uci-cbcl / DeepLung

WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"
GNU General Public License v3.0
153 stars 54 forks source link

ground truth images #10

Closed monjoybme closed 5 years ago

monjoybme commented 5 years ago

Your study is very impressive. Could you share a link to download ground truth images?

wentaozhu commented 5 years ago

LUNA16 dataset https://luna16.grand-challenge.org/data/ LIDC_IDRI dataset https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI

monjoybme commented 5 years ago

for LUNA16 download link is not working. It will be helpful if you can share ground truth dataset.

wentaozhu commented 5 years ago

https://luna16.grand-challenge.org/download/

You need to register first to get the dataset. I am sorry that I cannot share the original dataset. Even for the processed dataset, it is too big to share. Try to register first.

monjoybme commented 5 years ago

Thanks, by the way, this download link is working http://academictorrents.com/collection/luna-lung-nodule-analysis-16---isbi-2016-challenge. The dataset contains "annotations.csv" file. Did you extract ground truth images using the .csv file and CT images and after that fed into the deep learning model?

wentaozhu commented 5 years ago

You may read the paper to get a general idea of the task https://arxiv.org/pdf/1801.09555.pdf

monjoybme commented 5 years ago

Thanks