Microscopic melanoma detection and classification: A framework of pixel‐based fusion and multilevel features reduction

The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel‐based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean‐based function is implemented and fed input to top‐hat and bottom‐hat filters which later fused for contrast stretching, (b) seed region growing and graph‐cut method‐based lesion segmentation and fused both segmented lesions through pixel‐based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy‐based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method.     

Construction of saliency map and hybrid set of features for efficient segmentation and classification of skin lesion

Skin cancer is being a most deadly type of cancers which have grown extensively worldwide from the last decade. For an accurate detection and classification of melanoma, several measures should be considered which include, contrast stretching, irregularity measurement, selection of most optimal features, and so forth. A poor contrast of lesion affects the segmentation accuracy and also increases classification error. To overcome this problem, an efficient model for accurate border detection and classification is presented. The proposed model improves the segmentation accuracy in its preprocessing phase, utilizing contrast enhancement of lesion area compared to the background. The enhanced 2D blue channel is selected for the construction of saliency map, at the end of which threshold function produces the binary image. In addition, particle swarm optimization (PSO) based segmentation is also utilized for accurate border detection and refinement. Few selected features including shape, texture, local, and global are also extracted which are later selected based on genetic algorithm with an advantage of identifying the fittest chromosome. Finally, optimized features are later fed into the support vector machine (SVM) for classification. Comprehensive experiments have been carried out on three datasets named as PH2, ISBI2016, and ISIC (i.e., ISIC MSK‐1, ISIC MSK‐2, and ISIC UDA). The improved accuracy of 97.9, 99.1, 98.4, and 93.8%, respectively obtained for each dataset. The SVM outperforms on the selected dataset in terms of sensitivity, precision rate, accuracy, and FNR. Furthermore, the selection method outperforms and successfully removed the redundant features.     

Brain tumor detection and classification: A framework of marker‐based watershed algorithm and multilevel priority features selection

Brain tumor identification using magnetic resonance images (MRI) is an important research domain in the field of medical imaging. Use of computerized techniques helps the doctors for the diagnosis and treatment against brain cancer. In this article, an automated system is developed for tumor extraction and classification from MRI. It is based on marker‐based watershed segmentation and features selection. Five primary steps are involved in the proposed system including tumor contrast, tumor extraction, multimodel features extraction, features selection, and classification. A gamma contrast stretching approach is implemented to improve the contrast of a tumor. Then, segmentation is done using marker‐based watershed algorithm. Shape, texture, and point features are extracted in the next step and high ranked 70% features are only selected through chi‐square max conditional priority features approach. In the later step, selected features are fused using a serial‐based concatenation method before classifying using support vector machine. All the experiments are performed on three data sets including Harvard, BRATS 2013, and privately collected MR images data set. Simulation results clearly reveal that the proposed system outperforms existing methods with greater precision and accuracy.     

最速上升关联向量机高光谱影像分类

针对高光谱影像近邻波段高度相关,直接在高维空间分类并非最优的问题,提出了基于最速上升和关联向量机(SA-RVM)的高光谱影像分类算法.使用最速上升(SA)算法搜索最优特征子空间,剔除冗余特征;然后,在特征子空间中训练RVM并分类.对4套测试数据进行的实验表明,SA选择的特征子空间中,RVM分类精度提高了2.5％以上,与支持向量机(SVM)相当.对训练样本较少的2套数据,精度提高了5.63％和6.2％.此外,SA-RVM的解稀疏,预测未知样本类别属性所需时间短.总体来看,SA-RVM精度高、判别速度快,适合处理大场景高光谱影像.     

基于DRGAN和支持向量机的合成孔径雷达图像目标识别

为解决SAR图像目标识别中样本缺乏和方位角敏感问题,提出了一种基于DRGAN和SVM的SAR图像目标识别算法。首先,采用多尺度分形特征对SAR图像进行增强,经过分割得到目标二值图像,基于Hu二阶矩估计目标的方位角。然后对估计得到的目标方位角进行量化编码,结合原始图像作为输入,对设计的DRGAN模型参数进行训练与优化。由于DRGAN中的深度生成模型将目标姿态与外观表示进行解耦设计,故可利用该模型将SAR图像样本变换到同一方位角区间。基于变换后的训练样本分别提取归一化灰度特征,利用SVM训练分类器。采用MSTAR数据集在多个不同操作条件下对提出的算法进行测试,实验结果表明,在带变体的标准操作条件下,能够达到97.97%的分类精度,优于部分基于CNN模型的分类精度,在4种扩展操作条件下的分类精度分别为97.83%,91.77%,97.11%和97.04%,均优于传统方法的分类精度。在SAR图像目标方位角估计存在一定误差的情况下,训练得到的GAN模型作为SAR图像目标旋转估计器,能够使得在不进行复杂样本预处理的前提下,仍然取得较高的SAR图像目标识别精度。     

基于区域划分的多特征纹理图像分割

由于纹理图像的复杂性和多样性,仅依靠传统的单一特征实现纹理图像分割无法满足其对分割精度的要求。本文提出结合区域划分的多特征纹理图像分割方法。首先,依据像素灰度的空间相关性定义多个纹理特征;然后利用区域划分将图像域划分成不同子区域,待分割同质区域由这些子区域拟合而成;通过分别定义多个特征图像的同质区域之间的异质性势能函数和刻画各子区域邻域关系势能函数来定义全局势能函数,并构建非约束吉布斯概率分布,从而建立纹理分割模型;最后,采用M-H算法采样上述概率分布,从而获得最优图像分割结果。分别对模拟纹理图像、遥感图像、自然纹理图像和SAR海冰图像进行了分割实验,并与利用单一特征得到的分割结果进行对比分析,定性和定量的测试结果验证了算法的有效性。     

基于数学形态学的新方法在脑组织分割中的应用

针对人体脑部切片图像特点,提出了一种基于数学形态学的脑组织自动分割算法.该算法首先通过形态重构获得粗糙的脑组织区域,然后运用腐蚀和膨胀运算进行边界定位分割出了脑组织,最后对连续断层图像的分割结果进行了三维重建.结果表明该算法分割准确且自动化程度高,适合于大量序列切片图像的快速自动分割.     

Deep learning model integrating features and novel classifiers fusion for brain tumor segmentation

Automatic and precise segmentation and classification of tumor area in medical images is still a challenging task in medical research. Most of the conventional neural network based models usefully connected or convolutional neural networks to perform segmentation and classification. In this research, we present deep learning models using long short term memory (LSTM) and convolutional neural networks (ConvNet) for accurate brain tumor delineation from benchmark medical images. The two different models, that is, ConvNet and LSTM networks are trained using the same data set and combined to form an ensemble to improve the results. We used publicly available MICCAI BRATS 2015 brain cancer data set consisting of MRI images of four modalities T1, T2, T1c, and FLAIR. To enhance the quality of input images, multiple combinations of preprocessing methods such as noise removal, histogram equalization, and edge enhancement are formulated and best performer combination is applied. To cope with the class imbalance problem, class weighting is used in proposed models. The trained models are tested on validation data set taken from the same image set and results obtained from each model are reported. The individual score (accuracy) of ConvNet is found 75% whereas for LSTM based network produced 80% and ensemble fusion produced 82.29% accuracy.     

结合先验稀疏字典和空洞填充的CT图像肝脏分割

针对复杂多变的肝脏图像,提出了一种基于先验稀疏字典和空洞填充的三维肝脏图像分割方法。对腹部CT图像进行Gabor特征提取,并分别在Gabor图像和灰度图像的肝脏金标准边界上选择大小相同的图像块作为两组训练集,利用训练集得到两种查询字典及稀疏编码。将金标准图像与待分割图像配准,并将配准后的肝脏边界作为待分割图像的肝脏初始边界;在初始边界点上的十邻域内选择大小相同的两组图像块作为测试样本,利用测试样本与查询字典计算稀疏编码及重构误差,并选择重构误差最小的图像块的中心作为待分割肝脏的边界点;最后,设计一种空洞填充方法对肝脏边界进行补全和平滑处理,得到最终分割结果。利用医学图像计算和计算机辅助介入国际会议中提供的肝脏数据进行了实验验证。结果表明,该方法对肝脏分割图像具有较好的适用性和鲁棒性,并获得了较高的分割精度。其中,平均体积重叠率误差为(5.21±0.45)%,平均相对体积误差为(0.72±0.12)%,平均对称表面距离误差为(0.93±0.14)mm。     

纹理引导的稀疏张量表示及在肺CT图像中的应用

基于张量理论在高维图像处理中的应用,提出一种张量模式的稀疏表示方法,以便有效地去除肺部CT序列图像的噪声,增强图像的有用信息。首先,设计了张量模式的正交匹配追踪法(TOMP)来表达稀疏系数;构建了高维K-奇异值分解法(HOK-SVD)用于字典更新。然后,对张量乘法的参数进行优化,即通过构造三维灰度共生矩阵,建立三维纹理特征与张量乘法模式之间的数学模型。最后,将这种方法应用于LIDC数据库的150组CT序列图像的预处理,对各算法的稀疏表示效果进行评价。与当前应用的其他方法相比,本文提出的高维K-SVD算法的的峰值信噪比提高了1.5%,平均误差降低了1.2%;在此预处理基础上进行的图像分割结果表明:图像的边缘偏移误差下降了3.0%,体积重叠率提高了1.2%。上述结果显示基于张量的方法可以更精确地完成对三维CT图像序列的稀疏表示。     

基于融合特征约减和支持向量机的控制图模式识别

为提高产品加工过程中质量监测的智能化程度,在运用控制图描述质量波动的基础上,提出了一种基于融合特征约减的KPCA-SVM控制图分类方法。先通过蒙特卡洛模拟生成控制图数据集,提取统计特征和形状特征,并将其与原始特征相融合,运用核主成分分析对高维融合特征降维,再使用遗传算法优化支持向量机的参数。通过仿真实验,将降维前后、不同分类器的识别精度进行了比较,结果表明运用所提方法能够得到更好的识别效果。     

基于多尺度分割的高光谱图像稀疏表示与分类

针对高光谱特征的稀疏表示,提出了一种基于多尺度分割的空间加权算法用于高光谱图像分类。该算法采用更合理的邻域定义挖掘空间先验信息,优化类边缘像元的稀疏表示。首先,通过多尺度分割提供邻域空间约束;结合拉普拉斯尺度混合(LSM)先验,分别对每个邻域组内像元进行空间加权的稀疏表示。然后,采用概率支持向量机(SVM)分类,同时提供像元的分类标签及其置信度。最后,以此置信度为权重,对多尺度分类图进行加权融合,生成最终的分类图。实验显示,本文算法能够增强光谱特征表示的稀疏性和鲁棒性,提高总体分类精度;在小样本训练下,单类的分类精度可提升30%左右,表明该算法在高光谱应用中具有较强的实用性。     

Modified cuckoo search algorithm in microscopic image segmentation of hippocampus

Microscopic image analysis is one of the challenging tasks due to the presence of weak correlation and different segments of interest that may lead to ambiguity. It is also valuable in foremost meadows of technology and medicine. Identification and counting of cells play a vital role in features extraction to diagnose particular diseases precisely. Different segments should be identified accurately in order to identify and to count cells in a microscope image. Consequently, in the current work, a novel method for cell segmentation and identification has been proposed that incorporated marking cells. Thus, a novel method based on cuckoo search after pre‐processing step is employed. The method is developed and evaluated on light microscope images of rats’ hippocampus which used as a sample for the brain cells. The proposed method can be applied on the color images directly. The proposed approach incorporates the McCulloch's method for lévy flight production in cuckoo search (CS) algorithm. Several objective functions, namely Otsu's method, Kapur entropy and Tsallis entropy are used for segmentation. In the cuckoo search process, the Otsu's between class variance, Kapur's entropy and Tsallis entropy are employed as the objective functions to be optimized. Experimental results are validated by different metrics, namely the peak signal to noise ratio (PSNR), mean square error, feature similarity index and CPU running time for all the test cases. The experimental results established that the Kapur's entropy segmentation method based on the modified CS required the least computational time compared to Otsu's between‐class variance segmentation method and the Tsallis entropy segmentation method. Nevertheless, Tsallis entropy method with optimized multi‐threshold levels achieved superior performance compared to the other two segmentation methods in terms of the PSNR.     

Integrated approach for segmentation of 3-D confocal images of a tissue specimen

In this article we have proposed an integrated approach for segmentation of cells in volumetric image data obtained using the Confocal Microscope. The volumetric images are the stack of two-dimensional (2-D) images. Segmentation of cells in such an image stack is a difficult problem due to the complex structure of the objects and the spatial relationship of the object signatures in different image slices of the image stack. Here we have proposed a segmentation technique, which is a combination of several known and novel segmentation methods. Low-level techniques such as edge operators, middle-level techniques such as 3-D watershed, rule-based merging, and a high level technique, active surface model optimization, are integrated in one approach to get better segmentation with less human interaction. Some image enhancement and noise reduction techniques are also used to reduce the error in intermediate stages and speed up the segmentation process. Results are shown on 3-D images of prostate cancer tissue specimen.     

基于图像融合技术的变电站二次设备热故障自主定位研究

提出基于图像融合技术的变电站二次设备热故障自主定位方法。通过非下采样Contourlet变换法融合变电站二次设备红外图像与可见光图像,运用了最大类间方差法分割融合图像,获得包含变电站二次设备热故障区域的感兴趣区域。采用了形态学开闭运算和像素统计,分别完成分割图像的预处理与结构区域划分,实现变电站二次设备热故障自主定位以及热故障等级判断。实验结果表明：该方法所得融合图像的质量明显高于融合前的2种图像质量;图像分割获得的感兴趣区域较为完整,能很好地保留设备边缘轮廓和纹理特征;各二次设备热故障自主定位区域与热故障实际区域相同,且自主定位最高用时仅为37 s。     

加权空-谱与最近邻分类器相结合的高光谱图像分类

提出了一种基于加权空-谱距离(WSSD)的相似性度量方法 ,并将其应用到最近邻分类器(KNN)中,导出了一种新的高光谱图像分类算法。该算法利用高光谱图像的物理特性,通过引入空间窗口和光谱因子这两个参数来挖掘出图像中的空间信息与光谱信息,利用空间近邻点对中心像元进行重构。在最大限度减少图像冗余信息的基础上,增大了同类像元间的相似性以及异类像元间的差异性,获得了更为有效的鉴别特征,从而更好地实现了数据间的相似性度量。基于Indian Pines和PaviaU高光谱数据集进行了实验,结果表明:将提出的WSSD-KNN算法应用于高光谱图像分类时,其分类精度高于其他算法,总体分类精度分别达到了91.72%和96.56%。由于算法较好地融合了图像中的空间-光谱信息,提取出了更为有效的鉴别特征,故不仅有效地改善了高光谱数据的地物分类精度,而且可在训练样本较少时,保持较高的识别率。     

自然光线环境中的空间物体快速识别和定位算法研究

针对智能机械臂在自然光环境的三维空间中对目标物体的自主识别率和定位精度低的问题,提出了一种基于深度学习的视觉和光学雷达融合定位算法,实现自然光线下空间物体的高精度快速定位。首先,采集 RGB 图像和深度数据,利用深度学习算法对图像进行目标识别与实例分割;然后,将实例分割目标物的二维深度矩阵转换成三维空间点云;最后,用综合修正算法对位置修正,实现对目标物体在三维空间的抓取位置精准定位。 通过不同光照强度下的目标物体识别和定位实验验证了该算法的有效性和实用性,获取的目标物体的三维空间坐标较为精确,单位距离的定位误差在 0. 5%以内,受照明亮度影响较小,对机械臂智能抓取的研究具有较为重要的意义。     

Intelligent microscopic approach for identification and recognition of citrus deformities

Plant diseases are accountable for economic losses in an agricultural country. The manual process of plant diseases diagnosis is a key challenge from last one decade; therefore, researchers in this area introduced automated systems. In this research work, automated system is proposed for citrus fruit diseases recognition using computer vision technique. The proposed method incorporates five fundamental steps such as preprocessing, disease segmentation, feature extraction and reduction, fusion, and classification. The noise is being removed followed by a contrast stretching procedure in the very first phase. Later, watershed method is applied to excerpt the infectious regions. The shape, texture, and color features are subsequently computed from these infection regions. In the fourth step, reduced features are fused using serial‐based approach followed by a final step of classification using multiclass support vector machine. For dimensionality reduction, principal component analysis is utilized, which is a statistical procedure that enforces an orthogonal transformation on a set of observations. Three different image data sets (Citrus Image Gallery, Plant Village, and self‐collected) are combined in this research to achieving a classification accuracy of 95.5%. From the stats, it is quite clear that our proposed method outperforms several existing methods with greater precision and accuracy.     

Overlapping nuclei segmentation based on Bayesian networks and stepwise merging strategy

This paper presents a new approach to the segmentation of fluorescence in situ hybridization images. First, to segment the cell nuclei from the background, a threshold is estimated using a Gaussian mixture model and maximizing the likelihood function of the grey values for the cell images. After the nuclei segmentation, the overlapping and isolated nuclei are classified to facilitate a more accurate nuclei analysis. To do this, the morphological features of the nuclei, such their compactness, smoothness and moments, are extracted from training data to generate three probability distribution functions that are then applied to a Bayesian network as evidence. Following the nuclei classification, the overlapping nuclei are segmented into isolated nuclei using an intensity gradient transform and watershed algorithm. A new stepwise merging strategy is also proposed to merge fragments into a major nucleus. Experimental results using fluorescence in situ hybridization images confirm that the proposed system produced better segmentation results when compared to previous methods, because of the nuclei classification before separating the overlapping nuclei.     

Empirical gradient threshold technique for automated segmentation across image modalities and cell lines

New microscopy technologies are enabling image acquisition of terabyte‐sized data sets consisting of hundreds of thousands of images. In order to retrieve and analyze the biological information in these large data sets, segmentation is needed to detect the regions containing cells or cell colonies. Our work with hundreds of large images (each 21 000×21 000 pixels) requires a segmentation method that: (1) yields high segmentation accuracy, (2) is applicable to multiple cell lines with various densities of cells and cell colonies, and several imaging modalities, (3) can process large data sets in a timely manner, (4) has a low memory footprint and (5) has a small number of user‐set parameters that do not require adjustment during the segmentation of large image sets. None of the currently available segmentation methods meet all these requirements. Segmentation based on image gradient thresholding is fast and has a low memory footprint. However, existing techniques that automate the selection of the gradient image threshold do not work across image modalities, multiple cell lines, and a wide range of foreground/background densities (requirement 2) and all failed the requirement for robust parameters that do not require re‐adjustment with time (requirement 5). We present a novel and empirically derived image gradient threshold selection method for separating foreground and background pixels in an image that meets all the requirements listed above. We quantify the difference between our approach and existing ones in terms of accuracy, execution speed, memory usage and number of adjustable parameters on a reference data set. This reference data set consists of 501 validation images with manually determined segmentations and image sizes ranging from 0.36 Megapixels to 850 Megapixels. It includes four different cell lines and two image modalities: phase contrast and fluorescent. Our new technique, called Empirical Gradient Threshold (EGT), is derived from this reference data set with a 10‐fold cross‐validation method. EGT segments cells or colonies with resulting Dice accuracy index measurements above 0.92 for all cross‐validation data sets. EGT results has also been visually verified on a much larger data set that includes bright field and Differential Interference Contrast (DIC) images, 16 cell lines and 61 time‐sequence data sets, for a total of 17 479 images. This method is implemented as an open‐source plugin to ImageJ as well as a standalone executable that can be downloaded from the following link: https://isg.nist.gov/ .