no code implementations • 14 Sep 2019 • Nicole Bussola, Alessia Marcolini, Valerio Maggio, Giuseppe Jurman, Cesare Furlanello
We verify that accuracy scores may be inflated up to 41%, even if a well-designed 10x5 iterated cross-validation DAP is applied, unless all images from the same subject are kept together either in the internal training or validation splits.
no code implementations • 22 Nov 2017 • Valerio Maggio, Marco Chierici, Giuseppe Jurman, Cesare Furlanello
Neuroblastoma is a strongly heterogeneous cancer with very diverse clinical courses that may vary from spontaneous regression to fatal progression; an accurate patient's risk estimation at diagnosis is essential to design appropriate tumor treatment strategies.
no code implementations • 16 Oct 2017 • Giuseppe Jurman, Valerio Maggio, Diego Fioravanti, Ylenia Giarratano, Isotta Landi, Margherita Francescatto, Claudio Agostinelli, Marco Chierici, Manlio De Domenico, Cesare Furlanello
Convolutional Neural Networks (CNNs) are a popular deep learning architecture widely applied in different domains, in particular in classifying over images, for which the concept of convolution with a filter comes naturally.
no code implementations • 6 Sep 2017 • Diego Fioravanti, Ylenia Giarratano, Valerio Maggio, Claudio Agostinelli, Marco Chierici, Giuseppe Jurman, Cesare Furlanello
We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure.