Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.

Digital pathology enables automatic analysis of histopathological sections using artificial intelligence. Automatic evaluation could improve diagnostic efficiency and find associations between morphological features and clinical outcome. For development of such prediction models in breast cancer, id...

Full description

Saved in:
Bibliographic Details
Main Authors: Maren Høibø, André Pedersen, Vibeke Grotnes Dale, Sissel Marie Berget, Borgny Ytterhus, Cecilia Lindskog, Elisabeth Wik, Lars A Akslen, Ingerid Reinertsen, Erik Smistad, Marit Valla
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0328033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849317317290229760
author Maren Høibø
André Pedersen
Vibeke Grotnes Dale
Sissel Marie Berget
Borgny Ytterhus
Cecilia Lindskog
Elisabeth Wik
Lars A Akslen
Ingerid Reinertsen
Erik Smistad
Marit Valla
author_facet Maren Høibø
André Pedersen
Vibeke Grotnes Dale
Sissel Marie Berget
Borgny Ytterhus
Cecilia Lindskog
Elisabeth Wik
Lars A Akslen
Ingerid Reinertsen
Erik Smistad
Marit Valla
author_sort Maren Høibø
collection DOAJ
description Digital pathology enables automatic analysis of histopathological sections using artificial intelligence. Automatic evaluation could improve diagnostic efficiency and find associations between morphological features and clinical outcome. For development of such prediction models in breast cancer, identifying invasive epithelial cells, and separating these from benign epithelial cells and in situ lesions would be important. In this study, we trained an attention gated U-Net for segmentation of epithelial cells in hematoxylin and eosin stained breast cancer sections. We generated epithelial ground truths by immunohistochemistry, restaining hematoxylin and eosin sections with cytokeratin AE1/AE3, combined with pathologists' annotations. Tissue microarrays from 839 patients, and whole slide images from two patients, were used for training and evaluation of the models. The sections were derived from four breast cancer cohorts. Tissue microarray cores from a fifth cohort of 21 patients was used as a second test set. In quantitative evaluation, mean Dice scores of 0.70, 0.79, and 0.75 were achieved for invasive epithelial cells, benign epithelial cells, and in situ lesions, respectively. In qualitative scoring (0-5) by pathologists, the best results were reached for all epithelium and invasive epithelium, with scores of 4.7 and 4.4, respectively. Scores for benign epithelium and in situ lesions were 3.7 and 2.0, respectively. The proposed model segmented epithelial cells well, but further work is needed for accurate subclassification into benign, in situ, and invasive cells.
format Article
id doaj-art-ab644d0960fd46d4b7d7e20713b578db
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-ab644d0960fd46d4b7d7e20713b578db2025-08-20T03:51:14ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032803310.1371/journal.pone.0328033Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.Maren HøibøAndré PedersenVibeke Grotnes DaleSissel Marie BergetBorgny YtterhusCecilia LindskogElisabeth WikLars A AkslenIngerid ReinertsenErik SmistadMarit VallaDigital pathology enables automatic analysis of histopathological sections using artificial intelligence. Automatic evaluation could improve diagnostic efficiency and find associations between morphological features and clinical outcome. For development of such prediction models in breast cancer, identifying invasive epithelial cells, and separating these from benign epithelial cells and in situ lesions would be important. In this study, we trained an attention gated U-Net for segmentation of epithelial cells in hematoxylin and eosin stained breast cancer sections. We generated epithelial ground truths by immunohistochemistry, restaining hematoxylin and eosin sections with cytokeratin AE1/AE3, combined with pathologists' annotations. Tissue microarrays from 839 patients, and whole slide images from two patients, were used for training and evaluation of the models. The sections were derived from four breast cancer cohorts. Tissue microarray cores from a fifth cohort of 21 patients was used as a second test set. In quantitative evaluation, mean Dice scores of 0.70, 0.79, and 0.75 were achieved for invasive epithelial cells, benign epithelial cells, and in situ lesions, respectively. In qualitative scoring (0-5) by pathologists, the best results were reached for all epithelium and invasive epithelium, with scores of 4.7 and 4.4, respectively. Scores for benign epithelium and in situ lesions were 3.7 and 2.0, respectively. The proposed model segmented epithelial cells well, but further work is needed for accurate subclassification into benign, in situ, and invasive cells.https://doi.org/10.1371/journal.pone.0328033
spellingShingle Maren Høibø
André Pedersen
Vibeke Grotnes Dale
Sissel Marie Berget
Borgny Ytterhus
Cecilia Lindskog
Elisabeth Wik
Lars A Akslen
Ingerid Reinertsen
Erik Smistad
Marit Valla
Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
PLoS ONE
title Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
title_full Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
title_fullStr Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
title_full_unstemmed Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
title_short Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides.
title_sort immunohistochemistry guided segmentation of benign epithelial cells in situ lesions and invasive epithelial cells in breast cancer slides
url https://doi.org/10.1371/journal.pone.0328033
work_keys_str_mv AT marenhøibø immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT andrepedersen immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT vibekegrotnesdale immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT sisselmarieberget immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT borgnyytterhus immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT cecilialindskog immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT elisabethwik immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT larsaakslen immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT ingeridreinertsen immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT eriksmistad immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides
AT maritvalla immunohistochemistryguidedsegmentationofbenignepithelialcellsinsitulesionsandinvasiveepithelialcellsinbreastcancerslides