A morphometric signature to identify ductal carcinoma in situ with a low risk of progression
Abstract Ductal carcinoma in situ (DCIS) may progress to ipsilateral invasive breast cancer (iIBC), but often never will. Because DCIS is treated as early breast cancer, many women with harmless DCIS face overtreatment. To identify features associated with progression, we developed an artificial int...
Saved in:
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2025-01-01
|
Series: | npj Precision Oncology |
Online Access: | https://doi.org/10.1038/s41698-024-00769-6 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832572054694526976 |
---|---|
author | Marcelo Sobral-Leite Simon P. Castillo Shiva Vonk Hendrik A. Messal Xenia Melillo Noomie Lam Brandi de Bruijn Yeman B. Hagos Myrna van den Bos Joyce Sanders Mathilde Almekinders Lindy L. Visser Emma J. Groen Petra Kristel Caner Ercan Leyla Azarang Jacco van Rheenen E. Shelley Hwang Yinyin Yuan Grand Challenge PRECISION Consortium Renee Menezes Esther H. Lips Jelle Wesseling |
author_facet | Marcelo Sobral-Leite Simon P. Castillo Shiva Vonk Hendrik A. Messal Xenia Melillo Noomie Lam Brandi de Bruijn Yeman B. Hagos Myrna van den Bos Joyce Sanders Mathilde Almekinders Lindy L. Visser Emma J. Groen Petra Kristel Caner Ercan Leyla Azarang Jacco van Rheenen E. Shelley Hwang Yinyin Yuan Grand Challenge PRECISION Consortium Renee Menezes Esther H. Lips Jelle Wesseling |
author_sort | Marcelo Sobral-Leite |
collection | DOAJ |
description | Abstract Ductal carcinoma in situ (DCIS) may progress to ipsilateral invasive breast cancer (iIBC), but often never will. Because DCIS is treated as early breast cancer, many women with harmless DCIS face overtreatment. To identify features associated with progression, we developed an artificial intelligence-based DCIS morphometric analysis pipeline (AIDmap) on hematoxylin-eosin-stained (H&E) tissue sections. We analyzed 689 digitized H&Es of pure primary DCIS of which 226 were diagnosed with subsequent iIBC and 463 were not. The distribution of 15 duct morphological measurements was summarized in 55 morphometric variables. A ridge regression classifier with cross validation predicted 5-years-free of iIBC with an area-under the curve of 0.67 (95% CI 0.57–0.77). A combined clinical-morphometric signature, characterized by small-sized ducts, a low number of cells and a low DCIS/stroma ratio, was associated with outcome (HR = 0.56; 95% CI 0.28–0.78). AIDmap has potential to identify harmless DCIS that may not need treatment. |
format | Article |
id | doaj-art-29d313b94b7744e9a3d2b9c1f4e25bfe |
institution | Kabale University |
issn | 2397-768X |
language | English |
publishDate | 2025-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Precision Oncology |
spelling | doaj-art-29d313b94b7744e9a3d2b9c1f4e25bfe2025-02-02T12:06:34ZengNature Portfolionpj Precision Oncology2397-768X2025-01-019111310.1038/s41698-024-00769-6A morphometric signature to identify ductal carcinoma in situ with a low risk of progressionMarcelo Sobral-Leite0Simon P. Castillo1Shiva Vonk2Hendrik A. Messal3Xenia Melillo4Noomie Lam5Brandi de Bruijn6Yeman B. Hagos7Myrna van den Bos8Joyce Sanders9Mathilde Almekinders10Lindy L. Visser11Emma J. Groen12Petra Kristel13Caner Ercan14Leyla Azarang15Jacco van Rheenen16E. Shelley Hwang17Yinyin Yuan18Grand Challenge PRECISION ConsortiumRenee Menezes19Esther H. Lips20Jelle Wesseling21Division of Molecular Pathology, Netherlands Cancer InstituteDivision of Pathology and Laboratory Medicine, Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer CenterDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteSarcoma Molecular Pathology Team, The Institute of Cancer ResearchDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Pathology and Laboratory Medicine, Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer CenterBiostatistics Centre and Division of Psychosocial Research and Epidemiology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDepartment of Surgery, Duke University Comprehensive Cancer CenterDivision of Pathology and Laboratory Medicine, Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer CenterBiostatistics Centre and Division of Psychosocial Research and Epidemiology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteDivision of Molecular Pathology, Netherlands Cancer InstituteAbstract Ductal carcinoma in situ (DCIS) may progress to ipsilateral invasive breast cancer (iIBC), but often never will. Because DCIS is treated as early breast cancer, many women with harmless DCIS face overtreatment. To identify features associated with progression, we developed an artificial intelligence-based DCIS morphometric analysis pipeline (AIDmap) on hematoxylin-eosin-stained (H&E) tissue sections. We analyzed 689 digitized H&Es of pure primary DCIS of which 226 were diagnosed with subsequent iIBC and 463 were not. The distribution of 15 duct morphological measurements was summarized in 55 morphometric variables. A ridge regression classifier with cross validation predicted 5-years-free of iIBC with an area-under the curve of 0.67 (95% CI 0.57–0.77). A combined clinical-morphometric signature, characterized by small-sized ducts, a low number of cells and a low DCIS/stroma ratio, was associated with outcome (HR = 0.56; 95% CI 0.28–0.78). AIDmap has potential to identify harmless DCIS that may not need treatment.https://doi.org/10.1038/s41698-024-00769-6 |
spellingShingle | Marcelo Sobral-Leite Simon P. Castillo Shiva Vonk Hendrik A. Messal Xenia Melillo Noomie Lam Brandi de Bruijn Yeman B. Hagos Myrna van den Bos Joyce Sanders Mathilde Almekinders Lindy L. Visser Emma J. Groen Petra Kristel Caner Ercan Leyla Azarang Jacco van Rheenen E. Shelley Hwang Yinyin Yuan Grand Challenge PRECISION Consortium Renee Menezes Esther H. Lips Jelle Wesseling A morphometric signature to identify ductal carcinoma in situ with a low risk of progression npj Precision Oncology |
title | A morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
title_full | A morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
title_fullStr | A morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
title_full_unstemmed | A morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
title_short | A morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
title_sort | morphometric signature to identify ductal carcinoma in situ with a low risk of progression |
url | https://doi.org/10.1038/s41698-024-00769-6 |
work_keys_str_mv | AT marcelosobralleite amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT simonpcastillo amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT shivavonk amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT hendrikamessal amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT xeniamelillo amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT noomielam amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT brandidebruijn amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT yemanbhagos amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT myrnavandenbos amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT joycesanders amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT mathildealmekinders amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT lindylvisser amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT emmajgroen amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT petrakristel amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT canerercan amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT leylaazarang amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT jaccovanrheenen amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT eshelleyhwang amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT yinyinyuan amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT grandchallengeprecisionconsortium amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT reneemenezes amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT estherhlips amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT jellewesseling amorphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT marcelosobralleite morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT simonpcastillo morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT shivavonk morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT hendrikamessal morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT xeniamelillo morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT noomielam morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT brandidebruijn morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT yemanbhagos morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT myrnavandenbos morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT joycesanders morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT mathildealmekinders morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT lindylvisser morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT emmajgroen morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT petrakristel morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT canerercan morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT leylaazarang morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT jaccovanrheenen morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT eshelleyhwang morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT yinyinyuan morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT grandchallengeprecisionconsortium morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT reneemenezes morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT estherhlips morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression AT jellewesseling morphometricsignaturetoidentifyductalcarcinomainsituwithalowriskofprogression |