1 code implementation • 30 Jun 2022 • Jiancheng Yang, Rui Shi, Udaranga Wickramasinghe, Qikui Zhu, Bingbing Ni, Pascal Fua
Besides, we develop a new Adrenal gLand ANalysis (ALAN) dataset with the proposed NeAR, where each case consists of a 3D shape of adrenal gland and its diagnosis label (normal vs. abnormal) assigned by experts.
no code implementations • 21 Jun 2022 • Patrick M. Jensen, Udaranga Wickramasinghe, Anders B. Dahl, Pascal Fua, Vedrana A. Dahl
During training the latent vectors are constrained to have the same value, which avoids overfitting.
no code implementations • CVPR 2022 • Jiancheng Yang, Udaranga Wickramasinghe, Bingbing Ni, Pascal Fua
Deep implicit shape models have become popular in the computer vision community at large but less so for biomedical applications.
no code implementations • 7 Jun 2021 • Udaranga Wickramasinghe, Patrick M. Jensen, Mian Shah, Jiancheng Yang, Pascal Fua
There are many approaches to weakly-supervised training of networks to segment 2D images.
no code implementations • CVPR 2021 • Udaranga Wickramasinghe, Graham Knott, Pascal Fua
Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them.
1 code implementation • 8 Dec 2019 • Udaranga Wickramasinghe, Edoardo Remelli, Graham Knott, Pascal Fua
CNN-based volumetric methods that label individual voxels now dominate the field of biomedical segmentation.
1 code implementation • 18 Sep 2019 • Udaranga Wickramasinghe, Graham Knott, Pascal Fua
Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs).