Open AccessMultimodal Medical Image Fusion Techniques – A Review
Author(s) -
T. Tirupal,
B. Chandra Mohan,
S. Srinivas Kumar
Publication year - 2021
Publication title -
current signal transduction therapy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.128
H-Index - 17
eISSN - 2212-389X
pISSN - 1574-3624
DOI - 10.2174/1574362415666200226103116
Subject(s) - image fusion , computer science , artificial intelligence , image (mathematics) , operator (biology) , fuzzy logic , medical imaging , fusion , pattern recognition (psychology) , computer vision , machine learning , biochemistry , chemistry , linguistics , philosophy , repressor , transcription factor , gene
The main objective of image fusion for multimodal medical images is to retrieve valuableinformation by combining multiple images obtained from various sources into a single imagesuitable for better diagnosis. In this paper, a detailed survey on various existing medical image fusionalgorithms, with a comparative discussion is presented. Image fusion algorithms available inthe current literature are categorized into various methods known as (1) morphological methods,(2) human value system operator based methods, (3) sub-band decomposition methods, (4) neuraln++32w1etwork based methods, and (5) fuzzy logic based methods. This research concludes thateven though there exist a few open-ended creative and logical difficulties, the fusion of medicalimages in many combinations assists in utilizing medical image fusion for medicinal diagnosticsand examination. There is a tremendous progress in the fields of deep learning, artificial intelligenceand bio-inspired optimization techniques. Effective utilization of these techniques can beused to further improve the efficiency of image fusion algorithms.