The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels.
Using the state-of-the-art CorticalFlow model as a blueprint, this paper proposes three modifications to improve its accuracy and interoperability with existing surface analysis tools, while not sacrificing its fast inference time and low GPU memory consumption.
In this paper we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object.
Results show that training 2D-3D mapping network models on synthetic data is a viable alternative to using real data.
In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object.
Having these limitations in mind, we propose DeepCSR, a 3D deep learning framework for cortical surface reconstruction from MRI.
Brain morphometry from magnetic resonance imaging (MRI) is a consolidated biomarker for many neurodegenerative diseases.
The recent application of deep learning technologies in medical image registration has exponentially decreased the registration time and gradually increased registration accuracy when compared to their traditional counterparts.