Image fusion is an approach which is used to amalgamate the corresponding features in a sequence of input images to a single composite image that preserves all the significant features of the input images. Image fusion is also known as pansharpening. It is a method which is used to integrate and add the geometric detail of a high-resolution panchromatic (Pan) image and the information of color of a low-resolution multispectral (MS) image for the production of a high-resolution MS image. This methodology is mainly most important and significant for any large-scale applications. Image fusion classification based on its systems (models and algorithms) are considered and overviewed in this survey. The basic two algorithms categories are analyzed and compared to each other, in the analysis and discussion section the major points to be considered while performing image fusion are highlighted.

/pdf/image-fusion-methods-a-survey-8j5od88zup.pdf

Image Fusion Methods: A Survey

Computer-aided diagnostic (CAD) systems use machine learning methods that provide a synergistic effect between the neuroradiologist and the computer, enabling an efficient and rapid diagnosis of the patient’s condition. As part of the early diagnosis of Alzheimer’s disease (AD), which is a major public health problem, the CAD system provides a neuropsychological assessment that helps mitigate its effects. The use of data fusion techniques by CAD systems has proven to be useful, they allow for the merging of information relating to the brain and its tissues from MRI, with that of other types of modalities. This multimodal fusion refines the quality of brain images by reducing redundancy and randomness, which contributes to improving the clinical reliability of the diagnosis compared to the use of a single modality. The purpose of this article is first to determine the main steps of the CAD system for brain magnetic resonance imaging (MRI). Then to bring together some research work related to the diagnosis of brain disorders, emphasizing AD. Thus the most used methods in the stages of classification and brain regions segmentation are described, highlighting their advantages and disadvantages. Secondly, on the basis of the raised problem, we propose a solution within the framework of multimodal fusion. In this context, based on quantitative measurement parameters, a performance study of multimodal CAD systems is proposed by comparing their effectiveness with those exploiting a single MRI modality. In this case, advances in information fusion techniques in medical imagery are accentuated, highlighting their advantages and disadvantages. The contribution of multimodal fusion and the interest of hybrid models are finally addressed, as well as the main scientific assertions made, in the field of brain disease diagnosis.

A Survey on Computer-Aided Diagnosis of Brain Disorders through MRI Based on Machine Learning and Data Mining Methodologies with an Emphasis on Alzheimer Disease Diagnosis and the Contribution of the Multimodal Fusion

This work introduces an efficient approach for brain tumour detection using curvelet transform–based statistical features combined with GLCM (Grey Level Cooccurrence Matrix) texture features. The detection of the brain tumour is considered as a challenging problem, due to the irregularity of the highly varying structure of the tumour cells. The major contribution of the proposed work resides in the selection of significant features from both spatial and frequency domains for training the system. It combines the curvelet transform–based statistical features in the frequency domain with the GLCM texture features in the spatial domain. The proposed method applies skull–stripping as the pre–processing step to extract the brain portion from the MRI slice. This pre–processed image is subjected to watershed transform–based segmentation process to extract the necessary region of interest. From the extracted region of interest, frequency and spatial domain–based features are extracted. Finally, the classification model is developed using support vector machine. Experiments reveal that the proposed classifier is good in terms of accuracy.

A comprehensive framework for classification of brain tumour images using SVM and curvelet transform

Objectives: In this paper, the performance of similarity measures such as Edge Based Similarity Measure and Structural Similarity Index Measure is evaluated and also compared with the existing medical image fusion techniques. Materials and Methods: Multimodality Medical Image fusion is the process of fusing two Medical images obtained from two different sensors for better diagnosis. Medical image fusion combines and merges all relevant and complementary information from multiple source images into single composite image which facilitates more precise diagnosis and better treatment. The fused image should convey a better description of the scene than the individual images. The performance of the fused image is evaluated by various metrics such as Peak Signal to Noise Ratio (PSNR), Entropy, Standard deviation, Edge Based Similarity Measure (EBSM) and Structural Similarity Index Measure (SSIM). This paper proposes a method for fusion of Medical images using Dual Tree Complex Wavelet Transform (DTCWT) and Self Organizing Feature Map (SOFM). Findings: The performance of the proposed fusion algorithm is evaluated over pairs of CT and MR images obtained from patients in comparison with existing fusion techniques such as Discrete Wavelet Transform (DWT), Nonsubsampled Contourlet Transform (NSCT) and Fast Discrete Curvelet Transform (FDCT). In this paper, performance is evaluated by using the metric; Edge based Similarity Measure (EBSM), and Structural Similarity Index (SSIM). Applications / Improvements: Through the simulation result, as compared with the DWT, FDCT, NSCT and DTCWT fusion methods, it is concluded that the Multimodality image fusion using DTCWT with Robust Second Order First Moment (SOFM) gives better Edge based similarity measure and Structural similarity index measure.

Comparative Analysis of Similarity Measure Performance for Multimodality Image Fusion using DTCWT and SOFM with Various Medical Image Fusion Techniques

Image fusion is the process of combining relevant information from a set of images into a single image in which the fused image contains more information than any of the input images. This technique improves the quality of data. Image fusion is one of the important re-processing steps in digital image reconstruction. In this paper a review on some of the image fusion techniques like curvelet transform, wavelet transform, contourlet transform, stationary wavelet transform, framelet transform etc. used in image fusion is submitted.

/pdf/analysis-on-image-fusion-techniques-formedical-applications-377ur3qlj3.pdf

Analysis on Image Fusion Techniques forMedical Applications

Image Fusion is a technique that integrates complementary information from multiple images such that the fused image is more suitable for processing tasks. The paper starts with the study of initial concepts for image fusion. In this paper, the fusion of images from different sources using multiresolution wavelet transform with preprocessing of Image Fusion is proposed. The fused image has more complete information which is useful for human or machine perception. The fused image with such rich information will improve the performance of image analysis algorithms for medical applications.

Image Fusion based on Wavelet Transform for Medical Application

The brain tumor is a cluster of the abnormal tissues, and it is essential to categorize brain tumors for treatment using Magnetic Resonance Imaging (MRI). The segmentation of tumors from brain MRI is understood to be complicated and also crucial tasks. It can be further use in surgery, medical preparation, and assessments. In addition to this, the brain MRI classification is also essential. The enhancement of machine learning and technology will aid radiologists in diagnosing tumors without taking invasive steps. In this paper, the method to detect a brain tumor and classification has been present. Brain tumor detection processes through pre-processing, skull stripping, and tumor segmentation. It is employing a thresholding method followed by morphological operations. The number of training image influences the feature extracted by the CNN, then CNN models overfit after some epoch. Hence, deep learning CNN with transfer learning techniques has evolved. The tumorous brain MRI is classified using CNN based AlexNet architecture. Further, the malignant brain tumor is classified using GooLeNet transfer learning architecture. The performance of this approach is evaluated by precision, recall, F-measure, and accuracy metrics.

/pdf/a-framework-for-brain-tumor-segmentation-and-classification-42yl2150pn.pdf

A framework for Brain Tumor Segmentation and Classification using Deep Learning Algorithm

A brain tumor is the gathering, or mass, of unusual cells in the cerebrum. The skull, which encases the mind, is extremely unbending. Any advancement inside such a confined space can cause issues. Experts refers a tumor based on where the tumor cells started, and whether they are dangerous (malignant) or not (benign). Main aim of the image segmentation is to find the location and size of the tumor present in the brain. In this paper various types of segmentation algorithms are reviewed.

A Review on Image Segmentation for Brain Tumor Detection

The image fusion algorithm based on wavelet transform works successfully for linear objects but its basic limitation arises for fusion of curved shapes. It is observed that most of medical images contain curved shape objects. In this paper Innovative Image fusion algorithm based on Fast Discrete Curvelet transform with different Fusion Rules such as Minimum Selection, PCA based rule, Averaging rule, Maximum selection rule and Laplacian pyramid rule is implemented and experimental results from different fusion rules are compared with each other. The performance evaluation is done by considering 7 quality metrics parameters like Mean, Standard deviation, Entropy, Average Gradient, Correlation coefficient, RMSE and PSNR etc which proves improved performance than Wavelet transform and other Curvelet transforms in terms of visual quality and information content of fused image. The results obtained can be helpful for medical diagnosis of patient for further treatment.

Innovative image fusion algorithm based on fast discrete curvelet transform with different fusion rules

fusion is widely used term in different applications namely satellite imaging, remote sensing, multifocus imaging and medical imaging. In this paper, we have implemented multi level image fusion in which fusion is carried out in two stages. Firstly, Discrete wavelet or Fast Discrete Curvelet transform is applied on both source images and secondly image fusion is carried out with either spatial domain methods like Averaging, Minimum selection, maximum selection and PCA or with Pyramid transform methods like Laplacian Pyramid transform. Further, comparative analysis of fused image obtained from both Discrete Wavelet and Fast Discrete Curvelet transform is done which proves effective image fusion using proposed Curvelet transform than Wavelet transform through enhanced visual quality of fused image and by analysis of 7 quality metrics parameters. The proposed method is very innovative which can be applied to medical and multifocus imaging applications in real time. These analyses can be useful for further research work in image fusion and also the fused image obtained using Curvelet transform can be helpful for better medical diagnosis.

/pdf/innovative-multilevel-image-fusion-algorithm-using-4ut6wvoho6.pdf

Innovative Multilevel Image Fusion Algorithm using Combination of Transform Domain and Spatial Domain Methods with Comparative Analysis of Wavelet and Curvelet Transform

Sunita M. Kulkarni

Papers

Image Fusion based on Wavelet Transform for Medical Application

A framework for Brain Tumor Segmentation and Classification using Deep Learning Algorithm

A Review on Image Segmentation for Brain Tumor Detection

Innovative image fusion algorithm based on fast discrete curvelet transform with different fusion rules

Innovative Multilevel Image Fusion Algorithm using Combination of Transform Domain and Spatial Domain Methods with Comparative Analysis of Wavelet and Curvelet Transform