Cargando…

StarDist Image Segmentation Improves Circulating Tumor Cell Detection

SIMPLE SUMMARY: Automated enumeration of circulating tumor cells (CTC) from immunofluorescence images starts with a selection of areas containing potential CTC. The CellSearch system has a built-in selection algorithm that has been observed to fail in samples with high cell density, thereby underest...

Descripción completa

Detalles Bibliográficos
Autores principales: Stevens, Michiel, Nanou, Afroditi, Terstappen, Leon W. M. M., Driemel, Christiane, Stoecklein, Nikolas H., Coumans, Frank A. W.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9221404/
https://www.ncbi.nlm.nih.gov/pubmed/35740582
http://dx.doi.org/10.3390/cancers14122916
_version_ 1784732613386174464
author Stevens, Michiel
Nanou, Afroditi
Terstappen, Leon W. M. M.
Driemel, Christiane
Stoecklein, Nikolas H.
Coumans, Frank A. W.
author_facet Stevens, Michiel
Nanou, Afroditi
Terstappen, Leon W. M. M.
Driemel, Christiane
Stoecklein, Nikolas H.
Coumans, Frank A. W.
author_sort Stevens, Michiel
collection PubMed
description SIMPLE SUMMARY: Automated enumeration of circulating tumor cells (CTC) from immunofluorescence images starts with a selection of areas containing potential CTC. The CellSearch system has a built-in selection algorithm that has been observed to fail in samples with high cell density, thereby underestimating the true CTC load. We evaluated the deep learning method StarDist for the selection of possible CTC. In whole blood sample images, StarDist recovered 99.95% of CTC detected by CellSearch and segmented 10% additional CTC. In diagnostic leukapheresis (DLA) samples, StarDist segmented 20% additional CTC and performed well, whereas CellSearch had serious failures in 9% of samples. ABSTRACT: After a CellSearch-processed circulating tumor cell (CTC) sample is imaged, a segmentation algorithm selects nucleic acid positive (DAPI+), cytokeratin-phycoerythrin expressing (CK-PE+) events for further review by an operator. Failures in this segmentation can result in missed CTCs. The CellSearch segmentation algorithm was not designed to handle samples with high cell density, such as diagnostic leukapheresis (DLA) samples. Here, we evaluate deep-learning-based segmentation method StarDist as an alternative to the CellSearch segmentation. CellSearch image archives from 533 whole blood samples and 601 DLA samples were segmented using CellSearch and StarDist and inspected visually. In 442 blood samples from cancer patients, StarDist segmented 99.95% of CTC segmented by CellSearch, produced good outlines for 98.3% of these CTC, and segmented 10% more CTC than CellSearch. Visual inspection of the segmentations of DLA images showed that StarDist continues to perform well when the cell density is very high, whereas CellSearch failed and generated extremely large segmentations (up to 52% of the sample surface). Moreover, in a detailed examination of seven DLA samples, StarDist segmented 20% more CTC than CellSearch. Segmentation is a critical first step for CTC enumeration in dense samples and StarDist segmentation convincingly outperformed CellSearch segmentation.
format Online
Article
Text
id pubmed-9221404
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92214042022-06-24 StarDist Image Segmentation Improves Circulating Tumor Cell Detection Stevens, Michiel Nanou, Afroditi Terstappen, Leon W. M. M. Driemel, Christiane Stoecklein, Nikolas H. Coumans, Frank A. W. Cancers (Basel) Article SIMPLE SUMMARY: Automated enumeration of circulating tumor cells (CTC) from immunofluorescence images starts with a selection of areas containing potential CTC. The CellSearch system has a built-in selection algorithm that has been observed to fail in samples with high cell density, thereby underestimating the true CTC load. We evaluated the deep learning method StarDist for the selection of possible CTC. In whole blood sample images, StarDist recovered 99.95% of CTC detected by CellSearch and segmented 10% additional CTC. In diagnostic leukapheresis (DLA) samples, StarDist segmented 20% additional CTC and performed well, whereas CellSearch had serious failures in 9% of samples. ABSTRACT: After a CellSearch-processed circulating tumor cell (CTC) sample is imaged, a segmentation algorithm selects nucleic acid positive (DAPI+), cytokeratin-phycoerythrin expressing (CK-PE+) events for further review by an operator. Failures in this segmentation can result in missed CTCs. The CellSearch segmentation algorithm was not designed to handle samples with high cell density, such as diagnostic leukapheresis (DLA) samples. Here, we evaluate deep-learning-based segmentation method StarDist as an alternative to the CellSearch segmentation. CellSearch image archives from 533 whole blood samples and 601 DLA samples were segmented using CellSearch and StarDist and inspected visually. In 442 blood samples from cancer patients, StarDist segmented 99.95% of CTC segmented by CellSearch, produced good outlines for 98.3% of these CTC, and segmented 10% more CTC than CellSearch. Visual inspection of the segmentations of DLA images showed that StarDist continues to perform well when the cell density is very high, whereas CellSearch failed and generated extremely large segmentations (up to 52% of the sample surface). Moreover, in a detailed examination of seven DLA samples, StarDist segmented 20% more CTC than CellSearch. Segmentation is a critical first step for CTC enumeration in dense samples and StarDist segmentation convincingly outperformed CellSearch segmentation. MDPI 2022-06-13 /pmc/articles/PMC9221404/ /pubmed/35740582 http://dx.doi.org/10.3390/cancers14122916 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Stevens, Michiel
Nanou, Afroditi
Terstappen, Leon W. M. M.
Driemel, Christiane
Stoecklein, Nikolas H.
Coumans, Frank A. W.
StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title_full StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title_fullStr StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title_full_unstemmed StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title_short StarDist Image Segmentation Improves Circulating Tumor Cell Detection
title_sort stardist image segmentation improves circulating tumor cell detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9221404/
https://www.ncbi.nlm.nih.gov/pubmed/35740582
http://dx.doi.org/10.3390/cancers14122916
work_keys_str_mv AT stevensmichiel stardistimagesegmentationimprovescirculatingtumorcelldetection
AT nanouafroditi stardistimagesegmentationimprovescirculatingtumorcelldetection
AT terstappenleonwmm stardistimagesegmentationimprovescirculatingtumorcelldetection
AT driemelchristiane stardistimagesegmentationimprovescirculatingtumorcelldetection
AT stoeckleinnikolash stardistimagesegmentationimprovescirculatingtumorcelldetection
AT coumansfrankaw stardistimagesegmentationimprovescirculatingtumorcelldetection