{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:56:05Z","timestamp":1787759765336,"version":"build-2784847793"},"reference-count":38,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Council Canada"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>While no longer a public health emergency of international concern, COVID-19 remains an established and ongoing global health threat. As the global population continues to face significant negative impacts of the pandemic, there has been an increased usage of point-of-care ultrasound (POCUS) imaging as a low-cost, portable, and effective modality of choice in the COVID-19 clinical workflow. A major barrier to the widespread adoption of POCUS in the COVID-19 clinical workflow is the scarcity of expert clinicians who can interpret POCUS examinations, leading to considerable interest in artificial intelligence-driven clinical decision support systems to tackle this challenge. A major challenge to building deep neural networks for COVID-19 screening using POCUS is the heterogeneity in the types of probes used to capture ultrasound images (e.g., convex vs. linear probes), which can lead to very different visual appearances. In this study, we propose an analytic framework for COVID-19 assessment able to consume ultrasound images captured by linear and convex probes. We analyze the impact of leveraging extended linear-convex ultrasound augmentation learning on producing enhanced deep neural networks for COVID-19 assessment, where we conduct data augmentation on convex probe data alongside linear probe data that have been transformed to better resemble convex probe data. The proposed explainable framework, called COVID-Net L2C-ULTRA, employs an efficient deep columnar anti-aliased convolutional neural network designed via a machine-driven design exploration strategy. Our experimental results confirm that the proposed extended linear\u2013convex ultrasound augmentation learning significantly increases performance, with a gain of 3.9% in test accuracy and 3.2% in AUC, 10.9% in recall, and 4.4% in precision. The proposed method also demonstrates a much more effective utilization of linear probe images through a 5.1% performance improvement in recall when such images are added to the training dataset, while all other methods show a decrease in recall when trained on the combined linear\u2013convex dataset. We further verify the validity of the model by assessing what the network considers to be the critical regions of an image with our contribution clinician.<\/jats:p>","DOI":"10.3390\/s24051664","type":"journal-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T08:03:47Z","timestamp":1709539427000},"page":"1664","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["COVID-Net L2C-ULTRA: An Explainable Linear-Convex Ultrasound Augmentation Learning Framework to Improve COVID-19 Assessment and Monitoring"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8034-596X","authenticated-orcid":false,"given":"E. Zhixuan","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-9105","authenticated-orcid":false,"given":"Ashkan","family":"Ebadi","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"},{"name":"Digital Technologies Research Centre, National Research Council Canada, Toronto, ON M5T 3J1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Florea","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, McGill University, Montreal, QC H4A 3J1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"},{"name":"Waterloo Artificial Intelligence Institute, Waterloo, ON N2L 3G1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2021). Recommendations for National SARS-CoV-2 Testing Strategies and Diagnostic Capacities: Interim Guidance, 25 June 2021, World Health Organization. Technical Report."},{"key":"ref_2","unstructured":"World Health Organization (2020). Use of Chest Imaging in COVID-19: A Rapid Advice Guide, 11 June 2020, World Health Organization. Technical Report."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"00196","DOI":"10.1183\/23120541.00196-2022","article-title":"The use of lung ultrasound in COVID-19","volume":"9","author":"Blazic","year":"2023","journal-title":"ERJ Open Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1007\/s00261-018-1517-0","article-title":"Machine learning for medical ultrasound: Status, methods, and future opportunities","volume":"43","author":"Brattain","year":"2018","journal-title":"Abdom. Radiol."},{"key":"ref_5","unstructured":"MacLean, A., Abbasi, S., Ebadi, A., Zhao, A., Pavlova, M., Gunraj, H., Xi, P., Kohli, S., and Wong, A. (2021). Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health, Springer."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Song, J., Ebadi, A., Florea, A., Xi, P., Tremblay, S., and Wong, A. (2023). COVID-Net USPro: An Explainable Few-Shot Deep Prototypical Network for COVID-19 Screening Using Point-of-Care Ultrasound. Sensors, 23.","DOI":"10.3390\/s23052621"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"7068349","DOI":"10.1155\/2018\/7068349","article-title":"Deep learning for computer vision: A brief review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei, L. (2009, January 20\u201325). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the CVPR09, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Razzak, M.I., Naz, S., and Zaib, A. (2018). Deep learning for medical image processing: Overview, challenges and the future. Classification in BioApps: Automation of Decision Making, Springer.","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing medical imaging data for machine learning","volume":"295","author":"Willemink","year":"2020","journal-title":"Radiology"},{"key":"ref_12","first-page":"1","article-title":"The effectiveness of data augmentation in image classification using deep learning","volume":"11","author":"Wang","year":"2017","journal-title":"Convolutional. Neural. Netw. Vis. Recognit"},{"key":"ref_13","unstructured":"Carmody, K.A., Moore, C.L., and Feller-Kopman, D. (2011). Handbook of Critical Care and Emergency Ultrasound, The McGraw-Hill Companies."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/j.ultrasmedbio.2019.09.018","article-title":"Deep convolutional neural network-based automatic classification of neonatal hip ultrasound images: A novel data augmentation approach with speckle noise reduction","volume":"46","author":"Sezer","year":"2020","journal-title":"Ultrasound Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1109\/TIP.2009.2024064","article-title":"Nonlocal means-based speckle filtering for ultrasound images","volume":"18","author":"Hellier","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tirindelli, M., Eilers, C., Simson, W., Paschali, M., Azampour, M.F., and Navab, N. (2021). Rethinking Ultrasound Augmentation: A Physics-Inspired Approach. arXiv.","DOI":"10.1007\/978-3-030-87237-3_66"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1007\/s11548-020-02203-1","article-title":"SpeckleGAN: A generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing","volume":"15","author":"Bargsten","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Win, K.K., Wang, J., Zhang, C., and Yang, R. (2010, January 15\u201317). Identification and removal of reverberation in ultrasound imaging. Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, Taichung, Taiwan.","DOI":"10.1109\/ICIEA.2010.5515209"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.compmedimag.2010.09.003","article-title":"A wavelet thresholding method to reduce ultrasound artifacts","volume":"35","author":"Tay","year":"2011","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_20","unstructured":"Hung, A.L.Y., Chen, E., and Galeotti, J. (2020). Weakly-and semi-supervised probabilistic segmentation and quantification of ultrasound needle-reverberation artifacts to allow better ai understanding of tissue beneath needles. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","article-title":"Generative adversarial networks: An overview","volume":"35","author":"Creswell","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"168","DOI":"10.5455\/aim.2011.19.168-171","article-title":"Application of ultrasound in medicine","volume":"19","author":"Carovac","year":"2011","journal-title":"Acta Inform. Medica"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Duck, F.A., Baker, A.C., and Starritt, H.C. (2020). Ultrasound in Medicine, CRC Press.","DOI":"10.1201\/9780367802479"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/S0301-5629(00)00204-0","article-title":"International recommendations and guidelines for the safe use of diagnostic ultrasound in medicine","volume":"26","author":"Barnett","year":"2000","journal-title":"Ultrasound Med. Biol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2230","DOI":"10.1109\/TUFFC.2020.3020055","article-title":"Current ultrasound technologies and instrumentation in the assessment and monitoring of COVID-19 positive patients","volume":"67","author":"Qian","year":"2020","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10396-020-01074-y","article-title":"Point-of-care lung ultrasound for the assessment of pneumonia: A narrative review in the COVID-19 era","volume":"48","author":"Kameda","year":"2021","journal-title":"J. Med. Ultrason."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/s40477-021-00586-8","article-title":"The role of PoCUS in the assessment of COVID-19 patients","volume":"25","author":"Karp","year":"2022","journal-title":"J. Ultrasound"},{"key":"ref_28","unstructured":"Institute, C.U. (2023, November 21). Types of Ultrasound Transducers and Their Benefits. Available online: https:\/\/www.canadianultrasound.com\/types-of-ultrasound-transducers-and-their-benefits\/."},{"key":"ref_29","unstructured":"Allan, P.L., Baxter, G.M., and Weston, M.J. (2011). Clinical Ultrasound, Churchill Livingstone. [3rd ed.]."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yaron, D., Keidar, D., Goldstein, E., Shachar, Y., Blass, A., Frank, O., Schipper, N., Shabshin, N., Grubstein, A., and Suhami, D. (2021, January 6\u201311). Point of care image analysis for COVID-19. Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9413687"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s13089-018-0109-0","article-title":"Which ultrasound transducer type is best for diagnosing pneumothorax?","volume":"10","author":"Ketelaars","year":"2018","journal-title":"Crit. Ultrasound J."},{"key":"ref_32","first-page":"83","article-title":"Ultrasound Diagnosis of Chest Diseaseses","volume":"5","author":"Liao","year":"2013","journal-title":"Adv. Break. Ultrasound Imaging"},{"key":"ref_33","first-page":"198","article-title":"COVIDx-US: An Open-Access Benchmark Dataset of Ultrasound Imaging Data for AI-Driven COVID-19 Analytics","volume":"27","author":"Ebadi","year":"2022","journal-title":"FBL"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Born, J., Wiedemann, N., Cossio, M., Buhre, C., Br\u00e4ndle, G., Leidermann, K., Aujayeb, A., Moor, M., Rieck, B., and Borgwardt, K. (2021). Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis. Appl. Sci., 11.","DOI":"10.3390\/app11020672"},{"key":"ref_35","unstructured":"Carmody, K.A., Moore, C.L., and Feller-Kopman, D. (2011). Handbook of Critical Care and Emergency Ultrasound, The McGraw-Hill Companies."},{"key":"ref_36","unstructured":"Wong, A., Shafiee, M.J., Chwyl, B., and Li, F. (2018). Ferminets: Learning generative machines to generate efficient neural networks via generative synthesis. arXiv."},{"key":"ref_37","unstructured":"Zhang, R. (2019, January 9\u201315). Making convolutional networks shift-invariant again. Proceedings of the International Conference on Machine Learning (PMLR), Long Beach, CA, USA."},{"key":"ref_38","unstructured":"Lin, Z.Q., Shafiee, M.J., Bochkarev, S., Jules, M.S., Wang, X.Y., and Wong, A. (2019). Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/5\/1664\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:09:03Z","timestamp":1760105343000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/5\/1664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["s24051664"],"URL":"https:\/\/doi.org\/10.3390\/s24051664","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,4]]}}}