R
Raúl Ramos-Pollán
Researcher at Industrial University of Santander
Publications - 21
Citations - 684
Raúl Ramos-Pollán is an academic researcher from Industrial University of Santander. The author has contributed to research in topics: Mammography & Convolutional neural network. The author has an hindex of 7, co-authored 21 publications receiving 537 citations. Previous affiliations of Raúl Ramos-Pollán include National University of Colombia.
Papers
More filters
Journal ArticleDOI
Representation learning for mammography mass lesion classification with convolutional neural networks
John Arevalo,Fabio A. González,Raúl Ramos-Pollán,José Luís Oliveira,Miguel Angel Guevara Lopez +4 more
TL;DR: An innovative representation learning framework for breast cancer diagnosis in mammography that integrates deep learning techniques to automatically learn discriminative features avoiding the design of specific hand-crafted image-based feature detectors is described.
Proceedings ArticleDOI
Convolutional neural networks for mammography mass lesion classification
John Arevalo,Fabio A. González,Raúl Ramos-Pollán,José Luís Oliveira,Miguel Angel Guevara Lopez +4 more
TL;DR: This work presents an evaluation of convolutional neural networks to learn features for mammography mass lesions before feeding them to a classification stage, and Experimental results showed that this approach is a suitable strategy outperforming the state-of-the-art representation.
Journal ArticleDOI
Discovering Mammography-based Machine Learning Classifiers for Breast Cancer Diagnosis
Raúl Ramos-Pollán,Miguel Ángel Guevara-López,Cesar Suarez-Ortega,Guillermo Díaz-Herrero,Jose Miguel Franco-Valiente,Manuel Rubio-Del-Solar,Naimy González-de-Posada,Mário Vaz,Joana A. Loureiro,Isabel Ramos +9 more
TL;DR: This work massively evaluated MLC configurations to classify features vectors extracted from segmented regions (pathological lesion or normal tissue) on craniocaudal and mediolateral oblique mammography image views, providing BI-RADS diagnosis.
Book ChapterDOI
Supervised Greedy Layer-Wise Training for Deep Convolutional Networks with Small Datasets
TL;DR: This work proposes to train DCNs with a greedy layer-wise method, analogous to that used in unsupervised deep networks, and shows how this method outperforms DCNs which do not use pretrained models and results reported in the literature with other methods.
Journal ArticleDOI
A Software Framework for Building Biomedical Machine Learning Classifiers through Grid Computing Resources
TL;DR: The BiomedTK software framework was experimentally validated by training thousands of classifier configurations for representative biomedical UCI datasets reaching in little time classification levels comparable to those reported in existing literature.