Cargando…
Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction
Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-wei...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Grapho Publications, LLC
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6752289/ https://www.ncbi.nlm.nih.gov/pubmed/31572790 http://dx.doi.org/10.18383/j.tom.2019.00010 |
_version_ | 1783452756891140096 |
---|---|
author | Bielak, Lars Wiedenmann, Nicole Nicolay, Nils Henrik Lottner, Thomas Fischer, Johannes Bunea, Hatice Grosu, Anca-Ligia Bock, Michael |
author_facet | Bielak, Lars Wiedenmann, Nicole Nicolay, Nils Henrik Lottner, Thomas Fischer, Johannes Bunea, Hatice Grosu, Anca-Ligia Bock, Michael |
author_sort | Bielak, Lars |
collection | PubMed |
description | Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-weighted data using data of patients with head and neck tumors; 18 patients with head and neck tumors underwent multiparametric magnetic resonance imaging, including T2w, T1w, T2*, perfusion (k(trans)), and apparent diffusion coefficient (ADC) measurements. Owing to strong geometrical distortions in diffusion-weighted echo planar imaging in the head and neck region, ADC data were additionally distortion corrected. To investigate the influence of geometrical correction, first 14 CNNs were trained on data with geometrically corrected ADC and another 14 CNNs were trained using data without the correction on different samples of 13 patients for training and 4 patients for validation each. The different sets were each trained from scratch using randomly initialized weights, but the training data distributions were pairwise equal for corrected and uncorrected data. Segmentation performance was evaluated on the remaining 1 test-patient for each of the 14 sets. The CNN segmentation performance scored an average Dice coefficient of 0.40 ± 0.18 for data including distortion-corrected ADC and 0.37 ± 0.21 for uncorrected data. Paired t test revealed that the performance was not significantly different (P = .313). Thus, geometrical distortion on diffusion-weighted imaging data in patients with head and neck tumor does not significantly impair CNN segmentation performance in use. |
format | Online Article Text |
id | pubmed-6752289 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Grapho Publications, LLC |
record_format | MEDLINE/PubMed |
spelling | pubmed-67522892019-09-30 Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction Bielak, Lars Wiedenmann, Nicole Nicolay, Nils Henrik Lottner, Thomas Fischer, Johannes Bunea, Hatice Grosu, Anca-Ligia Bock, Michael Tomography Research Articles Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-weighted data using data of patients with head and neck tumors; 18 patients with head and neck tumors underwent multiparametric magnetic resonance imaging, including T2w, T1w, T2*, perfusion (k(trans)), and apparent diffusion coefficient (ADC) measurements. Owing to strong geometrical distortions in diffusion-weighted echo planar imaging in the head and neck region, ADC data were additionally distortion corrected. To investigate the influence of geometrical correction, first 14 CNNs were trained on data with geometrically corrected ADC and another 14 CNNs were trained using data without the correction on different samples of 13 patients for training and 4 patients for validation each. The different sets were each trained from scratch using randomly initialized weights, but the training data distributions were pairwise equal for corrected and uncorrected data. Segmentation performance was evaluated on the remaining 1 test-patient for each of the 14 sets. The CNN segmentation performance scored an average Dice coefficient of 0.40 ± 0.18 for data including distortion-corrected ADC and 0.37 ± 0.21 for uncorrected data. Paired t test revealed that the performance was not significantly different (P = .313). Thus, geometrical distortion on diffusion-weighted imaging data in patients with head and neck tumor does not significantly impair CNN segmentation performance in use. Grapho Publications, LLC 2019-09 /pmc/articles/PMC6752289/ /pubmed/31572790 http://dx.doi.org/10.18383/j.tom.2019.00010 Text en © 2019 The Authors. Published by Grapho Publications, LLC http://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 | Research Articles Bielak, Lars Wiedenmann, Nicole Nicolay, Nils Henrik Lottner, Thomas Fischer, Johannes Bunea, Hatice Grosu, Anca-Ligia Bock, Michael Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title | Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title_full | Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title_fullStr | Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title_full_unstemmed | Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title_short | Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction |
title_sort | automatic tumor segmentation with a convolutional neural network in multiparametric mri: influence of distortion correction |
topic | Research Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6752289/ https://www.ncbi.nlm.nih.gov/pubmed/31572790 http://dx.doi.org/10.18383/j.tom.2019.00010 |
work_keys_str_mv | AT bielaklars automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT wiedenmannnicole automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT nicolaynilshenrik automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT lottnerthomas automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT fischerjohannes automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT buneahatice automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT grosuancaligia automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection AT bockmichael automatictumorsegmentationwithaconvolutionalneuralnetworkinmultiparametricmriinfluenceofdistortioncorrection |