OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms
This provides a standardized resource for researchers and practitioners in medical imaging to compare methods across heterogeneous AI platforms, though it is incremental as it builds on existing tools and benchmarks.
The authors introduced OpenMedIA, an open-source toolbox for medical image analysis that includes deep learning methods for tasks like classification and segmentation, implemented on PyTorch and MindSpore across NVIDIA and Huawei Ascend platforms, and it is the first to provide comparative implementations and results on benchmark datasets.
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.