Automated hippocampus segmentation with the Channeler Ant Model: Results on different datasets

Elisa Fiorina, Francesco Pennazio, Cristiana Peroni, Ernesto Lopez Torres, Maria Evelina Fantacci, Alessandra Retico, Luca Rei, Andrea Chincarini, Paolo Bosco, Marina Boccardi, Martina Bocchetta, Piergiorgio Cerello

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The hippocampus segmentation in Magnetic Resonance (MRI) scans is a relevant issue for the diagnosis of many pathologies. The present work describes a fully automated method for the hippocampal segmentation and discusses the results obtained on three datasets provided by different institutions and referring to different pathologies that involve hippocampus anatomy. The algorithm is based on an extension of the Channeler Ant Model, a powerful non linear segmentation tool belonging to the family of ant colony-based models, whose application to medical image processing already provided some promising results in the analysis of CT and PET scans. In this application, thanks to a modified pheromone deposition rule, both the grey matter intensity and the expected average hippocampus shape are taken into account. In this paper, the results on the three available datasets, obtained from the comparison to manual segmentations by different subjects and protocols, are shown: an average Dice Index in the 0.72-0.79 range, depending on the analysed dataset, is reached.

Original languageEnglish
Title of host publication2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages24-29
Number of pages6
ISBN (Print)9781479964765
DOIs
Publication statusPublished - Jun 30 2015
Event2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Torino, Italy
Duration: May 7 2015May 9 2015

Other

Other2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015
CountryItaly
CityTorino
Period5/7/155/9/15

Fingerprint

Pathology
Medical image processing
Magnetic resonance
Magnetic Resonance Imaging

ASJC Scopus subject areas

  • Biomedical Engineering
  • Computer Science Applications

Cite this

Fiorina, E., Pennazio, F., Peroni, C., Torres, E. L., Fantacci, M. E., Retico, A., ... Cerello, P. (2015). Automated hippocampus segmentation with the Channeler Ant Model: Results on different datasets. In 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings (pp. 24-29). [7145166] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MeMeA.2015.7145166

Automated hippocampus segmentation with the Channeler Ant Model : Results on different datasets. / Fiorina, Elisa; Pennazio, Francesco; Peroni, Cristiana; Torres, Ernesto Lopez; Fantacci, Maria Evelina; Retico, Alessandra; Rei, Luca; Chincarini, Andrea; Bosco, Paolo; Boccardi, Marina; Bocchetta, Martina; Cerello, Piergiorgio.

2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 24-29 7145166.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fiorina, E, Pennazio, F, Peroni, C, Torres, EL, Fantacci, ME, Retico, A, Rei, L, Chincarini, A, Bosco, P, Boccardi, M, Bocchetta, M & Cerello, P 2015, Automated hippocampus segmentation with the Channeler Ant Model: Results on different datasets. in 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings., 7145166, Institute of Electrical and Electronics Engineers Inc., pp. 24-29, 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015, Torino, Italy, 5/7/15. https://doi.org/10.1109/MeMeA.2015.7145166
Fiorina E, Pennazio F, Peroni C, Torres EL, Fantacci ME, Retico A et al. Automated hippocampus segmentation with the Channeler Ant Model: Results on different datasets. In 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 24-29. 7145166 https://doi.org/10.1109/MeMeA.2015.7145166
Fiorina, Elisa ; Pennazio, Francesco ; Peroni, Cristiana ; Torres, Ernesto Lopez ; Fantacci, Maria Evelina ; Retico, Alessandra ; Rei, Luca ; Chincarini, Andrea ; Bosco, Paolo ; Boccardi, Marina ; Bocchetta, Martina ; Cerello, Piergiorgio. / Automated hippocampus segmentation with the Channeler Ant Model : Results on different datasets. 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 24-29
@inproceedings{5b69bd77bb5b4243adead4803dd2afa4,
title = "Automated hippocampus segmentation with the Channeler Ant Model: Results on different datasets",
abstract = "The hippocampus segmentation in Magnetic Resonance (MRI) scans is a relevant issue for the diagnosis of many pathologies. The present work describes a fully automated method for the hippocampal segmentation and discusses the results obtained on three datasets provided by different institutions and referring to different pathologies that involve hippocampus anatomy. The algorithm is based on an extension of the Channeler Ant Model, a powerful non linear segmentation tool belonging to the family of ant colony-based models, whose application to medical image processing already provided some promising results in the analysis of CT and PET scans. In this application, thanks to a modified pheromone deposition rule, both the grey matter intensity and the expected average hippocampus shape are taken into account. In this paper, the results on the three available datasets, obtained from the comparison to manual segmentations by different subjects and protocols, are shown: an average Dice Index in the 0.72-0.79 range, depending on the analysed dataset, is reached.",
author = "Elisa Fiorina and Francesco Pennazio and Cristiana Peroni and Torres, {Ernesto Lopez} and Fantacci, {Maria Evelina} and Alessandra Retico and Luca Rei and Andrea Chincarini and Paolo Bosco and Marina Boccardi and Martina Bocchetta and Piergiorgio Cerello",
year = "2015",
month = "6",
day = "30",
doi = "10.1109/MeMeA.2015.7145166",
language = "English",
isbn = "9781479964765",
pages = "24--29",
booktitle = "2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automated hippocampus segmentation with the Channeler Ant Model

T2 - Results on different datasets

AU - Fiorina, Elisa

AU - Pennazio, Francesco

AU - Peroni, Cristiana

AU - Torres, Ernesto Lopez

AU - Fantacci, Maria Evelina

AU - Retico, Alessandra

AU - Rei, Luca

AU - Chincarini, Andrea

AU - Bosco, Paolo

AU - Boccardi, Marina

AU - Bocchetta, Martina

AU - Cerello, Piergiorgio

PY - 2015/6/30

Y1 - 2015/6/30

N2 - The hippocampus segmentation in Magnetic Resonance (MRI) scans is a relevant issue for the diagnosis of many pathologies. The present work describes a fully automated method for the hippocampal segmentation and discusses the results obtained on three datasets provided by different institutions and referring to different pathologies that involve hippocampus anatomy. The algorithm is based on an extension of the Channeler Ant Model, a powerful non linear segmentation tool belonging to the family of ant colony-based models, whose application to medical image processing already provided some promising results in the analysis of CT and PET scans. In this application, thanks to a modified pheromone deposition rule, both the grey matter intensity and the expected average hippocampus shape are taken into account. In this paper, the results on the three available datasets, obtained from the comparison to manual segmentations by different subjects and protocols, are shown: an average Dice Index in the 0.72-0.79 range, depending on the analysed dataset, is reached.

AB - The hippocampus segmentation in Magnetic Resonance (MRI) scans is a relevant issue for the diagnosis of many pathologies. The present work describes a fully automated method for the hippocampal segmentation and discusses the results obtained on three datasets provided by different institutions and referring to different pathologies that involve hippocampus anatomy. The algorithm is based on an extension of the Channeler Ant Model, a powerful non linear segmentation tool belonging to the family of ant colony-based models, whose application to medical image processing already provided some promising results in the analysis of CT and PET scans. In this application, thanks to a modified pheromone deposition rule, both the grey matter intensity and the expected average hippocampus shape are taken into account. In this paper, the results on the three available datasets, obtained from the comparison to manual segmentations by different subjects and protocols, are shown: an average Dice Index in the 0.72-0.79 range, depending on the analysed dataset, is reached.

UR - http://www.scopus.com/inward/record.url?scp=84939505543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939505543&partnerID=8YFLogxK

U2 - 10.1109/MeMeA.2015.7145166

DO - 10.1109/MeMeA.2015.7145166

M3 - Conference contribution

AN - SCOPUS:84939505543

SN - 9781479964765

SP - 24

EP - 29

BT - 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -