TY - JOUR
T1 - Transfer learning for medical images analyses
T2 - A survey
AU - Yu, Xiang
AU - Wang, Jian
AU - Hong, Qing Qi
AU - Teku, Raja
AU - Wang, Shui Hua
AU - Zhang, Yu Dong
N1 - Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2022/6/7
Y1 - 2022/6/7
N2 - The advent of deep learning has brought great change to the community of computer science and also revitalized numerous fields where traditional machine learning methods failed to make breakthroughs. Benefitted from the development of deep learning, analysis of medical images, which used to be a challenging yet exhausting task carried out manually by physicians, has experienced fast development as well. However, training deep learning models in these systems for analysis from scratch can be quite challenging. The small-scale data can't guarantee the performance of the developed systems, while large-scale data is usually unavailable due to expensive costs in the process of collection and storage. To allow a fast transition from one domain to another for reuse, experts and researchers have extensively delved transfer learning, which turns out to be an efficient and low-cost learning technique. In this paper, we will present a comprehensive survey of transfer learning on medical image analysis. The imaging modalities include but not limits to Computed Tomography (CT), Ultrasound (US), and Magnetic Resonance Imaging (MRI). The subjects covered in this paper include the brain, breast, lung, kidney, etc. Besides, this survey provides systematic knowledge about deep learning and transfer learning for beginners. Readers with different backgrounds can easily catch up with the interdisciplinary knowledge and new trends of transfer learning via this survey.
AB - The advent of deep learning has brought great change to the community of computer science and also revitalized numerous fields where traditional machine learning methods failed to make breakthroughs. Benefitted from the development of deep learning, analysis of medical images, which used to be a challenging yet exhausting task carried out manually by physicians, has experienced fast development as well. However, training deep learning models in these systems for analysis from scratch can be quite challenging. The small-scale data can't guarantee the performance of the developed systems, while large-scale data is usually unavailable due to expensive costs in the process of collection and storage. To allow a fast transition from one domain to another for reuse, experts and researchers have extensively delved transfer learning, which turns out to be an efficient and low-cost learning technique. In this paper, we will present a comprehensive survey of transfer learning on medical image analysis. The imaging modalities include but not limits to Computed Tomography (CT), Ultrasound (US), and Magnetic Resonance Imaging (MRI). The subjects covered in this paper include the brain, breast, lung, kidney, etc. Besides, this survey provides systematic knowledge about deep learning and transfer learning for beginners. Readers with different backgrounds can easily catch up with the interdisciplinary knowledge and new trends of transfer learning via this survey.
KW - Deep learning
KW - Imaging modalities
KW - Medical image analysis
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85126600274&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2021.08.159
DO - 10.1016/j.neucom.2021.08.159
M3 - Article
AN - SCOPUS:85126600274
SN - 0925-2312
VL - 489
SP - 230
EP - 254
JO - Neurocomputing
JF - Neurocomputing
ER -