通讯技术>> PLS-Net>> 返回
项目作者： andreped

项目描述 ：
Reimplementation of the PLS-Net architecture used for lung lobe segmentation in CT
高级语言： Python
项目地址: git://github.com/andreped/PLS-Net.git
创建时间： 2020-11-24T12:25:41Z
项目社区：https://github.com/andreped/PLS-Net
开源协议：MIT License
下载




PLS-Net (PyTorch)


Reimplementation of the PLS-Net architecture used for lung lobe segmentation in CT proposed by Lee et al. (2019).



test
License
Paper

The implementation was made for this study by Bouget et al. (2021). The original implementation can be found here.

Usage

The source code was tested in Python 3.6 with CUDA 10.0.

Clone repo and install requirements

  1. git clone git+https://github.com/andreped/PLS-Net
  2. cd "PLS-Net"
  3. pip install -r requirements.txt

Define network

  1. from PLS_pytorch import PLS
  2. network = PLS()

(Alternatively) in PyTorch-Lightning:

  1. from PLS_lightning import PLS
  2. network = PLS()

Disclaimer: Note that the Lightning implementation contains some hardcoded setup and Dataloaders, and thus only serves as an example. However, PyTorch implementation should work out-of-the-box.

How to cite

If the source code is used in any scientific publication, please, cite the following papers:

  1. @article{bouget2021code,
  2.   author = {David Bouget and Andr{\'e} Pedersen and Sayied Abdol Mohieb Hosainey and Johanna Vanel and Ole Solheim and Ingerid Reinertsen},
  3.   title = {{Fast meningioma segmentation in T1-weighted magnetic resonance imaging volumes using a lightweight 3D deep learning architecture}},
  4.   volume = {8},
  5.   journal = {Journal of Medical Imaging},
  6.   number = {2},
  7.   publisher = {SPIE},
  8.   pages = {024002},
  9.   keywords = {three-dimensional segmentation, deep learning, meningioma, magnetic resonance imaging, clinical diagnosis, Magnetic resonance imaging, Image segmentation, Tumors, Brain, 3D image processing, 3D modeling, Image resolution, Data modeling, Neural networks, Surgery},
  10.   year = {2021},
  11.   doi = {10.1117/1.JMI.8.2.024002},
  12.   url = {https://doi.org/10.1117/1.JMI.8.2.024002}
  13. }
  1. @misc{lee2019plsnet,
  2.   author = {Lee, Hoileong and Matin, Tahreema and Gleeson, Fergus and Grau, Vicente},
  3.   title = {{Efficient 3D Fully Convolutional Networks for Pulmonary Lobe Segmentation in CT Images}},
  4.   publisher = {arXiv},
  5.   year = {2019},
  6.   copyright = {arXiv.org perpetual, non-exclusive license},
  7.   keywords = {Image and Video Processing (eess.IV), Computer Vision and Pattern Recognition (cs.CV), FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Computer and information sciences, FOS: Computer and information sciences},
  8.   doi = {10.48550/ARXIV.1909.07474},
  9.   url = {https://arxiv.org/abs/1909.07474}
  10. }