4S-DT: Self-Supervised Super Sample Decomposition for Transfer Learning With Application to COVID-19 Detection

Abbas, Asmaa and Abdelsamea, Mohammed M. and Gaber, Mohamed Medhat (2021) 4S-DT: Self-Supervised Super Sample Decomposition for Transfer Learning With Application to COVID-19 Detection. IEEE Transactions on Neural Networks and Learning Systems, 32 (7). ['lib/metafield/pagerange:range' not defined

to

2808

from

2798

pagerange

2798-2808

]. ISSN 2162-237X

['page:fulltext' not defined]

['lib/document:preview' not defined]

['document_typename_text' not defined] document.pdf - ['content_typename_published' not defined] Download (4MB)

['eprint_fieldname_abstract' not defined]

Due to the high availability of large-scale annotated image datasets, knowledge transfer from pretrained models showed outstanding performance in medical image classification. However, building a robust image classification model for datasets with data irregularity or imbalanced classes can be a very challenging task, especially in the medical imaging domain. In this article, we propose a novel deep convolutional neural network,which we called self-supervised super sample decomposition for transfer learning (4S-DT) model. The 4S-DT encourages a coarse-to-fine transfer learning from large-scale image recognition tasks to a specific chest X-ray image classification task using a generic self-supervised sample decomposition approach. Our main contribution is a novel self-supervised learning mechanism guided by a super sample decomposition of unlabeled chest X-ray images. 4S-DT helps in improving the robustness of knowledge
transformation via a downstream learning strategy with a class decomposition (CD) layer to simplify the local structure of the data. The 4S-DT can deal with any irregularities in the image dataset by investigating its class boundaries using a downstream CD mechanism. We used 50 000 unlabeled chest X-ray images to achieve our coarse-to-fine transfer learning with an application to COVID-19 detection, as an exemplar. The 4S-DT has achieved a high accuracy of 99.8% on the larger of the two datasets used in the experimental study and an accuracy of 97.54% on the smaller dataset, which was enriched by augmented images, out of which all real COVID-19 cases were detected.

['eprint_fieldname_type' not defined]:	['eprint_typename_article' not defined]
['eprint_fieldname_id_number' not defined]:	10.1109/TNNLS.2021.3082015
Dates:	Date Event 17 ['lib/utils:month_05' not defined] 2021 Accepted 26 ['lib/utils:month_05' not defined] 2021 Published Online
['eprint_fieldname_keywords' not defined]:	Chest X-ray image classification, convolutional neural network (CNN), data irregularities, self-supervision, transfer learning
['eprint_fieldname_subjects' not defined]:	CAH11 - computing['lib/metafield:join_subject_parts' not defined]CAH11-01 - computing['lib/metafield:join_subject_parts' not defined]CAH11-01-05 - artificial intelligence
['eprint_fieldname_divisions' not defined]:	Architecture, Built Environment, Computing and Engineering['lib/metafield:join_subject_parts' not defined]Computer Science
['eprint_fieldname_userid' not defined]:	Mohammed Abdelsamea
['eprint_fieldname_datestamp' not defined]:	27 ['lib/utils:month_short_10' not defined] 2021 12:24
['eprint_fieldname_lastmod' not defined]:	06 ['lib/utils:month_short_06' not defined] 2022 14:14
URI:	https://www.open-access.bcu.ac.uk/id/eprint/12322

Actions (login required)

['Plugin/Screen/EPrint/View:title' not defined]