A5090610889- Advanced Image Fusion Techniques
- Ultrasound Imaging and Elastography
- Ultrasound and Hyperthermia Applications
- Photoacoustic and Ultrasonic Imaging
- Image Enhancement Techniques
- Image Processing Techniques and Applications
- Remote-Sensing Image Classification
- Image and Signal Denoising Methods
- Remote Sensing and Land Use
- Spectroscopy Techniques in Biomedical and Chemical Research
- Flow Measurement and Analysis
- Advanced MRI Techniques and Applications
- Advanced Data Compression Techniques
- Brain Tumor Detection and Classification
- Peripheral Artery Disease Management
- Tendon Structure and Treatment
- Medical Imaging and Analysis
- Medical Image Segmentation Techniques
- Diagnosis and Treatment of Venous Diseases
- Digital Filter Design and Implementation
Technical University of Denmark
2022-2024
Babol Noshirvani University of Technology
2015-2022
The purpose of multi-focus image fusion is gathering the essential information and focused parts from input images into a single image. These are captured with different depths focus cameras. A lot techniques have been introduced using considering measurement in spatial domain. However, processing very time-saving appropriate discrete cosine transform (DCT) domain, especially when JPEG used visual sensor networks (VSN). So most researchers interested measurements calculation processes...
Deep learning (DL) methods have been recently utilized in medical imaging diagnosis and prognosis, which significantly improved the performance of algorithms. As Alzheimer's Disease (AD) is one most financial costly diseases, many researchers concentrated on introducing a high accuracy automated algorithm for classifying AD Normal Control (NC) cases. In this paper we proposed new deep based method disease diagnosis. Among DL networks, Siamese Convolutional Neural Network (SCNN) implemented...
Multi-focus image fusion is a process that fuses several images from scene with different focal lengths into whole in which all areas are focused on. Image methods the Discrete Cosine Transform (DCT) domain efficient due to their low time and energy consumption, complexity. This especially true when fusing compressed JPEG format Visual Sensor Networks (VSN). In this paper, complexity multi-focus DCT presented increases output quality. Our proposed method makes it suitable for real-time...
Super resolution ultrasound imaging using the erythrocytes (SURE) has recently been introduced. The method uses as targets instead of fragile microbubbles (MBs). abundance erythrocyte scatterers makes it possible to acquire SURE data in just a few seconds compared several minutes localization microscopy (ULM) MBs. A high number can reduce acquisition time, however, tracking uncorrelated and high-density is quite challenging. This paper hypothesizes that detect track obtain vascular flow...
A new approach for vascular super resolution imaging using the erythrocytes as targets (SURE imaging) is described and investigated. SURE does not require fragile contrast agent bubbles, making it possible to use maximum allowable mechanical index ultrasound scanning an increased penetration depth. synthetic aperture sequence was employed with 12 virtual sources a 10 MHz GE L8-18i-D linear array hockey stick probe. The axial 1.20λ,(185.0μm) lateral 1.50λ,(231.3μm). Field IIpro simulations...
Multi-focus image fusion is used to collect useful and necessary information from input images with different focus depths in order create an output that ideally has all images. In this article, efficient, new simple method proposed for multi-focus which based on correlation coefficient calculation the discrete cosine transform (DCT) domain. Image algorithms are DCT very appropriate, they consume less time energy, especially when JPEG visual sensor networks (VSN). The evaluates amount of...
Image fusion process is defined as extracting information and specific features from multiple input images combining them into a single image which has all essential information. methods have been proposed in DCT domain are very convenient time-saving real-time applications. The fused output of existing low quality due to the side effects their algorithms. In this article, an efficient simple method using improved variance criteria presented. uses sharpened make larger difference between...
Velocity estimation in ultrasound imaging is a technique to measure the speed and direction of blood flow. The flow velocity small vessels, i.e., arterioles, venules, capillaries, can be estimated using super-resolution (SRUS). However, vessel width SRUS relatively compared with full-width-half-maximum beam elevation (FWHM
Deep Learning (DL) has been recently utilized for image fusion applications. The aim of DL based multi-focus methods is to create the better decision map fusing input images compared with previous traditional in spatial and transform domains. Hence, Convolution Neural Networks (CNN) Fully (FCN) that were used recent have unsuitable initial segmented map, their architectures a large number parameters which need be updated during training process. This paper proposed simple method inspired by...
The purpose of multi-focus image fusion is gathering the essential information and focused parts from input images into a single image. These multi-focused are captured with different depths focus cameras. Multi-focus very time-saving appropriate in discrete cosine transform (DCT) domain, especially when JPEG used visual sensor networks (VSN). previous works DCT domain have some errors selection suitable divided blocks according to their criterion for measurement block contrast. In this...
One of the integral parts super-resolution ultrasound imaging (SRI) is particle tracking. This paper presents tracking for a new approach SUper Resolution using Erythrocytes (SURE), which uses erythrocytes as target instead fragile microbubbles. The acquisition SURE data can be accomplished in seconds due to abundance targets. nearest-neighbor (NN) algorithm was used track erythrocytes. erythrocyte targets were tracked create intensity map by three NN trackers with constraint on maximum...
Microbubbles (MBs) tracking is an integral part of super-resolution ultrasound imaging (SRI). In SRI, MBs are tracked to make intensity and velocity maps. These must be sparse separable reliable for a desired However, the distribution necessitates several minutes long acquisitions go through whole circulation. Because abundance targets in SUper Resolution with Erythrocyte (SURE), it possible super resolution image just seconds instead SRI MBs. That means increasing number scatterers could...
Filtering is an important issue in signals and images processing. Many videos are compressed using discrete cosine transform (DCT). For reducing the computation complexity, we interested filtering block directly DCT domain. This article proposed efficient yet very simple method domain for any symmetric, asymmetric, separable, inseparable one or two dimensional filter. The achieved by mathematical relations vector processing image which it equivalent to spatial zero padding filtering. Also...
This paper presents fast pixel-wise multi-focus image fusion in the spatial domain without bells and whistles. The proposed method just uses determinant of sliding windows from input images as a metric to create decision map. 15 pixels with stride 7 are passed through images. Then it creates map for Also, some simple tricks like global threshold using Otsu's removal small objects by morphological closing operation used refine is high-speed can fuse pair 512x512 around 0.05 seconds (50...
Super-resolution ultrasound imaging (SRI) has shown the potential for visualization of vasculature with sub-wavelength resolution. Microbubble (MB) tracking in SRI can improve image quality and enable velocity estimation. However, it is usually neglected that size vessel might be relatively small compared to full width half maximum resolution elevation direction (FWHMy) estimated by algorithms lower than true velocity. Considering desired vessels SRI, hypothesized underestimated when MB...
A key component of super-resolution ultrasound imaging (SRI) is the detection and tracking scatterers. These scatterers can be microbubbles (MBs) in SRI, or erythrocytes SUper Resolution using Erythrocytes (SURE). To ensure reliability MBs must sparse. However, sparse distribution necessitates several minutes acquisition. In contrast, there are large numbers SURE. Increasing number reduce acquisition time, however uncorrelated high-density quite challenging. It hypothesized that recursive...
SUper-Resolution ultrasound imaging using the Erythrocytes (SURE) can visualize blood vessels at about 25 to 50 µm resolution, but validation is required assess how accurately vasculature and its morphology are represented. Previous work compared maximum intensity projections (MIP) of micro-CT volumes an insufficient voxel size 22.6 µm. Here, a 5 volume cortical region in excised rat kidney was acquired test hypothesis that down diameter detected with SURE imaging. For volume, were segmented...