Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol
Hippocampus atrophy is an early structural feature that can be measured from magnetic resonance imaging (MRI) to improve the diagnosis of neurological diseases. An accurate and robust standardized hippocampus segmentation method is required for reliable atrophy assessment. The aim of this work was t...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/7/2427 |
id |
doaj-426267791f1c49a7afaf8b264f5f8365 |
---|---|
record_format |
Article |
spelling |
doaj-426267791f1c49a7afaf8b264f5f83652021-04-01T23:05:00ZengMDPI AGSensors1424-82202021-04-01212427242710.3390/s21072427Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized ProtocolSamaneh Nobakht0Morgan Schaeffer1Nils D. Forkert2Sean Nestor3Sandra E. Black4Philip Barber5the Alzheimer’s Disease Neuroimaging InitiativeMedical Sciences Graduate Program, University of Calgary, Calgary, AB T2N 1N4, CanadaDepartment of Clinical Neurosciences, University of Calgary, Calgary, AB T2N 1N4, CanadaDepartment of Clinical Neurosciences, University of Calgary, Calgary, AB T2N 1N4, CanadaDepartment of Psychiatry, University of Toronto, Toronto, ON M5S, CanadaDepartment of Psychiatry, University of Toronto, Toronto, ON M5S, CanadaDepartment of Clinical Neurosciences, University of Calgary, Calgary, AB T2N 1N4, CanadaHippocampus atrophy is an early structural feature that can be measured from magnetic resonance imaging (MRI) to improve the diagnosis of neurological diseases. An accurate and robust standardized hippocampus segmentation method is required for reliable atrophy assessment. The aim of this work was to develop and evaluate an automatic segmentation tool (DeepHarp) for hippocampus delineation according to the ADNI harmonized hippocampal protocol (HarP). DeepHarp utilizes a two-step process. First, the approximate location of the hippocampus is identified in T1-weighted MRI datasets using an atlas-based approach, which is used to crop the images to a region-of-interest (ROI) containing the hippocampus. In the second step, a convolutional neural network trained using datasets with corresponding manual hippocampus annotations is used to segment the hippocampus from the cropped ROI. The proposed method was developed and validated using 107 datasets with manually segmented hippocampi according to the ADNI-HarP standard as well as 114 multi-center datasets of patients with Alzheimer’s disease, mild cognitive impairment, cerebrovascular disease, and healthy controls. Twenty-three independent datasets manually segmented according to the ADNI-HarP protocol were used for testing to assess the accuracy, while an independent test-retest dataset was used to assess precision. The proposed DeepHarp method achieved a mean Dice similarity score of 0.88, which was significantly better than four other established hippocampus segmentation methods used for comparison. At the same time, the proposed method also achieved a high test-retest precision (mean Dice score: 0.95). In conclusion, DeepHarp can automatically segment the hippocampus from T1-weighted MRI datasets according to the ADNI-HarP protocol with high accuracy and robustness, which can aid atrophy measurements in a variety of pathologies.https://www.mdpi.com/1424-8220/21/7/2427magnetic resonance imaginghippocampussegmentationconvolutional neural networkADNI harmonized hippocampal protocol |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Samaneh Nobakht Morgan Schaeffer Nils D. Forkert Sean Nestor Sandra E. Black Philip Barber the Alzheimer’s Disease Neuroimaging Initiative |
spellingShingle |
Samaneh Nobakht Morgan Schaeffer Nils D. Forkert Sean Nestor Sandra E. Black Philip Barber the Alzheimer’s Disease Neuroimaging Initiative Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol Sensors magnetic resonance imaging hippocampus segmentation convolutional neural network ADNI harmonized hippocampal protocol |
author_facet |
Samaneh Nobakht Morgan Schaeffer Nils D. Forkert Sean Nestor Sandra E. Black Philip Barber the Alzheimer’s Disease Neuroimaging Initiative |
author_sort |
Samaneh Nobakht |
title |
Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol |
title_short |
Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol |
title_full |
Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol |
title_fullStr |
Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol |
title_full_unstemmed |
Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol |
title_sort |
combined atlas and convolutional neural network-based segmentation of the hippocampus from mri according to the adni harmonized protocol |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-04-01 |
description |
Hippocampus atrophy is an early structural feature that can be measured from magnetic resonance imaging (MRI) to improve the diagnosis of neurological diseases. An accurate and robust standardized hippocampus segmentation method is required for reliable atrophy assessment. The aim of this work was to develop and evaluate an automatic segmentation tool (DeepHarp) for hippocampus delineation according to the ADNI harmonized hippocampal protocol (HarP). DeepHarp utilizes a two-step process. First, the approximate location of the hippocampus is identified in T1-weighted MRI datasets using an atlas-based approach, which is used to crop the images to a region-of-interest (ROI) containing the hippocampus. In the second step, a convolutional neural network trained using datasets with corresponding manual hippocampus annotations is used to segment the hippocampus from the cropped ROI. The proposed method was developed and validated using 107 datasets with manually segmented hippocampi according to the ADNI-HarP standard as well as 114 multi-center datasets of patients with Alzheimer’s disease, mild cognitive impairment, cerebrovascular disease, and healthy controls. Twenty-three independent datasets manually segmented according to the ADNI-HarP protocol were used for testing to assess the accuracy, while an independent test-retest dataset was used to assess precision. The proposed DeepHarp method achieved a mean Dice similarity score of 0.88, which was significantly better than four other established hippocampus segmentation methods used for comparison. At the same time, the proposed method also achieved a high test-retest precision (mean Dice score: 0.95). In conclusion, DeepHarp can automatically segment the hippocampus from T1-weighted MRI datasets according to the ADNI-HarP protocol with high accuracy and robustness, which can aid atrophy measurements in a variety of pathologies. |
topic |
magnetic resonance imaging hippocampus segmentation convolutional neural network ADNI harmonized hippocampal protocol |
url |
https://www.mdpi.com/1424-8220/21/7/2427 |
work_keys_str_mv |
AT samanehnobakht combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT morganschaeffer combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT nilsdforkert combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT seannestor combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT sandraeblack combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT philipbarber combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol AT thealzheimersdiseaseneuroimaginginitiative combinedatlasandconvolutionalneuralnetworkbasedsegmentationofthehippocampusfrommriaccordingtotheadniharmonizedprotocol |
_version_ |
1724175655273234432 |