3D Neural Architecture Search (NAS) for Pulmonary Nodules Classification

Hanliang Jiang, Fuhao Shen, Fei Gao*, Weidong Han. Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification. Pattern Recognition, 113: 107825, 2021.

@article{Jiang2021naslung,
author = {Hanliang Jiang and Fuhao Shen and Fei Gao and Weidong Han},
title = {Learning efficient, explainable and discriminative representations for pulmonary nodules classification},
journal = {Pattern Recognition},
volume = {113},
pages = {107825},
year = {2021},
issn = {0031-3203},
doi = {https://doi.org/10.1016/j.patcog.2021.107825},
}

[Paper@PR] [Paper@arxiv] [Code@Github]

• Linux or similar environment
• Python 3.7
• Pytorch 0.4.1
• NVIDIA GPU + CUDA CuDNN

• Clone this repo:

  git clone https://github.com/fei-hdu/NAS-Lung
  cd NAS-Lung

• Install PyTorch 0.4+ and torchvision from Pytorch and other dependencies (e.g., visdom and dominate). You can install all the dependencies by

  pip install -r requirments.txt

• Download Dataset LIDC-IDRI

python search_main.py --train_data_path {train_data_path}  --test_data_path {test_data_path} --save_module_path {save_module_path}

• Train a model

  sh run_training.sh

• Test a model

  python test.py --test_data_path {test_data_path} --preprocess_path {preprocess_path} --model_path {model_path}

• LIDC-IDRI

• our final result can be download:Google Drive

• Best practice for training and testing your models.
• Feel free to ask any questions about coding. Fuhao Shen, [email protected]

• Our work/code is inspired by Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search, CVPR 2019.

• S. Armato III, G. et al., Data from LIDC-IDRI, The Cancer Imaging . LIDC-IDRI.
• X. Li, Y. Zhou, Z. Pan, J. Feng, Partial order pruning: For best speed/accuracy trade-off in neural architecture search (2019) 9145–9153.
• S. Woo, J. Park, J.-Y. Lee, I. So Kweon, CBAM: Convolutional block attention module, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 3–19.
• W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, L. Song, Sphereface: Deep hypersphere embedding for face recognition, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
• T. Elsken, J. H. Metzen, F. Hutter, Neural architecture search: A survey, Journal of Machine Learning Research 20 (55) (2019) 1–21.
• W. Zhu, C. Liu, W. Fan, X. Xie, Deeplung: Deep 3d dual path nets for automated pulmonary nodule detection and classification, in: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2018, pp. 673–681.