Cargando…

Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry

Thyroid volumetry is crucial in the diagnosis, treatment, and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural networ...

Descripción completa

Detalles Bibliográficos
Autores principales: Krönke, Markus, Eilers, Christine, Dimova, Desislava, Köhler, Melanie, Buschner, Gabriel, Schweiger, Lilit, Konstantinidou, Lemonia, Makowski, Marcus, Nagarajah, James, Navab, Nassir, Weber, Wolfgang, Wendler, Thomas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9337648/
https://www.ncbi.nlm.nih.gov/pubmed/35905038
http://dx.doi.org/10.1371/journal.pone.0268550
_version_ 1784759798150987776
author Krönke, Markus
Eilers, Christine
Dimova, Desislava
Köhler, Melanie
Buschner, Gabriel
Schweiger, Lilit
Konstantinidou, Lemonia
Makowski, Marcus
Nagarajah, James
Navab, Nassir
Weber, Wolfgang
Wendler, Thomas
author_facet Krönke, Markus
Eilers, Christine
Dimova, Desislava
Köhler, Melanie
Buschner, Gabriel
Schweiger, Lilit
Konstantinidou, Lemonia
Makowski, Marcus
Nagarajah, James
Navab, Nassir
Weber, Wolfgang
Wendler, Thomas
author_sort Krönke, Markus
collection PubMed
description Thyroid volumetry is crucial in the diagnosis, treatment, and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural network regarding inter- and intraobserver variability, time, and accuracy. Volume reference was MRI. 28 healthy volunteers (24—50 a) were scanned with 2D and 3D ultrasound (and by MRI) by three physicians (MD 1, 2, 3) with different experience levels (6, 4, and 1 a). In the 2D scans, the thyroid lobe volumes were calculated with the ellipsoid formula. A convolutional deep neural network (CNN) automatically segmented the 3D thyroid lobes. 26, 6, and 6 random lobe scans were used for training, validation, and testing, respectively. On MRI (T1 VIBE sequence) the thyroid was manually segmented by an experienced MD. MRI thyroid volumes ranged from 2.8 to 16.7ml (mean 7.4, SD 3.05). The CNN was trained to obtain an average Dice score of 0.94. The interobserver variability comparing two MDs showed mean differences for 2D and 3D respectively of 0.58 to 0.52ml (MD1 vs. 2), −1.33 to −0.17ml (MD1 vs. 3) and −1.89 to −0.70ml (MD2 vs. 3). Paired samples t-tests showed significant differences for 2D (p = .140, p = .002 and p = .002) and none for 3D (p = .176, p = .722 and p = .057). Intraobsever variability was similar for 2D and 3D ultrasound. Comparison of ultrasound volumes and MRI volumes showed a significant difference for the 2D volumetry of all MDs (p = .002, p = .009, p <.001), and no significant difference for 3D ultrasound (p = .292, p = .686, p = 0.091). Acquisition time was significantly shorter for 3D ultrasound. Tracked 3D ultrasound combined with a CNN segmentation significantly reduces interobserver variability in thyroid volumetry and increases the accuracy of the measurements with shorter acquisition times.
format Online
Article
Text
id pubmed-9337648
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93376482022-07-30 Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry Krönke, Markus Eilers, Christine Dimova, Desislava Köhler, Melanie Buschner, Gabriel Schweiger, Lilit Konstantinidou, Lemonia Makowski, Marcus Nagarajah, James Navab, Nassir Weber, Wolfgang Wendler, Thomas PLoS One Research Article Thyroid volumetry is crucial in the diagnosis, treatment, and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural network regarding inter- and intraobserver variability, time, and accuracy. Volume reference was MRI. 28 healthy volunteers (24—50 a) were scanned with 2D and 3D ultrasound (and by MRI) by three physicians (MD 1, 2, 3) with different experience levels (6, 4, and 1 a). In the 2D scans, the thyroid lobe volumes were calculated with the ellipsoid formula. A convolutional deep neural network (CNN) automatically segmented the 3D thyroid lobes. 26, 6, and 6 random lobe scans were used for training, validation, and testing, respectively. On MRI (T1 VIBE sequence) the thyroid was manually segmented by an experienced MD. MRI thyroid volumes ranged from 2.8 to 16.7ml (mean 7.4, SD 3.05). The CNN was trained to obtain an average Dice score of 0.94. The interobserver variability comparing two MDs showed mean differences for 2D and 3D respectively of 0.58 to 0.52ml (MD1 vs. 2), −1.33 to −0.17ml (MD1 vs. 3) and −1.89 to −0.70ml (MD2 vs. 3). Paired samples t-tests showed significant differences for 2D (p = .140, p = .002 and p = .002) and none for 3D (p = .176, p = .722 and p = .057). Intraobsever variability was similar for 2D and 3D ultrasound. Comparison of ultrasound volumes and MRI volumes showed a significant difference for the 2D volumetry of all MDs (p = .002, p = .009, p <.001), and no significant difference for 3D ultrasound (p = .292, p = .686, p = 0.091). Acquisition time was significantly shorter for 3D ultrasound. Tracked 3D ultrasound combined with a CNN segmentation significantly reduces interobserver variability in thyroid volumetry and increases the accuracy of the measurements with shorter acquisition times. Public Library of Science 2022-07-29 /pmc/articles/PMC9337648/ /pubmed/35905038 http://dx.doi.org/10.1371/journal.pone.0268550 Text en © 2022 Krönke et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Krönke, Markus
Eilers, Christine
Dimova, Desislava
Köhler, Melanie
Buschner, Gabriel
Schweiger, Lilit
Konstantinidou, Lemonia
Makowski, Marcus
Nagarajah, James
Navab, Nassir
Weber, Wolfgang
Wendler, Thomas
Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title_full Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title_fullStr Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title_full_unstemmed Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title_short Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
title_sort tracked 3d ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9337648/
https://www.ncbi.nlm.nih.gov/pubmed/35905038
http://dx.doi.org/10.1371/journal.pone.0268550
work_keys_str_mv AT kronkemarkus tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT eilerschristine tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT dimovadesislava tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT kohlermelanie tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT buschnergabriel tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT schweigerlilit tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT konstantinidoulemonia tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT makowskimarcus tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT nagarajahjames tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT navabnassir tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT weberwolfgang tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry
AT wendlerthomas tracked3dultrasoundanddeepneuralnetworkbasedthyroidsegmentationreduceinterobservervariabilityinthyroidvolumetry