DenseVNet Multi-organ Segmentation on Abdominal CT

This dataset includes the multi-organ abdominal CT reference segmentations publicly released in conjunction with the IEEE Transactions on Medical Imaging paper "Automatic Multi-organ Segmentation on Abdominal CT with Dense V-networks" [1].

The data comprises reference segmentations for 90 abdominal CT images delineating multiple organs: the spleen, left kidney, gallbladder, esophagus, liver, stomach, pancreas and duodenum.

The abdominal CT images and some of the reference segmentations were drawn from two data sets: The Cancer Image Archive (TCIA) Pancreas-CT data set [2-4] and the Beyond the Cranial Vault (BTCV) Abdomen data set [5-6]. The Pancreas-CT data set comprises abdominal CT acquired at the National Institutes of Health Clinical Center from pre-nephrectomy healthy kidney donors or patients with neither major abdominal pathologies nor pancreatic cancer lesions. Segmentations of the pancreas are included with this data set; images were manually labeled slice-by-slice by a medical student, and verified/modified by an experienced radiologist. The BTCV data set comprises abdominal CT acquired at the Vanderbilt University Medical Center from metastatic liver cancer patients or post-operative ventral hernia patients. Segmentations of the spleen, right and left kidney, gallbladder, esophagus, liver, stomach, aorta, inferior vena cava, portal vein and splenic vein, pancreas, right adrenal gland, left adrenal gland are included in this data set; images were manually labeled by two experienced undergraduate students, and verified by a radiologist on a volumetric basis using the MIPAV software.

Segmentations that were not present in the original data sets were performed interactively using Matlab 2015b and ITK-SNAP 3.2 by an image research fellow under the supervision of a board-certified radiologist with 8 years of experience in gastrointestinal CT and MRI image interpretation. Segmentations that were present in the original data sets were edited to ensure a consistent segmentation protocol across the data set.

Terms of use

The terms of use of this data set include the terms of use of both the TCIA Pancreas-CT data set (see tabs for data links and terms of use) and the Beyond the Cranial Vault (BTCV) Abdomen data set (terms of use; after registration, you can access the data). If you use these reference segmentations, please cite the above manuscript and the references below. Because these data include manual segmentations of images from the Beyond the Cranial Vault challenge test data, they may not be used to develop submissions for the challenge.

References

[1] Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K, Davidson B, Pereira SP, Clarkson MJ, Barratt DC. Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Transactions on Medical Imaging, 2018.

[2] Roth HR, Farag A, Turkbey EB, Lu L, Liu J, and Summers RM. (2016). Data From Pancreas-CT. The Cancer Imaging Archive. http://doi.org/10.7937/K9/TCIA.2016.tNB1kqBU

[3] Roth HR, Lu L, Farag A, Shin H-C, Liu J, Turkbey EB, Summers RM. DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation. N. Navab et al. (Eds.): MICCAI 2015, Part I, LNCS 9349, pp. 556–564, 2015. http://arxiv.org/pdf/1506.06448.pdf

[4] Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. http://doi.org/10.1007/s10278-013-9622-7

[5] Xu Z, Lee CP, Heinrich MP, Modat M, Rueckert D, Ourselin S, Abramson RG, and Landman BA, “Evaluation of six registration methods for the human abdomen on clinically acquired CT,” IEEE Trans. Biomed. Eng., vol. 63, no. 8, pp. 1563–1572, 2016.http://doi.org/10.1109/TBME.2016.2574816

[6] Landman BA, Xu Z, Igelsias JE, Styner M, Langerak TR, and Klein A, “MICCAI multi-atlas labeling beyond the cranial vault - workshop and challenge,” 2015, https://doi.org/10.7303/syn3193805

File format

1. spleen
2. right kidney*
3. left kidney
4. gallbladder
5. esophagus
6. liver
7. stomach
8. aorta*
9. inferior vena cava*
10. portal vein and splenic vein*
11. pancreas
12. right adrenal gland*
13. left adrenal gland*
14. duodenum

Subjects included in the dataset

The data comprises segmentation volumes for 90 cases, and the cropping coordinates (cropping.csv) used in the manuscript. The abdominal CT can be obtained from the links above. The reference standard segmentations may be incomplete outside of the specified cropping region. The cases are listed by their subject identifiers in their original data set: