ABSTRACT
In today’s technological advancements, clinical imaging is playing a significant role in numerous aspects of diagnosis and treatment. Accurate diagnosis requires precise images and appropriate data. Many types of clinical imaging are available today, some of which are especially suitable for particular clinical situations. For instance, computed tomography (CT) imaging gives better data on thick tissues like bones, and magnetic resonance (MR) imaging provides better data on delicate tissues. Nonetheless, no single methodology can achieve the necessary accuracy and high resolution and for complete diagnosis. Clinical image fusion is the most common way of consolidating different pictures from single or numerous types of imaging. However, several of the available medical image fusion techniques experience noise, blurring, and colour distortion. To resolve these issues, multi-modal image fusion using Laplacian re-decomposition is employed. This method uses a deep learning convolutional neural network to generate a weight map. The outcomes are excellent in terms of visual quality and target measurements.
