Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation

no code implementations • 6 Jul 2021 • Giammarco La Barbera, Pietro Gori, Haithem Boussaid, Bruno Belucci, Alessandro Delmonte, Jeanne Goulin, Sabine Sarnacki, Laurence Rouet, Isabelle Bloch

Due to a high heterogeneity in pose and size and to a limited number of available data, segmentation of pediatric images is challenging for deep learning methods.

Data Augmentation Tumor Segmentation

Fast and Exact: ADMM-Based Discriminative Shape Segmentation with Loopy Part Models

no code implementations • CVPR 2014 • Haithem Boussaid, Iasonas Kokkinos

In this work we use loopy part models to segment ensembles of organs in medical images.

Medical Image Segmentation Semantic Segmentation +1