Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering
With the rapid development of medical imaging methods, multimodal medical image fusion techniques have caught the interest of researchers. The aim is to preserve information from diverse sensors using various models to generate a single informative image. The main challenge is to derive a trade-off...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Royal Society
2024-04-01
|
| Series: | Royal Society Open Science |
| Subjects: | |
| Online Access: | https://royalsocietypublishing.org/doi/10.1098/rsos.231762 |
| _version_ | 1827249730486272000 |
|---|---|
| author | Shiva Moghtaderi Mokarrameh Einlou Khan A. Wahid Kiven Erique Lukong |
| author_facet | Shiva Moghtaderi Mokarrameh Einlou Khan A. Wahid Kiven Erique Lukong |
| author_sort | Shiva Moghtaderi |
| collection | DOAJ |
| description | With the rapid development of medical imaging methods, multimodal medical image fusion techniques have caught the interest of researchers. The aim is to preserve information from diverse sensors using various models to generate a single informative image. The main challenge is to derive a trade-off between the spatial and spectral qualities of the resulting fused image and the computing efficiency. This article proposes a fast and reliable method for medical image fusion depending on multilevel Guided edge-preserving filtering (MLGEPF) decomposition rule. First, each multimodal medical image was divided into three sublayer categories using an MLGEPF decomposition scheme: small-scale component, large-scale component and background component. Secondly, two fusion strategies—pulse-coupled neural network based on the structure tensor and maximum based—are applied to combine the three types of layers, based on the layers' various properties. The three different types of fused sublayers are combined to create the fused image at the end. A total of 40 pairs of brain images from four separate categories of medical conditions were tested in experiments. The pair of images includes various case studies including magnetic resonance imaging (MRI) , TITc, single-photon emission computed tomography (SPECT) and positron emission tomography (PET). We included qualitative analysis to demonstrate that the visual contrast between the structure and the surrounding tissue is increased in our proposed method. To further enhance the visual comparison, we asked a group of observers to compare our method’s outputs with other methods and score them. Overall, our proposed fusion scheme increased the visual contrast and received positive subjective review. Moreover, objective assessment indicators for each category of medical conditions are also included. Our method achieves a high evaluation outcome on feature mutual information (FMI), the sum of correlation of differences (SCD), Qabf and Qy indexes. This implies that our fusion algorithm has better performance in information preservation and efficient structural and visual transferring. |
| first_indexed | 2024-04-24T11:34:07Z |
| format | Article |
| id | doaj.art-69cdbc16711d426b93d71f7ac2e8bf69 |
| institution | Directory Open Access Journal |
| issn | 2054-5703 |
| language | English |
| last_indexed | 2025-03-21T23:52:17Z |
| publishDate | 2024-04-01 |
| publisher | The Royal Society |
| record_format | Article |
| series | Royal Society Open Science |
| spelling | doaj.art-69cdbc16711d426b93d71f7ac2e8bf692024-05-17T20:02:35ZengThe Royal SocietyRoyal Society Open Science2054-57032024-04-0111410.1098/rsos.231762Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filteringShiva Moghtaderi0Mokarrameh Einlou1Khan A. Wahid2Kiven Erique Lukong3Department of Electrical and Computer Engineering, University of Saskatchewan , Saskatoon, Saskatchewan S7N 5A9, CanadaDepartment of Electrical and Computer Engineering, University of Saskatchewan , Saskatoon, Saskatchewan S7N 5A9, CanadaDepartment of Electrical and Computer Engineering, University of Saskatchewan , Saskatoon, Saskatchewan S7N 5A9, CanadaDepartment of Biochemistry, Microbiology and Immunology, University of Saskatchewan , Saskatoon, Saskatchewan S7N 5E5, CanadaWith the rapid development of medical imaging methods, multimodal medical image fusion techniques have caught the interest of researchers. The aim is to preserve information from diverse sensors using various models to generate a single informative image. The main challenge is to derive a trade-off between the spatial and spectral qualities of the resulting fused image and the computing efficiency. This article proposes a fast and reliable method for medical image fusion depending on multilevel Guided edge-preserving filtering (MLGEPF) decomposition rule. First, each multimodal medical image was divided into three sublayer categories using an MLGEPF decomposition scheme: small-scale component, large-scale component and background component. Secondly, two fusion strategies—pulse-coupled neural network based on the structure tensor and maximum based—are applied to combine the three types of layers, based on the layers' various properties. The three different types of fused sublayers are combined to create the fused image at the end. A total of 40 pairs of brain images from four separate categories of medical conditions were tested in experiments. The pair of images includes various case studies including magnetic resonance imaging (MRI) , TITc, single-photon emission computed tomography (SPECT) and positron emission tomography (PET). We included qualitative analysis to demonstrate that the visual contrast between the structure and the surrounding tissue is increased in our proposed method. To further enhance the visual comparison, we asked a group of observers to compare our method’s outputs with other methods and score them. Overall, our proposed fusion scheme increased the visual contrast and received positive subjective review. Moreover, objective assessment indicators for each category of medical conditions are also included. Our method achieves a high evaluation outcome on feature mutual information (FMI), the sum of correlation of differences (SCD), Qabf and Qy indexes. This implies that our fusion algorithm has better performance in information preservation and efficient structural and visual transferring.https://royalsocietypublishing.org/doi/10.1098/rsos.231762medical imagingmultimodal image fusionsalient feature extraction |
| spellingShingle | Shiva Moghtaderi Mokarrameh Einlou Khan A. Wahid Kiven Erique Lukong Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering Royal Society Open Science medical imaging multimodal image fusion salient feature extraction |
| title | Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering |
| title_full | Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering |
| title_fullStr | Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering |
| title_full_unstemmed | Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering |
| title_short | Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering |
| title_sort | advancing multimodal medical image fusion an adaptive image decomposition approach based on multilevel guided filtering |
| topic | medical imaging multimodal image fusion salient feature extraction |
| url | https://royalsocietypublishing.org/doi/10.1098/rsos.231762 |
| work_keys_str_mv | AT shivamoghtaderi advancingmultimodalmedicalimagefusionanadaptiveimagedecompositionapproachbasedonmultilevelguidedfiltering AT mokarrameheinlou advancingmultimodalmedicalimagefusionanadaptiveimagedecompositionapproachbasedonmultilevelguidedfiltering AT khanawahid advancingmultimodalmedicalimagefusionanadaptiveimagedecompositionapproachbasedonmultilevelguidedfiltering AT kiveneriquelukong advancingmultimodalmedicalimagefusionanadaptiveimagedecompositionapproachbasedonmultilevelguidedfiltering |