Images Of Different Modalities Research Articles

Latent space manipulation for high-resolution medical image synthesis via the StyleGAN

IntroductionThis paper explores the potential of the StyleGAN model as an high-resolution image generator for synthetic medical images. The possibility to generate sample patient images of different modalities can be helpful for training deep learning algorithms as e.g. a data augmentation technique. MethodsThe StyleGAN model was trained on Computed Tomography (CT) and T2- weighted Magnetic Resonance (MR) images from 100 patients with pelvic malignancies. The resulting model was investigated with regards to three features: Image Modality, Sex, and Longitudinal Slice Position. Further, the style transfer feature of the StyleGAN was used to move images between the modalities. The root-mean-squard error (RMSE) and the Mean Absolute Error (MAE) were used to quantify errors for MR and CT, respectively. ResultsWe demonstrate how these features can be transformed by manipulating the latent style vectors, and attempt to quantify how the errors change as we move through the latent style space. The best results were achieved by using the style transfer feature of the StyleGAN (58.7 HU MAE for MR to CT and 0.339 RMSE for CT to MR). Slices below and above an initial central slice can be predicted with an error below 75 HU MAE and 0.3 RMSE within 4cm for CT and MR, respectively. DiscussionThe StyleGAN is a promising model to use for generating synthetic medical images for MR and CT modalities as well as for 3D volumes.

Simultaneous photoacoustic microscopy, spectral-domain optical coherence tomography, and fluorescein microscopy multi-modality retinal imaging

The goal of this study is to further develop a multi-modality eye imaging system and evaluate its feasibility of acquiring images of different modalities simultaneously. An integrated multimodality imaging system combining spectral-domain optical coherence tomography (SD-OCT), photoacoustic microscopy (PAM), and fluorescence microscopy (FM) was developed, and its performance for eye imaging was validated on multiple clinically-relevant retinal disease models in vivo in rabbits. OCT imaging allows for visualization of the different anatomic retinal layers with high axial resolution. PAM can be used to image vasculature, angiogenesis, and hemorrhages. The leakage of neovascularization can be verified with FM and fluorescein dye. Simultaneous imaging with OCT, PAM, and FM ensures co-registration of the three modalities without being affected by motion artifacts caused by breathing, body or eye movements, and heartbeat. This simultaneous multi-modality eye imaging system could be a new tool for applications both in ophthalmology and other fields.

Medical Image Analysis (MedIA) using Deep Learning

Medical Image analysis has gained momentum in the research since last ten years. Medical images of different modalities like X-rays, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound etc. are generated with an increase of 15% to 20% every year. Medical image analysis requires high processing power and huge memory for storing the medical images, processing them, extracting features for useful information and segment the interested area for analysis. Thus, here comes the role of deep learning which proves to be promising for medical image analysis. The major focus of the paper is on exploring the literature on the broad areas of medical image analysis like Image Classification, Tumor/lesion classification and detection, Organ/Sub-structure Segmentation, Image Registration and Image Construction/ Enhancement using deep learning. Paper also highlights the physiological and medical challenges to be taken care, while analyzing medical images. It also discusses the technical challenges of using deep learning for medical image analysis and its solutions.

Adversarial Disentanglement Spectrum Variations and Cross-Modality Attention Networks for NIR-VIS Face Recognition

Near-infrared and visual (NIR-VIS) matching task refers to the face recognition between the two images of different modalities, which remains a challenging task in the field of machine vision. The main problems of NIR-VIS Heterogeneous Face Recognition (HFR) tasks include two aspects: large intra-class differences caused by cross-modal data, and insufficient paired training samples. In this paper, an effective Adversarial Disentanglement spectrum variations and Cross-modality Attention Networks (ADCANs) is proposed for VIS-NIR matching task. Three key components are introduced to the ADCANs for reducing the gap of cross-modal images: Advanced Scatter Loss (ASL), Modality-adversarial Feature Learning (MaFL) and Cross-modality Attention Block (CmAB). The proposed ASL loss captures between- and within-class information of the data and embeds them to the network for more effective training, and it focuses on categories with small between-class distance and increases the distance between them. The MaFL consists of an Identity-Discriminative Feature Learning Network (IDFLN) and a Modality-Adversarial Disentanglement Network (MADN), which can enhance the identity-discriminative feature representations as well as disentangling spectrum variations via an adversarial learning. The IDFLN built by an end-to-end CNNs aims at learning identity-discriminative feature. While the MADN built by a discriminator $D$ and a generator $G$ focuses on removing modality-related information. Furthermore, to increase representation power as well as disentangling spectrum variations effectively, a CmAB block is introduced to the network, which sequentially applies spatial and channel attention modules to both the IDFLN and MADN. Since the channel attention module focuses on ‘what’ features to suppress or emphasize, an orthogonality constraint is introduced to the two channel attention modules, which allows MADN and IDFLN to focus on learning modality-related features and identity-related features, respectively. In particular, the ADCANs consists of multiple CmAB blocks to learn discriminative features and disentangle spectrum variations. A large number of experiments on three challenging HFR datasets indicate that the proposed ADCANs is effective for VIS-NIR HFR task.

Discrete Wavelet Transform and Bird Swarm Optimized Bayesian Multimodal Medical Image Fusion

A novel Bayesian image fusion scheme using bird swarm optimization algorithm (BSA) is being proposed here.The medical Image fusion is progressed using the MRI brain images taken from the BRATS database and thesource images of different modalities are fused effectively to present an information rich fused image. The sourceimages are subjected to the Haar discrete wavelet transform (DWT) and the Bayesian fusion is performed usingthe Bayesian parameter, which is determined optimally using the BSA optimization. The analysis reveals that themethod outperformed the three existing methods of fusion that is nonsubsampled contourlet transform (NSCT),cascaded static wavelet (SWT) and NSCT ,that is (SWT-NSCT) and Holoentropy and SP-Whale Optimizationmethod (HW Fusion) with improved values of mutual information(1.4764),peak signal-to-noise ratio (37.2114)and root mean square error (9.9341) .

Unpaired Multi-Modal Segmentation via Knowledge Distillation.

Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI, and only employ modality-specific internal normalization layers which compute respective statistics. To effectively train such a highly compact model, we introduce a novel loss term inspired by knowledge distillation, by explicitly constraining the KL-divergence of our derived prediction distributions between modalities. We have extensively validated our approach on two multi-class segmentation problems: i) cardiac structure segmentation, and ii) abdominal organ segmentation. Different network settings, i.e., 2D dilated network and 3D U-net, are utilized to investigate our method's general efficacy. Experimental results on both tasks demonstrate that our novel multi-modal learning scheme consistently outperforms single-modal training and previous multi-modal approaches.

Domain adaptation for unsupervised change detection of multisensor multitemporal remote-sensing images

ABSTRACTWith the advancement of the space-based imaging technology, large amounts of images of different modality and spatial, spectral, and temporal resolutions are available. However, it is clearly demonstrated that combining images from different sources improves results in remote-sensing applications, it still remains a challenge to make full use of their benefits. These challenges become complicate, extending to multitemporal analysis and very high resolution (VHR) images, which includes different acquisition conditions, and consequently radiometric and geometric differences between images. To design methods that are robust to data set shifts, recent remote-sensing literature has considered solutions based on domain adaptation (DA) approaches. In this research, we aim to propose a method based on autoencoder which is a DA method to achieve fused features of synthetic aperture radar (SAR) and optical to benefit from their complementary information, and simultaneously aligning multitemporal features by reduction in spectral and radiometric differences and make multitemporal features more similar for better accuracy in change detection (CD). In continuation, to cope with the problem of detecting changes using VHR images, we introduce a framework to obtain the change map, in which, the differences caused by the registration error as well as the geometric differences of VHR images will be minimized, by maximum use of spatial information of images. For these purposes, a multitemporal pair of co-registered images, each composed of optical multispectral channels and a SAR amplitude channel acquired over the same urban area before and after changes, is assumed. Finally, the strategy of detecting changes resulted in improvement compared to common and simpler methods and also individual sensor CD method, which demonstrate the effectiveness of the proposed approach.

Precise correlative method of Cryo-SXT and Cryo-FM for organelle identification.

Cryogenic soft X-ray tomography (Cryo-SXT) is ideally suitable to image the 3D sub-cellular architecture and organization of cells with high resolution in the near-native preservation state. Cryogenic fluorescence microscopy (Cryo-FM) can determine the location of a molecule of interest that has been labeled with a fluorescent tag, thus revealing the function of the cells. To understand the relations between the sub-cellular architecture and the function of cells, correlative Cryo-SXT and Cryo-FM was applied. This method required the matching of images of different modalities, and the accuracy of the matching is important. Here, a precise correlative method of Cryo-SXT and Cryo-FM is introduced. The capability of matching images of different modalities with high resolution was verified by simulations and practical experiments, and the method was used to identify vacuoles and mitochondria.

A Fast Fusion Method for Visible and Infrared Images Using Fourier Transform and Difference Minimization

Images of different modalities play important roles in the fields of military, navigation, and target detection, including visible and infrared images. Existing fusion methods can reach relatively good fusion effects, but often make the processing speed slow. To achieve the purpose of faster fusion, this paper proposes a fast fusion of visible and infrared images (FFVI) based on Fourier transform and difference minimization. First, both visible and infrared images are transformed using Fourier transform, and the contour information of infrared image is extracted out at the same time. Then the two transformed images are added together to obtain a composite image, the inverse Fourier transform and the grayscale normalization are performed on the composite transformation image, which will generate an image that reflects the target features. Finally, the resulting image is reconstructed by fusing visible and the generated images according to the principle of “difference minimization”. The experimental results show that the novel method FFVI proposed in this paper can attain remarkable fusion effects in terms of the subjective qualitative and the objective quantitative analysis. In addition, this method outperforms several representative image fusion algorithms in the computational speed, which will be beneficial to practical application.

CNN-based superresolution reconstruction of 3D MR images using thick-slice scans

Due to inherent physical and hardware limitations, 3D MR images are often acquired in the form of orthogonal thick slices, resulting in highly anisotropic voxels. This causes the partial volume effect, which introduces blurring of image details, appearance of staircase artifacts and significantly decreases the diagnostic value of images. To restore high resolution isotropic volumes, we propose to use a convolutional neural network (CNN) driven by patches taken from three orthogonal thick-slice images. To assess the validity and efficiency of this postprocessing approach, we used 1x1x1 mm3-voxel brain images of different modalities, available via the well known BrainWeb database. They served as a high resolution reference and were numerically preprocessed to create input images of different slice thickness and anatomical orientation, for CNN training, validation and testing. The visual quality of reconstructed images was indeed superior, compared to images obtained by fusion of interpolated thick-slice images, or to images reconstructed with the CNN using a single input MR scan. The significant increase of objectively computed figures of merit, e.g. the Structural Similarity Image Metric, was also noticed. Keeping in mind that any single value of such quality metrics represents a number of psychophysical effects, we applied the CNN trained on brain images for superresolution reconstruction of synthetic and acquired blood vessel tree images. We then used the restored superresolution volumes for estimation of vessel radii. It was demonstrated that vessel radius values derived from superresolution images of simulated vessel trees are significantly more accurate than those obtained from a standard fusion of interpolated thick-slice orthogonal scans. Superiority of the CNN-based superresolution images was also observed for scanner-acquired MR scans according to the evaluated parameters. These three experiments show the efficiency of CNN-based image reconstruction for qualitative and quantitative improvement of its diagnostic quality, as well as illustrates the practical usefulness of transfer learning - networks trained on example images of one kind can be used to restore superresolution images of physically different objects.

Spatial Analysis of Tumor Sub-Volume Using Multi-Modality Images for Rhabdomyosarcoma in Children

To compare imaging of multi-modality for evaluating children patients with rhabdomyosacroma. To analyze the spatial relationship of tumor volumes between different imaging techniques. To identify the high risk sub-regions in tumor volumes. 16 pediatric patients with rhabdomyosarcoma underwent imaging with PET/CT, T2-MRI, ADC and spectral CT with iodine contrast. From the spectral CT, the volumetric iodine density and effective Z of patients’ images were extracted. Tumor/GTV contours were generated by clinical physicians on simulation CT. The images of different modalities were rigidly registered on the simulation CTs and the tumor contours were populated to other images in the same coordinate of simulation CTs. The tumor subvolumes of modalities were defined by isothreshold and fuzzy mean clustering. The spatial relations of these sub regions including similarity and incongruity were then evaluated with Dice’s coefficient and ANOVA. The modalities can be categorized with two groups. Group 1: ADC and T2-MRI; Group 2: iodine density, effective Z from spectral CT and PET. In the same patient of most cases, the sub-regions of ADC and T2 had high similarity. The sub-regions of iodine, effective Z and PET had high similarity. The sub-region of ADC showed a disjoint spatial relation with the sub-region of iodine density, e.g. the high iodine density signal of the sub region expressed a low ADC signal in the same region. The fuzzy mean clustering showed the better performance of sub volume determination. The average similarity of between and T2 images has Dice coefficient of 0.88±0.082. The average similarity of between iodine density, effective Z from spectral CT and PET images has Dice coefficient of 0.78±0.042. The average similarity of between ADC and iodine density images has Dice coefficient of 0.14±0.12. The sub-regions of tumor volumes were investigated between images of five modalities. Each modality provides different type of functional imaging based on physical properties of tumor tissues. The spatial correlation of sub-volumes in different modalities can help physicians identify the high risk sub-region of GTV for treatment planning.

Fusion of Multi Modal Lumber Spine Scans using Wavelet and Convolutional Neural Network

Multiple medical images of different modalities are fused together to generate a new more informative image thereby reducing the treatment planning time of medical practitioners. In recent years, wavelets and deep learning methods have been widely used in various image processing applications. In this study, we present convolutional neural network and wavelet based fusion of MR and CT images of lumber spine to generate a single image which comprises all the important features of MR and CT images. Both CT and MR images are first decomposed into detail and approximate coefficients using wavelets. Then the corresponding detail and approximate coefficients are fused using convolutional neural network framework. Inverse wavelet transform is then used to generate fused image. The experimental results indicate that the proposed approach achieves good performance as compared to conventional methods.

Automatic spondylolisthesis grading from MRIs across modalities using faster adversarial recognition network.

Grading spondylolisthesis into several stages from MRI images is challenging because detecting critical vertebrae and locating landmarks in images of different characteristics is difficult. We propose Faster Adversarial Recognition (FAR) network to accurately perform spondylolisthesis grading by excellently detecting critical vertebrae without the need of locating the landmarks. The FAR network introduces the adversarial scheme by using a multi-task recognition network as the generator and an adversarial module as the discriminator. The multi-task recognition network (generator) is an integrated network that can reliably perform multi-scale hierarchical feature learning, critical vertebrae detection, detected vertebrae classification, bounding box regression, and spondylolisthesis grading in a hybrid supervised manner. The adversarial module (discriminator) takes the detection results as inputs to supervise the generative network by leveraging the high-order statistics of the distribution of the detected bounding box coordinates. The FAR network is evaluated to be accurate and robust in spondylolisthesis grading (training accuracy: 0.9883 ± 0.0094, testing accuracy: 0.8933 ± 0.0276) for MRI images of different modalities, which can be attributed to the excellent critical vertebrae detection (detection mAP75 for training: 1 ± 0, for testing: 0.9636 ± 0.0180, and IoU (Intersection-over-union) ≥ 0.9/0.8 for most detections with their corresponding ground truth in the training/testing dataset). This accuracy is comparable to that of the physicians and outperforms other state-of-the-art methods. These results indicate the potential of our framework to perform spondylolisthesis grading for clinical diagnosis.

A Platform for Collection and Analysis of Image Data on Stroke.

Identifying imaging biomarkers (IBs) of stroke remains a priority in neurodiagnostics. There is a number of different methods for image analysis and learning rules applicable in this field, but all of them require large arrays of DICOM images and clinical data. In order to amass such dataset,we havedesigneda platform for systematic collection of clinical data and medical images in different modalities. The platform provides easy-to-use tools to create formalized radiology reports, contour and tag the regions of interest (ROIs) on the DICOM images, and extract radiomics data. Subsequent analysis of the obtained data will allow identifying the most relevant IBs that predict clinical outcome and possible complications. The results of the analysis will be used to develop predictive algorithms for stroke diagnostics.

An optimal wavelet-based multi-modality medical image fusion approach based on modified central force optimization and histogram matching

This paper introduces an optimal solution for wavelet-based medical image fusion using different wavelet families and Principal Component Ana1ysis (PCA) based on the Modified Central Force Optimization (MCFO) technique. The main motivation of this work is to increase the quality of medical fused images in order to provide correct diagnosis of diseases for the objective of optimal therapy. This can be achieved by fusing medical images of different modalities using an optimization technique based on the MCFO. The MCFO technique gives the optimum gain parameters that achieve the best fused image quality. Histogram matching is applied to improve the overall values of the Peak Signal-to-Noise Ratio (PSNR), entropy, local contrast, and quality of the fused image. A comparative study is performed between the proposed algorithm, the traditional Discrete Wavelet Transform (DWT), and the PCA fusion using maximum fusion rule. The proposed algorithm is evaluated subjectively and objectively with different fusion quality metrics. Simulation results demonstrate that the proposed MCFO optimized wavelet-based fusion algorithm using Haar wavelet and histogram matching achieves a superior performance with the highest image quality and clearest image details in a very short processing time.

Discriminant Deep Feature Learning based on joint supervision Loss and Multi-layer Feature Fusion for heterogeneous face recognition

Heterogeneous face recognition (HFR) is still a challenging problem in computer vision community due to large appearance difference between near infrared (NIR) and visible light (VIS) modalities. Recently, breakthroughs have been made for traditional face recognition by applying deep learning on a huge amount of labeled VIS face samples. However, the same deep learning approach cannot be simply applied to HFR task due to large domain difference as well as insufficient pairwise images in different modalities during training. In general, the pooling layer of deep network can play the role of feature reduction, but also lead to the loss of useful face information, resulting in a decrease in the performance of HFR problem. It is important to eliminate modal-related information and retain more facial identity information. In this paper, we propose a novel method called Discriminant Deep Feature Learning Based on Joint Supervision Loss and Multi-layer Feature Fusion (DDFLJM) for HFR task. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new loss function called Scatter Loss (SL), which embeds both inter- and intra-class information for effectively training the deep model. To make full use of the various layers of the deep network, a Dimension Reduction Block (DRB) is designed to effectively extract the auxiliary features on multiple mid-level layers. An orthogonality constraint is introduced to the DRB block to reduce spectrum variations of two different modalities. The proposed SL is applied to multiple layers of network for joint supervision training, which enables multiple layers of the network to obtain discriminative identity features. Moreover, a Modified Gate Two-stream Neural Network (MGTNN) is adopted to fuse multiple-layer features. Extensive experiments are carried out on two challenging NIR-VIS HFR datasets CASIA NIR-VIS 2.0 and Oulu-CASIA NIR-VIS, demonstrating the superiority of the proposed method.

Efficient level‐set segmentation model driven by the local GMM and split Bregman method

An efficient level-set model driven by the local Gaussian mixture model (GMM) and split Bregman method is proposed for image segmentation. Firstly, the two intensity fitting functions in the original local binary fitting (LBF) model are pre-estimated by using a local GMM-based intensity distribution estimator before curve evolution. The benefit of this pre-computation strategy is to avoid updating the fitting functions at each step of the curve evolution, and it also overcomes the initialisation problem of common gradient descent-based active contour models, i.e. the level-set function can be initialised as an arbitrary random matrix instead of a signed distance function in the proposed processing framework. Secondly, two processing ideas named global convex segmentation (GCS) method and split Bregman are introduced into the numerical implementation, where the role of GCS is to transform the proposed model into a simplified convex segmentation model, and the purpose of the split Bregman is to quickly output a convergent solution of the newly derived convex segmentation model in an alternate iterative format. Experimental results for synthetic and real images of different modalities with inhomogeneity or homogeneity validate the desired performances of the proposed method in terms of accuracy, robustness, and rapidity.

Multi-Modal Medical Image Fusion With Adaptive Weighted Combination of NSST Bands Using Chaotic Grey Wolf Optimization

Recently, medical image fusion has emerged as an impressive technique in merging the medical images of different modalities. Certainly, the fused image assists the physician in disease diagnosis for effective treatment planning. The fusion process combines multi-modal images to incur a single image with excellent quality, retaining the information of original images. This paper proposes a multi-modal medical image fusion through a weighted blending of high-frequency subbands of nonsubsampled shearlet transform (NSST) domain via chaotic grey wolf optimization algorithm. As an initial step, the NSST is applied on source images to decompose into the multi-scale and multi-directional components. The low-frequency bands are fused based on a simple max rule to sustain the energy of an individual. The texture details of input images are preserved by an adaptively weighted combination of high-frequency images using a recent chaotic grey wolf optimization algorithm to minimize the distance between the fused image and source images. The entire process emphasizes on retaining the energy of the low-frequency band and the transferring of texture features from source images to the fused image. Finally, the fused image is formed using inverse NSST of merged low and high-frequency bands. The experiments are carried out on eight different disease datasets obtained from Brain Atlas, which consists of MR-T1 and MR-T2, MR and SPECT, MR and PET, and MR and CT. The effectiveness of the proposed method is validated using more than 100 pairs of images based on the subjective and objective quality assessment. The experimental results confirm that the proposed method performs better in contrast with the current state-of-the-art image fusion techniques in terms of entropy, VIFF, and FMI. Hence, the proposed method will be helpful for disease diagnosis, medical treatment planning, and surgical procedure.

Image synthesis-based multi-modal image registration framework by using deep fully convolutional networks.

Multi-modal image registration has significant meanings in clinical diagnosis, treatment planning, and image-guided surgery. Since different modalities exhibit different characteristics, finding a fast and accurate correspondence between images of different modalities is still a challenge. In this paper, we propose an image synthesis-based multi-modal registration framework. Image synthesis is performed by a ten-layer fully convolutional network (FCN). The network is composed of 10 convolutional layers combined with batch normalization (BN) and rectified linear unit (ReLU), which can be trained to learn an end-to-end mapping from one modality to the other. After the cross-modality image synthesis, multi-modal registration can be transformed into mono-modal registration. The mono-modal registration can be solved by methods with lower computational complexity, such as sum of squared differences (SSD). We tested our method in T1-weighted vs T2-weighted, T1-weighted vs PD, and T2-weighted vs PD image registrations with BrainWeb phantom data and IXI real patients' data. The result shows that our framework can achieve higher registration accuracy than the state-of-the-art multi-modal image registration methods, such as local mutual information (LMI) and α-mutual information (α-MI). The average registration errors of our method in experiment with IXI real patients' data were 1.19, 2.23, and 1.57 compared to 1.53, 2.60, and 2.36 of LMI and 1.34, 2.39, and 1.76 of α-MI in T2-weighted vs PD, T1-weighted vs PD, and T1-weighted vs T2-weighted image registration, respectively. In this paper, we propose an image synthesis-based multi-modal image registration framework. A deep FCN model is developed to perform image synthesis for this framework, which can capture the complex nonlinear relationship between different modalities and discover complex structural representations automatically by a large number of trainable mapping and parameters and perform accurate image synthesis. The framework combined with the deep FCN model and mono-modal registration methods (SSD) can achieve fast and robust results in multi-modal medical image registration. Graphical abstract The workflow of proposed multi-modal image registration framework.

Medical Image Fusion using bi-dimensional empirical mode decomposition (BEMD) and an Efficient Fusion Scheme.

Background: Medical image fusion is being widely used for capturing complimentary information from images of different modalities. Combination of useful information presented in medical images is the aim of image fusion techniques, and the fused image will exhibit more information in comparison with source images.Objective: In the current study, a BEMD-based multi-modal medical image fusion technique is utilized. Moreover, Teager-Kaiser energy operator (TKEO) was applied to lower BIMFs. The results were compared to six routine methods.Material and Methods: In this study, which is of experimental type, an image fusion technique using bi-dimensional empirical mode decomposition (BEMD), Teager-Kaiser energy operator (TKEO) as a local feature selection and Hierarchical Model And X (HMAX) model is presented. BEMD fusion technique can preserve much functional information. In the process of fusion, we adopt the fusion rule of TKEO for lower bi-dimensional intrinsic mode functions (BIMFs) of two images and HMAX visual cortex model as a fusion rule for higher BIMFs, which are verified to be more appropriate for human vision system. Integrating BEMD and this efficient fusion scheme can retain more spatial and functional features of input images.Results: We compared our method with IHS, DWT, LWT, PCA, NSCT and SIST methods. The simulation results and fusion performance show that the presented method is effective in terms of mutual information, quality of fused image (QAB/F), standard deviation, peak signal to noise ratio, structural similarity and considerably better results compared to six typical fusion methods.Conclusion: The statistical analyses revealed that our algorithm significantly improved spatial features and diminished the color distortion compared to other fusion techniques. The proposed approach can be used for routine practice. Fusion of functional and morphological medical images is possible before, during and after treatment of tumors in different organs. Image fusion can enable interventional events and can be further assessed.