LCCST

[Yajun Liu], [Zenghui Zhang], [Jiang Yue], [Dongying Li], [Wenxian Yu]

Pytorch implementation of our paper: "LCCST: ".

Contents

• Abstract
• Introduction
• Requirements
• Datasets
• Usage
• Acknowledgements

Abstract

Introduction

Official code for "LCCST".

Requirements

This repository is based on PyTorch 1.8.0, CUDA 11.3 and Python 3.8.10. All experiments in our paper were conducted on NVIDIA Quadro RTX 6000 24GB GPU with an identical experimental setting.

Datasets

Preprocess: refer to the image pre-processing method in CoraNet and BCP for the Pancreas dataset, Left atrium and ACDC dataset. The dataloaders folder contains the necessary code to preprocess the Left atrium and ACDC dataset. Pancreas pre-processing code can be got at CoraNet.

Dataset split: The ./Datasets folder contains the information about the train-test split for all three datasets.

Usage

We provide code, data_split and models (Include pre-trained models and fully trained models) for Pancreas, LA and ACDC dataset.

Data could be got at Pancreas, LA and ACDC.

To train a model,

python ./code/LA_train.py  #for LA training

To test a model,

python ./code/test_LA.py  #for LA testing

Acknowledgements

Our code is largely based on BCP and SS-Net. Thanks for these authors for their valuable work, hope our work can also contribute to related research.