Fast Segmentation through surface fairing (FastSURF): A novel semi-automatic hippocampus segmentation method

Fabian Bartel, Hugo Vrenken, Marcel van Herk, Michiel de Ruiter, Jose Belderbos, Joost Hulshof, Jan C. de Munck

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Objective The objective is to present a proof-of-concept of a semi-automatic method to reduce hippocampus segmentation time on magnetic resonance images (MRI). Materials and methods FAst Segmentation Through SURface Fairing (FASTSURF) is based on a surface fairing technique which reconstructs the hippocampus from sparse delineations. To validate FASTSURF, simulations were performed in which sparse delineations extracted from full manual segmentations served as input. On three different datasets with different diagnostic groups, FASTSURF hippocampi were compared to the original segmentations using Jaccard overlap indices and percentage volume differences (PVD). In one data set for which back-to-back scans were available, unbiased estimates of overlap and PVD were obtained. Using longitudinal scans, we compared hippocampal atrophy rates measured by manual, FASTSURF and two automatic segmentations (FreeSurfer and FSL-FIRST). Results With only seven input contours, FASTSURF yielded mean Jaccard indices ranging from 72 (±4.3)% to 83(±2.6)% and PVDs ranging from 0.02(±2.40)% to 3.2(±3.40)% across the three datasets. Slightly poorer results were obtained for the unbiased analysis, but the performance was still considerably better than both tested automatic methods with only five contours. Conclusions FASTSURF segmentations have high accuracy and require only a fraction of the delineation effort of fully manual segmentation. Atrophy rate quantification based on completely manual segmentation is well reproduced by FASTSURF. Therefore, FASTSURF is a promising tool to be implemented in clinical workflow, provided a future prospective validation confirms our findings.

Original languageEnglish
Article numbere0210641
Pages (from-to)1-26
Number of pages26
JournalPLoS ONE
Volume14
Issue number1
DOIs
Publication statusPublished - 18 Jan 2019

Fingerprint

hippocampus
Hippocampus
Atrophy
Workflow
Magnetic Resonance Spectroscopy
atrophy
methodology
Datasets
Physical vapor deposition
Magnetic resonance

Cite this

Bartel, Fabian ; Vrenken, Hugo ; van Herk, Marcel ; de Ruiter, Michiel ; Belderbos, Jose ; Hulshof, Joost ; de Munck, Jan C. / Fast Segmentation through surface fairing (FastSURF) : A novel semi-automatic hippocampus segmentation method. In: PLoS ONE. 2019 ; Vol. 14, No. 1. pp. 1-26.
@article{13ad051207a64cbf8a58250e61265df2,
title = "Fast Segmentation through surface fairing (FastSURF): A novel semi-automatic hippocampus segmentation method",
abstract = "Objective The objective is to present a proof-of-concept of a semi-automatic method to reduce hippocampus segmentation time on magnetic resonance images (MRI). Materials and methods FAst Segmentation Through SURface Fairing (FASTSURF) is based on a surface fairing technique which reconstructs the hippocampus from sparse delineations. To validate FASTSURF, simulations were performed in which sparse delineations extracted from full manual segmentations served as input. On three different datasets with different diagnostic groups, FASTSURF hippocampi were compared to the original segmentations using Jaccard overlap indices and percentage volume differences (PVD). In one data set for which back-to-back scans were available, unbiased estimates of overlap and PVD were obtained. Using longitudinal scans, we compared hippocampal atrophy rates measured by manual, FASTSURF and two automatic segmentations (FreeSurfer and FSL-FIRST). Results With only seven input contours, FASTSURF yielded mean Jaccard indices ranging from 72 (±4.3){\%} to 83(±2.6){\%} and PVDs ranging from 0.02(±2.40){\%} to 3.2(±3.40){\%} across the three datasets. Slightly poorer results were obtained for the unbiased analysis, but the performance was still considerably better than both tested automatic methods with only five contours. Conclusions FASTSURF segmentations have high accuracy and require only a fraction of the delineation effort of fully manual segmentation. Atrophy rate quantification based on completely manual segmentation is well reproduced by FASTSURF. Therefore, FASTSURF is a promising tool to be implemented in clinical workflow, provided a future prospective validation confirms our findings.",
author = "Fabian Bartel and Hugo Vrenken and {van Herk}, Marcel and {de Ruiter}, Michiel and Jose Belderbos and Joost Hulshof and {de Munck}, {Jan C.}",
year = "2019",
month = "1",
day = "18",
doi = "10.1371/journal.pone.0210641",
language = "English",
volume = "14",
pages = "1--26",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

Fast Segmentation through surface fairing (FastSURF) : A novel semi-automatic hippocampus segmentation method. / Bartel, Fabian; Vrenken, Hugo; van Herk, Marcel; de Ruiter, Michiel; Belderbos, Jose; Hulshof, Joost; de Munck, Jan C.

In: PLoS ONE, Vol. 14, No. 1, e0210641, 18.01.2019, p. 1-26.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Fast Segmentation through surface fairing (FastSURF)

T2 - A novel semi-automatic hippocampus segmentation method

AU - Bartel, Fabian

AU - Vrenken, Hugo

AU - van Herk, Marcel

AU - de Ruiter, Michiel

AU - Belderbos, Jose

AU - Hulshof, Joost

AU - de Munck, Jan C.

PY - 2019/1/18

Y1 - 2019/1/18

N2 - Objective The objective is to present a proof-of-concept of a semi-automatic method to reduce hippocampus segmentation time on magnetic resonance images (MRI). Materials and methods FAst Segmentation Through SURface Fairing (FASTSURF) is based on a surface fairing technique which reconstructs the hippocampus from sparse delineations. To validate FASTSURF, simulations were performed in which sparse delineations extracted from full manual segmentations served as input. On three different datasets with different diagnostic groups, FASTSURF hippocampi were compared to the original segmentations using Jaccard overlap indices and percentage volume differences (PVD). In one data set for which back-to-back scans were available, unbiased estimates of overlap and PVD were obtained. Using longitudinal scans, we compared hippocampal atrophy rates measured by manual, FASTSURF and two automatic segmentations (FreeSurfer and FSL-FIRST). Results With only seven input contours, FASTSURF yielded mean Jaccard indices ranging from 72 (±4.3)% to 83(±2.6)% and PVDs ranging from 0.02(±2.40)% to 3.2(±3.40)% across the three datasets. Slightly poorer results were obtained for the unbiased analysis, but the performance was still considerably better than both tested automatic methods with only five contours. Conclusions FASTSURF segmentations have high accuracy and require only a fraction of the delineation effort of fully manual segmentation. Atrophy rate quantification based on completely manual segmentation is well reproduced by FASTSURF. Therefore, FASTSURF is a promising tool to be implemented in clinical workflow, provided a future prospective validation confirms our findings.

AB - Objective The objective is to present a proof-of-concept of a semi-automatic method to reduce hippocampus segmentation time on magnetic resonance images (MRI). Materials and methods FAst Segmentation Through SURface Fairing (FASTSURF) is based on a surface fairing technique which reconstructs the hippocampus from sparse delineations. To validate FASTSURF, simulations were performed in which sparse delineations extracted from full manual segmentations served as input. On three different datasets with different diagnostic groups, FASTSURF hippocampi were compared to the original segmentations using Jaccard overlap indices and percentage volume differences (PVD). In one data set for which back-to-back scans were available, unbiased estimates of overlap and PVD were obtained. Using longitudinal scans, we compared hippocampal atrophy rates measured by manual, FASTSURF and two automatic segmentations (FreeSurfer and FSL-FIRST). Results With only seven input contours, FASTSURF yielded mean Jaccard indices ranging from 72 (±4.3)% to 83(±2.6)% and PVDs ranging from 0.02(±2.40)% to 3.2(±3.40)% across the three datasets. Slightly poorer results were obtained for the unbiased analysis, but the performance was still considerably better than both tested automatic methods with only five contours. Conclusions FASTSURF segmentations have high accuracy and require only a fraction of the delineation effort of fully manual segmentation. Atrophy rate quantification based on completely manual segmentation is well reproduced by FASTSURF. Therefore, FASTSURF is a promising tool to be implemented in clinical workflow, provided a future prospective validation confirms our findings.

UR - http://www.scopus.com/inward/record.url?scp=85060141425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060141425&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0210641

DO - 10.1371/journal.pone.0210641

M3 - Article

VL - 14

SP - 1

EP - 26

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 1

M1 - e0210641

ER -