A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics

Azam, Muhammad Adeel; Khan, Khan Bahadar; Salahuddin, Sana; Rehman, Eid; Khan, Sajid Ali; Khan, Muhammad Attique; Kadry, Seifedine; Gandomi, Amir H.

doi:10.1016/j.compbiomed.2022.105253

Cited by 189 publications

(77 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each branch has a varied number of parameters to capture different features. Moreover, after the improvement shown by the fusion in medical signals and images [ 47 , 48 , 49 ], we investigate the effect of fusion of the output feature maps from EEGNet blocks with the output from the EEG-CBAM blocks to reduce feature loss and construct a comprehensive feature map. For that, we propose the FMBEEGCBAM model ( Figure 6 ) that has the same blocks and connections as in the MBEEGCBAM model with an extra step.…”

Section: Methodsmentioning

confidence: 99%

Electroencephalogram-Based Motor Imagery Signals Classification Using a Multi-Branch Convolutional Neural Network Model with Attention Blocks

Altuwaijri

Muhammad

2022

Bioengineering

View full text Add to dashboard Cite

Brain signals can be captured via electroencephalogram (EEG) and be used in various brain–computer interface (BCI) applications. Classifying motor imagery (MI) using EEG signals is one of the important applications that can help a stroke patient to rehabilitate or perform certain tasks. Dealing with EEG-MI signals is challenging because the signals are weak, may contain artefacts, are dependent on the patient’s mood and posture, and have low signal-to-noise ratio. This paper proposes a multi-branch convolutional neural network model called the Multi-Branch EEGNet with Convolutional Block Attention Module (MBEEGCBAM) using attention mechanism and fusion techniques to classify EEG-MI signals. The attention mechanism is applied both channel-wise and spatial-wise. The proposed model is a lightweight model that has fewer parameters and higher accuracy compared to other state-of-the-art models. The accuracy of the proposed model is 82.85% and 95.45% using the BCI-IV2a motor imagery dataset and the high gamma dataset, respectively. Additionally, when using the fusion approach (FMBEEGCBAM), it achieves 83.68% and 95.74% accuracy, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Electroencephalogram-Based Motor Imagery Signals Classification Using a Multi-Branch Convolutional Neural Network Model with Attention Blocks

Altuwaijri

Muhammad

2022

Bioengineering

View full text Add to dashboard Cite

show abstract

“…Image quality assessment is very much necessary as it talks about how much improvement is needed for a better visual of images for researchers. Image quality measures or parameters and their role in image quality assessment has been described in detail [21,22].…”

Section: Fusion Performance Measuresmentioning

confidence: 99%

A Novel MRI And CT Image Fusion Based on Discrete Wavelet Transform and Principal Component Analysis for Enhanced Clinical Diagnosis

Richa¹,

Kaur²,

Singh³

2022

Int. J. Onl. Eng.

View full text Add to dashboard Cite

A large percentage of healthcare resources, including imaging tools, like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) have been dedicated to the management of affected patients in this pandemic of Coronavirus disease 2019 (COVID-19). The diagnostic modalities in medical research are improving at a rapid pace with an objective to acquire maximum information with as little data as possible without any artifacts. That is where image fusion comes into the picture. It is a technique of merging source medical pictures to maximize the necessary information. CT is generally used for bony structures, whereas MRI is more appropriate for soft tissues. A fusion of MRI and CT images would lead to enhancement of the overall image quality while giving comprehensive information, at the same time artifacts are also eliminated. Image fusion methods are applied in medical science and various other sectors. Several image processing techniques are used in medical diagnostics, like Principal Component analysis (PCA), Intensity-Hue-Saturation, Discrete Wavelet Transform (DWT), and others. This study suggests an image fusion algorithm utilising the principal component averaging and the DWT along with the performance analysis of the fusion of the MRI and CT images of brain. The technique used in our study significantly enhances the image quality in terms of various fusion performance measures that helps the medical practitioners to diagnose any infection and aids in its treatment.

show abstract

“…Detection and segmentation of the brain tumor is considered to be the challenging issue in the field of medical sciences [27]. There are many techniques developed for this purpose including kmeans clustering, discrete cosine transform (DCT), Fuzzy C-Mean, and many more.…”

Section: Introductionmentioning

confidence: 99%

Brain Tumor Detection and Classification Using PSO and Convolutional Neural Network

Ali¹,

Shah²,

Khan³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Tumor detection has been an active research topic in recent years due to the high mortality rate. Computer vision (CV) and image processing techniques have recently become popular for detecting tumors in MRI images. The automated detection process is simpler and takes less time than manual processing. In addition, the difference in the expanding shape of brain tumor tissues complicates and complicates tumor detection for clinicians. We proposed a new framework for tumor detection as well as tumor classification into relevant categories in this paper. For tumor segmentation, the proposed framework employs the Particle Swarm Optimization (PSO) algorithm, and for classification, the convolutional neural network (CNN) algorithm. Popular preprocessing techniques such as noise removal, image sharpening, and skull stripping are used at the start of the segmentation process. Then, PSO-based segmentation is applied. In the classification step, two pre-trained CNN models, alexnet and inception-V3, are used and trained using transfer learning. Using a serial approach, features are extracted from both trained models and fused features for final classification. For classification, a variety of machine learning classifiers are used. Average dice values on datasets BRATS-2018 and BRATS-2017 are 98.11 percent and 98.25 percent, respectively, whereas average jaccard values are 96.30 percent and 96.57% (Segmentation Results). The results were extended on the same datasets for classification and achieved 99.0% accuracy, sensitivity of 0.99, specificity of 0.99, and precision of 0.99. Finally, the proposed method is compared to state-of-the-art existing methods and outperforms them.

show abstract

A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics

Cited by 189 publications

References 79 publications

Electroencephalogram-Based Motor Imagery Signals Classification Using a Multi-Branch Convolutional Neural Network Model with Attention Blocks

Electroencephalogram-Based Motor Imagery Signals Classification Using a Multi-Branch Convolutional Neural Network Model with Attention Blocks

A Novel MRI And CT Image Fusion Based on Discrete Wavelet Transform and Principal Component Analysis for Enhanced Clinical Diagnosis

Brain Tumor Detection and Classification Using PSO and Convolutional Neural Network

Contact Info

Product

Resources

About