Cargando…

Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration

Convolutional neural networks (CNNs) have recently led to significant advances in automatic segmentations of anatomical structures in medical images, and a wide variety of network architectures are now available to the research community. For applications such as segmentation of the prostate in magn...

Descripción completa

Detalles Bibliográficos
Autores principales: Ghavami, Nooshin, Hu, Yipeng, Gibson, Eli, Bonmati, Ester, Emberton, Mark, Moore, Caroline M., Barratt, Dean C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7985677/
https://www.ncbi.nlm.nih.gov/pubmed/31526965
http://dx.doi.org/10.1016/j.media.2019.101558
_version_ 1783668297310404608
author Ghavami, Nooshin
Hu, Yipeng
Gibson, Eli
Bonmati, Ester
Emberton, Mark
Moore, Caroline M.
Barratt, Dean C.
author_facet Ghavami, Nooshin
Hu, Yipeng
Gibson, Eli
Bonmati, Ester
Emberton, Mark
Moore, Caroline M.
Barratt, Dean C.
author_sort Ghavami, Nooshin
collection PubMed
description Convolutional neural networks (CNNs) have recently led to significant advances in automatic segmentations of anatomical structures in medical images, and a wide variety of network architectures are now available to the research community. For applications such as segmentation of the prostate in magnetic resonance images (MRI), the results of the PROMISE12 online algorithm evaluation platform have demonstrated differences between the best-performing segmentation algorithms in terms of numerical accuracy using standard metrics such as the Dice score and boundary distance. These small differences in the segmented regions/boundaries outputted by different algorithms may potentially have an unsubstantial impact on the results of downstream image analysis tasks, such as estimating organ volume and multimodal image registration, which inform clinical decisions. This impact has not been previously investigated. In this work, we quantified the accuracy of six different CNNs in segmenting the prostate in 3D patient T2-weighted MRI scans and compared the accuracy of organ volume estimation and MRI-ultrasound (US) registration errors using the prostate segmentations produced by different networks. Networks were trained and tested using a set of 232 patient MRIs with labels provided by experienced clinicians. A statistically significant difference was found among the Dice scores and boundary distances produced by these networks in a non-parametric analysis of variance (p < 0.001 and p < 0.001, respectively), where the following multiple comparison tests revealed that the statistically significant difference in segmentation errors were caused by at least one tested network. Gland volume errors (GVEs) and target registration errors (TREs) were then estimated using the CNN-generated segmentations. Interestingly, there was no statistical difference found in either GVEs or TREs among different networks, (p = 0.34 and p = 0.26, respectively). This result provides a real-world example that these networks with different segmentation performances may potentially provide indistinguishably adequate registration accuracies to assist prostate cancer imaging applications. We conclude by recommending that the differences in the accuracy of downstream image analysis tasks that make use of data output by automatic segmentation methods, such as CNNs, within a clinical pipeline should be taken into account when selecting between different network architectures, in addition to reporting the segmentation accuracy.
format Online
Article
Text
id pubmed-7985677
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-79856772021-03-24 Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration Ghavami, Nooshin Hu, Yipeng Gibson, Eli Bonmati, Ester Emberton, Mark Moore, Caroline M. Barratt, Dean C. Med Image Anal Article Convolutional neural networks (CNNs) have recently led to significant advances in automatic segmentations of anatomical structures in medical images, and a wide variety of network architectures are now available to the research community. For applications such as segmentation of the prostate in magnetic resonance images (MRI), the results of the PROMISE12 online algorithm evaluation platform have demonstrated differences between the best-performing segmentation algorithms in terms of numerical accuracy using standard metrics such as the Dice score and boundary distance. These small differences in the segmented regions/boundaries outputted by different algorithms may potentially have an unsubstantial impact on the results of downstream image analysis tasks, such as estimating organ volume and multimodal image registration, which inform clinical decisions. This impact has not been previously investigated. In this work, we quantified the accuracy of six different CNNs in segmenting the prostate in 3D patient T2-weighted MRI scans and compared the accuracy of organ volume estimation and MRI-ultrasound (US) registration errors using the prostate segmentations produced by different networks. Networks were trained and tested using a set of 232 patient MRIs with labels provided by experienced clinicians. A statistically significant difference was found among the Dice scores and boundary distances produced by these networks in a non-parametric analysis of variance (p < 0.001 and p < 0.001, respectively), where the following multiple comparison tests revealed that the statistically significant difference in segmentation errors were caused by at least one tested network. Gland volume errors (GVEs) and target registration errors (TREs) were then estimated using the CNN-generated segmentations. Interestingly, there was no statistical difference found in either GVEs or TREs among different networks, (p = 0.34 and p = 0.26, respectively). This result provides a real-world example that these networks with different segmentation performances may potentially provide indistinguishably adequate registration accuracies to assist prostate cancer imaging applications. We conclude by recommending that the differences in the accuracy of downstream image analysis tasks that make use of data output by automatic segmentation methods, such as CNNs, within a clinical pipeline should be taken into account when selecting between different network architectures, in addition to reporting the segmentation accuracy. Elsevier 2019-12 /pmc/articles/PMC7985677/ /pubmed/31526965 http://dx.doi.org/10.1016/j.media.2019.101558 Text en © 2019 The Authors. Published by Elsevier B.V. http://creativecommons.org/licenses/by/4.0/ This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ghavami, Nooshin
Hu, Yipeng
Gibson, Eli
Bonmati, Ester
Emberton, Mark
Moore, Caroline M.
Barratt, Dean C.
Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title_full Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title_fullStr Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title_full_unstemmed Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title_short Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
title_sort automatic segmentation of prostate mri using convolutional neural networks: investigating the impact of network architecture on the accuracy of volume measurement and mri-ultrasound registration
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7985677/
https://www.ncbi.nlm.nih.gov/pubmed/31526965
http://dx.doi.org/10.1016/j.media.2019.101558
work_keys_str_mv AT ghavaminooshin automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT huyipeng automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT gibsoneli automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT bonmatiester automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT embertonmark automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT moorecarolinem automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration
AT barrattdeanc automaticsegmentationofprostatemriusingconvolutionalneuralnetworksinvestigatingtheimpactofnetworkarchitectureontheaccuracyofvolumemeasurementandmriultrasoundregistration