Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis
Abstract Background Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels of a CNN with respect to the segmentation performance of head&ne...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-07-01
|
Series: | Radiation Oncology |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13014-020-01618-z |
id |
doaj-0bbef60024804f9997e3d3e1de751dd2 |
---|---|
record_format |
Article |
spelling |
doaj-0bbef60024804f9997e3d3e1de751dd22020-11-25T04:04:02ZengBMCRadiation Oncology1748-717X2020-07-011511910.1186/s13014-020-01618-zConvolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysisLars Bielak0Nicole Wiedenmann1Arnie Berlin2Nils Henrik Nicolay3Deepa Darshini Gunashekar4Leonard Hägele5Thomas Lottner6Anca-Ligia Grosu7Michael Bock8Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of FreiburgGerman Cancer Consortium (DKTK), Partner Site FreiburgMathWorks, IncGerman Cancer Consortium (DKTK), Partner Site FreiburgDepartment of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of FreiburgDepartment of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of FreiburgDepartment of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of FreiburgGerman Cancer Consortium (DKTK), Partner Site FreiburgDepartment of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of FreiburgAbstract Background Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels of a CNN with respect to the segmentation performance of head&neck cancer. Methods Head&neck cancer patients underwent multi-parametric MRI including T2w, pre- and post-contrast T1w, T2*, perfusion (ktrans, ve) and diffusion (ADC) measurements at 3 time points before and during radiochemotherapy. The 7 different MRI contrasts (input channels) and manually defined gross tumor volumes (primary tumor and lymph node metastases) were used to train CNNs for lesion segmentation. A reference CNN with all input channels was compared to individually trained CNNs where one of the input channels was left out to identify which MRI contrast contributes the most to the tumor segmentation task. A statistical analysis was employed to account for random fluctuations in the segmentation performance. Results The CNN segmentation performance scored up to a Dice similarity coefficient (DSC) of 0.65. The network trained without T2* data generally yielded the worst results, with ΔDSCGTV-T = 5.7% for primary tumor and ΔDSCGTV-Ln = 5.8% for lymph node metastases compared to the network containing all input channels. Overall, the ADC input channel showed the least impact on segmentation performance, with ΔDSCGTV-T = 2.4% for primary tumor and ΔDSCGTV-Ln = 2.2% respectively. Conclusions We developed a method to reduce overall scan times in MRI protocols by prioritizing those sequences that add most unique information for the task of automatic tumor segmentation. The optimized CNNs could be used to aid in the definition of the GTVs in radiotherapy planning, and the faster imaging protocols will reduce patient scan times which can increase patient compliance. Trial registration The trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under register number DRKS00003830 on August 20th, 2015.http://link.springer.com/article/10.1186/s13014-020-01618-zMulti-parametric MRIRadiation therapyAutomatic tumor segmentationConvolutional neuronal network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lars Bielak Nicole Wiedenmann Arnie Berlin Nils Henrik Nicolay Deepa Darshini Gunashekar Leonard Hägele Thomas Lottner Anca-Ligia Grosu Michael Bock |
spellingShingle |
Lars Bielak Nicole Wiedenmann Arnie Berlin Nils Henrik Nicolay Deepa Darshini Gunashekar Leonard Hägele Thomas Lottner Anca-Ligia Grosu Michael Bock Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis Radiation Oncology Multi-parametric MRI Radiation therapy Automatic tumor segmentation Convolutional neuronal network |
author_facet |
Lars Bielak Nicole Wiedenmann Arnie Berlin Nils Henrik Nicolay Deepa Darshini Gunashekar Leonard Hägele Thomas Lottner Anca-Ligia Grosu Michael Bock |
author_sort |
Lars Bielak |
title |
Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis |
title_short |
Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis |
title_full |
Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis |
title_fullStr |
Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis |
title_full_unstemmed |
Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis |
title_sort |
convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric mri: a leave-one-out analysis |
publisher |
BMC |
series |
Radiation Oncology |
issn |
1748-717X |
publishDate |
2020-07-01 |
description |
Abstract Background Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels of a CNN with respect to the segmentation performance of head&neck cancer. Methods Head&neck cancer patients underwent multi-parametric MRI including T2w, pre- and post-contrast T1w, T2*, perfusion (ktrans, ve) and diffusion (ADC) measurements at 3 time points before and during radiochemotherapy. The 7 different MRI contrasts (input channels) and manually defined gross tumor volumes (primary tumor and lymph node metastases) were used to train CNNs for lesion segmentation. A reference CNN with all input channels was compared to individually trained CNNs where one of the input channels was left out to identify which MRI contrast contributes the most to the tumor segmentation task. A statistical analysis was employed to account for random fluctuations in the segmentation performance. Results The CNN segmentation performance scored up to a Dice similarity coefficient (DSC) of 0.65. The network trained without T2* data generally yielded the worst results, with ΔDSCGTV-T = 5.7% for primary tumor and ΔDSCGTV-Ln = 5.8% for lymph node metastases compared to the network containing all input channels. Overall, the ADC input channel showed the least impact on segmentation performance, with ΔDSCGTV-T = 2.4% for primary tumor and ΔDSCGTV-Ln = 2.2% respectively. Conclusions We developed a method to reduce overall scan times in MRI protocols by prioritizing those sequences that add most unique information for the task of automatic tumor segmentation. The optimized CNNs could be used to aid in the definition of the GTVs in radiotherapy planning, and the faster imaging protocols will reduce patient scan times which can increase patient compliance. Trial registration The trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under register number DRKS00003830 on August 20th, 2015. |
topic |
Multi-parametric MRI Radiation therapy Automatic tumor segmentation Convolutional neuronal network |
url |
http://link.springer.com/article/10.1186/s13014-020-01618-z |
work_keys_str_mv |
AT larsbielak convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT nicolewiedenmann convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT arnieberlin convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT nilshenriknicolay convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT deepadarshinigunashekar convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT leonardhagele convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT thomaslottner convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT ancaligiagrosu convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis AT michaelbock convolutionalneuralnetworksforheadandnecktumorsegmentationon7channelmultiparametricmrialeaveoneoutanalysis |
_version_ |
1724437981213753344 |