Size and Texture-Based Classification of Lung Tumors with 3D CNNs
Abstract
In this paper, we explore the use of current deep learning methods in the field of computer-aided diagnosis (CAD). Specifically we propose the use of 3D convolutional neural nets (CNN) in classifying lung nodules based off of their appearance in CT scans. We explore the choices of network architectures, learning parameters and problem formulations. Comparing these results to other methods we show that the proposed method has close to perfect performance on the publicly available LIDC dataset, achieving an AUC of 0:9685 and a false positive rate of 0:46% with a true positive rate of 90% where the ground truth is the expert opinion of a radiologist.
Cite
Text
Luo et al. "Size and Texture-Based Classification of Lung Tumors with 3D CNNs." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017. doi:10.1109/WACV.2017.95Markdown
[Luo et al. "Size and Texture-Based Classification of Lung Tumors with 3D CNNs." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017.](https://mlanthology.org/wacv/2017/luo2017wacv-size/) doi:10.1109/WACV.2017.95BibTeX
@inproceedings{luo2017wacv-size,
title = {{Size and Texture-Based Classification of Lung Tumors with 3D CNNs}},
author = {Luo, Zhihao and Brubaker, Marcus A. and Brudno, Michael},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2017},
pages = {806-814},
doi = {10.1109/WACV.2017.95},
url = {https://mlanthology.org/wacv/2017/luo2017wacv-size/}
}