This repository provides the code and models files for multi-organ segmentation in abdominal CT using cascaded 3D U-Net models. The models are described in:
"Hierarchical 3D fully convolutional networks for multi-organ segmentation" Holger R. Roth, Hirohisa Oda, Yuichiro Hayashi, Masahiro Oda, Natsuki Shimizu, Michitaka Fujiwara, Kazunari Misawa, Kensaku Mori https://arxiv.org/abs/1704.06382
Annotated pancreas CT data
Available at TCIA under collection Pancreas-CT.
Anatomy-specific classification of medical images using deep convolutional nets
Holger R. Roth, Christopher T. Lee, Hoo-Chang Shin, Ari Seff, Lauren Kim, Jianhua Yao, Le Lu, Ronald M. Summers, In Proceedings: IEEE International Symposium on Biomedical Imaging, April 16-19, 2015, New York Marriott at Brooklyn Bridge, NY, USA
Software/code: CNNSliceClassifier
Annotated lymph node CT data
90 mediastinal and 86 abdominal CT cases with annotated lymph node locations can be downloaded at:
Just click "Search Images" and select "CT lymph nodes" from the collection list. Add to basket and download.
The annotation files including lymph node sizes can be downloaded here (see section "Related Data"). Furthermore, there are ground truth segmentation masks of lymph nodes, plus true and false positive candidate CADe marks available for download in the same section.
The annotations include a folder for each case with text files of voxel indices, physical coordinates and a MITK point set file (.mps), which can be visualized using the MITK workbench (Note: only release 2014.10.0 and later supports visualization of point set files using the "point set interaction plugin").
Please cite our papers in any publications resulting from using this data: bibtex
Related software/code: LymphNodeRFCNNPipeline
Please contact me if you have any questions.
Project site & Data with registration reference standard: http://cmic.cs.ucl.ac.uk/CTC/