Breaking Information Isolation: Accelerating MRI via Inter-sequence Mapping and Progressive Masking

Authors: Jianwei Zheng, Xiaomin Yao, Guojiang Shen, Wei Li, Jiawei Jiang

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Massive experiments are conducted under various sampling patterns and acceleration rates, whose results demonstrate that, without any sophisticated architectures, our IMA outperforms the current cutting-edge methods both visually and numerically. Codes are available as an attachment and will be publicly released.
Researcher Affiliation Academia Jianwei Zheng, Xiaomin Yao, Guojiang Shen, Wei Li, and Jiawei Jiang* Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China EMAIL, EMAIL
Pseudocode No The paper describes the model optimization and network design using mathematical equations and descriptive text, but it does not include a clearly labeled pseudocode or algorithm block.
Open Source Code Yes Codes are available as an attachment and will be publicly released.
Open Datasets Yes We evaluate our proposal on two publicly available datasets: IXI (578 registered T2 and PD image pairs, 256 256) and knee fast MRI (240 PD image pairs, 320 320).
Dataset Splits Yes The data is split into training, validation, and testing sets (7:1:2).
Hardware Specification Yes All experiments are conducted using Py Torch on an NVIDIA Ge Force RTX 3090 GPU.
Software Dependencies No The paper mentions "Py Torch" but does not specify a version number or any other software dependencies with their versions.
Experiment Setup Yes For our IMA, we use l1-norm loss, the Adam optimizer (0.9, 0.999), 100 epochs, an initial learning rate of 10 4, batch size of 1, ratio=0.9, γ = 0.5, δ = 3, and T=12.