OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

Jia-Xin Zhuang; Xiansong Huang; Yang Yang; Jiancong Chen; Yue Yu; Wei Gao; Ge Li; Jie Chen; Tong Zhang

OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

Image and Video Processing 2022-09-09 v2 Computer Vision and Pattern Recognition Machine Learning

Authors: Jia-Xin Zhuang , Xiansong Huang , Yang Yang , Jiancong Chen , Yue Yu , Wei Gao , Ge Li , Jie Chen , Tong Zhang

Abstract

In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms. Various medical image analysis methods, including 2D/3D medical image classification, segmentation, localisation, and detection, have been included in the toolbox with PyTorch and/or MindSpore implementations under heterogeneous NVIDIA and Huawei Ascend computing systems. To our best knowledge, OpenMedIA is the first open-source algorithm library providing compared PyTorch and MindSpore implementations and results on several benchmark datasets. The source codes and models are available at https://git.openi.org.cn/OpenMedIA.

Keywords

medical image registration

Cite

@article{arxiv.2208.05616,
  title  = {OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms},
  author = {Jia-Xin Zhuang and Xiansong Huang and Yang Yang and Jiancong Chen and Yue Yu and Wei Gao and Ge Li and Jie Chen and Tong Zhang},
  journal= {arXiv preprint arXiv:2208.05616},
  year   = {2022}
}

Comments

12 pages, 1 figure

OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

Abstract

Keywords

Cite

Comments

Related papers