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.

Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning / D. Peruzzo, F. Arrigoni, F. Triulzi, C. Parazzini, U. Castellani (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE). - In: Medical Image Computing and Computer-Assisted Intervention / [a cura di] P. Golland, N. Hata, C. Barillot, J. Hornegger, R. Howe. - [s.l] : Springer Verlag, 2014. - ISBN 9783319104690. - pp. 300-307 (( convegno 17th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2014 tenutosi a Boston, MA, usa nel 2014 [10.1007/978-3-319-10470-6_38].

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

F. Arrigoni;F. Triulzi;
2014

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.
magnetic resonance imaging; multiple kernel learning; brain imaging; computer-aided diagnosis
Settore MED/37 - Neuroradiologia
2014
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Peruzzo2014_Chapter_DetectionOfCorpusCallosumMalfo.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 451.77 kB
Formato Adobe PDF
451.77 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/822010
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 3
social impact