NIH Pancreas-CT Dataset
Holger R. Roth and Amal Farag and Evrim B. Turkbey and Le Lu and Jiamin Liu and Ronald M. Summers.

Pancreas-CT (164 files)
TCIA_pancreas_labels-02-05-2017/label0081.nii.gz 63.03kB
TCIA_pancreas_labels-02-05-2017/label0082.nii.gz 65.71kB
TCIA_pancreas_labels-02-05-2017/label0079.nii.gz 75.31kB
TCIA_pancreas_labels-02-05-2017/label0080.nii.gz 56.08kB
TCIA_pancreas_labels-02-05-2017/label0078.nii.gz 90.32kB
TCIA_pancreas_labels-02-05-2017/label0076.nii.gz 63.25kB
TCIA_pancreas_labels-02-05-2017/label0077.nii.gz 68.15kB
TCIA_pancreas_labels-02-05-2017/label0074.nii.gz 62.26kB
TCIA_pancreas_labels-02-05-2017/label0075.nii.gz 67.09kB
TCIA_pancreas_labels-02-05-2017/label0072.nii.gz 65.42kB
TCIA_pancreas_labels-02-05-2017/label0073.nii.gz 93.32kB
TCIA_pancreas_labels-02-05-2017/label0070.nii.gz 63.84kB
TCIA_pancreas_labels-02-05-2017/label0071.nii.gz 61.44kB
TCIA_pancreas_labels-02-05-2017/label0068.nii.gz 64.95kB
TCIA_pancreas_labels-02-05-2017/label0069.nii.gz 66.48kB
TCIA_pancreas_labels-02-05-2017/label0066.nii.gz 63.27kB
TCIA_pancreas_labels-02-05-2017/label0067.nii.gz 64.10kB
TCIA_pancreas_labels-02-05-2017/label0064.nii.gz 64.91kB
TCIA_pancreas_labels-02-05-2017/label0065.nii.gz 64.37kB
TCIA_pancreas_labels-02-05-2017/label0062.nii.gz 63.42kB
TCIA_pancreas_labels-02-05-2017/label0063.nii.gz 90.47kB
TCIA_pancreas_labels-02-05-2017/label0060.nii.gz 90.70kB
TCIA_pancreas_labels-02-05-2017/label0061.nii.gz 72.53kB
TCIA_pancreas_labels-02-05-2017/label0058.nii.gz 94.77kB
TCIA_pancreas_labels-02-05-2017/label0059.nii.gz 59.53kB
TCIA_pancreas_labels-02-05-2017/label0056.nii.gz 64.68kB
TCIA_pancreas_labels-02-05-2017/label0057.nii.gz 69.20kB
TCIA_pancreas_labels-02-05-2017/label0054.nii.gz 66.13kB
TCIA_pancreas_labels-02-05-2017/label0055.nii.gz 63.24kB
TCIA_pancreas_labels-02-05-2017/label0052.nii.gz 66.64kB
TCIA_pancreas_labels-02-05-2017/label0053.nii.gz 90.80kB
TCIA_pancreas_labels-02-05-2017/label0050.nii.gz 88.85kB
TCIA_pancreas_labels-02-05-2017/label0051.nii.gz 61.77kB
TCIA_pancreas_labels-02-05-2017/label0049.nii.gz 67.61kB
TCIA_pancreas_labels-02-05-2017/label0047.nii.gz 59.72kB
TCIA_pancreas_labels-02-05-2017/label0048.nii.gz 61.84kB
TCIA_pancreas_labels-02-05-2017/label0046.nii.gz 61.53kB
TCIA_pancreas_labels-02-05-2017/label0044.nii.gz 141.52kB
TCIA_pancreas_labels-02-05-2017/label0045.nii.gz 64.38kB
TCIA_pancreas_labels-02-05-2017/label0043.nii.gz 64.13kB
TCIA_pancreas_labels-02-05-2017/label0041.nii.gz 70.88kB
TCIA_pancreas_labels-02-05-2017/label0042.nii.gz 90.02kB
TCIA_pancreas_labels-02-05-2017/label0040.nii.gz 74.55kB
TCIA_pancreas_labels-02-05-2017/label0038.nii.gz 64.25kB
TCIA_pancreas_labels-02-05-2017/label0039.nii.gz 60.76kB
TCIA_pancreas_labels-02-05-2017/label0037.nii.gz 62.14kB
TCIA_pancreas_labels-02-05-2017/label0035.nii.gz 67.93kB
TCIA_pancreas_labels-02-05-2017/label0036.nii.gz 68.26kB
TCIA_pancreas_labels-02-05-2017/label0034.nii.gz 64.43kB
Too many files! Click here to view them all.
Type: Dataset
Tags:

Bibtex:
@article{,
title= {NIH Pancreas-CT Dataset},
keywords= {},
journal= {},
author= {Holger R. Roth and Amal Farag and Evrim B. Turkbey and Le Lu and Jiamin Liu and Ronald M. Summers. },
year= {},
url= {http://doi.org/10.7937/K9/TCIA.2016.tNB1kqBU},
license= {Creative Commons Attribution 3.0 Unported License},
abstract= {### Summary

The National Institutes of Health Clinical Center performed 82 abdominal contrast enhanced 3D CT scans (~70 seconds after intravenous contrast injection in portal-venous) from 53 male and 27 female subjects.  Seventeen of the subjects are healthy kidney donors scanned prior to nephrectomy.  The remaining 65 patients were selected by a radiologist from patients who neither had major abdominal pathologies nor pancreatic cancer lesions.  Subjects' ages range from 18 to 76 years with a mean age of 46.8 ± 16.7. The CT scans have resolutions of 512x512 pixels with varying pixel sizes and slice thickness between 1.5 − 2.5 mm, acquired on Philips and Siemens MDCT scanners (120 kVp tube voltage).

A medical student manually performed slice-by-slice segmentations of the pancreas as ground-truth and these were verified/modified by an experienced radiologist.

The images were processed into nii files using the following script:

```
for i in `ls . | grep PAN`; do 
   echo $i; 
   dcm2niix -vox 1 -z y -o ./data/ -m y -s y -f %n $i
done
```

### Citation

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. 

### Examples

![](https://i.imgur.com/4aZNgw6.gifv)

![](https://i.imgur.com/kfhhH7x.png)

![](https://i.imgur.com/kGbz9hl.png)

},
superseded= {},
terms= {}
}


Send Feedback