biostudies-literatureUnknown102Hussain MASimon Fraser UniversitySupervised deep learning has become a standard approach to solving medical image segmentation tasks. However, serious difficulties in attaining pixel-level annotations for sufficiently large volumetric datasets in real-life applications have highlighted the critical need for alternative approaches, such as semi-supervised learning, where model training can leverage small expert-annotated datasets to enable learning from much larger datasets without laborious annotation. Most of the semi-supervised approaches combine expert annotations and machine-generated annotations with equal weights within deep model training, despite the latter annotations being relatively unreliable and likely to affect model optimization negatively. To overcome this, we propose an active learning approach that uses Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society102127https://www.ebi.ac.uk/biostudies/studies/S-EPMC9540707biostudies-literatureActive deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT.PMC9540707Neshat AAMomeny MGarbi RMarhamati MMirikharaji ZHussain MAHamarneh GfalseActive deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT.Supervised deep learning has become a standard approach to solving medical image segmentation tasks. However, serious difficulties in attaining pixel-level annotations for sufficiently large volumetric datasets in real-life applications have highlighted the critical need for alternative approaches, such as semi-supervised learning, where model training can leverage small expert-annotated datasets to enable learning from much larger datasets without laborious annotation. Most of the semi-supervised approaches combine expert annotations and machine-generated annotations with equal weights within deep model training, despite the latter annotations being relatively unreliable and likely to affect model optimization negatively. To overcome this, we propose an active learning approach that uses 2022-01-01T00:00:00Z2022 Dec2025-04-04T22:32:06.844Z2025-02-19T03:22:56.48ZS-EPMC95407073625709210.1016/j.compmedimag.2022.102127