Data

Tools

Indexes

Applications

Experiments

Open Source Science

siim-covid-19-detection

👩‍⚕️ Identification and Localization COVID-19 Abnormalities on Chest Radiographs

https://github.com/pvti/siim-covid-19-detection

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.6%) to scientific vocabulary

Keywords

classification covid-19 covid19-data cxr-images detection detr efficientnet weighted-box-fusion yolo
Last synced: 4 months ago · JSON representation ·

Repository

👩‍⚕️ Identification and Localization COVID-19 Abnormalities on Chest Radiographs

Basic Info
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
classification covid-19 covid19-data cxr-images detection detr efficientnet weighted-box-fusion yolo
Created over 4 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

Visitors

👩‍⚕️ Identification and Localization COVID-19 Abnormalities on Chest Radiographs

1Université de Toulon, Aix Marseille Université, CNRS, LIS, UMR 7020, France  ✉Corresponding Author
Solutions to screen and diagnose positive patients for SARS-CoV-2 promptly and efficiently are critical in the context of the COVID-19 pandemic’s complex evolution. Recent researches have demonstrated the efficiency of deep learning and particularly convolutional neural networks (CNNs) in classifying and detecting lung disease-related lesions from radiographs. This paper presents a solution using ensemble learning techniques on advanced CNNs to classify as well as localize COVID-19-related abnormalities in radiographs. Two classifiers including EfficientNetV2 and NFNet are combined with three detectors, DETR, Yolov7, and EfficientDet. Along with gathering and training the model on a large number of datasets, image augmentation, and cross-validation are also addressed. Since then, this study has shown promising results and has received excellent marks in the Society for Imaging Informatics in Medicine’s competition. The analysis in model selection for the trade-off between speed and accuracy is also given.

📋 News

  • [2023.01.02] Paper is accepted to AICV 2023.
  • [2022.09.06] Create baseline.

🦠 Main results

Evaluation of the COVID-19 lesion detector on the SIIM test set:

| Detector | Accuracy (mAP@ IoU 0.5:0.95) | | | Performance | | |---------------------|:----------------------------:|:--------------:|:---------------------:|:---------------------------:|:---------------:| | | Discrete model | Lung localized | Inference speed (FPS) | GPU memory requirement (MB) | Model size (MB) | | DETR | 0.542 | 0.587 | 25 | 2683 | 232 | | Yolov7 | 0.563 | 0.591 | 34 | 3520 | 290 | | EfficientDet | 0.499 | 0.574 | 19 | 1903 | 187 | | Weighted Box Fusion | 0.605 | 0.612 | 8 | 8106 | 709 |

💉 Installation

Please refer to INSTALL.md for installation instructions.

🧬 Model zoo

Trained models are available in the MODEL_ZOO.md.

💻 Dataset zoo

Please see DATASET_ZOO.md for detailed description of the training/evaluation datasets.

🔍 Getting Started

Follow the aforementioned instructions to install environments and download models and datasets.

GETTING_STARTED.md provides a brief intro of the usage of builtin command-line tools.

🔬 Citing

If you use this work in your research or wish to refer to the results, please use the following BibTeX entry.

BibTeX @inproceedings{pham2023identification, title={Identification and localization COVID-19 abnormalities on chest radiographs}, author={Pham, Van Tien and Nguyen, Thanh Phuong}, booktitle={The International Conference on Artificial Intelligence and Computer Vision}, pages={251--261}, year={2023}, organization={Springer} }

Owner

  • Name: _
  • Login: pvti
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: If you find this work useful, please consider citing it.
authors:
- family-names: Pham
  given-names: Van Tien
  orcid: https://orcid.org/0000-0003-3890-7188
- family-names: Nguyen
  given-names:  Thanh Phuong
title: "Identification and Localization COVID-19 Abnormalities on Chest Radiographs"
version: 0.1.0
url: https://github.com/pvtien96/SIIM-COVID-19-Detection
preferred-citation:
  type: article
  authors:
  - family-names: Pham
    given-names: Van Tien
    orcid: https://orcid.org/0000-0003-3890-7188
  - family-names: Nguyen
    given-names:  Thanh Phuong
  title: "Identification and Localization COVID-19 Abnormalities on Chest Radiographs"
  journal: "The 3rd International Conference on Artificial Intelligence and Computer Vision (AICV2023), March 5--7, 2023"
  start: 251
  end: 261
  year: 2023

GitHub Events

Total
Last Year