A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants

Mohamed Salah Khlif, Natalia Egorova, Emilio Werden, Alberto Redolfi, Marina Bocardi, Charles DeCarli, Evan Fletcher, Baljeet Singh, Qi Li, Laura Bird, Amy Brodtmann

Research output: Contribution to journalArticle

Abstract

Manual quantification of the hippocampal atrophy state and rate is time consuming and prone to poor reproducibility, even when performed by neuroanatomical experts. The automation of hippocampal segmentation has been investigated in normal aging, epilepsy, and in Alzheimer's disease. Our first goal was to compare manual and automated hippocampal segmentation in ischemic stroke and to, secondly, study the impact of stroke lesion presence on hippocampal volume estimation. We used eight automated methods to segment T1-weighted MR images from 105 ischemic stroke patients and 39 age-matched controls sampled from the Cognition And Neocortical Volume After Stroke (CANVAS) study. The methods were: AdaBoost, Atlas-based Hippocampal Segmentation (ABHS) from the IDeALab, Computational Anatomy Toolbox (CAT) using 3 atlas variants (Hammers, LPBA40 and Neuromorphometics), FIRST, FreeSurfer v5.3, and FreeSurfer v6.0-Subfields. A number of these methods were employed to re-segment the T1 images for the stroke group after the stroke lesions were masked (i.e., removed). The automated methods were assessed on eight measures: process yield (i.e. segmentation success rate), correlation (Pearson's R and Shrout's ICC), concordance (Lin's RC and Kandall's W), slope ‘a’ of best-fit line from correlation plots, percentage of outliers from Bland-Altman plots, and significance of control−stroke difference. We eliminated the redundant measures after analysing between-measure correlations using Spearman's rank correlation. We ranked the automated methods based on the sum of the remaining non-redundant measures where each measure ranged between 0 and 1. Subfields attained an overall score of 96.3%, followed by AdaBoost (95.0%) and FIRST (94.7%). CAT using the LPBA40 atlas inflated hippocampal volumes the most, while the Hammers atlas returned the smallest volumes overall. FIRST (p = 0.014), FreeSurfer v5.3 (p = 0.007), manual tracing (p = 0.049), and CAT using the Neuromorphometics atlas (p = 0.017) all showed a significantly reduced hippocampal volume mean for the stroke group compared to control at three months. Moreover, masking of the stroke lesions prior to segmentation resulted in hippocampal volumes which agreed less with manual tracing. These findings recommend an automated segmentation without lesion masking as a more reliable procedure for the estimation of hippocampal volume in ischemic stroke.

LanguageEnglish (US)
Article number101581
JournalNeuroImage: Clinical
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Healthy Volunteers
Stroke
Atlases
Anatomy
Stroke Volume
Process Assessment (Health Care)
Automation
Cognition
Atrophy
Epilepsy
Alzheimer Disease

Keywords

  • Automatic segmentation
  • Hippocampus
  • Magnetic resonance imaging
  • Manual segmentation
  • Stroke

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology
  • Cognitive Neuroscience

Cite this

A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants. / Khlif, Mohamed Salah; Egorova, Natalia; Werden, Emilio; Redolfi, Alberto; Bocardi, Marina; DeCarli, Charles; Fletcher, Evan; Singh, Baljeet; Li, Qi; Bird, Laura; Brodtmann, Amy.

In: NeuroImage: Clinical, 01.01.2019.

Research output: Contribution to journalArticle

Khlif, Mohamed Salah ; Egorova, Natalia ; Werden, Emilio ; Redolfi, Alberto ; Bocardi, Marina ; DeCarli, Charles ; Fletcher, Evan ; Singh, Baljeet ; Li, Qi ; Bird, Laura ; Brodtmann, Amy. / A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants. In: NeuroImage: Clinical. 2019.
@article{a5c7fe10c84141a98e71da55825d1eb8,
title = "A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants",
abstract = "Manual quantification of the hippocampal atrophy state and rate is time consuming and prone to poor reproducibility, even when performed by neuroanatomical experts. The automation of hippocampal segmentation has been investigated in normal aging, epilepsy, and in Alzheimer's disease. Our first goal was to compare manual and automated hippocampal segmentation in ischemic stroke and to, secondly, study the impact of stroke lesion presence on hippocampal volume estimation. We used eight automated methods to segment T1-weighted MR images from 105 ischemic stroke patients and 39 age-matched controls sampled from the Cognition And Neocortical Volume After Stroke (CANVAS) study. The methods were: AdaBoost, Atlas-based Hippocampal Segmentation (ABHS) from the IDeALab, Computational Anatomy Toolbox (CAT) using 3 atlas variants (Hammers, LPBA40 and Neuromorphometics), FIRST, FreeSurfer v5.3, and FreeSurfer v6.0-Subfields. A number of these methods were employed to re-segment the T1 images for the stroke group after the stroke lesions were masked (i.e., removed). The automated methods were assessed on eight measures: process yield (i.e. segmentation success rate), correlation (Pearson's R and Shrout's ICC), concordance (Lin's RC and Kandall's W), slope ‘a’ of best-fit line from correlation plots, percentage of outliers from Bland-Altman plots, and significance of control−stroke difference. We eliminated the redundant measures after analysing between-measure correlations using Spearman's rank correlation. We ranked the automated methods based on the sum of the remaining non-redundant measures where each measure ranged between 0 and 1. Subfields attained an overall score of 96.3{\%}, followed by AdaBoost (95.0{\%}) and FIRST (94.7{\%}). CAT using the LPBA40 atlas inflated hippocampal volumes the most, while the Hammers atlas returned the smallest volumes overall. FIRST (p = 0.014), FreeSurfer v5.3 (p = 0.007), manual tracing (p = 0.049), and CAT using the Neuromorphometics atlas (p = 0.017) all showed a significantly reduced hippocampal volume mean for the stroke group compared to control at three months. Moreover, masking of the stroke lesions prior to segmentation resulted in hippocampal volumes which agreed less with manual tracing. These findings recommend an automated segmentation without lesion masking as a more reliable procedure for the estimation of hippocampal volume in ischemic stroke.",
keywords = "Automatic segmentation, Hippocampus, Magnetic resonance imaging, Manual segmentation, Stroke",
author = "Khlif, {Mohamed Salah} and Natalia Egorova and Emilio Werden and Alberto Redolfi and Marina Bocardi and Charles DeCarli and Evan Fletcher and Baljeet Singh and Qi Li and Laura Bird and Amy Brodtmann",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.nicl.2018.10.019",
language = "English (US)",
journal = "NeuroImage: Clinical",
issn = "2213-1582",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants

AU - Khlif, Mohamed Salah

AU - Egorova, Natalia

AU - Werden, Emilio

AU - Redolfi, Alberto

AU - Bocardi, Marina

AU - DeCarli, Charles

AU - Fletcher, Evan

AU - Singh, Baljeet

AU - Li, Qi

AU - Bird, Laura

AU - Brodtmann, Amy

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Manual quantification of the hippocampal atrophy state and rate is time consuming and prone to poor reproducibility, even when performed by neuroanatomical experts. The automation of hippocampal segmentation has been investigated in normal aging, epilepsy, and in Alzheimer's disease. Our first goal was to compare manual and automated hippocampal segmentation in ischemic stroke and to, secondly, study the impact of stroke lesion presence on hippocampal volume estimation. We used eight automated methods to segment T1-weighted MR images from 105 ischemic stroke patients and 39 age-matched controls sampled from the Cognition And Neocortical Volume After Stroke (CANVAS) study. The methods were: AdaBoost, Atlas-based Hippocampal Segmentation (ABHS) from the IDeALab, Computational Anatomy Toolbox (CAT) using 3 atlas variants (Hammers, LPBA40 and Neuromorphometics), FIRST, FreeSurfer v5.3, and FreeSurfer v6.0-Subfields. A number of these methods were employed to re-segment the T1 images for the stroke group after the stroke lesions were masked (i.e., removed). The automated methods were assessed on eight measures: process yield (i.e. segmentation success rate), correlation (Pearson's R and Shrout's ICC), concordance (Lin's RC and Kandall's W), slope ‘a’ of best-fit line from correlation plots, percentage of outliers from Bland-Altman plots, and significance of control−stroke difference. We eliminated the redundant measures after analysing between-measure correlations using Spearman's rank correlation. We ranked the automated methods based on the sum of the remaining non-redundant measures where each measure ranged between 0 and 1. Subfields attained an overall score of 96.3%, followed by AdaBoost (95.0%) and FIRST (94.7%). CAT using the LPBA40 atlas inflated hippocampal volumes the most, while the Hammers atlas returned the smallest volumes overall. FIRST (p = 0.014), FreeSurfer v5.3 (p = 0.007), manual tracing (p = 0.049), and CAT using the Neuromorphometics atlas (p = 0.017) all showed a significantly reduced hippocampal volume mean for the stroke group compared to control at three months. Moreover, masking of the stroke lesions prior to segmentation resulted in hippocampal volumes which agreed less with manual tracing. These findings recommend an automated segmentation without lesion masking as a more reliable procedure for the estimation of hippocampal volume in ischemic stroke.

AB - Manual quantification of the hippocampal atrophy state and rate is time consuming and prone to poor reproducibility, even when performed by neuroanatomical experts. The automation of hippocampal segmentation has been investigated in normal aging, epilepsy, and in Alzheimer's disease. Our first goal was to compare manual and automated hippocampal segmentation in ischemic stroke and to, secondly, study the impact of stroke lesion presence on hippocampal volume estimation. We used eight automated methods to segment T1-weighted MR images from 105 ischemic stroke patients and 39 age-matched controls sampled from the Cognition And Neocortical Volume After Stroke (CANVAS) study. The methods were: AdaBoost, Atlas-based Hippocampal Segmentation (ABHS) from the IDeALab, Computational Anatomy Toolbox (CAT) using 3 atlas variants (Hammers, LPBA40 and Neuromorphometics), FIRST, FreeSurfer v5.3, and FreeSurfer v6.0-Subfields. A number of these methods were employed to re-segment the T1 images for the stroke group after the stroke lesions were masked (i.e., removed). The automated methods were assessed on eight measures: process yield (i.e. segmentation success rate), correlation (Pearson's R and Shrout's ICC), concordance (Lin's RC and Kandall's W), slope ‘a’ of best-fit line from correlation plots, percentage of outliers from Bland-Altman plots, and significance of control−stroke difference. We eliminated the redundant measures after analysing between-measure correlations using Spearman's rank correlation. We ranked the automated methods based on the sum of the remaining non-redundant measures where each measure ranged between 0 and 1. Subfields attained an overall score of 96.3%, followed by AdaBoost (95.0%) and FIRST (94.7%). CAT using the LPBA40 atlas inflated hippocampal volumes the most, while the Hammers atlas returned the smallest volumes overall. FIRST (p = 0.014), FreeSurfer v5.3 (p = 0.007), manual tracing (p = 0.049), and CAT using the Neuromorphometics atlas (p = 0.017) all showed a significantly reduced hippocampal volume mean for the stroke group compared to control at three months. Moreover, masking of the stroke lesions prior to segmentation resulted in hippocampal volumes which agreed less with manual tracing. These findings recommend an automated segmentation without lesion masking as a more reliable procedure for the estimation of hippocampal volume in ischemic stroke.

KW - Automatic segmentation

KW - Hippocampus

KW - Magnetic resonance imaging

KW - Manual segmentation

KW - Stroke

UR - http://www.scopus.com/inward/record.url?scp=85059239456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059239456&partnerID=8YFLogxK

U2 - 10.1016/j.nicl.2018.10.019

DO - 10.1016/j.nicl.2018.10.019

M3 - Article

JO - NeuroImage: Clinical

T2 - NeuroImage: Clinical

JF - NeuroImage: Clinical

SN - 2213-1582

M1 - 101581

ER -