Semi-automatic hippocampus delineation algorithm using surface fairing

Fabian Bartel, H. Vrenken, M. van Herk, M. B. de Ruiter, J. Belderbos, J. Hulshof, J. C. de Munck

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Background: Manual hippocampus segmentation on structural magnetic resonance images (MRI) is labor intensive and time consuming. This paper presents a semi-automatic hippocampus segmentation method that decreases segmentation time without compromising accuracy. Methods: We present a method that reconstructs sparse delineations into full hippocampal surfaces meshes with a smooth surface reconstruction technique. From fully manual segmented hippocampi in ten subjects with about 20 slice contours, we simulated sparse delineations ranging from 4-10 contours to simulate decreased contouring time by at least half. We compared the original hippocampi with reconstructed hippocampi as well as automatic segmentations obtained from each subjects’ T1 weighted MRI using FSL-FIRST and FreeSurfer. We computed Dice overlap indices, percentage volume differences (PVD) and intra-correlation coefficients (ICC) with manual hippocampus segmentations. Results: For the hippocampi reconstructed from 4 to 10 contours, we obtained high mean dice overlaps, low mean PVDs and high ICCs in the range of 81(±0.03)-91(±0.01)%, 6.85(±5.33)-1.98(±1.63)% and 0.970–0.997 respectively. Reconstructed hippocampi agreed consistently better with manual segmentations than automatic segmentation methods, even when 5 contours were used. Conclusions: We were able to reconstruct hippocampi from a minimum number of contours and maintained high accuracy results that were consistently better than automatic methods. We next need to test this method on a larger scale and validate reproducibility and robustness.

Original languageEnglish
Title of host publicationEMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017
PublisherSpringer Verlag
Pages956-959
Number of pages4
Volume65
ISBN (Print)9789811051210
DOIs
Publication statusPublished - 2017
EventJoint Conference of the European Medical and Biological Engineering Conference, EMBEC 2017 and Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2107 - Tampere, Finland
Duration: 11 Jun 201715 Jun 2017

Conference

ConferenceJoint Conference of the European Medical and Biological Engineering Conference, EMBEC 2017 and Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2107
CountryFinland
CityTampere
Period11/06/201715/06/2017

Cite this

Bartel, F., Vrenken, H., van Herk, M., de Ruiter, M. B., Belderbos, J., Hulshof, J., & de Munck, J. C. (2017). Semi-automatic hippocampus delineation algorithm using surface fairing. In EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017 (Vol. 65, pp. 956-959). Springer Verlag. https://doi.org/10.1007/978-981-10-5122-7_239
Bartel, Fabian ; Vrenken, H. ; van Herk, M. ; de Ruiter, M. B. ; Belderbos, J. ; Hulshof, J. ; de Munck, J. C. / Semi-automatic hippocampus delineation algorithm using surface fairing. EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017. Vol. 65 Springer Verlag, 2017. pp. 956-959
@inproceedings{a7d1a13ea76d46d6859fa24eab043129,
title = "Semi-automatic hippocampus delineation algorithm using surface fairing",
abstract = "Background: Manual hippocampus segmentation on structural magnetic resonance images (MRI) is labor intensive and time consuming. This paper presents a semi-automatic hippocampus segmentation method that decreases segmentation time without compromising accuracy. Methods: We present a method that reconstructs sparse delineations into full hippocampal surfaces meshes with a smooth surface reconstruction technique. From fully manual segmented hippocampi in ten subjects with about 20 slice contours, we simulated sparse delineations ranging from 4-10 contours to simulate decreased contouring time by at least half. We compared the original hippocampi with reconstructed hippocampi as well as automatic segmentations obtained from each subjects’ T1 weighted MRI using FSL-FIRST and FreeSurfer. We computed Dice overlap indices, percentage volume differences (PVD) and intra-correlation coefficients (ICC) with manual hippocampus segmentations. Results: For the hippocampi reconstructed from 4 to 10 contours, we obtained high mean dice overlaps, low mean PVDs and high ICCs in the range of 81(±0.03)-91(±0.01){\%}, 6.85(±5.33)-1.98(±1.63){\%} and 0.970–0.997 respectively. Reconstructed hippocampi agreed consistently better with manual segmentations than automatic segmentation methods, even when 5 contours were used. Conclusions: We were able to reconstruct hippocampi from a minimum number of contours and maintained high accuracy results that were consistently better than automatic methods. We next need to test this method on a larger scale and validate reproducibility and robustness.",
keywords = "FreeSurfer, FSL-FIRST, Hippocampus, Semi-automatic delineation, Surface fairing",
author = "Fabian Bartel and H. Vrenken and {van Herk}, M. and {de Ruiter}, {M. B.} and J. Belderbos and J. Hulshof and {de Munck}, {J. C.}",
year = "2017",
doi = "10.1007/978-981-10-5122-7_239",
language = "English",
isbn = "9789811051210",
volume = "65",
pages = "956--959",
booktitle = "EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017",
publisher = "Springer Verlag",
address = "Germany",

}

Bartel, F, Vrenken, H, van Herk, M, de Ruiter, MB, Belderbos, J, Hulshof, J & de Munck, JC 2017, Semi-automatic hippocampus delineation algorithm using surface fairing. in EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017. vol. 65, Springer Verlag, pp. 956-959, Joint Conference of the European Medical and Biological Engineering Conference, EMBEC 2017 and Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2107, Tampere, Finland, 11/06/2017. https://doi.org/10.1007/978-981-10-5122-7_239

Semi-automatic hippocampus delineation algorithm using surface fairing. / Bartel, Fabian; Vrenken, H.; van Herk, M.; de Ruiter, M. B.; Belderbos, J.; Hulshof, J.; de Munck, J. C.

EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017. Vol. 65 Springer Verlag, 2017. p. 956-959.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Semi-automatic hippocampus delineation algorithm using surface fairing

AU - Bartel, Fabian

AU - Vrenken, H.

AU - van Herk, M.

AU - de Ruiter, M. B.

AU - Belderbos, J.

AU - Hulshof, J.

AU - de Munck, J. C.

PY - 2017

Y1 - 2017

N2 - Background: Manual hippocampus segmentation on structural magnetic resonance images (MRI) is labor intensive and time consuming. This paper presents a semi-automatic hippocampus segmentation method that decreases segmentation time without compromising accuracy. Methods: We present a method that reconstructs sparse delineations into full hippocampal surfaces meshes with a smooth surface reconstruction technique. From fully manual segmented hippocampi in ten subjects with about 20 slice contours, we simulated sparse delineations ranging from 4-10 contours to simulate decreased contouring time by at least half. We compared the original hippocampi with reconstructed hippocampi as well as automatic segmentations obtained from each subjects’ T1 weighted MRI using FSL-FIRST and FreeSurfer. We computed Dice overlap indices, percentage volume differences (PVD) and intra-correlation coefficients (ICC) with manual hippocampus segmentations. Results: For the hippocampi reconstructed from 4 to 10 contours, we obtained high mean dice overlaps, low mean PVDs and high ICCs in the range of 81(±0.03)-91(±0.01)%, 6.85(±5.33)-1.98(±1.63)% and 0.970–0.997 respectively. Reconstructed hippocampi agreed consistently better with manual segmentations than automatic segmentation methods, even when 5 contours were used. Conclusions: We were able to reconstruct hippocampi from a minimum number of contours and maintained high accuracy results that were consistently better than automatic methods. We next need to test this method on a larger scale and validate reproducibility and robustness.

AB - Background: Manual hippocampus segmentation on structural magnetic resonance images (MRI) is labor intensive and time consuming. This paper presents a semi-automatic hippocampus segmentation method that decreases segmentation time without compromising accuracy. Methods: We present a method that reconstructs sparse delineations into full hippocampal surfaces meshes with a smooth surface reconstruction technique. From fully manual segmented hippocampi in ten subjects with about 20 slice contours, we simulated sparse delineations ranging from 4-10 contours to simulate decreased contouring time by at least half. We compared the original hippocampi with reconstructed hippocampi as well as automatic segmentations obtained from each subjects’ T1 weighted MRI using FSL-FIRST and FreeSurfer. We computed Dice overlap indices, percentage volume differences (PVD) and intra-correlation coefficients (ICC) with manual hippocampus segmentations. Results: For the hippocampi reconstructed from 4 to 10 contours, we obtained high mean dice overlaps, low mean PVDs and high ICCs in the range of 81(±0.03)-91(±0.01)%, 6.85(±5.33)-1.98(±1.63)% and 0.970–0.997 respectively. Reconstructed hippocampi agreed consistently better with manual segmentations than automatic segmentation methods, even when 5 contours were used. Conclusions: We were able to reconstruct hippocampi from a minimum number of contours and maintained high accuracy results that were consistently better than automatic methods. We next need to test this method on a larger scale and validate reproducibility and robustness.

KW - FreeSurfer

KW - FSL-FIRST

KW - Hippocampus

KW - Semi-automatic delineation

KW - Surface fairing

UR - http://www.scopus.com/inward/record.url?scp=85021704991&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-5122-7_239

DO - 10.1007/978-981-10-5122-7_239

M3 - Conference contribution

SN - 9789811051210

VL - 65

SP - 956

EP - 959

BT - EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017

PB - Springer Verlag

ER -

Bartel F, Vrenken H, van Herk M, de Ruiter MB, Belderbos J, Hulshof J et al. Semi-automatic hippocampus delineation algorithm using surface fairing. In EMBEC and NBC 2017 - Joint Conference of the European Medical and Biological Engineering Conference EMBEC 2017 and the Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2017. Vol. 65. Springer Verlag. 2017. p. 956-959 https://doi.org/10.1007/978-981-10-5122-7_239