Special issue on Deep Learning for Medical Imaging and Health Informatics
• 大类 : 工程技术 - 3区
• 小类 : 计算机：人工智能 - 3区
Due to increasing alarming and appalling ailments in human beings, nowadays more effort has been conducted on medical image analysis. Different computerized methods are designed in literature for the identification of diseases related to specific parts of body based on their size, shape and appearance. But due to scalability and flexibility of existing methods, they do not accurately measure the disease. Because of their over simplified reality and poor detection performance, they never achieved extensive medical adoption.
Deep learning provides a better solution to overcome all existing limitations. Deep learning is a more powerful tool to incorporate wide gamut of disease in whole body that can cover all input modalities such as MRI, CT scans, pathological and X-rays tests etc. Thus the main goal of this issue is the adoption of healthcare related with machine learning, artificial intelligence and deep learning algorithms to mimic its practices and theories. The main objective is to provide a sophisticated research platform for researchers, scientists, students and teachers to share their own novel contribution in discussing how to generate healthcare information in real time applications by using deep learning methods to transmute into computational practices of healthcare.
Deep learning is a multilayer model in which underlying output is used as input on the top. In unsupervised learning from below to above process, informative features are automatically learned. On the other hand, supervised learning assigns labels across each input data and parameters are to be optimized to learn whole model on the basis of better characteristics of learning capability. The presentation and learning structure of this ability is more robust to image translation and deformation.
This special issue focuses on proper concatenations of deep learning and recent medicinal information schemes. Thus it includes topics of interest, but not limited to
Deep learning for virtual medical systems
Deep learning for health information mining
Deep learning for leukocyte detection
Deep convolutional network (DNN) learning model for brain tumor detection
Long term short memory (LSTM) model for Collection of crowd sourced medical data for proper scaling in Healthcare
Extreme learning method (ELM) method for medical image analysis Fully convolutional network (FCN) for medical image analysis
Deep learning in Healthcare planning, policy, practice and planning development
Convolutional neural network for image analysis of anatomical structures, functions and lesions
Neural networks for computer-aided detection and diagnosis
Neural network models for multi-modality fusion for analysis, diagnosis and intervention
Neural networks for medical image reconstruction
Deep Neural networks for medical image retrieval
Deep Neural networks for molecular, pathologic and cellular image analysis
Neural network models for dynamic, functional and physiologic imaging