1.3k citations · 1.7k across the 20 of their papers we have counts for
6 papers · 1 filter
On the Initialization of Long Short-Term Memory Networks
Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4
Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the…
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
Mathias Perslev, Erik Bjørnager Dam, Akshay Pai +1
Many recent medical segmentation systems rely on powerful deep learning models to solve highly specific tasks. To maximize performance, it is standard practice to evaluate numerous…
Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning
Mauricio Orbes-Arteaga, Thomas Varsavsky, Carole H. Sudre +9
Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this cha…
Knowledge distillation for semi-supervised domain adaptation
Mauricio Orbes-Arteaga, Jorge Cardoso, Lauge Sørensen +5
In the absence of sufficient data variation (e.g., scanner and protocol variability) in annotated data, deep neural networks (DNNs) tend to overfit during training. As a result, th…
Robust parametric modeling of Alzheimer's disease progression
Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4
Quantitative characterization of disease progression using longitudinal data can provide long-term predictions for the pathological stages of individuals. This work studies the rob…
Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling
Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai +4
Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make pa…