1 code implementation • 3 Oct 2023 • Etienne Pochet, Rami Maroun, Roger Trullo
This module can perform full self-attention with relative position encoding on patches of large and arbitrary shaped WSIs, solving the need for correlation between instances and spatial modeling of tissues.
no code implementations • 12 Aug 2022 • Roger Trullo, Quoc-Anh Bui, Qi Tang, Reza Olfati-Saber
Numerous deep learning based methods have been developed for nuclei segmentation for H&E images and have achieved close to human performance.
no code implementations • 26 Jun 2021 • Arturo Mendoza, Roger Trullo, Yanneck Wielhorski
In this work we propose a novel and fully automated method for extracting the yarn geometrical features in woven composites so that a direct parametrization of the textile reinforcement is achieved (e. g., FE mesh).
1 code implementation • IEEE Transactions on Biomedical Engineering 2018 • Dong Nie, Roger Trullo, Jun Lian, Li Wang, Caroline Petitjean, Su Ruan, Qian Wang, and Dinggang Shen, Fellow, IEEE
To better model a nonlinear mapping from source to target and to produce more realistic target images, we propose to use the adversarial learning strategy to better model the FCN.
no code implementations • 16 Dec 2016 • Dong Nie, Roger Trullo, Caroline Petitjean, Su Ruan, Dinggang Shen
To better model the nonlinear relationship from MRI to CT and to produce more realistic images, we propose to use the adversarial training strategy and an image gradient difference loss function.