Human Disease Classification and Segmentation using Machine and Deep Learning
1Bennett University, Gr. Noida, India
2Brunel University, London, UK
Human Disease Classification and Segmentation using Machine and Deep Learning
Description
In the last decade, the field of machine and deep learning has attracted attention due to its vast applications in various domains such as healthcare, security, military, finance, weather forecasting, image quality enhancement, etc.
Before the introduction of deep learning, prediction and forecasting was carried out using statistical and machine learning techniques. However, the performance of machine learning algorithms is not good with huge amount of data. Performance of deep learning models is always better than the machine learning approach, but it requires enough data with huge computational power. Nowadays, there is no restrictions on computational power as well as medical data because many healthcare organizations or hospitals are moving towards utilizing machine intelligence for human disease classification. Machine intelligence can also be utilized in the identification of human disease, detection and localization of lung nodules, disease severity estimation, etc.
The aim of this Special Issue is to bring together original research and review articles in the recent advancements, latest applications, and latest trends in the classification of human disease using machine and deep learning. Research on developing new approaches for tuning the hyper parameters of deep neural networks or machine learning techniques are also encouraged.
Potential topics include but are not limited to the following:
- Development of novel machine learning approaches for the detection of lung cancer in early stages
- Application of popular deep neural networks (i.e., convolution neural networks, generative adversarial networks (GAN)) for identification of human disease
- Human disease severity estimation using deep neural networks
- Detection of nodules or irregular cells in organs (i.e., lung, liver, kidney, etc.)
- Applying ensemble learning for the identification of human diseases
- Development of feature extraction techniques for medical data
- Development of new algorithms to clean medical data (i.e., ultra-sound images, MRI, CT-scan etc.)
- Use of pre-trained models (i.e., AlexNet, VGG19, ResNet, MobileNet) for human disease classification