Efficient Pre-Processing and Segmentation for Lung Cancer Detection Using Fused CT Images

Over the last two decades, radiologists have been using multi-view images to detect tumors. Computer Tomography (CT) imaging is considered as one of the reliable imaging techniques. Many medical-image-processing techniques have been developed to diagnoses lung cancer at early or later stages through CT images; however, it is still a big challenge to improve the accuracy and sensitivity of the algorithms. In this paper, we propose an algorithm based on image fusion for lung segmentation to optimize lung cancer diagnosis. The image fusion technique was developed through Laplacian Pyramid (LP) decomposition along with Adaptive Sparse Representation (ASR). The suggested fusion technique fragments medical images into different sizes using the LP. After that, the LP is used to fuse the four decomposed layers. For the evaluation purposes of the proposed technique, the Lungs Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) was used. The results showed that the Dice Similarity Coefficient (DSC) index of our proposed method was 0.9929, which is better than recently published results. Furthermore, the values of other evaluation parameters such as the sensitivity, specificity, and accuracy were 89%, 98% and 99%, respectively, which are also competitive with the recently published results.

Pan-Sharpening for Spectral Details Preservation Via Convolutional Sparse Coding in Non-Subsampled Shearlet Space

The optical satellite sensors encounter certain constraints on producing high-resolution multispectral (HRMS) images. Pan-sharpening (PS) is a remote sensing image fusion technique, which is an effective mechanism to overcome the limitations of available imaging products. The prevalent issue in PS algorithms is the imbalance between spatial quality and spectral details preservation, thereby producing intensity variations in the fused image. In this paper, a PS method is proposed based on convolutional sparse coding (CSC) implemented in the non-subsampled shearlet transform (NSST) domain. The source images, panchromatic (PAN) and multispectral (MS) images, are decomposed using NSST. The resultant high-frequency bands are fused using adaptive weights determined from chaotic grey wolf optimization (CGWO) algorithm. The CSC-based model is employed to fuse the low-frequency bands. Further, an iterative filtering mechanism is developed to enhance the quality of fused image. Four datasets with different geographical content like urban area, vegetation, etc. and eight existing algorithms are used for evaluation of the proposed PS method. The comprehensive visual and quantitative results approve that the proposed method accomplishes considerable improvement in spatial and spectral details equivalence in the pan-sharpened image.

Astrometric Observations of a Near-Earth Object Using the Image Fusion Technique

The precise astrometric observation of small near-Earth objects (NEOs) is an important observational research topic in the astrometric discipline, which greatly promotes multidisciplinary research, such as the origin and evolution of the solar system, the detection and early warning of small NEOs, and deep-space navigation. The characteristics of small NEOs, such as faintness and fast moving speed, restrict the accuracy and precision of their astrometric observations. In the paper, we present a method to improve the accurate and precise astrometric positions of NEOs based on image fusion technique. The noise analysis and astrometric test from the observed images of the open cluster M23 are given. Using the image fusion technique, we obtain the sets of superimposed images and original images containing reference stars and moving targets, respectively. The final fused image set includes background stars with high signal-to-noise ratios and ideal NEO images simultaneously and avoids the saturation of background stars. Using the fused images, we can reduce the influence of telescope tracking and NEO ephemeris errors on astrometric observations, and our results indicate that the accuracy and precision of NEO Eros astrometry are improved obviously after we choose suitable image fuse mode.

Polarimetric Dehazing Method Based on Image Fusion and Adaptive Adjustment Algorithm

To improve the robustness of current polarimetric dehazing scheme in the condition of low degree of polarization, we report a polarimetric dehazing method based on the image fusion technique and adaptive adjustment algorithm which can operate well in many different conditions. A splitting focus plane linear polarization camera was employed to grab the images of four different polarization directions, and the haze was separated from the hazy images by low-pass filtering roughly. Then the image fusion technique was used to optimize the method of estimating the transmittance map. To improve the quality of the dehazed images, an adaptive adjustment algorithm was introduced to adjust the illumination distribution of the dehazed images. The outdoor experiments have been implemented and the results indicated that the presented method could restore the target information obviously, and both the visual effect and quantitative evaluation have been enhanced.

Assessment of 3D Lumbosacral Vascular Anatomy for OLIF51 by Non-Enhanced MRI and CT Medical Image Fusion Technique

Study design: Prospective study. Objective: Medical image fusion can provide information from multiple modalities in a single image. The present study aimed to determine whether three-dimensional (3D) lumbosacral vascular anatomy could be adequately portrayed using a non-enhanced CT–MRI medical image fusion technique. Summary of Background Data: Lateral lumbar interbody fusion has gained popularity for the surgical treatment of adult spinal deformity (ASD). Oblique lumbar interbody fusion at L5–S1 (OLIF51) is receiving considerable attention as a method of creating good L5–S1 lordosis. Access in OLIF51 requires evaluation of the vascular anatomy in the lumbosacral region. Conventional imaging modalities need a contrast medium to describe the vascular anatomy. Methods: Participants comprised 15 patients with ASD or degenerative lumbar disease who underwent corrective surgery at our hospital between January 2020 and June 2021. A 3D vascular image with bony structures was obtained by fusing results from MRI and CT. We processed the merged image and measured the distance between left and right common iliac arteries and veins at two levels: the lower end of the L5 vertebral body (Window A) and the upper end of the S1 vertebral body (Window B). Results: The mean sizes of Window A and Window B were 29.7 ± 10.7 mm and 36.9 ± 10.3 mm, respectively. The mean distance from the bifurcation to the lower end of the L5 vertebra was 23.7 ± 10.9 mm. Coronal deviation of the bifurcation was, from center to left, 12.6 ± 12.3 mm, and the distance from the center of the L5 vertebral body to the bifurcation was 0.79 ± 7.3 mm. Only one case showed a median sacral vein (6.7%). Clinically, we performed OLIF51 in 12 of the 15 cases (80%). Conclusion: Evaluating 3D lumbosacral vascular anatomy using a non-enhanced MRI and CT medical image fusion technique is very useful for OLIF51, particularly for patients in whom the use of contrast medium is contraindicated.

Fusión de imágenes satelitales usando la transformada de Brovey y enriquecimiento espectral sobre computación heterogénea CPU/GPU

Satellite image fusion provides a context for potential applications in several fields such as agricultural development, hydrology, environmental studies, and natural disaster actions plans. However, when dealing with large-size images, the time required for the fusion process grows significantly. To reduce processing delays, the present study proposes the use of the Brovey transform as an image-fusion technique together with a spectral richness calibration stage. The proposal makes use of a CPU/GPU heterogeneous computing architecture based on mass parallel processing, conducted with CUDA. The fusion process of a 8192-pixel image evinced a speed-up of 532X. Regarding the quality of the resulting image, a per-band average correlation coefficient of 0.9714 (spatial detail) was obtained when comparing the fused and panchromatic images in an (R,G,B) color space.

A Novel Approach of Image Fusion Techniques using Ant Colony Optimization

Ant Colony Optimization (ACO) is a relatively high approach for finding a relatively strong solution to the problem of optimization. The ACO based image fusion technique is proposed. The objective function and distance matrix is designed for image fusion. ACO is used to fuse input images at the feature-level by learning the fusion parameters. It is used to select the fusion parameters according to the user-defined cost functions. This algorithm transforms the results into the initial pheromone distribution and seeks the optimal solution by using the features. As to relevant parameters for the ACO, three parameters (α, β, ρ ) have the greatest impact on convergence. If the values of α, β are appropriately increased, convergence can speed up. But if the gap between these two is too large, the precision of convergence will be negatively affected. Since the ACO is a random search algorithm, its computation speed is relatively slow.

Defect Detection Based on Segmentation of Thermographic Images of Frequency Modulated Thermal Wave Imaging

To improve the usefulness of the data, the raw images acquired during non-destructive testing should be processed by image processing techniques. In this paper, by Frequency Modulated Thermal Wave Imaging, we use the image fusion technique to boost the detection capability of defects in a GFRP sample with 25 squared Teflon inserts of different sizes positioned at various depths. In applications such as detection, image segmentation is useful where it is difficult to process the entire image at a time. In this paper, Adaptive Thresholding Image segmentation is used to classify the delamination in Thermographic Images of Infrared Non-Destructive Research on images captured at two different times. Image fusion is later applied to segmented images. Image fusion is used to merge two or more pictures of a different focus and to provide the best picture quality. Fusion is carried out using the Basic Averaging Method here. Using Relative Foreground Area error, the performance of the proposed method is quantitatively assessed. The region and shape of an object are important parameters in the case of Non-Destructive Evaluation. Such parameters are contrasted with current methods of segmentation