Scikit-learn: Machine Learning in Python
- Fabian Pedregosa, G. Varoquaux, E. Duchesnay
- Computer ScienceJournal of machine learning research
- 1 February 2011
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing…
A framework to study the cortical folding patterns
Asynchrony of the early maturation of white matter bundles in healthy infants: Quantitative landmarks revealed noninvasively by diffusion tensor imaging
A specific maturation model, based on the respective roles of different maturational processes on the diffusion phenomena, was designed to highlight asynchronous maturation across bundles by evaluating the time‐course of mean diffusivity and anisotropy changes over the considered developmental period.
Object-based morphometry of the cerebral cortex
This study reveals some correlates of handedness on the size of the sulci located in motor areas, which was not detected previously using standard voxel based morphometry.
Inverse retinotopy: Inferring the visual content of images from brain activation patterns
Significant correlation between a set of genetic polymorphisms and a functional brain network revealed by feature selection and sparse Partial Least Squares
Cortical folding abnormalities in schizophrenia patients with resistant auditory hallucinations
Feature selection and classification of imbalanced datasets Application to PET images of children with autistic spectrum disorders
Classification Based on Cortical Folding Patterns
- E. Duchesnay, A. Cachia, J. F. Mangin
- Computer ScienceIEEE Transactions on Medical Imaging
- 2 April 2007
A classifier pipeline with one- or two-stage of descriptor selection based on machine-learning methods, followed by a support vector machine classifier or linear discriminant analysis is described, highlighting the attractiveness of multivariate recognition models combined with appropriate descriptor selection.
Using structural MRI to identify bipolar disorders – 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group
Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures.