Cargando…
Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury
Registration-based methods are commonly used in the automatic segmentation of magnetic resonance (MR) brain images. However, these methods are not robust to the presence of gross pathologies that can alter the brain anatomy and affect the alignment of the atlas image with the target image. In this w...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8891699/ https://www.ncbi.nlm.nih.gov/pubmed/35250823 http://dx.doi.org/10.3389/fneur.2022.820267 |
_version_ | 1784661953022525440 |
---|---|
author | De Feo, Riccardo Hämäläinen, Elina Manninen, Eppu Immonen, Riikka Valverde, Juan Miguel Ndode-Ekane, Xavier Ekolle Gröhn, Olli Pitkänen, Asla Tohka, Jussi |
author_facet | De Feo, Riccardo Hämäläinen, Elina Manninen, Eppu Immonen, Riikka Valverde, Juan Miguel Ndode-Ekane, Xavier Ekolle Gröhn, Olli Pitkänen, Asla Tohka, Jussi |
author_sort | De Feo, Riccardo |
collection | PubMed |
description | Registration-based methods are commonly used in the automatic segmentation of magnetic resonance (MR) brain images. However, these methods are not robust to the presence of gross pathologies that can alter the brain anatomy and affect the alignment of the atlas image with the target image. In this work, we develop a robust algorithm, MU-Net-R, for automatic segmentation of the normal and injured rat hippocampus based on an ensemble of U-net-like Convolutional Neural Networks (CNNs). MU-Net-R was trained on manually segmented MR images of sham-operated rats and rats with traumatic brain injury (TBI) by lateral fluid percussion. The performance of MU-Net-R was quantitatively compared with methods based on single and multi-atlas registration using MR images from two large preclinical cohorts. Automatic segmentations using MU-Net-R and multi-atlas registration were of excellent quality, achieving cross-validated Dice scores above 0.90 despite the presence of brain lesions, atrophy, and ventricular enlargement. In contrast, the performance of single-atlas segmentation was unsatisfactory (cross-validated Dice scores below 0.85). Interestingly, the registration-based methods were better at segmenting the contralateral than the ipsilateral hippocampus, whereas MU-Net-R segmented the contralateral and ipsilateral hippocampus equally well. We assessed the progression of hippocampal damage after TBI by using our automatic segmentation tool. Our data show that the presence of TBI, time after TBI, and whether the hippocampus was ipsilateral or contralateral to the injury were the parameters that explained hippocampal volume. |
format | Online Article Text |
id | pubmed-8891699 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-88916992022-03-04 Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury De Feo, Riccardo Hämäläinen, Elina Manninen, Eppu Immonen, Riikka Valverde, Juan Miguel Ndode-Ekane, Xavier Ekolle Gröhn, Olli Pitkänen, Asla Tohka, Jussi Front Neurol Neurology Registration-based methods are commonly used in the automatic segmentation of magnetic resonance (MR) brain images. However, these methods are not robust to the presence of gross pathologies that can alter the brain anatomy and affect the alignment of the atlas image with the target image. In this work, we develop a robust algorithm, MU-Net-R, for automatic segmentation of the normal and injured rat hippocampus based on an ensemble of U-net-like Convolutional Neural Networks (CNNs). MU-Net-R was trained on manually segmented MR images of sham-operated rats and rats with traumatic brain injury (TBI) by lateral fluid percussion. The performance of MU-Net-R was quantitatively compared with methods based on single and multi-atlas registration using MR images from two large preclinical cohorts. Automatic segmentations using MU-Net-R and multi-atlas registration were of excellent quality, achieving cross-validated Dice scores above 0.90 despite the presence of brain lesions, atrophy, and ventricular enlargement. In contrast, the performance of single-atlas segmentation was unsatisfactory (cross-validated Dice scores below 0.85). Interestingly, the registration-based methods were better at segmenting the contralateral than the ipsilateral hippocampus, whereas MU-Net-R segmented the contralateral and ipsilateral hippocampus equally well. We assessed the progression of hippocampal damage after TBI by using our automatic segmentation tool. Our data show that the presence of TBI, time after TBI, and whether the hippocampus was ipsilateral or contralateral to the injury were the parameters that explained hippocampal volume. Frontiers Media S.A. 2022-02-17 /pmc/articles/PMC8891699/ /pubmed/35250823 http://dx.doi.org/10.3389/fneur.2022.820267 Text en Copyright © 2022 De Feo, Hämäläinen, Manninen, Immonen, Valverde, Ndode-Ekane, Gröhn, Pitkänen and Tohka. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neurology De Feo, Riccardo Hämäläinen, Elina Manninen, Eppu Immonen, Riikka Valverde, Juan Miguel Ndode-Ekane, Xavier Ekolle Gröhn, Olli Pitkänen, Asla Tohka, Jussi Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title | Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title_full | Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title_fullStr | Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title_full_unstemmed | Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title_short | Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury |
title_sort | convolutional neural networks enable robust automatic segmentation of the rat hippocampus in mri after traumatic brain injury |
topic | Neurology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8891699/ https://www.ncbi.nlm.nih.gov/pubmed/35250823 http://dx.doi.org/10.3389/fneur.2022.820267 |
work_keys_str_mv | AT defeoriccardo convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT hamalainenelina convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT mannineneppu convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT immonenriikka convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT valverdejuanmiguel convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT ndodeekanexavierekolle convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT grohnolli convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT pitkanenasla convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury AT tohkajussi convolutionalneuralnetworksenablerobustautomaticsegmentationoftherathippocampusinmriaftertraumaticbraininjury |