Special Issue "Recent Advances in Deep Learning for Medical Image Analysis"

Submission Deadline: 01 April 2021 (closed)
Guest Editors
Dr. Tallha Akram, COMSATS University Islamabad, Pakistan.
Prof. Dr. Yu-Dong Zhang, University of Leicester, UK.
Prof. Dr. Robertas Damaševičius, Kaunas University of Technology, Lithuania.
Dr. Muhammad Attique Khan, HITEC University Taxila, Pakistan.


Artificial intelligence showed a huge interest, especially in the area of medical imaging from the last three years. Due to the spread of medical imaging modalities such as Magnetic Resonance Imaging (MRI), Ultrasound, and Positron Emission Tomography (PET), Dermoscopic images, X-Ray images, Mammograms, and histological images, enormous amounts of data are being generated related to these medical domains. The data is generated in the form of some images and related to health informatics. However, the amount of this data is too large and difficult to use by employing classical techniques (i.e. hand crafted features). The question is that how we can use this big amount of biomedical data to build the automated system with better accuracy and less computational time. Also, how we can utilize this data to develop an automated system for better diagnosis of cancers such as brain tumor, skin cancer, lung cancer, stomach cancer, COVID19 infected patients, and breast cancer. To handle the large amount of biomedical data, researchers of computer vision used deep learning. However, they facing several issues (i.e. high data dimensionality and imbalanced datasets) and to these issues, the performance of system were degraded. Therefore, the most of existing solutions are based on the balanced datasets which is not a good option for the multiclass classification problem. Therefore, it is essential to develop some advanced deep learning techniques. Also, it is required to develop dimensionality reduction techniques to minimize the prediction time. Also, the less prediction time can be useful for real-time computerized system.

The aim of this special issue is to provide a diverse, but complementary set of solutions using deep learning for medical images. The solutions cover the above mentioned issues. We would also like to accept the new solutions but not limited to the following:
• Deep learning based features extraction for medical images
• Visualization of deep learning features for medical images
• Features selection using heuristic techniques for medical images
• Features selection using met heuristic techniques
• Deep learning features fusion
• Deep learning based biomedical images information fusion
• Transfer learning in medical imaging
• Features reduction techniques
• Theoretical analysis of deep learning for medical images
• Deep learning based segmentation of infected regions
• Semi-Supervised deep learning for medical imaging
• Semantic Segmentation for medical image analysis
• Multitask Learning for medical image analysis