Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction

Authors: Chun-Mei Feng, Zhanyuan Yang, Geng Chen, Yong Xu, Ling Shao116-124

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on an in vivo knee dataset under different undersampling patterns and acceleration factors. The experimental results demonstrate the superiority of our model in accelerated parallel MR image reconstruction.
Researcher Affiliation Collaboration 1 Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology (Shenzhen), China 2 Peng Cheng Laboratory, Shenzhen, China 3 School of Automation Engineering, University of Electronic Science and Technology of China, China 4 Inception Institute of Artificial Intelligence, Abu Dhabi, UAE
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Our code is available at: github.com/chunmeifeng/Dual-Oct Conv.
Open Datasets Yes We use the in vivo multi-coil fully-sampled MR knee dataset that is acquired using a clinical 3T Siemens Magnetom Skyra scanner with a sequence called Coronal Spin Density Weighted without Fat Suppression (Hammernik et al. 2018).
Dataset Splits Yes We randomly select 14 patients for training, 3 for validation, and 3 for testing.
Hardware Specification Yes We implement our model using Tensorflow 1.14 and perform experiments using an NVIDIA 1080Ti GPU with a 11GB memory.
Software Dependencies Yes We implement our model using Tensorflow 1.14 and perform experiments using an NVIDIA 1080Ti GPU with a 11GB memory.
Experiment Setup Yes The network is trained using the Adam optimizer (Wang et al. 2020) with initial learning rate 0.001 and weight decay 0.95. The batch size is set to 4 and convolutional kernel size is set to 3x3.