Open Source


2021-04-12: SAINT (tool for super resolution)

This is the pypi pakage for the SAINT (Spatially Aware Interpolation NeTwork for Medical Slice Synthesis), you can execute the command “pip install py_saint” to install it. Just follow the description( if you have any questions while you are using this pakage.

Citation: C. Peng, W.-A. Lin, H. Liao, R. Chellappa, S. Kevin Zhou, “SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis,” in IEEE CVPR, pp. 7747-7756, 2020.


· CTPelvic1K

Resources of the paper “Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models”.

· CTFilm20K CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models DATASET: LINK passwd: 7ou3

· CTSpine1K

Resources of the paper “CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography”.


· DecGAN: Chest X-ray Bone Suppression

DecGAN decomposes X-ray into separate components by taking advantage of the unpaired 3D knowledge from CT in the framework of the generative adversarial network (GAN).

· DuDoNet

Code of the preparing metal artifact dataset in DuDoNet and DuDoNet++.

· Cuda Spatial Deform

A fast tool to do image augmentation by CUDA on GPU.

· Miss the point

Code of the paper “Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection”.

· Universal U-Net

Code of the paper: “3D U2-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation.”

· Marginal and Exclusion Loss

Code of the proposed Marginal loss and exclusion loss for partially supervised multi-organ segmentation.

· Bounding Map

Code of the implementation of Bounding Map in MVP-Net.