CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer

Related tags

Deep LearningCSAW-M
Overview

CSAW-M

This repository contains code for CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer. Source code for training models to estimate the mammographic masking level along with the checkpoints are made available here.
The repo containing the annotation tool developed to annotate CSAW-M could be found here. The dataset could be found here.


Training and evaluation

  • In order to train a model, please refer to scripts/train.sh where we have prepared commands and arguments to train a model. In order to encourage reproducibility, we also provide the cross-validation splits that we used in the project (please refer to the dataset website to access them). scripts/cross_val.sh provides example commands to run cross-validation.
  • In order to evaluate a trained model, please refer to scripts/eval.sh with example commands and arguments to evaluate a model.
  • Checkpoints could be downloaded from here.

Important arguments defined in in the main module

  • --train and --evaluate which should be used in training and evaluating models respectively.
  • --model_name: specifies the model name, which will then be used for saving/loading checkpoints
  • --loss_type: defines which loss type to train the model with. It could be either one_hot which means training the model in a multi-class setup under usual cross entropy loss, or multi_hot which means training the model in a multi-label setup using multi-hot encoding (defined for ordinal labels). Please refer to paper for more details.
  • --img_size: specifies the image size to train the model with.
  • Almost all the params in params.yml could be overridden using the corresponding arguments. Please refer to main.py to see the corresponding args.

Other notes

  • It is assumed that main.py is called from inside the src directory.
  • It is important to note that in the beginning of the main script, after reading/checking arguments, params defined in params.ymlis read and updated according to args, after which a call to the set_globals (defined in main.py) is made. This sets global params needed to run the program (GPU device, loggers etc.) For every new high-level module (like main.py) that accepts running arguments and calls other modules, this function shoud be called, as other modules assume that these global params are set.
  • By default, there is no suggested validation csv files, but in cross-validation (using --cv) the train/validation splits in each fold are extracted from the cv_files paths specified in params.yml.
  • In src/experiments.py you can find the call to the function that preprocesses the raw images. For some images we have defined a special set of parameters to be used to ensure text is successfully removed from the images during preprocessing. We have documented every step of the preprocessing function to make it more udnerstandable - feel free to modify it if you want to have your own preprocessed images!
  • The Dockerfile and packages used in this project could be found in the docker folder.

Citation

If you use this work, please cite our paper:

@article{sorkhei2021csaw,
  title={CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer},
  author={Sorkhei, Moein and Liu, Yue and Azizpour, Hossein and Azavedo, Edward and Dembrower, Karin and Ntoula, Dimitra and Zouzos, Athanasios and Strand, Fredrik and Smith, Kevin},
  year={2021}
}

Questions or suggestions?

Please feel free to contact us in case you have any questions or suggestions!

Owner
Yue Liu
PhD student in deep learning at KTH.
Yue Liu
Learning Neural Painters Fast! using PyTorch and Fast.ai

The Joy of Neural Painting Learning Neural Painters Fast! using PyTorch and Fast.ai Blogpost with more details: The Joy of Neural Painting The impleme

Libre AI 72 Nov 10, 2022
A production-ready, scalable Indexer for the Jina neural search framework, based on HNSW and PSQL

🌟 HNSW + PostgreSQL Indexer HNSWPostgreSQLIndexer Jina is a production-ready, scalable Indexer for the Jina neural search framework. It combines the

Jina AI 25 Oct 14, 2022
Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception, IROS 2021

For academic use only. Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang and Robert Mahony Th

Ziwei Wang 11 Jan 04, 2023
Official Pytorch Implementation of Unsupervised Image Denoising with Frequency Domain Knowledge

Unsupervised Image Denoising with Frequency Domain Knowledge (BMVC 2021 Oral) : Official Project Page This repository provides the official PyTorch im

Donggon Jang 12 Sep 26, 2022
Generative vs Discriminative: Rethinking The Meta-Continual Learning (NeurIPS 2021)

Generative vs Discriminative: Rethinking The Meta-Continual Learning (NeurIPS 2021) In this repository we provide PyTorch implementations for GeMCL; a

4 Apr 15, 2022
Xi Dongbo 78 Nov 29, 2022
[IJCAI-2021] A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation"

DataFree A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation" Authors: Gongfa

ZJU-VIPA 47 Jan 09, 2023
Streaming Anomaly Detection Framework in Python (Outlier Detection for Streaming Data)

Python Streaming Anomaly Detection (PySAD) PySAD is an open-source python framework for anomaly detection on streaming multivariate data. Documentatio

Selim Firat Yilmaz 181 Dec 18, 2022
PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"

Non-Autoregressive Transformer Code release for Non-Autoregressive Neural Machine Translation by Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K.

Salesforce 261 Nov 12, 2022
training script for space time memory network

Trainig Script for Space Time Memory Network This codebase implemented training code for Space Time Memory Network with some cyclic features. Requirem

Yuxi Li 100 Dec 20, 2022
Mercury: easily convert Python notebook to web app and share with others

Mercury Share your Python notebooks with others Easily convert your Python notebooks into interactive web apps by adding parameters in YAML. Simply ad

MLJAR 2.2k Dec 27, 2022
Notepy is a full-featured Notepad Python app

Notepy A full featured python text-editor Notable features Autocompletion for parenthesis and quote Auto identation Syntax highlighting Compile and ru

Mirko Rovere 11 Sep 28, 2022
Python inverse kinematics for your robot model based on Pinocchio.

Python inverse kinematics for your robot model based on Pinocchio.

Stéphane Caron 50 Dec 22, 2022
One line to host them all. Bootstrap your image search case in minutes.

One line to host them all. Bootstrap your image search case in minutes. Survey NOW gives the world access to customized neural image search in just on

Jina AI 403 Dec 30, 2022
A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering.

DeepFilterNet A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering. libDF contains Rust code used for dat

Hendrik Schröter 292 Dec 25, 2022
Repository for the semantic WMI loss

Installation: pip install -e . Installing DL2: First clone DL2 in a separate directory and install it using the following commands: git clone https:/

Nick Hoernle 4 Sep 15, 2022
CrossNorm and SelfNorm for Generalization under Distribution Shifts (ICCV 2021)

CrossNorm (CN) and SelfNorm (SN) (Accepted at ICCV 2021) This is the official PyTorch implementation of our CNSN paper, in which we propose CrossNorm

100 Dec 28, 2022
Ludwig is a toolbox that allows to train and evaluate deep learning models without the need to write code.

Translated in 🇰🇷 Korean/ Ludwig is a toolbox that allows users to train and test deep learning models without the need to write code. It is built on

Ludwig 8.7k Jan 05, 2023
BMN: Boundary-Matching Network

BMN: Boundary-Matching Network A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generatio

qinxin 260 Dec 06, 2022
[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

TTSR Official PyTorch implementation of the paper Learning Texture Transformer Network for Image Super-Resolution accepted in CVPR 2020. Contents Intr

Multimedia Research 689 Dec 28, 2022