Segmentation for medical image.

Overview

EfficientSegmentation

Introduction

EfficientSegmentation is an open source, PyTorch-based segmentation framework for 3D medical image.

Features

  • A whole-volume-based coarse-to-fine segmentation framework. The segmentation network is decomposed into different components, including encoder, decoder and context module. Anisotropic convolution block and anisotropic context block are designed for efficient and effective segmentation.
  • Pre-process data in multi-process. Distributed and Apex training support. Postprocess is performed asynchronously in inference stage.

Benchmark

Task Architecture Parameters(MB) Flops(GB) DSC NSC Inference time(s) GPU memory(MB)
FLARE21 BaseUNet 11 812 0.908 0.837 0.92 3183
FLARE21 EfficientSegNet 9 333 0.919 0.848 0.46 2269

Installation

Installation by docker image

  • Download the docker image.
  link: https://pan.baidu.com/s/1UkMwdntwAc5paCWHoZHj9w 
  password:9m3z
  • Put the abdomen CT image in current folder $PWD/inputs/.
  • Run the testing cases with the following code:
docker image load < fosun_aitrox.tgz
nvidia-docker container run --name fosun_aitrox --rm -v $PWD/inputs/:/workspace/inputs/ -v $PWD/outputs/:/workspace/outputs/ fosun_aitrox:latest /bin/bash -c "sh predict.sh"'

Installation step by step

Environment

  • Ubuntu 16.04.12
  • Python 3.6+
  • Pytorch 1.5.0+
  • CUDA 10.0+

1.Git clone

git clone https://github.com/Shanghai-Aitrox-Technology/EfficientSegmentation.git

2.Install Nvidia Apex

  • Perform the following command:
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir ./

3.Install dependencies

pip install -r requirements.txt

Get Started

preprocessing

  1. Download FLARE21, resulting in 361 training images and masks, 50 validation images.
  2. Copy image and mask to 'FlareSeg/dataset/' folder.
  3. Edit the 'FlareSeg/data_prepare/config.yaml'. 'DATA_BASE_DIR'(Default: FlareSeg/dataset/) is the base dir of databases. If set the 'IS_SPLIT_5FOLD'(Default: False) to true, 5-fold cross-validation datasets will be generated.
  4. Run the data preprocess with the following command:
python FlareSeg/data_prepare/run.py

The image data and lmdb file are stored in the following structure:

DATA_BASE_DIR directory structure:
├── train_images
   ├── train_000_0000.nii.gz
   ├── train_001_0000.nii.gz
   ├── train_002_0000.nii.gz
   ├── ...
├── train_mask
   ├── train_000.nii.gz
   ├── train_001.nii.gz
   ├── train_002.nii.gz
   ├── ...
└── val_images
    ├── validation_001_0000.nii.gz
    ├── validation_002_0000.nii.gz
    ├── validation_003_0000.nii.gz
    ├── ...
├── file_list
    ├──'train_series_uids.txt', 
    ├──'val_series_uids.txt',
    ├──'lesion_case.txt',
├── db
    ├──seg_raw_train         # The 361 training data information.
    ├──seg_raw_test          # The 50 validation images information.
    ├──seg_train_database    # The default training database.
    ├──seg_val_database      # The default validation database.
    ├──seg_pre-process_database # Temporary database.
    ├──seg_train_fold_1
    ├──seg_val_fold_1
├── coarse_image
    ├──160_160_160
          ├── train_000.npy
          ├── train_001.npy
          ├── ...
├── coarse_mask
    ├──160_160_160
          ├── train_000.npy
          ├── train_001.npy
          ├── ...
├── fine_image
    ├──192_192_192
          ├── train_000.npy
          ├── train_001.npy
          ├──  ...
├── fine_mask
    ├──192_192_192
          ├── train_000.npy
          ├── train_001.npy
          ├── ...

The data information is stored in the lmdb file with the following format:

{
    series_id = {
        'image_path': data.image_path,
        'mask_path': data.mask_path,
        'smooth_mask_path': data.smooth_mask_path,
        'coarse_image_path': data.coarse_image_path,
        'coarse_mask_path': data.coarse_mask_path,
        'fine_image_path': data.fine_image_path,
        'fine_mask_path': data.fine_mask_path
    }
}

Training

Remark: Coarse segmentation is trained on Nvidia GeForce 2080Ti(Number:8) in the experiment, while fine segmentation on Nvidia A100(Number:4). If you use different hardware, please set the "ENVIRONMENT.NUM_GPU", "DATA_LOADER.NUM_WORKER" and "DATA_LOADER.BATCH_SIZE" in 'FlareSeg/coarse_base_seg/config.yaml' and 'FlareSeg/fine_efficient_seg/config.yaml' files.

Coarse segmentation:

  • Edit the 'FlareSeg/coarse_base_seg/config.yaml'
  • Train coarse segmentation with the following command:
cd FlareSeg/coarse_base_seg
sh run.sh

Fine segmentation:

  • Edit the 'FlareSeg/fine_efficient_seg/config.yaml'.
  • Edit the 'FlareSeg/fine_efficient_seg/run.py', set the 'tune_params' for different experiments.
  • Train fine segmentation with the following command:
cd  FlareSeg/fine_efficient_seg
sh run.sh

Inference:

  • The model weights are stored in 'FlareSeg/model_weights/'.
  • Run the inference with the following command:
sh predict.sh

Contact

This repository is currently maintained by Fan Zhang ([email protected]) and Yu Wang ([email protected])

Citation

Acknowledgement

Scripts and a shader to get you started on setting up an exported Koikatsu character in Blender.

KK Blender Shader Pack A plugin and a shader to get you started with setting up an exported Koikatsu character in Blender. The plugin is a Blender add

166 Jan 01, 2023
Supervised Contrastive Learning for Product Matching

Contrastive Product Matching This repository contains the code and data download links to reproduce the experiments of the paper "Supervised Contrasti

Web-based Systems Group @ University of Mannheim 18 Dec 10, 2022
Source code of the paper "Deep Learning of Latent Variable Models for Industrial Process Monitoring".

Source code of the paper "Deep Learning of Latent Variable Models for Industrial Process Monitoring".

Xiangyin Kong 7 Nov 08, 2022
Model Quantization Benchmark

Introduction MQBench is an open-source model quantization toolkit based on PyTorch fx. The envision of MQBench is to provide: SOTA Algorithms. With MQ

500 Jan 06, 2023
How to Train a GAN? Tips and tricks to make GANs work

(this list is no longer maintained, and I am not sure how relevant it is in 2020) How to Train a GAN? Tips and tricks to make GANs work While research

Soumith Chintala 10.8k Dec 31, 2022
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ALBERT ***************New March 28, 2020 *************** Add a colab tutorial to run fine-tuning for GLUE datasets. ***************New January 7, 2020

Google Research 3k Jan 01, 2023
a reimplementation of LiteFlowNet in PyTorch that matches the official Caffe version

pytorch-liteflownet This is a personal reimplementation of LiteFlowNet [1] using PyTorch. Should you be making use of this work, please cite the paper

Simon Niklaus 365 Dec 31, 2022
UFT - Universal File Transfer With Python

UFT 2.0.0 UFT (Universal File Transfer) is a CLI tool , which can be used to upl

Merwin 1 Feb 18, 2022
An end-to-end machine learning library to directly optimize AUC loss

LibAUC An end-to-end machine learning library for AUC optimization. Why LibAUC? Deep AUC Maximization (DAM) is a paradigm for learning a deep neural n

Andrew 75 Dec 12, 2022
This repo includes our code for evaluating and improving transferability in domain generalization (NeurIPS 2021)

Transferability for domain generalization This repo is for evaluating and improving transferability in domain generalization (NeurIPS 2021), based on

gordon 9 Nov 29, 2022
Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21.

Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21. We optimized wind turbine placement in a wind farm, subject to wake effects, using Q-learni

Manasi Sharma 2 Sep 27, 2022
202 Jan 06, 2023
Can we learn gradients by Hamiltonian Neural Networks?

Can we learn gradients by Hamiltonian Neural Networks? This project was carried out as part of the Optimization for Machine Learning course (CS-439) a

2 Aug 22, 2022
Implementation of Monocular Direct Sparse Localization in a Prior 3D Surfel Map (DSL)

DSL Project page: https://sites.google.com/view/dsl-ram-lab/ Monocular Direct Sparse Localization in a Prior 3D Surfel Map Authors: Haoyang Ye, Huaiya

Haoyang Ye 93 Nov 30, 2022
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng Internati

Princeton Vision & Learning Lab 115 Jan 04, 2023
A general-purpose encoder-decoder framework for Tensorflow

READ THE DOCUMENTATION CONTRIBUTING A general-purpose encoder-decoder framework for Tensorflow that can be used for Machine Translation, Text Summariz

Google 5.5k Jan 07, 2023
NCVX (NonConVeX): A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning.

The source code is temporariy removed, as we are solving potential copyright and license issues with GRANSO (http://www.timmitchell.com/software/GRANS

SUN Group @ UMN 28 Aug 03, 2022
Black box hyperparameter optimization made easy.

BBopt BBopt aims to provide the easiest hyperparameter optimization you'll ever do. Think of BBopt like Keras (back when Theano was still a thing) for

Evan Hubinger 70 Nov 03, 2022
ML-Decoder: Scalable and Versatile Classification Head

ML-Decoder: Scalable and Versatile Classification Head Paper Official PyTorch Implementation Tal Ridnik, Gilad Sharir, Avi Ben-Cohen, Emanuel Ben-Baru

189 Jan 04, 2023
PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Sharpness-aware Quantization for Deep Neural Networks This is the official repository for our paper: Sharpness-aware Quantization for Deep Neural Netw

Zhuang AI Group 30 Dec 19, 2022