Medical image fusion based on hybrid intelligence

• A new hybrid algorithm called hybrid intelligence image fusion (HIIF) is used for fusing multimodal medical images.
• It uses two stages of intelligence. In the first stage, edges are detected using ACO technique and the edges are enhanced.
• The first stage output is given as the input to the second stage which is a simplified pulse coupled neural network.
• The algorithm was tested on 5 datasets of PET and MRI and 5 datasets of SPECT and MRI.
• The proposed algorithm performs better compared to the existing intelligence method.

Medical image fusion combines complementary images from different modalities for proper diagnosis and surgical planning. A new approach for medical image fusion based on the hybrid intelligence system is proposed. This paper has integrated the swarm intelligence and neural network to achieve a better fused output. The edges are an important feature of an image and they are detected and optimized by using ant colony optimization. The detected edges are enhanced and it is given as the feeding input to the simplified pulse coupled neural network. The firing maps are generated and the maximum fusion rule is applied to get the fused image. The performance of the proposed method is compared both subjectively and objectively, with the genetic algorithm method, neuro-fuzzy method and also with the modified pulse coupled neural network. The results show that the proposed hybrid intelligent method performs better when compared to the existing computational and hybrid intelligent methods.

Figure optionsDownload as PowerPoint slide