1. ABOUT THE DATASET -------------------- Title: Lung ultrasound COVID phantom dataset used for training machine learning model Creator(s): [Enter names of dataset Creators and add reference numbers to correspond with named Organisations if necessary, e.g.: Ben Jones[1], Alice Smith[2]] Organisation(s): [Enter names of organisations with which creators are affiliated. Add reference numbers if necessary to correspond to relevant Creators' names, e.g. 1. University of Leeds. 2. University of York] Rights-holder(s):Unless otherwise stated, Copyright 2023 University of Leeds Publication Year: 2024 Description: This data repository contains all the raw imaging videos taken on a COVID-19 lung ultrasound phantom with a range of diagnostic ultrasound systems outlined in the methods section of the accompanying paper. These videos were used to generate a bank of imaging frames with a wide variety of COVID-19 features from the ultrasound phantom. MatLab code used to do this is also included in the repository. This data was used to train the included machine learning model, along with the labelled training and test datasets. Cite as: Howell, Lewis and McLaughlan, James (2024) Dataset for 'Lung ultrasound COVID phantom dataset used for training machine learning model'. University of Leeds. [Dataset] https://doi.org/10.5518/1485. Related publication: Lewis Howell, Nicola Ingram, Roger Lapham, Adam Morrell, James R. McLaughlan,Deep learning for real-time multi-class segmentation of artefacts in lung ultrasound, Ultrasonics, Volume 140, 2024, 107251, ISSN 0041-624X, https://doi.org/10.1016/j.ultras.2024.107251. Contact: James R. McLaughlan, j.r.mclaughlan@leeds.ac.uk 2. TERMS OF USE --------------- Copyright 2024 University of Leeds, . This dataset is licensed under a Creative Commons Attribution 4.0 International Licence: https://creativecommons.org/licenses/by/4.0/. 3. PROJECT AND FUNDING INFORMATION ---------------------------------- Title: Establishing lung ultrasound as a key tool in the stratification and monitoring of COVID-19 patients Dates: Nov 2020 - May 2022 Funding organisation: UKRI Grant no.: EP/V043714/1 4. CONTENTS ----------- LUS_model - folder containing test/training images used for ML model VideoClips - all 2s ultrasound cineloops os LUS phantom used to generate frames for training. vidtoImage.m - a matlab script to take a random number of frames from cineloops for subisquent labelling. 5. METHODS ---------- See manuscript for methodology used with this dataset. https://github.com/ljhowell/LUS-Segmentation-RT