Technical Considerations for Semantic Segmentation in MRI using Convolutional Neural Networks
arXiv:1902.01977
Abstract
High-fidelity semantic segmentation of magnetic resonance volumes is critical for estimating tissue morphometry and relaxation parameters in both clinical and research applications. While manual segmentation is accepted as the gold-standard, recent advances in deep learning and convolutional neural networks (CNNs) have shown promise for efficient automatic segmentation of soft tissues. However, due to the stochastic nature of deep learning and the multitude of hyperparameters in training networks, predicting network behavior is challenging. In this paper, we quantify the impact of three factors associated with CNN segmentation performance: network architecture, training loss functions, and training data characteristics. We evaluate the impact of these variations on the segmentation of femoral cartilage and propose potential modifications to CNN architectures and training protocols to train these models with confidence.
Submitted to Magnetic Resonance in Medicine
References in corpus (10)
- TensorFlow: A system for large-scale machine learning
- Rethinking Atrous Convolution for Semantic Image Segmentation
- On the difficulty of training Recurrent Neural Networks
- Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Opening the Black Box of Deep Neural Networks via Information
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
- Deep Learning Scaling is Predictable, Empirically
- On the Expressive Power of Deep Neural Networks
- An analytic theory of generalization dynamics and transfer learning in deep linear networks