The 10th annual MLSP competition: First place

Author

Solin, Arno ; Sarkka, Simo

Author_Institution

Dept. of Biomed. Eng. & Comput. Sci., Aalto Univ., Espoo, Finland

fYear

2014

fDate

21-24 Sept. 2014

Firstpage

1

Lastpage

3

Abstract

The goal of the MLSP 2014 Schizophrenia Classification Challenge was to automatically diagnose subjects with schizophrenia based on multimodal features derived from their magnetic resonance imaging (MRI) brain scans. This challenge took place between June 5 and July 20, 2014, and was organized on Kaggle. We present how this classification problem can be solved in terms of a Bayesian machine learning paradigm known as Gaussian process (GP) classification. The proposed solution achieved an AUC score of 0.928, and it ranked first on the Kaggle private leaderboard.

Keywords

Gaussian processes; biomedical MRI; brain; image classification; medical image processing; AUC score; Bayesian machine learning paradigm; GP classification; Gaussian process classification; Kaggle private leaderboard; MLSP 2014 Schizophrenia Classification Challenge; MRI brain scans; magnetic resonance imaging brain scans; Bayes methods; Brain modeling; Gaussian processes; Lead; Magnetic resonance imaging; Mathematical model; Gaussian process classification; Schizophrenia; magnetic resonance imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning for Signal Processing (MLSP), 2014 IEEE International Workshop on

Conference_Location

Reims

Type

conf

DOI

10.1109/MLSP.2014.6958886

Filename

6958886