Longitudinal studies are very important to understand cerebral structural changes especially during the course of pathologies. For instance, in the context of mental health research, it is interesting to evaluate how a certain disease degenerates over time in order to discriminate between pathological and normal time dependent brain deformations. However longitudinal data are not easily available, and very often they are characterized by a large variability in both the age of subjects and time between acquisitions (follow up time). This leads to heterogeneous data that may affect the overall study. In this paper we propose a learning method to deal with this kind of heterogeneous data by exploiting covariate measures in a Multiple Kernel Learning (MKL) framework. Cortical thickness and white matter volume of the left middle temporal region are collected from each subject. Then, a subject-dependent kernel weighting procedure is introduced in order to obtain the correction of covariate effect simultaneously with classification. Experiments are reported for First Episode Psychosis detection by showing very promising results.

Learning with Heterogeneous Data for Longitudinal Studies / L. Squarcina, C. Perlini, M. Bellani, A. Lasalvia, M. Ruggeri, P. Brambilla, U. Castellani (LECTURE NOTES IN COMPUTER SCIENCE). - In: Medical image computing and computer-assisted intervention -- MICCAI 2015 / [a cura di] N. Navab, J. Hornegger, W.M. Wells, A.F. Frangi. - New York : Springer, 2015. - ISBN 978-3-319-24574-4. - pp. 535-542 (( Intervento presentato al 18. convegno International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) tenutosi a Munich nel 2015 [10.1007/978-3-319-24574-4_64].

Learning with Heterogeneous Data for Longitudinal Studies

L. Squarcina;P. Brambilla;
2015

Abstract

Longitudinal studies are very important to understand cerebral structural changes especially during the course of pathologies. For instance, in the context of mental health research, it is interesting to evaluate how a certain disease degenerates over time in order to discriminate between pathological and normal time dependent brain deformations. However longitudinal data are not easily available, and very often they are characterized by a large variability in both the age of subjects and time between acquisitions (follow up time). This leads to heterogeneous data that may affect the overall study. In this paper we propose a learning method to deal with this kind of heterogeneous data by exploiting covariate measures in a Multiple Kernel Learning (MKL) framework. Cortical thickness and white matter volume of the left middle temporal region are collected from each subject. Then, a subject-dependent kernel weighting procedure is introduced in order to obtain the correction of covariate effect simultaneously with classification. Experiments are reported for First Episode Psychosis detection by showing very promising results.
First Episode Psychosis; Longitudinal study; Multiple Kernel Learning; Support Vector Machines
Settore MED/25 - Psichiatria
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
chp%3A10.1007%2F978-3-319-24574-4_64.pdf

non disponibili

Tipologia: Publisher's version/PDF
Dimensione 190.9 kB
Formato Adobe PDF
190.9 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento 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: http://hdl.handle.net/2434/437481
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact