医学人工智能研究依赖于高质量、大样本、标准化的数据，以及开源的算法代码和软件。本部将适时提供有利于学术交流的算法代码、开源脱敏的数据和模型、智能医学相关的软件和教程，后续的项目将持续更新：
Project 1: semantic segmentation of lumbar CT
Lumbar disc herniation (LDH) is well presented in high-resolution CT. The segmentations of soft tissue (e.g. disc, nerve) could also benefit the surgical planning of spinal interventions. The dataset consists of 27 thin-layer lumbar CT with LDH, each containing at least 5 lumbar vertebrae. All images are stored in the nearly raw raster data (NRRD) format.
If you use this dataset in your work, you should cite the following paper:
Fan G., Liu H., Wu Z., Li Y., Feng C., Wang D., Luo J., Wells W M., He S., (2019). Deep Learning-Based Automatic Segmentation of Lumbosacral Nerves on CT for Spinal Intervention: A Translational Study. Am J Neuroradiol, 40, 1074-1081.
To obtain the dataset in this project, please send your request to the email: fanguoxin@sustech-hospital.com
To obtain the code in this project, you can directly click on https://github.com/Huatsing-Lau/Unet3D-bagging--CT-Spine-Segmentation
