To evaluate the performance of the proposed de-identification tool, a comparative study was conducted between several existing defacing and refacing tools, with two different segmentation algorithms (FAST and Morphobox).
The weak labels extracted from radiology reports allowed us to increase dataset size more than 3-fold, and improve VGG classification results from 75% to 82% AUC.
no code implementations • 17 Nov 2021 • Javier Ortega-Garcia, Julian Fierrez, Fernando Alonso-Fernandez, Javier Galbally, Manuel R Freire, Joaquin Gonzalez-Rodriguez, Carmen Garcia-Mateo, Jose-Luis Alba-Castro, Elisardo Gonzalez-Agulla, Enrique Otero-Muras, Sonia Garcia-Salicetti, Lorene Allano, Bao Ly-Van, Bernadette Dorizzi, Josef Kittler, Thirimachos Bourlai, Norman Poh, Farzin Deravi, Ming NR Ng, Michael Fairhurst, Jean Hennebert, Andreas Humm, Massimo Tistarelli, Linda Brodo, Jonas Richiardi, Andrezj Drygajlo, Harald Ganster, Federico M Sukno, Sri-Kaushik Pavani, Alejandro Frangi, Lale Akarun, Arman Savran
It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1) over the Internet, 2) in an office environment with desktop PC, and 3) in indoor/outdoor environments with mobile portable hardware.
1 code implementation • 10 Mar 2021 • Tommaso Di Noto, Guillaume Marie, Sebastien Tourbier, Yasser Alemán-Gómez, Oscar Esteban, Guillaume Saliou, Meritxell Bach Cuadra, Patric Hagmann, Jonas Richiardi
Here, we present a DL model for aneurysm detection that overcomes the issue with ''weak'' labels: oversized annotations which are considerably faster to create.
We compare two strategies for negative patch sampling that have an increasing level of difficulty for the network and we show how this choice can strongly affect the results.
In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients.