Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT. (December 2022)

• Record Type: Journal Article
• Authors: Hussain, Mohammad Arafat; Mirikharaji, Zahra; Momeny, Mohammad; Marhamati, Mahmoud; Neshat, Ali Asghar; Garbi, Rafeef; Hamarneh, Ghassan
• Is Part Of: Computerized medical imaging and graphics. Volume 102(2022)
• Publication Date: 2022-12
• Subjects: Deep learning -- Semi-supervised learning -- Active learning -- Segmentation -- Noisy teacher -- COVID-19 -- Pneumonia; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102127
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: 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 an example re-weighting strategy, where machine-annotated samples are weighted (i) based on the similarity of their gradient directions of descent to those of expert-annotated data, and (ii) based on the gradient magnitude of the last layer of the deep model. Specifically, we present an active learning strategy with a query function that enables the selection of reliable and more informative samples from machine-annotated batch data generated by a noisy teacher. When validated on clinical COVID-19 CT benchmark data, our method improved the performance of pneumonia infection segmentation compared to the state of the art. Highlights: We propose an example reweighting-based active learning from noisy teacher approach. Our strategy uses gradient similarity and magnitude in determining the sample weights. Our strategy uses a query to select more reliable and informative samples.