Special Issue on Advanced Deep Learning Methods for Biomedical Image Analysis
• 大类 : 工程技术 - 1区
• 小类 : 计算机：人工智能 - 2区
• 小类 : 神经科学 - 2区
Biomedical processing involves the analysis of heart rate, blood pressure, oxygen saturation levels, blood glucose, nerve conduction and brain activity to provide useful information upon which clinicians can make decisions. It furthers emphasis on practical, applications-led research on the use of methods and devices in clinical diagnosis, patient monitoring and management.
Large amount of biomedical information and health data (particularly images) was gathered these years. However, how to develop new advanced imaging methods and computational models for efficient data processing, analysis and modelling from the collected data is important for clinical applications and in understanding the underlying biological process.
Deep neural network is a subset of machine learning, using a model inspired by the structure of the brain. It has been rapidly developed recent years, in terms of both methodological development and practical applications. It provides computational models of multiple processing neural-network layers to learn and represent data with multiple levels of abstraction. It is able to implicitly capture intricate structures of large-scale data and ideally suited to some of the hardware architectures that are currently available.
The importance of our special issue is to bring the latest theoretical and technical advancements of deep learning to biomedical image and health data analysis. Meanwhile, the investigations on the applications of deep learning to biomedical image and health data analysis may bring the reflect of improving the models of deep neural network.
The purpose of this special issue aims to provide a diverse, but complementary, set of contributions to demonstrate new developments and applications of Deep learning and Computational Machine Learning, to solve problems in biomedical engineering. The ultimate goal is to promote research and development of deep learning for multimodal biomedical images and other health data, by publishing high-quality research articles and reviews/tutorials in this rapidly growing interdisciplinary field.
Main Topics include:
Theoretical understanding of deep learning in biomedical engineering
Transfer learning, disentangling task transfer learning, and multi-task learning
Joint Semantic Segmentation, Object Detection and Scene Recognition on biomedical images
Adversarial training on biomedical images and other health data
Improvising on the computation of a deep network; exploiting parallel computation techniques and GPU programming