Segmentation of glioma tumors using convolutional neural networks

The abnormal development of cells in brain leads to the formation of tumors in brain. In this article, image fusion based brain tumor detection and segmentation methodology is proposed using convolutional neural networks (CNN). This proposed methodology consists of image fusion, feature extraction, classification, and segmentation. Discrete wavelet transform (DWT) is used for image fusion and enhanced brain image is obtained by fusing the coefficients of the DWT transform. Further, Grey Level Co‐occurrence Matrix features are extracted and fed to the CNN classifier for glioma image classifications. Then, morphological operations with closing and opening functions are used to segment the tumor region in classified glioma brain image.     

一种抽样小波域的遥感影像融合新方法

针对传统图像融合方法的不足,提出了一种新的基于IHS变换与抽样小波变换的高清晰遥感影像融合方法.该方法将直方图匹配后的全色影像的高频系数作为融合后的高频系数,而融合后的低频系数依据新提出的融合规则得到,最后采用小波逆变换与逆IHS变换获得融合图像.实验结果表明,该方法在提高融合影像的空间分辨率与光谱质量之间得到了更好的折衷.该方法的计算复杂度接近于常用的基于抽样小波变换的融合方法,明显少于基于非抽样小波变换的融合方法.     

Multimodal neurological image fusion based on adaptive biological inspired neural model in nonsubsampled Shearlet domain

Multimodal medical image fusion (MMIF) has a significant role for a better visualization of the diagnostic statistics, those help the medical professionals in the precise diagnosis of several critical diseases. This paper presents an improved fusion framework that uses the entire features extracted by the nonsubsampled shearlet transform (NSST) and adaptive biologically inspired neural model. The proposed scheme retains the required information without losing the resolution of the disease morphology. In the proposed method, the adaptive neural model based on local visibility and log Gabor energy based rules are applied to low and high-frequency components, respectively. The better fusion results obtained by the proposed approach are confirmed by a large extent of simulations on the different MR-SPECT and CT-MR neurological images. Based on all these simulated results, it states that the proposed approach is superior than the other approaches as it produces better visually fused images with improved computational measures.     

基于小波神经网络的图像表述

小波神经网络有机地融合了小波分析的时频特性和神经网络自适应优点。本文将小波神经网络应用于图像表述，提出相应的图像表述算法。分别采用两种小波函数作为网络激励函数，以验证图像表述效果。实验结果表明，小波神经网络能够有效地表述图像，其算法具有较强的鲁棒性。     

Medical image fusion based on laws of texture energy measures in stationary wavelet transform domain

Medical image fusion is widely used in various clinical procedures for the precise diagnosis of a disease. Image fusion procedures are used to assist real-time image-guided surgery. These procedures demand more accuracy and less computational complexity in modern diagnostics. Through the present work, we proposed a novel image fusion method based on stationary wavelet transform (SWT) and texture energy measures (TEMs) to address poor contrast and high-computational complexity issues of fusion outcomes. SWT extracts approximate and detail information of source images. TEMs have the capability to capture various features of the image. These are considered for fusion of approximate information. In addition, the morphological operations are used to refine the fusion process. Datasets consisting of images of seven patients suffering from neurological disorders are used in this study. Quantitative comparison of fusion results with visual information fidelity-based image fusion quality metric, ratio of spatial frequency error, edge information-based image fusion quality metric, and structural similarity index-based image fusion quality metrics proved the superiority. Also, the proposed method is superior in terms of average execution time to state-of-the-art image fusion methods. The proposed work can be extended for fusion of other imaging modalities like fusion of functional image with an anatomical image. Suitability of the fused images by the proposed method for image analysis tasks needs to be studied.     

A curvelet transform approach for the fusion of MR and CT images

There are several medical imaging techniques such as the magnetic resonance (MR) and the computed tomography (CT) techniques. Both techniques give sophisticated characteristics of the region to be imaged. This paper proposes a curvelet based approach for fusing MR and CT images to obtain images with as much detail as possible, for the sake of medical diagnosis. This approach is based on the application of the additive wavelet transform (AWT) on both images and the segmentation of their detail planes into small overlapping tiles. The ridgelet transform is then applied on each of these tiles, and the fusion process is performed on the ridgelet transforms of the tiles. Simulation results show the superiority of the proposed curvelet fusion approach to the traditional fusion techniques like the multiresolution discrete wavelet transform (DWT) technique and the principal component analysis (PCA) technique. The fusion of MR and CT images in the presence of noise is also studied and the results reveal that unlike the DWT fusion technique, the proposed curvelet fusion approach doesn't require denoising.     

基于小波系数邻域特征的CT与MR图像融合方法

提出一种基于小波变换的像素级CT,MR医学图像融合方法,利用离散小波变换分别将两幅源图像进行多尺度分解,再用不同的小波系数邻域特征指导高频分量和低频分量的小波系数的融合,低频分量采用邻域方差指导,高频分量采用邻域能量指导,最后根据融合图像的各小波系数重构融合图像.实验表明:不论从主观感受,还是采用信息熵和平均梯度两项指标作为客观定量评价标准,该方法都优于传统的融合方法,获得的融合图像有效地综合了CT与MR图像信息,能够同时清晰地显示脑部骨组织和软组织.     

一种NSCT域多聚焦图像融合新方法

针对多聚焦图像融合存在的问题,提出一种基于非下采样Contourlet变换（NSCT）的多聚焦图像融合新方法。首先,采用NSCT对多聚焦图像进行分解;然后,对低频系数采用基于改进拉普拉斯能量和（SML）的视觉特征对比度进行融合,对高频系数采用基于二维Log-Gabor能量进行融合;最后,对得到的融合系数进行重构得到融合图像。实验结果表明,无论是运用视觉的主观评价,还是基于互信息、边缘信息保留值等客观评价标准,该文所提方法都优于传统的离散小波变换、平移不变离散小波变换、NSCT等融合方法。     

多义图像合成算法研究

提出了一种基于小波变换的多义图像合成算法。该算法首先通过视角来选择小波分解级对两幅目标图像进行小波分解,然后根据可选的小波融合规则和权值变量融合并重构出在两个视角下的多义图像;对小波算法与现有两种算法进行了分析比较,通过试验证明该算法合成的结果多义特性更好,合成图视觉效果醒目并充分保留原目标图像的色彩和细节特征。合成结果采取了均值降噪。     

Image fusion based on wavelet transform and gray-level features

Image fusion makes the fused image more reliable and intelligible, and more suitable for human vision and computer detection, classification, recognition and understanding. This paper proposes a pixel-level image fusion method for merging two source images of the same scene using wavelet transform and gray-level features (GLF). First, a three-level discrete two-dimensional wavelet transform is used to decompose the two source images into low-frequency image components and horizontal, vertical, and diagonal high-frequency components. Then, the spatial frequency correlation coefficient is used to determine the pixel fusion rule to apply to each of the low-frequency images, and the correlation coefficient of the GLF is used to determine the pixel fusion rule to apply to each of the high-frequency images. Finally, the fused image is reconstructed using inverse wavelet transform. The results of the experiments conducted indicate that the proposed method is more effective than relevant conventional methods.     

Multifocus noisy image fusion using contourlet transform

Abstract

Image fusion is a challenging area of research with a variety of applications. The process of image fusion collects information from different sources and combines them in a single composite image. The composite fused image can better describe the scene than any of the source images. In this paper, we have proposed a method for noisy image fusion in contourlet domain. The proposed method works equally well for fusion of noise free images. Contourlet transform is a multiscale, multidirectional transform with various aspect ratios. These properties make it more suitable for image fusion than other conventional transforms. In the proposed work, the fusion algorithm is combined with a denoising algorithm to reverse the effect of noise. In the proposed method, we have used a level dependent threshold that is based on standard deviation of contourlet coefficients, mean and median of the absolute contourlet coefficients. Experimental results demonstrate that the proposed method performs well in the presence of different types of noise. Performance of the proposed method is compared with principal components analysis and sharp fusion based methods as well as other fusion methods based on variants of wavelet transform like dual tree complex wavelet transform, discrete wavelet transform, lifting wavelet transform, multiwavelet transform, stationary wavelet transform and pyramid transform using six standard quantitative quality metrics (entropy, standard deviation, edge strength, fusion factor, sharpness and peak signal to noise ratio). The combined qualitative and quantitative evaluation of the experimental results shows that the proposed method performs better than other methods.     

基于Curvelet变换的多聚焦图像融合方法

由于可见光成像系统的聚焦范围有限,很难获得同一场景内所有物体都清晰的图像.多聚焦图像融合技术可有效地解决这一问题.在分析了传统多聚焦图像融合方法和Curvelet变换的原理后,提出了一种基于Curvelet变换的多聚焦图像融合方法,先对不同聚焦图像分别进行Curvelet变换,采用低频系数取平均,高频系数取大的融合规则,再进行Curvelet反变换得到融合结果.仿真试验表明,基于Curvelet变换的融合方法可有效综合多聚焦图像,相比小波变换法,获得了更好的融合效果.     

基于边缘信息的偏振图像融合算法及评价

偏振遥感图像通常都采用强度、偏振度、偏振角来表征目标偏振特性.本文提出的基于边缘信息的偏振图像融合算法是将三幅偏振图像利用离散小波变换把图像分解成不同尺度的低频和高频部分,采用小波区域窗口和子区域窗口统计把小波系数分类成边缘和非边缘系数,通过这些方法进行有效的边缘细节信息提取.在融合处理中,低频图像的小波系数平均值作为融合后的低频系数,高频细节系数根据不同区域特征选择方法以及对应输入图像小波系数的窗口区域方差来确定融合后高频小波系数.仿真实验结果表明,这样使得融合后的图像细节更真实更丰富,图像的偏振特性体现更为充分,同时减少对源图像的预处理要求,使图像在整体上有较好的视觉效果.从而证明这种方法能够在保留图像微小细节方面获得满意的结果,且算法有效性优于其他的图像融合方法.     

Residual learning based CNN for breast cancer histopathological image classification

Biopsy is one of the most commonly used modality to identify breast cancer in women, where tissue is removed and studied by the pathologist under the microscope to look for abnormalities in tissue. This technique can be time-consuming, error-prone, and provides variable results depending on the expertise level of the pathologist. An automated and efficient approach not only aids in the diagnosis of breast cancer but also reduces human effort. In this paper, we develop an automated approach for the diagnosis of breast cancer tumors using histopathological images. In the proposed approach, we design a residual learning-based 152-layered convolutional neural network, named as ResHist for breast cancer histopathological image classification. ResHist model learns rich and discriminative features from the histopathological images and classifies histopathological images into benign and malignant classes. In addition, to enhance the performance of the developed model, we design a data augmentation technique, which is based on stain normalization, image patches generation, and affine transformation. The performance of the proposed approach is evaluated on publicly available BreaKHis dataset. The proposed ResHist model achieves an accuracy of 84.34% and an F1-score of 90.49% for the classification of histopathological images. Also, this approach achieves an accuracy of 92.52% and F1-score of 93.45% when data augmentation is employed. The proposed approach outperforms the existing methodologies in the classification of benign and malignant histopathological images. Furthermore, our experimental results demonstrate the superiority of our approach over the pre-trained networks, namely AlexNet, VGG16, VGG19, GoogleNet, Inception-v3, ResNet50, and ResNet152 for the classification of histopathological images.     

Greyscale image encoding and watermarking based on optical asymmetric cryptography and variational image decomposition

In this paper, a novel greyscale image encoding and a watermarking scheme based on optical asymmetric cryptography and variational image decomposition (VID) are proposed. In this proposed scheme, the greyscale watermark is encoded into a noise-like pattern by the phase-truncated Fresnel transform (PT-FrT)-based optical asymmetric cryptography. The greyscale host image is decomposed into its cartoon part and texture part by the VID technique. After that, the encoded watermark is embedded into the host image’s texture part by a discrete wavelet transform (DWT) based fusion approach. The proposed scheme can achieve a better watermark invisibility and a higher robustness by embedding the watermark into the host image’s texture part. Additionally, the proposed scheme can achieve a high security, because the PT-FrT-based optical asymmetric cryptography can resist some common cryptographic attacks. The feasibility, robustness and security of the proposed scheme have been demonstrated by extensive experiments and comparison with other relevant image encoding and watermarking schemes.     

一种采用多个小波基的图像融合去噪方法

提出了一种新的基于多个小波基的图像融合去噪方法.首先利用多个不同的小波基对含噪图像进行阈值去噪,得到多幅恢复图像.然后对这些图像采用小波融合方法进行融合.对于低频系数采用基于边缘的融合算法,在多幅恢复图像中选择最有可能是边缘的点加以保留;对于高频系数,采用了平均的融合算法.最后得到一幅去噪图像.实验结果表明,无论是在视觉效果上还是在峰值信噪比定量指标上该方法去噪效果均明显优于单一小波基去噪.     

Combination of wavelet transform and singular value decomposition-based contrast enhancement technique for target detection in UAV reconnaissance thermal images

In Aerial surveillance, thermal images acquired by unmanned aerial vehicle (UAV) are greatly affected due to various external interferences, which results in a low contrast image. Widely used conventional contrast enhancement methods such as histogram equalization and dynamic range partitioning techniques suffer from severe brightness changes and reduced sharpness, which in turn fail to preserve the edge details of the image. Thus for efficient target detection, it is essential to develop effective thermal infrared image contrast and edge enhancement technique. In this paper, wavelet transform (WT) and singular value decomposition (SVD)-based image enhancement technique is attempted for the target detection using thermal images captured by UAV. The discrete wavelet transform (DWT), stationary wavelet transform (SWT) and SVD are used for texture feature enhancement, edge enhancement and illumination correction, respectively. The experimental results show that the proposed technique yields higher entropy (6.7485), EMEE (2.1212), MSSIM (0.8719) and lower AMBE (21.9049) values when compared to other existing techniques.     

A novel multi-modal medical image fusion method based on shift-invariant shearlet transform

Abstract

Medical image fusion plays an important role in clinical applications, such as image-guided surgery, image-guided radiotherapy, non-invasive diagnosis and treatment planning. Shearlet is a novel multi-scale geometric analysis (MGA) tool proposed recently. In order to overcome the drawback of the shearlet-based fusion methods that the pseudo-Gibbs phenomenon is easily caused around the singularities of the fused image, a new multi-modal medical image fusion method is proposed in shift-invariant shearlet transform domain. First, the original images are decomposed into lowpass sub-bands and highpass sub-bands; then, the lowpass sub-bands and high sub-bands are combined according to the fusion rules, respectively. All the operations are performed in shift-invariant shearlet domain. The final fused image is obtained by directly applying inverse shift-invariant shearlet transform to the fused lowpass sub-bands and highpass sub-bands. Experimental results demonstrate that the proposed method can not only suppress the pseudo-Gibbs phenomenon efficiently, but perform better than the popular wavelet transform-based method, contourlet transform-based method and non-subsampled contourlet transform-based method.     

基于向量小波与神经网络的图像融合算法

提出了一种基于向量小波和神经网络的图像融合算法.首先对各源图像进行向量小波变换,根据变换后系数计算出各子块图像的清晰度,选取子块图像部分区域清晰度作为前溃神经网络的训练样本,调整神经网络权重;然后用训练好的神经网络组合融合图像的向量小波系数,对组合后的系数进行一致性校验;最后对该系数进行向量小波逆变换,得到融合图像.仿真实验表明,该算法能够较好地解决多传感器图像融合问题,生成的融合图像效果优于有代表性的图像融合方法.     

基于小波变换的图像融合方法研究

图像融合是多传感器信息融合的一个重要分支,小波变换是这一领域研究方法上的重大突破。本文通过对小波变换理论的研究,分析了二维离散小波分解与重构的算法,提出了一种高频小波系数直接替换的算法,并利用MATLAB数学分析工具环境实现全色图像和多光谱图像的融合,实验结果表明这种方法能很好地增强图像的光谱分辨率,便于对图像进行分析和识别。