\/srep46450","volume":"7","author":"A Cruz-Roa","year":"2017","unstructured":"Cruz-Roa, A. et al. Accurate and reproducible invasive breast cancer detection in whole-slide images: a deep learning approach for quantifying tumor extent. Sci. Rep. 7, 46450 (2017).","journal-title":"Sci. Rep."},{"key":"205_CR19","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/s13058-015-0638-4","volume":"17","author":"CC Maley","year":"2015","unstructured":"Maley, C. C., Koelble, K., Natrajan, R., Aktipis, A. & Yuan, Y. An ecological measure of immune-cancer colocalization as a prognostic factor for breast cancer. Breast Cancer Res 17, 131 (2015).","journal-title":"Breast Cancer Res"},{"key":"205_CR20","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41379-020-0553-9","volume":"33","author":"MC Agahozo","year":"2020","unstructured":"Agahozo, M. C. et al. Immune response and stromal changes in ductal carcinoma in situ of the breast are subtype dependent. Mod. Pathol. 33, 1773\u20131782 (2020).","journal-title":"Mod. Pathol."},{"key":"205_CR21","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1186\/s12885-018-4013-6","volume":"18","author":"M Beguinot","year":"2018","unstructured":"Beguinot, M. et al. Analysis of tumour-infiltrating lymphocytes reveals two new biologically different subgroups of breast ductal carcinoma in situ. BMC Cancer 18, 129 (2018).","journal-title":"BMC Cancer"},{"key":"205_CR22","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1038\/modpathol.2015.79","volume":"28","author":"A Knopfelmacher","year":"2015","unstructured":"Knopfelmacher, A., Fox, J., Lo, Y., Shapiro, N. & Fineberg, S. Correlation of histopathologic features of ductal carcinoma in situ of the breast with the oncotype DX DCIS score. Mod. Pathol. 28, 1167 (2015).","journal-title":"Mod. Pathol."},{"key":"205_CR23","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1002\/path.3990","volume":"227","author":"L Hernandez","year":"2012","unstructured":"Hernandez, L. et al. Genomic and mutational profiling of ductal carcinomas in situ and matched adjacent invasive breast cancers reveals intra-tumour genetic heterogeneity and clonal selection. Am. J. Pathol. 227, 42\u201352 (2012).","journal-title":"Am. J. Pathol."},{"key":"205_CR24","doi-asserted-by":"publisher","first-page":"3980","DOI":"10.1158\/0008-5472.CAN-15-0506","volume":"75","author":"MC Abba","year":"2015","unstructured":"Abba, M. C. et al. A molecular portrait of high-grade ductal carcinoma in situ. Cancer Res. 75, 3980\u20133990 (2015).","journal-title":"Cancer Res."},{"key":"205_CR25","doi-asserted-by":"publisher","first-page":"3682","DOI":"10.1158\/1078-0432.CCR-19-2563","volume":"26","author":"F Pareja","year":"2020","unstructured":"Pareja, F. et al. Whole-exome sequencing analysis of the progression from non-low grade ductal carcinoma in situ to invasive ductal carcinoma. Clin. Cancer Res. 26, 3682\u20133693 (2020).","journal-title":"Clin. Cancer Res."},{"key":"205_CR26","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1016\/j.steroids.2011.02.032","volume":"76","author":"M Dowsett","year":"2011","unstructured":"Dowsett, M. et al. Predictive algorithms for adjuvant therapy: TransATAC. Steroids 76, 777\u2013780 (2011).","journal-title":"Steroids"},{"key":"205_CR27","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1093\/jnci\/djx137","volume":"110","author":"A Heindl","year":"2018","unstructured":"Heindl, A. et al. Relevance of spatial heterogeneity of immune infiltration for predicting risk of recurrence after endocrine therapy of ER. breast cancer. J. Natl Cancer Inst 110, 166\u2013175 (2018).","journal-title":"J. Natl Cancer Inst"},{"key":"205_CR28","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1023\/A:1026439204849","volume":"5","author":"E Mallon","year":"2000","unstructured":"Mallon, E. et al. The basic pathology of human breast cancer. J. Mammary Gland Biol. Neoplasia 5, 139\u2013163 (2000).","journal-title":"J. Mammary Gland Biol. Neoplasia"},{"key":"205_CR29","doi-asserted-by":"publisher","first-page":"27","DOI":"10.4103\/2153-3539.119005","volume":"4","author":"A Goode","year":"2013","unstructured":"Goode, A., Gilbert, B., Harkes, J., Jukic, D. & Satyanarayanan, M. OpenSlide: A vendor-neutral software foundation for digital pathology. Am. J. Pathol. Informatics 4, 27 (2013).","journal-title":"Am. J. Pathol. Informatics"},{"key":"205_CR30","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1109\/TMI.2016.2525803","volume":"35","author":"K Sirinukunwattana","year":"2016","unstructured":"Sirinukunwattana, K. et al. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Trans. Med. Imaging 35, 1196\u20131206 (2016).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"205_CR31","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1007\/s11538-009-9498-3","volume":"72","author":"M Bock","year":"2010","unstructured":"Bock, M., Tyagi, A. K., Kreft, J. U. & Alt, W. Generalized voronoi tessellation as a model of two-dimensional cell tissue dynamics. Bull. Math. Biol. 72, 1696\u20131731 (2010).","journal-title":"Bull. Math. Biol."},{"key":"205_CR32","doi-asserted-by":"publisher","first-page":"a026583","DOI":"10.1101\/cshperspect.a026583","volume":"6","author":"Y Yuan","year":"2016","unstructured":"Yuan, Y. Spatial Heterogeneity in the Tumor Microenvironment. Cold Spring Harb. Perspect. Med 6, a026583 (2016).","journal-title":"Cold Spring Harb. Perspect. Med"},{"key":"205_CR33","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L. R. Measures of the amount of ecologic association between species. Ecology 26, 297\u2013302 (1945).","journal-title":"Ecology"},{"key":"205_CR34","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1309\/AJCP3KFF1LTYWQIY","volume":"130","author":"R Bhargava","year":"2008","unstructured":"Bhargava, R., Beriwal, S., McManus, K. & Dabbs, D. J. CK5 is more sensitive than CK5\/6 in identifying the \u201cbasal-like\u201d phenotype of breast carcinoma. Am. J. Clin. Pathol. 130, 724\u2013730 (2008).","journal-title":"Am. J. Clin. Pathol."},{"key":"205_CR35","doi-asserted-by":"publisher","first-page":"279","DOI":"10.4300\/JGME-D-12-00156.1","volume":"4","author":"GM Sullivan","year":"2012","unstructured":"Sullivan, G. M. & Fein, R. Using effect size\u2014or why the P value is not enough. J. Grad. Med. Educ. 4, 279\u2013282 (2012).","journal-title":"J. Grad. Med. Educ."},{"key":"205_CR36","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1111\/1467-8721.ep10768783","volume":"1","author":"J Cohen","year":"1992","unstructured":"Cohen, J. Statistical power analysis. Curr. Dir. Psychol. Sci. 1, 98\u2013101 (1992).","journal-title":"Curr. Dir. Psychol. Sci."},{"key":"205_CR37","doi-asserted-by":"publisher","unstructured":"Narayanan, P. L. et al. Metadata record for the manuscript: Unmasking the immune microecology of ductal carcinoma in situ with deep learning. figshare https:\/\/doi.org\/10.6084\/m9.figshare.13007954 (2020).","DOI":"10.6084\/m9.figshare.13007954"},{"key":"205_CR38","doi-asserted-by":"crossref","unstructured":"Narayanan, P. L. et al. Unmasking the tissue microecology of ductal carcinoma in situ with deep learning. Preprint at https:\/\/www.biorxiv.org\/content\/10.1101\/812735v1 (2019).","DOI":"10.1101\/812735"}],"container-title":["npj Breast Cancer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41523-020-00205-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41523-020-00205-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41523-020-00205-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T15:14:24Z","timestamp":1669994064000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41523-020-00205-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["205"],"URL":"https:\/\/doi.org\/10.1038\/s41523-020-00205-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/812735","asserted-by":"object"}]},"ISSN":["2374-4677"],"issn-type":[{"value":"2374-4677","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]},"assertion":[{"value":"11 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The funders had no role in the design of the study; the collection, analysis, or interpretation of the data; the writing of the manuscript; or the decision to submit the manuscript for publication. Y.Y. has received speakers bureau honoraria from Roche and consulted for Merck and Co Inc. M.D. declares advisory fees from Radius, G1-Therapeutics, AbbVie, H3Biomedicine, Zentalis and Lilly, lecture fees from Nanostring and BCN Science and institutional grants from Pfizer and Lilly. All other authors declare that there are no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19"}}