Cargando…

Automated segmentation of lungs and lung tumors in mouse micro-CT scans

Here, we have developed an automated image processing algorithm for segmenting lungs and individual lung tumors in in vivo micro-computed tomography (micro-CT) scans of mouse models of non-small cell lung cancer and lung fibrosis. Over 3000 scans acquired across multiple studies were used to train/v...

Descripción completa

Detalles Bibliográficos
Autores principales: Ferl, Gregory Z., Barck, Kai H., Patil, Jasmine, Jemaa, Skander, Malamut, Evelyn J., Lima, Anthony, Long, Jason E., Cheng, Jason H., Junttila, Melissa R., Carano, Richard A.D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9792881/
https://www.ncbi.nlm.nih.gov/pubmed/36582483
http://dx.doi.org/10.1016/j.isci.2022.105712
_version_ 1784859731620265984
author Ferl, Gregory Z.
Barck, Kai H.
Patil, Jasmine
Jemaa, Skander
Malamut, Evelyn J.
Lima, Anthony
Long, Jason E.
Cheng, Jason H.
Junttila, Melissa R.
Carano, Richard A.D.
author_facet Ferl, Gregory Z.
Barck, Kai H.
Patil, Jasmine
Jemaa, Skander
Malamut, Evelyn J.
Lima, Anthony
Long, Jason E.
Cheng, Jason H.
Junttila, Melissa R.
Carano, Richard A.D.
author_sort Ferl, Gregory Z.
collection PubMed
description Here, we have developed an automated image processing algorithm for segmenting lungs and individual lung tumors in in vivo micro-computed tomography (micro-CT) scans of mouse models of non-small cell lung cancer and lung fibrosis. Over 3000 scans acquired across multiple studies were used to train/validate a 3D U-net lung segmentation model and a Support Vector Machine (SVM) classifier to segment individual lung tumors. The U-net lung segmentation algorithm can be used to estimate changes in soft tissue volume within lungs (primarily tumors and blood vessels), whereas the trained SVM is able to discriminate between tumors and blood vessels and identify individual tumors. The trained segmentation algorithms (1) significantly reduce time required for lung and tumor segmentation, (2) reduce bias and error associated with manual image segmentation, and (3) facilitate identification of individual lung tumors and objective assessment of changes in lung and individual tumor volumes under different experimental conditions.
format Online
Article
Text
id pubmed-9792881
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-97928812022-12-28 Automated segmentation of lungs and lung tumors in mouse micro-CT scans Ferl, Gregory Z. Barck, Kai H. Patil, Jasmine Jemaa, Skander Malamut, Evelyn J. Lima, Anthony Long, Jason E. Cheng, Jason H. Junttila, Melissa R. Carano, Richard A.D. iScience Article Here, we have developed an automated image processing algorithm for segmenting lungs and individual lung tumors in in vivo micro-computed tomography (micro-CT) scans of mouse models of non-small cell lung cancer and lung fibrosis. Over 3000 scans acquired across multiple studies were used to train/validate a 3D U-net lung segmentation model and a Support Vector Machine (SVM) classifier to segment individual lung tumors. The U-net lung segmentation algorithm can be used to estimate changes in soft tissue volume within lungs (primarily tumors and blood vessels), whereas the trained SVM is able to discriminate between tumors and blood vessels and identify individual tumors. The trained segmentation algorithms (1) significantly reduce time required for lung and tumor segmentation, (2) reduce bias and error associated with manual image segmentation, and (3) facilitate identification of individual lung tumors and objective assessment of changes in lung and individual tumor volumes under different experimental conditions. Elsevier 2022-12-05 /pmc/articles/PMC9792881/ /pubmed/36582483 http://dx.doi.org/10.1016/j.isci.2022.105712 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Ferl, Gregory Z.
Barck, Kai H.
Patil, Jasmine
Jemaa, Skander
Malamut, Evelyn J.
Lima, Anthony
Long, Jason E.
Cheng, Jason H.
Junttila, Melissa R.
Carano, Richard A.D.
Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title_full Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title_fullStr Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title_full_unstemmed Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title_short Automated segmentation of lungs and lung tumors in mouse micro-CT scans
title_sort automated segmentation of lungs and lung tumors in mouse micro-ct scans
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9792881/
https://www.ncbi.nlm.nih.gov/pubmed/36582483
http://dx.doi.org/10.1016/j.isci.2022.105712
work_keys_str_mv AT ferlgregoryz automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT barckkaih automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT patiljasmine automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT jemaaskander automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT malamutevelynj automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT limaanthony automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT longjasone automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT chengjasonh automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT junttilamelissar automatedsegmentationoflungsandlungtumorsinmousemicroctscans
AT caranorichardad automatedsegmentationoflungsandlungtumorsinmousemicroctscans