This is the source code of the 1st place solution for segmentation task (with Dice 90.32%) in 2021 CCF BDCI challenge.

Overview

1st place solution in CCF BDCI 2021 ULSEG challenge

This is the source code of the 1st place solution for ultrasound image angioma segmentation task (with Dice 90.32%) in 2021 CCF BDCI challenge.

[Challenge leaderboard πŸ† ]

1 Pipeline of our solution

Our solution includes data pre-processing, network training, ensemble inference and data post-processing.

drawing

Ultrasound images of hemangioma segmentation framework

1.1 Data pre-processing

To improve our performance on the leaderboard, 5-fold cross validation is used to evaluate the performance of our proposed method. In our opinion, it is necessary to keep the size distribution of tumor in the training and validation sets. We calculate the tumor area for each image and categorize the tumor size into classes: 1) less than 3200 pixels, 2) less than 7200 pixels and greater than 3200 pixels, and 3) greater than 7200 pixels. These two thresholds, 3200 pixels and 7200 pixels, are close to the tertiles. We divide images in each size grade group into 5 folds and combined different grades of single fold into new single fold. This strategy ensured that final 5 folds had similar size distribution.

drawing

Tumors of different sizes

1.2 Network training

Due to the small size of the training set, for this competition, we chose a lightweight network structure: Linknet with efficientnet-B6 encoder. Following methods are performed in data augmentation (DA): 1) horizontal flipping, 2) vertical flipping, 3) random cropping, 4) random affine transformation, 5) random scaling, 6) random translation, 7) random rotation, and 8) random shearing transformation. In addition, one of the following methods was randomly selected for enhanced data augmentation (EDA): 1) sharpening, 2) local distortion, 3) adjustment of contrast, 4) blurring (Gaussian, mean, median), 5) addition of Gaussian noise, and 6) erasing.

1.3 Ensemble inference

We ensemble five models (five folds) and do test time augmentation (TTA) for each model. TTA generally improves the generalization ability of the segmentation model. In our framework, the TTA includes vertical flipping, horizontal flipping, and rotation of 180 degrees for the segmentation task.

1.4 Data post-processing

We post-processe the obtained binary mask by removing small isolated points (RSIP) and edge median filtering (EMF) . The edge part of our predicted tumor is not smooth enough, which is not quite in line with the manual annotation of the physician, so we adopt a small trick, i.e., we do a median filtering specifically for the edge part, and the experimental results show that this can improve the accuracy of tumor segmentation.

2 Segmentation results on 2021 CCF BDCI dataset

We test our method on 2021 CCD BDCI dataset (215 for training and 107 for testing). The segmentation results of 5-fold CV based on "Linknet with efficientnet-B6 encoder" are as following:

fold Linknet Unet Att-Unet DeeplabV3+ Efficient-b5 Efficient-b6 Resnet-34 DA EDA TTA RSIP EMF Dice (%)
1 √ 85.06
1 √ √ 84.48
1 √ √ 84.72
1 √ √ 84.93
1 √ √ 86.52
1 √ √ 86.18
1 √ √ 86.91
1 √ √ √ 87.38
1 √ √ √ 88.36
1 √ √ √ √ 89.05
1 √ √ √ √ √ 89.20
1 √ √ √ √ √ √ 89.52
E √ √ √ √ √ √ 90.32

3 How to run this code?

Here, we split the whole process into 5 steps so that you can easily replicate our results or perform the whole pipeline on your private custom dataset.

  • step0, preparation of environment
  • step1, run the script preprocess.py to perform the preprocessing
  • step2, run the script train.py to train our model
  • step3, run the script inference.py to inference the test data.
  • step4, run the script postprocess.py to perform the preprocessing.

You should prepare your data in the format of 2021 CCF BDCI dataset, this is very simple, you only need to prepare: two folders store png format images and masks respectively. You can download them from [Homepage].

The complete file structure is as follows:

  |--- CCF-BDCI-2021-ULSEG-Rank1st
      |--- segmentation_models_pytorch_4TorchLessThan120
          |--- ...
          |--- ...
      |--- saved_model
          |--- pred
          |--- weights
      |--- best_model
          |--- best_model1.pth
          |--- ...
          |--- best_model5.pth
      |--- train_data
          |--- img
          |--- label
          |--- train.csv
      |--- test_data
          |--- img
          |--- predict
      |--- dataset.py
      |--- inference.py
      |--- losses.py
      |--- metrics.py
      |--- ploting.py
      |--- preprocess.py
      |--- postprocess.py
      |--- util.py
      |--- train.py
      |--- visualization.py
      |--- requirement.txt

3.1 Step0 preparation of environment

We have tested our code in following environment:

For installing these, run the following code:

pip install -r requirements.txt

3.2 Step1 preprocessing

In step1, you should run the script and train.csv can be generated under train_data fold:

python preprocess.py \
--image_path="./train_data/label" \
--csv_path="./train_data/train.csv"

3.3 Step2 training

With the csv file train.csv, you can directly perform K-fold cross validation (default is 5-fold), and the script uses a fixed random seed to ensure that the K-fold cv of each experiment is repeatable. Run the following code:

python train.py \
--input_channel=1 \
--output_class=1 \
--image_resolution=256 \
--epochs=100 \
--num_workers=2 \
--device=0 \
--batch_size=8 \
--backbone="efficientnet-b6" \
--network="Linknet" \
--initial_learning_rate=1e-7 \
--t_max=110 \
--folds=5 \
--k_th_fold=1 \
--fold_file_list="./train_data/train.csv" \
--train_dataset_path="./train_data/img" \
--train_gt_dataset_path="./train_data/label" \
--saved_model_path="./saved_model" \
--visualize_of_data_aug_path="./saved_model/pred" \
--weights_path="./saved_model/weights" \
--weights="./saved_model/weights/best_model.pth" 

By specifying the parameter k_th_fold from 1 to folds and running repeatedly, you can complete the training of all K folds. After each fold training, you need to copy the .pth file from the weights path to the best_model folder.

3.4 Step3 inference (test)

Before running the script, make sure that you have generated five models and saved them in the best_model folder. Run the following code:

python inference.py \
--input_channel=1 \
--output_class=1 \
--image_resolution=256 \
--device=0 \
--backbone="efficientnet-b6" \
--network="Linknet" \
--weights1="./saved_model/weights/best_model1.pth" \
--weights2="./saved_model/weights/best_model2.pth" \
--weights3="./saved_model/weights/best_model3.pth" \
--weights4="./saved_model/weights/best_model4.pth" \
--weights5="./saved_model/weights/best_model5.pth" \
--test_path="./test_data/img" \
--saved_path="./test_data/predict" 

The results of the model inference will be saved in the predict folder.

3.5 Step4 postprocessing

Run the following code:

python postprocess.py \
--image_path="./test_data/predict" \
--threshood=50 \
--kernel=20 

Alternatively, if you want to observe the overlap between the predicted result and the original image, we also provide a visualization script visualization.py. Modify the image path in the code and run the script directly.

drawing

Visualization of tumor margins

4 Acknowledgement

  • Thanks to the organizers of the 2021 CCF BDCI challenge.
  • Thanks to the 2020 MICCCAI TNSCUI TOP 1 for making the code public.
  • Thanks to qubvel, the author of smg and ttach, all network and TTA used in this code come from his implement.
Owner
Chenxu Peng
Data Science, Deep Learning
Chenxu Peng
RL Algorithms with examples in Python / Pytorch / Unity ML agents

Reinforcement Learning Project This project was created to make it easier to get started with Reinforcement Learning. It now contains: An implementati

Rogier Wachters 3 Aug 19, 2022
Modified prey-predator system - Modified prey–predator model describes the rate of change for each species by adding coupling terms.

Modified prey-predator system We aim to study the behaviors of the modified prey–predator model and establish the effects of several parameters that p

Seoyoung Oh 1 Jan 02, 2022
Processed, version controlled history of Minecraft's generated data and assets

mcmeta Processed, version controlled history of Minecraft's generated data and assets Repository structure Each of the following branches has a commit

Misode 75 Dec 28, 2022
Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution.

Ubiquitous Knowledge Processing Lab 22 Jan 02, 2023
MQBench Quantization Aware Training with PyTorch

MQBench Quantization Aware Training with PyTorch I am using MQBench(Model Quantization Benchmark)(http://mqbench.tech/) to quantize the model for depl

Ling Zhang 29 Nov 18, 2022
Rl-quickstart - Reinforcement Learning Quickstart

Reinforcement Learning Quickstart To get setup with the repository, git clone ht

UCLA DataRes 3 Jun 16, 2022
Unrolled Generative Adversarial Networks

Unrolled Generative Adversarial Networks Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein arxiv:1611.02163 This repo contains an example notebo

Ben Poole 292 Dec 06, 2022
The hippynn python package - a modular library for atomistic machine learning with pytorch.

The hippynn python package - a modular library for atomistic machine learning with pytorch. We aim to provide a powerful library for the training of a

Los Alamos National Laboratory 37 Dec 29, 2022
Delta Conformity Sociopatterns Analysis - Delta Conformity Sociopatterns Analysis

Delta_Conformity_Sociopatterns_Analysis βˆ†-Conformity is a local homophily measur

2 Jan 09, 2022
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai

Coursera-deep-learning-specialization - Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks an

Aman Chadha 1.7k Jan 08, 2023
An implementation of Geoffrey Hinton's paper "How to represent part-whole hierarchies in a neural network" in Pytorch.

GLOM An implementation of Geoffrey Hinton's paper "How to represent part-whole hierarchies in a neural network" for MNIST Dataset. To understand this

50 Oct 19, 2022
(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

BRNet Introduction This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds,

86 Oct 05, 2022
VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning

VisualGPT Our Paper VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning Main Architecture of Our VisualGPT Downloa

Vision CAIR Research Group, KAUST 140 Dec 28, 2022
Efficient Training of Visual Transformers with Small Datasets

Official codes for "Efficient Training of Visual Transformers with Small Datasets", NerIPS 2021.

Yahui Liu 112 Dec 25, 2022
Send text to girlfriend in the morning

Girlfriend Text Send text to girlfriend (or really anyone with a phone number) in the morning 1. Configure your settings in utils.py. phone_number = "

Paras Adhikary 199 Oct 25, 2022
Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization This is an official implementation of "Feature Stylization and Domain-

22 Sep 22, 2022
A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

This repository contains the similarity metrics designed and evaluated in the paper, and instructions and code to re-run the experiments. Implementation in the deep-learning framework PyTorch

Steffen 86 Dec 27, 2022
Does Pretraining for Summarization Reuqire Knowledge Transfer?

Pretraining summarization models using a corpus of nonsense

Approximately Correct Machine Intelligence (ACMI) Lab 12 Dec 19, 2022
QAT(quantize aware training) for classification with MQBench

MQBench Quantization Aware Training with PyTorch I am using MQBench(Model Quantization Benchmark)(http://mqbench.tech/) to quantize the model for depl

Ling Zhang 29 Nov 18, 2022
A CV toolkit for my papers.

PyTorch-Encoding created by Hang Zhang Documentation Please visit the Docs for detail instructions of installation and usage. Please visit the link to

Hang Zhang 2k Jan 04, 2023