Image analysis and pattern recognition are the foremost domains of computer engineering and computer science in several domains, such as medical, military, remote sensing, agriculture, and other real-world applications. In medical applications, image-guided decision support is one of the vital methods for accurate diagnosis. Image analysis systems combined with innovative computing procedures can extract quantifiable parameters from the medical image. However, it is still challenging to achieve high performance in image classification, target detection & recognition, video tracking, etc. because of the complex scenarios of the real world (e.g., noise, occlusion, deformation, etc.). Recently, the advances in the computer vision domain have shown their increased potential in practical applications. Deep neural network methodologies are commonly used in image and video processing, including image segmentation, registration, classification, recognition, etc. The advanced scientific programming methods include a combination of deep learning techniques like convolution neural networks (CNN), recurrent neural networks (RNN), and deep generative adversarial network (GAN) models, with novel meta-heuristic and nature-inspired optimisation methods such as ant colony optimisation, particle swarm, Harris hawks, polar bear, and red fox algorithms, have been applied for medical data efficiently. Application of such novel scientific programming methods to medical data can aid clinicians to make an accurate and fast diagnosis, especially in the context of e-health and tele-healthcare.

There are a great variety of challenges in medical imaging that can be posed as optimization problems such as image registration, extraction of deep features, feature selection or tuning of the hyper-parameters of machine learning or deep learning for higher performance in classification. As there are a great variety of nature-inspired and meta-heuristic optimization algorithms proposed recently, this Special Issue will address the problems of selecting appropriate metaheuristics for medical imaging tasks as well as using rigorous methodology to compare metaheuristics features, strategies, and their performance in the medical domain.

The aim of this Special Issue is to collate original research and review articles describing advances in this field. The focus is on the recent development to tackle the challenges that meta-heuristic algorithms might face when solving real-world problems and applications in the medical imaging domain. We invite colleagues to contribute original research articles as well as review articles that will stimulate the continuing effort on meta-heuristic approaches applied for medical imaging applications.

Potential topics include but are not limited to the following:

• Automatic tissue segmentation in medical images using nature-inspired meta-heuristics
• Bio-inspired computing in medical image and data analysis
• Computed tomography image enhancement for COVID-19 recognition
• Computing the medical image registration using meta-heuristics
• Hybrid architectures, methods and systems for biomedical image processing and classification
• Meta-heuristic algorithms in medical image segmentation
• Nature-inspired scientific programming methods for biomedical signal and image processing
• Reviews on various optimisation methods for biomedical data
• Scientific programming for medical imaging-based diagnostics
• Methodologies for feature extraction and feature selection in medical image analysis and classification tasks
• Applications in internet of medical things