دورية أكاديمية
Learning disentangled representations in the imaging domain.
| العنوان: | Learning disentangled representations in the imaging domain. |
|---|---|
| المؤلفون: | Liu X; School of Engineering, The University of Edinburgh, Edinburgh EH9 3FG, UK. Electronic address: Xiao.Liu@ed.ac.uk., Sanchez P; School of Engineering, The University of Edinburgh, Edinburgh EH9 3FG, UK., Thermos S; School of Engineering, The University of Edinburgh, Edinburgh EH9 3FG, UK., O'Neil AQ; School of Engineering, The University of Edinburgh, Edinburgh EH9 3FG, UK; Canon Medical Research Europe, Edinburgh EH6 5NP, UK., Tsaftaris SA; School of Engineering, The University of Edinburgh, Edinburgh EH9 3FG, UK; The Alan Turing Institute, London NW1 2DB, UK. |
| المصدر: | Medical image analysis [Med Image Anal] 2022 Aug; Vol. 80, pp. 102516. Date of Electronic Publication: 2022 Jun 17. |
| نوع المنشور: | Journal Article; Review; Research Support, Non-U.S. Gov't |
| اللغة: | English |
| بيانات الدورية: | Publisher: Elsevier Country of Publication: Netherlands NLM ID: 9713490 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1361-8423 (Electronic) Linking ISSN: 13618415 NLM ISO Abbreviation: Med Image Anal Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Amsterdam : Elsevier Original Publication: London : Oxford University Press, [1996- |
| مواضيع طبية MeSH: | Learning* , Machine Learning*, Humans ; Software |
| مستخلص: | Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using modest amounts of data, or used directly in unseen domains achieving remarkable performance in the corresponding task. This alleviation of the data and annotation requirements offers tantalising prospects for applications in computer vision and healthcare. In this tutorial paper, we motivate the need for disentangled representations, revisit key concepts, and describe practical building blocks and criteria for learning such representations. We survey applications in medical imaging emphasising choices made in exemplar key works, and then discuss links to computer vision applications. We conclude by presenting limitations, challenges, and opportunities. Competing Interests: Declaration of Competing Interest The authors declare no conflict of interest. (Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.) |
| فهرسة مساهمة: | Keywords: Applications; Computer vision; Content-style; Disentangled representation; Medical imaging; Tutorial |
| تواريخ الأحداث: | Date Created: 20220625 Date Completed: 20220726 Latest Revision: 20220727 |
| رمز التحديث: | 20221213 |
| DOI: | 10.1016/j.media.2022.102516 |
| PMID: | 35751992 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 1361-8423 |
|---|---|
| DOI: | 10.1016/j.media.2022.102516 |