lamansilla/nih_chest_xray14_segmentations

Segmentations for NIH Chest-XRay14 dataset

NIH Chest-XRay14 segmentations

Anatomical segmentation masks produced for the NIH Chest-XRay14 dataset using AC-RegNet and a multi-atlas segmentation model.

Content

• segmentations.tar.gz.*: Files containing the anatomical segmentation masks.
• rca_dice_scores.csv: File containing the Dice scores estimated with Reverse Classification Accuracy (RCA) for the segmentation masks.

To extract all segmentation masks you can use the cat command to first join the tar blocks and then the tar command to extract the entire file:

cat segmentations.tar.gz.* | tar xzvf -

Dataset Metadata

The following table is necessary for this dataset to be indexed by search engines such as Google Dataset Search.

name	NIH Chest-XRay14 segmentations
url	https://github.com/lucasmansilla/NIH_chest_xray14_segmentations
sameAs	https://github.com/lucasmansilla/NIH_chest_xray14_segmentations
description	Anatomical segmentation masks of lung and heart produced for the NIH Chest-XRay14 dataset using AC-RegNet with a multi-atlas segmentation model. If you use source code or results from this repository in your publication, please cite our paper: Mansilla, L., Milone, D. H., & Ferrante, E. (2020). Learning deformable registration of medical images with anatomical constraints. Neural Networks, 124, 269-279. 
citation	Mansilla, L., Milone, D. H., & Ferrante, E. (2020). Learning deformable registration of medical images with anatomical constraints. Neural Networks, 124, 269-279.
datePublished	2019-08-08
license	property value name MIT License url https://choosealicense.com/licenses/mit/

Reference

• Mansilla, L., Milone, D. H., & Ferrante, E. (2020). Learning deformable registration of medical images with anatomical constraints. Neural Networks, 124, 269-279.

License

MIT