Cargando…

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

Automatic breast and fibro-glandular tissue (FGT) segmentation in breast MRI allows for the efficient and accurate calculation of breast density. The U-Net architecture, either 2D or 3D, has already been shown to be effective at addressing the segmentation problem in breast MRI. However, the lack of...

Descripción completa

Detalles Bibliográficos
Autores principales: Samperna, Riccardo, Moriakov, Nikita, Karssemeijer, Nico, Teuwen, Jonas, Mann, Ritse M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9324146/
https://www.ncbi.nlm.nih.gov/pubmed/35885594
http://dx.doi.org/10.3390/diagnostics12071690
_version_ 1784756735663144960
author Samperna, Riccardo
Moriakov, Nikita
Karssemeijer, Nico
Teuwen, Jonas
Mann, Ritse M.
author_facet Samperna, Riccardo
Moriakov, Nikita
Karssemeijer, Nico
Teuwen, Jonas
Mann, Ritse M.
author_sort Samperna, Riccardo
collection PubMed
description Automatic breast and fibro-glandular tissue (FGT) segmentation in breast MRI allows for the efficient and accurate calculation of breast density. The U-Net architecture, either 2D or 3D, has already been shown to be effective at addressing the segmentation problem in breast MRI. However, the lack of publicly available datasets for this task has forced several authors to rely on internal datasets composed of either acquisitions without fat suppression (WOFS) or with fat suppression (FS), limiting the generalization of the approach. To solve this problem, we propose a data-centric approach, efficiently using the data available. By collecting a dataset of T1-weighted breast MRI acquisitions acquired with the use of the Dixon method, we train a network on both T1 WOFS and FS acquisitions while utilizing the same ground truth segmentation. Using the “plug-and-play” framework nnUNet, we achieve, on our internal test set, a Dice Similarity Coefficient (DSC) of 0.96 and 0.91 for WOFS breast and FGT segmentation and 0.95 and 0.86 for FS breast and FGT segmentation, respectively. On an external, publicly available dataset, a panel of breast radiologists rated the quality of our automatic segmentation with an average of 3.73 on a four-point scale, with an average percentage agreement of 67.5%.
format Online
Article
Text
id pubmed-9324146
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93241462022-07-27 Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI Samperna, Riccardo Moriakov, Nikita Karssemeijer, Nico Teuwen, Jonas Mann, Ritse M. Diagnostics (Basel) Article Automatic breast and fibro-glandular tissue (FGT) segmentation in breast MRI allows for the efficient and accurate calculation of breast density. The U-Net architecture, either 2D or 3D, has already been shown to be effective at addressing the segmentation problem in breast MRI. However, the lack of publicly available datasets for this task has forced several authors to rely on internal datasets composed of either acquisitions without fat suppression (WOFS) or with fat suppression (FS), limiting the generalization of the approach. To solve this problem, we propose a data-centric approach, efficiently using the data available. By collecting a dataset of T1-weighted breast MRI acquisitions acquired with the use of the Dixon method, we train a network on both T1 WOFS and FS acquisitions while utilizing the same ground truth segmentation. Using the “plug-and-play” framework nnUNet, we achieve, on our internal test set, a Dice Similarity Coefficient (DSC) of 0.96 and 0.91 for WOFS breast and FGT segmentation and 0.95 and 0.86 for FS breast and FGT segmentation, respectively. On an external, publicly available dataset, a panel of breast radiologists rated the quality of our automatic segmentation with an average of 3.73 on a four-point scale, with an average percentage agreement of 67.5%. MDPI 2022-07-11 /pmc/articles/PMC9324146/ /pubmed/35885594 http://dx.doi.org/10.3390/diagnostics12071690 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
Samperna, Riccardo
Moriakov, Nikita
Karssemeijer, Nico
Teuwen, Jonas
Mann, Ritse M.
Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title_full Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title_fullStr Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title_full_unstemmed Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title_short Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI
title_sort exploiting the dixon method for a robust breast and fibro-glandular tissue segmentation in breast mri
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9324146/
https://www.ncbi.nlm.nih.gov/pubmed/35885594
http://dx.doi.org/10.3390/diagnostics12071690
work_keys_str_mv AT sampernariccardo exploitingthedixonmethodforarobustbreastandfibroglandulartissuesegmentationinbreastmri
AT moriakovnikita exploitingthedixonmethodforarobustbreastandfibroglandulartissuesegmentationinbreastmri
AT karssemeijernico exploitingthedixonmethodforarobustbreastandfibroglandulartissuesegmentationinbreastmri
AT teuwenjonas exploitingthedixonmethodforarobustbreastandfibroglandulartissuesegmentationinbreastmri
AT mannritsem exploitingthedixonmethodforarobustbreastandfibroglandulartissuesegmentationinbreastmri