Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
arXiv:2009.00872 · doi:10.1371/journal.pone.0255397
Abstract
For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial. For example, existent segmentation algorithms based on natural images are neither efficient in their parameter use nor optimized for medical imaging. Here we present MoNet, a highly optimized neural-network-based pancreatic segmentation algorithm focused on achieving high performance by efficient multi-scale image feature utilization.
References in corpus (11)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Federated Learning: Challenges, Methods, and Future Directions
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Attention U-Net: Learning Where to Look for the Pancreas
- Language Models are Few-Shot Learners
- Federated Learning: Strategies for Improving Communication Efficiency
- Towards Federated Learning at Scale: System Design
- A large annotated medical image dataset for the development and evaluation of segmentation algorithms
- Federated Optimization:Distributed Optimization Beyond the Datacenter
- nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation