Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning

Denis Peruzzo, Filippo Arrigoni, Fabio Triulzi, Cecilia Parazzini, Umberto Castellani

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In this paper we propose a Multiple Kernel Learning (MKL) classifier to detect malformations of the Corpus Callosum (CC) and apply it in a pediatric population. Furthermore, we extend the concept of discriminative direction to the linear MKL methods, implementing it in a single subject analysis framework. The CC is characterized using different measures derived from Magnetic Resonance Imaging (MRI) data and the MKL approach is used to efficiently combine them. The discriminative direction analysis highlights those features that lead the classification for each given subject. In the case of a CC with malformation this means highlighting the abnormal characteristics of the CC that guide the diagnosis. Experiments show that the method correctly identifies the malformative aspects of the CC. Moreover, it is able to identify dishomogeneus, localized or widespread abnormalities among the different features. The proposed method is therefore suitable for supporting neuroradiologists in the decision-making process, providing them not only with a suggested diagnosis, but also with a description of the pathology.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages300-307
Number of pages8
Volume17
Publication statusPublished - 2014

Fingerprint

Agenesis of Corpus Callosum
Corpus Callosum
Learning
Pediatrics
Population
Decision Making
Magnetic Resonance Imaging
Pathology
Direction compound

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Peruzzo, D., Arrigoni, F., Triulzi, F., Parazzini, C., & Castellani, U. (2014). Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Vol. 17, pp. 300-307)

Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. / Peruzzo, Denis; Arrigoni, Filippo; Triulzi, Fabio; Parazzini, Cecilia; Castellani, Umberto.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. p. 300-307.

Research output: Chapter in Book/Report/Conference proceedingChapter

Peruzzo, D, Arrigoni, F, Triulzi, F, Parazzini, C & Castellani, U 2014, Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. vol. 17, pp. 300-307.
Peruzzo D, Arrigoni F, Triulzi F, Parazzini C, Castellani U. Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17. 2014. p. 300-307
Peruzzo, Denis ; Arrigoni, Filippo ; Triulzi, Fabio ; Parazzini, Cecilia ; Castellani, Umberto. / Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. pp. 300-307
@inbook{fc361d88a0634d7e9e05b401bb3dda4e,
title = "Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning",
abstract = "In this paper we propose a Multiple Kernel Learning (MKL) classifier to detect malformations of the Corpus Callosum (CC) and apply it in a pediatric population. Furthermore, we extend the concept of discriminative direction to the linear MKL methods, implementing it in a single subject analysis framework. The CC is characterized using different measures derived from Magnetic Resonance Imaging (MRI) data and the MKL approach is used to efficiently combine them. The discriminative direction analysis highlights those features that lead the classification for each given subject. In the case of a CC with malformation this means highlighting the abnormal characteristics of the CC that guide the diagnosis. Experiments show that the method correctly identifies the malformative aspects of the CC. Moreover, it is able to identify dishomogeneus, localized or widespread abnormalities among the different features. The proposed method is therefore suitable for supporting neuroradiologists in the decision-making process, providing them not only with a suggested diagnosis, but also with a description of the pathology.",
author = "Denis Peruzzo and Filippo Arrigoni and Fabio Triulzi and Cecilia Parazzini and Umberto Castellani",
year = "2014",
language = "English",
volume = "17",
pages = "300--307",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",

}

TY - CHAP

T1 - Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning

AU - Peruzzo, Denis

AU - Arrigoni, Filippo

AU - Triulzi, Fabio

AU - Parazzini, Cecilia

AU - Castellani, Umberto

PY - 2014

Y1 - 2014

N2 - In this paper we propose a Multiple Kernel Learning (MKL) classifier to detect malformations of the Corpus Callosum (CC) and apply it in a pediatric population. Furthermore, we extend the concept of discriminative direction to the linear MKL methods, implementing it in a single subject analysis framework. The CC is characterized using different measures derived from Magnetic Resonance Imaging (MRI) data and the MKL approach is used to efficiently combine them. The discriminative direction analysis highlights those features that lead the classification for each given subject. In the case of a CC with malformation this means highlighting the abnormal characteristics of the CC that guide the diagnosis. Experiments show that the method correctly identifies the malformative aspects of the CC. Moreover, it is able to identify dishomogeneus, localized or widespread abnormalities among the different features. The proposed method is therefore suitable for supporting neuroradiologists in the decision-making process, providing them not only with a suggested diagnosis, but also with a description of the pathology.

AB - In this paper we propose a Multiple Kernel Learning (MKL) classifier to detect malformations of the Corpus Callosum (CC) and apply it in a pediatric population. Furthermore, we extend the concept of discriminative direction to the linear MKL methods, implementing it in a single subject analysis framework. The CC is characterized using different measures derived from Magnetic Resonance Imaging (MRI) data and the MKL approach is used to efficiently combine them. The discriminative direction analysis highlights those features that lead the classification for each given subject. In the case of a CC with malformation this means highlighting the abnormal characteristics of the CC that guide the diagnosis. Experiments show that the method correctly identifies the malformative aspects of the CC. Moreover, it is able to identify dishomogeneus, localized or widespread abnormalities among the different features. The proposed method is therefore suitable for supporting neuroradiologists in the decision-making process, providing them not only with a suggested diagnosis, but also with a description of the pathology.

UR - http://www.scopus.com/inward/record.url?scp=84922273088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922273088&partnerID=8YFLogxK

M3 - Chapter

C2 - 25485392

AN - SCOPUS:84922273088

VL - 17

SP - 300

EP - 307

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -