Karyotyping of comparative genomic hybridization human metaphases by using support vector machines.

BACKGROUND: Comparative genomic hybridization (CGH) is a relatively new molecular cytogenetic method for detecting chromosomal imbalance. Karyotyping of human metaphases is an important step to assign each chromosome to one of 23 or 24 classes (22 autosomes and two sex chromosomes). Automatic karyotyping in CGH analysis is needed. However, conventional karyotyping approaches based on DAPI images require complex image enhancement procedures. METHODS: This paper proposes a simple feature extraction method, one that generates density profiles from original true color CGH images and uses normalized profiles as feature vectors without quantization. A classifier is developed by using support vector machine (SVM). It has good generalization ability and needs only limited training samples. RESULTS: Experiment results show that the feature extraction method of using color information in CGH images can improve greatly the classification success rate. The SVM classifier is able to acquire knowledge about human chromosomes from relatively few samples and has good generalization ability. A success rate of moe than 90% has been achieved and the time for training and testing is very short. CONCLUSIONS: The feature extraction method proposed here and the SVM-based classifier offer a promising computerized intelligent system for automatic karyotyping of CGH human chromosomes.     

Adaptive color basis transformation. An aid in image segmentation

Multispectral images of stained cells enable the use of color differences to segment and/or to discriminate between image components, such as cell types and cellular subcomponents. When the spectral characteristics of the image components do not change over the area of a slide or from slide to slide, one can create a constant weighted linear combination of spectral images to generate one-dimensional or two-dimensional images that have the desired contrast between the image components that must be discriminated. However, when the spectral characteristics are not constant, i.e., when they vary from image to image, a constant weighted linear combination cannot be employed; instead, an appropriate solution must be found for each selected image. This is usually a time-consuming, manual procedure that cannot be employed in a fully automated process of discriminating and segmenting stained cells. This paper describes an algorithm that uses principal components decomposition basis vectors to generate a nonstatic weighted linear combination of color images that can be used by an automated system. This algorithm relies on a semiconstant relationship between the areas (sizes) of the image components that are to be discriminated and/or segmented. The technique has been successfully applied as an aid in the segmentation of images of stained cervical smears; the images were acquired with a three-chip CCD camera that generates three broad-band color images.     

Small bowel image classification using cross-co-occurrence matrices on wavelet domain

This paper presents a novel system to compute the automated classification of wireless capsule endoscope images. Classification is achieved by a classical statistical approach, but novel features are extracted from the wavelet domain and they contain both color and texture information. First, a shift-invariant discrete wavelet transform (SIDWT) is computed to ensure that the multiresolution feature extraction scheme is robust to shifts. The SIDWT expands the signal (in a shift-invariant way) over the basis functions which maximize information. Then cross-co-occurrence matrices of wavelet subbands are calculated and used to extract both texture and color information. Canonical discriminant analysis is utilized to reduce the feature space and then a simple 1D classifier with the leave one out method is used to automatically classify normal and abnormal small bowel images. A classification rate of 94.7% is achieved with a database of 75 images (41 normal and 34 abnormal cases). The high success rate could be attributed to the robust feature set which combines multiresolutional color and texture features, with shift, scale and semi-rotational invariance. This result is very promising and the method could be used in a computer-aided diagnosis system or a content-based image retrieval scheme.     

基于颜色名和OpponentSIFT特征的鳞翅目昆虫图像识别

【目的】本研究旨在探索使用先进的计算机视觉技术实现对昆虫图像的自动分类方法。【方法】通过预处理对采集的昆虫标本图像去除背景,获得昆虫图像的前景蒙板,并由蒙板确定的轮廓计算出前景图像的最小包围盒,剪切出由最小包围盒确定的前景有效区域,然后对剪切得到的图像进行特征提取。首先提取颜色名特征,把原来的RGB（Red-Green-Blue）图像的像素值映射到11种颜色名空间,其值表示RGB值属于该颜色名的概率,每个颜色名平面划分成3×3像素大小的网格,用每格的概率均值作为网格中心点的描述子,最后用空阈金字塔直方图统计的方式形成颜色名视觉词袋特征;其次提取OpponentSIFT(Opponent Scale Invariant Feature Transform)特征,首先把RGB图像变换到对立色空间,对该空间每通道提取SIFT特征,最后用空域池化和直方图统计方法形成OpponentSIFT视觉词袋。将两种词袋特征串接后得到该昆虫图像的特征向量。使用昆虫图像样本训练集提取到的特征向量训练SVM（Support Vector Machine）分类器,使用这些训练得到的分类器即可实现对鳞翅目昆虫的分类识别。【结果】该方法在包含10种576个样本的昆虫图像数据库中进行了测试,取得了100%的识别正确率。【结论】试验结果证明基于颜色名和OpponentSIFT特征可以有效实现对鳞翅目昆虫图像的识别。     

Intravascular Optical Coherence Tomography Image Segmentation Based on Support Vector Machine Algorithm

Intravascular optical coherence tomography (IVOCT) is becoming more and more popular in clinical diagnosis of coronary atherosclerotic. However, reading IVOCT images is of large amount of work. This article describes a method based on image feature extraction and support vector machine (SVM) to achieve semi-automatic segmentation of IVOCT images. The image features utilized in this work including light attenuation coefficients and image textures based on gray level co-occurrence matrix. Different sets of hyper-parameters and image features were tested. This method achieved an accuracy of 83% on the test images. Single class accuracy of 89% for fibrous, 79.3% for calcification and 86.5% lipid tissue. The results show that this method can be a considerable way for semi-automatic segmentation of atherosclerotic plaque components in clinical IVOCT images.     

Computer-assisted analysis of epiluminescence microscopy images of pigmented skin lesions.

BACKGROUND: Epiluminescence microscopy (ELM) is a noninvasive clinical tool recently developed for the diagnosis of pigmented skin lesions (PSLs), with the aim of improving melanoma screening strategies. However, the complexity of the ELM grading protocol means that considerable expertise is required for differential diagnosis. In this paper we propose a computer-based tool able to screen ELM images of PSLs in order to aid clinicians in the detection of lesion patterns useful for differential diagnosis. METHODS: The method proposed is based on the supervised classification of pixels of digitized ELM images, and leads to the construction of classes of pixels used for image segmentation. This process has two major phases, i.e., a learning phase, where several hundred pixels are used in order to train and validate a classification model, and an application step, which consists of a massive classification of billions of pixels (i.e., the full image) by means of the rules obtained in the first phase. RESULTS: Our results show that the proposed method is suitable for lesion-from-background extraction, for complete image segmentation into several typical diagnostic patterns, and for artifact rejection. Hence, our prototype has the potential to assist in distinguishing lesion patterns which are associated with diagnostic information such as diffuse pigmentation, dark globules (black dots and brown globules), and the gray-blue veil. CONCLUSIONS: The system proposed in this paper can be considered as a tool to assist in PSL diagnosis.     

An expert system for the early detection of melanoma using knowledge-based image analysis

Melanoma is the most lethal skin cancer; however, nearly all patients can be saved and cured by early detection and prompt surgical treatment. It has been demonstrated that the major diagnostic and prognostic parameters of melanoma are the vertical thickness, three-dimensional (3D) size and shape, and color of the lesion. The other characteristic features of early melanoma are irregularities in the boundary of the lesion and the appearance of nonuniform pigmentation (with a variety of color). During early stages of development of the melanoma, the changes in these parameters are very difficult to assess since no good tool exists for measuring them in situ and analyzing them for malignancy. A novel optical instrument called the "Nevoscope" has been developed to obtain multiple views of the transilluminated skin lesion from several angles. These views have been used to measure the thickness and 3D size of the skin lesion without excision. A knowledge-based image analysis and interpretation system is being developed to analyze images of the skin lesion for a set of diagnostic and prognostic features: thickness, 3D size, color and margin, boundary and surface characteristics. This analysis combined with the patient's history, such as occurrence of melanoma or dysplastic nevi in the family, life style, skin type, etc., is used by the knowledge-based expert system to detect early or potentially malignant lesions. The diagnostic and prognostic knowledge bases for the early detection of melanoma are being developed with the help of expert dermatologists and published case studies.     

Neural network approach for image chromatic adaptation for skin color detection

The goal of image chromatic adaptation is to remove the effect of illumination and to obtain color data that reflects precisely the physical contents of the scene. We present in this paper an approach to image chromatic adaptation using Neural Networks (NN) with application for detecting--adapting human skin color. The NN is trained on randomly chosen color images containing human subject under various illuminating conditions, thereby enabling the model to dynamically adapt to the changing illumination conditions. The proposed network predicts directly the illuminant estimate in the image so as to adapt to human skin color. The comparison of our method with Gray World, White Patch and NN on White Patch methods for skin color stabilization is presented. The skin regions in the NN stabilized images are successfully detected using a computationally inexpensive thresholding operation. We also present results on detecting skin regions on a data set of test images. The results are promising and suggest a new approach for adapting human skin color using neural networks.     

基于灰度共生矩阵的人体皮肤纹理分析

对纹理图像的分析及特征提取是近年来图像处理领域的研究热点,在现实中有广泛的应用价值。灰度共生矩阵已被理论证明是图像纹理分析的一个很好的方法。为了使灰度共生矩阵所提取的特征值能够更好地描述皮肤老化的灰度分布信息,以不同年龄层的女性的不同部位的皮肤纹理图像作为研究对象,对采集到的图像进行预处理,采用灰度共生矩阵法提取纹理的特征值,通过统计分析得出了特征值的变化规律。实验结果对皮肤老化研究及其纹理分析有参考意义。     

Recursive N-Way Partial Least Squares for Brain-Computer Interface

In the article tensor-input/tensor-output blockwise Recursive N-way Partial Least Squares (RNPLS) regression is considered. It combines the multi-way tensors decomposition with a consecutive calculation scheme and allows blockwise treatment of tensor data arrays with huge dimensions, as well as the adaptive modeling of time-dependent processes with tensor variables. In the article the numerical study of the algorithm is undertaken. The RNPLS algorithm demonstrates fast and stable convergence of regression coefficients. Applied to Brain Computer Interface system calibration, the algorithm provides an efficient adjustment of the decoding model. Combining the online adaptation with easy interpretation of results, the method can be effectively applied in a variety of multi-modal neural activity flow modeling tasks.     

Digital photography provides a fast,reliable, and noninvasive method to estimate anthocyanin pigment concentration in reproductive and vegetative plant tissues

Anthocyanin pigments have become a model trait for evolutionary ecology as they often provide adaptive benefits for plants. Anthocyanins have been traditionally quantified biochemically or more recently using spectral reflectance. However, both methods require destructive sampling and can be labor intensive and challenging with small samples. Recent advances in digital photography and image processing make it the method of choice for measuring color in the wild. Here, we use digital images as a quick, noninvasive method to estimate relative anthocyanin concentrations in species exhibiting color variation. Using a consumer‐level digital camera and a free image processing toolbox, we extracted RGB values from digital images to generate color indices. We tested petals, stems, pedicels, and calyces of six species, which contain different types of anthocyanin pigments and exhibit different pigmentation patterns. Color indices were assessed by their correlation to biochemically determined anthocyanin concentrations. For comparison, we also calculated color indices from spectral reflectance and tested the correlation with anthocyanin concentration. Indices perform differently depending on the nature of the color variation. For both digital images and spectral reflectance, the most accurate estimates of anthocyanin concentration emerge from anthocyanin content‐chroma ratio, anthocyanin content‐chroma basic, and strength of green indices. Color indices derived from both digital images and spectral reflectance strongly correlate with biochemically determined anthocyanin concentration; however, the estimates from digital images performed better than spectral reflectance in terms of r² and normalized root‐mean‐square error. This was particularly noticeable in a species with striped petals, but in the case of striped calyces, both methods showed a comparable relationship with anthocyanin concentration. Using digital images brings new opportunities to accurately quantify the anthocyanin concentrations in both floral and vegetative tissues. This method is efficient, completely noninvasive, applicable to both uniform and patterned color, and works with samples of any size.     

Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study

Background

Computer-aided diagnosis (CADx) software that provides a second opinion has been widely used to assist physicians with various tasks. In dermatology, however, CADx has been mostly limited to melanoma or melanocytic skin cancer diagnosis. The frequency of non-melanocytic skin cancers and the accessibility of regular digital macrographs have raised interest in developing CADx for broader applications.

Objectives

To investigate the feasibility of using CADx to diagnose both melanocytic and non-melanocytic skin lesions based on conventional digital photographic images.

Methods

This study was approved by an institutional review board, and the requirement to obtain informed consent was waived. In total, 769 conventional photographs of melanocytic and non-melanocytic skin lesions were retrospectively reviewed and used to develop a CADx system. Conventional and new color-related image features were developed to classify the lesions as benign or malignant using support vector machines (SVMs). The performance of CADx was compared with that of dermatologists.

Results

The clinicians'' overall sensitivity, specificity, and accuracy were 83.33%, 85.88%, and 85.31%, respectively. New color correlation and principal component analysis (PCA) features improved the classification ability of the baseline CADx (p = 0.001). The estimated area under the receiver operating characteristic (ROC) curve (Az) of the proposed CADx system was 0.949, with a sensitivity and specificity of 85.63% and 87.65%, respectively, and a maximum accuracy of 90.64%.

Conclusions

We have developed an effective CADx system to classify both melanocytic and non-melanocytic skin lesions using conventional digital macrographs. The system''s performance was similar to that of dermatologists at our institute. Through improved feature extraction and SVM analysis, we found that conventional digital macrographs were feasible for providing useful information for CADx applications. The new color-related features significantly improved CADx applications for skin cancer.     

Automatic detection of pulmonary nodules in CT images by incorporating 3D tensor filtering with local image feature analysis

Computer-aided detection (CAD) technology has been developed and demonstrated its potential to assist radiologists in detecting pulmonary nodules especially at an early stage. In this paper, we present a novel scheme for automatic detection of pulmonary nodules in CT images based on a 3D tensor filtering algorithm and local image feature analysis. We first apply a series of preprocessing steps to segment the lung volume and generate the isotropic volumetric CT data. Next, a unique 3D tensor filtering approach and local image feature analysis are used to detect nodule candidates. A 3D level set segmentation method is used to correct and refine the boundaries of nodule candidates subsequently. Then, we extract the features of the detected candidates and select the optimal features by using a CFS (Correlation Feature Selection) subset evaluator attribute selection method. Finally, a random forest classifier is trained to classify the detected candidates. The performance of this CAD scheme is validated using two datasets namely, the LUNA16 (Lung Nodule Analysis 2016) database and the ANODE09 (Automatic Nodule Detection 2009) database. By applying a 10-fold cross-validation method, the CAD scheme yielded a sensitivity of 79.3% at an average of 4 false positive detections per scan (FP/Scan) for the former dataset, and a sensitivity of 84.62% and 2.8 FP/Scan for the latter dataset, respectively. Our detection results show that the use of 3D tensor filtering algorithm combined with local image feature analysis constitutes an effective approach to detect pulmonary nodules.     

Quaternion-based discriminant analysis method for color face recognition

Pattern recognition techniques have been used to automatically recognize the objects, personal identities, predict the function of protein, the category of the cancer, identify lesion, perform product inspection, and so on. In this paper we propose a novel quaternion-based discriminant method. This method represents and classifies color images in a simple and mathematically tractable way. The proposed method is suitable for a large variety of real-world applications such as color face recognition and classification of the ground target shown in multispectrum remote images. This method first uses the quaternion number to denote the pixel in the color image and exploits a quaternion vector to represent the color image. This method then uses the linear discriminant analysis algorithm to transform the quaternion vector into a lower-dimensional quaternion vector and classifies it in this space. The experimental results show that the proposed method can obtain a very high accuracy for color face recognition.     

Karyotyping of comparative genomic hybridization human metaphases using kernel nearest-neighbor algorithm

BACKGROUND: Comparative genomic hybridization (CGH) is a relatively new molecular cytogenetic method that detects chromosomal imbalances. Automatic karyotyping is an important step in CGH analysis because the precise position of the chromosome abnormality must be located and manual karyotyping is tedious and time-consuming. In the past, computer-aided karyotyping was done by using the 4',6-diamidino-2-phenylindole, dihydrochloride (DAPI)-inverse images, which required complex image enhancement procedures. METHODS: An innovative method, kernel nearest-neighbor (K-NN) algorithm, is proposed to accomplish automatic karyotyping. The algorithm is an application of the "kernel approach," which offers an alternative solution to linear learning machines by mapping data into a high dimensional feature space. By implicitly calculating Euclidean or Mahalanobis distance in a high dimensional image feature space, two kinds of K-NN algorithms are obtained. New feature extraction methods concerning multicolor information in CGH images are used for the first time. RESULTS: Experiment results show that the feature extraction method of using multicolor information in CGH images improves greatly the classification success rate. A high success rate of about 91.5% has been achieved, which shows that the K-NN classifier efficiently accomplishes automatic chromosome classification from relatively few samples. CONCLUSIONS: The feature extraction method proposed here and K-NN classifiers offer a promising computerized intelligent system for automatic karyotyping of CGH human chromosomes.     

IHC Profiler: An Open Source Plugin for the Quantitative Evaluation and Automated Scoring of Immunohistochemistry Images of Human Tissue Samples

In anatomic pathology, immunohistochemistry (IHC) serves as a diagnostic and prognostic method for identification of disease markers in tissue samples that directly influences classification and grading the disease, influencing patient management. However, till today over most of the world, pathological analysis of tissue samples remained a time-consuming and subjective procedure, wherein the intensity of antibody staining is manually judged and thus scoring decision is directly influenced by visual bias. This instigated us to design a simple method of automated digital IHC image analysis algorithm for an unbiased, quantitative assessment of antibody staining intensity in tissue sections. As a first step, we adopted the spectral deconvolution method of DAB/hematoxylin color spectra by using optimized optical density vectors of the color deconvolution plugin for proper separation of the DAB color spectra. Then the DAB stained image is displayed in a new window wherein it undergoes pixel-by-pixel analysis, and displays the full profile along with its scoring decision. Based on the mathematical formula conceptualized, the algorithm is thoroughly tested by analyzing scores assigned to thousands (n = 1703) of DAB stained IHC images including sample images taken from human protein atlas web resource. The IHC Profiler plugin developed is compatible with the open resource digital image analysis software, ImageJ, which creates a pixel-by-pixel analysis profile of a digital IHC image and further assigns a score in a four tier system. A comparison study between manual pathological analysis and IHC Profiler resolved in a match of 88.6% (P<0.0001, CI = 95%). This new tool developed for clinical histopathological sample analysis can be adopted globally for scoring most protein targets where the marker protein expression is of cytoplasmic and/or nuclear type. We foresee that this method will minimize the problem of inter-observer variations across labs and further help in worldwide patient stratification potentially benefitting various multinational clinical trial initiatives.     

Pigment network detection in dermatoscopic images for melanoma diagnosis

We propose in this paper an automated structural method for the pigment network detection in dermatoscopic images. The first module of the proposed method consists in extracting the skin lesion from the input image. In fact, after the image rehaussement and the lesion segmentation using a fuzzy region growing technique, a post-processing is required to make the lesion sharpened and to select a single luminance component. Given the extracted lesion of interest in the selected luminance image, the second phase is based on a LoG filter in order to detect holes and other structures within this lesion. Besides, a Gaussian-based thresholding process is introduced in order to filter only holes belonging to the pigment network while removing other round structures such as dots, globules and oil bubbles. The main contribution of the proposed method resides in the fuzzy assessment of the membership degree of a hole to the pigment network, what permits to keep the maximum of candidates and postpones the decision until obtaining further information at the following stages. The resulting holes are connected, while verifying a spatial constraint, towards a graph representing the pigment network. The proposed method achieved an area under the ROC curve of 0.821 for successfully detecting pigment network with a correct classification rate of 85% on a dataset of 122 real-world images.     

Fault diagnosis of a benchmark fermentation process: a comparative study of feature extraction and classification techniques

This paper investigates fault diagnosis in batch processes and presents a comparative study of feature extraction and classification techniques applied to a specific biotechnological case study: the fermentation process model by Birol et al. (Comput Chem Eng 26:1553–1565, 2002), which is a benchmark for advanced batch processes monitoring, diagnosis and control. Fault diagnosis is achieved using four approaches on four different process scenarios based on the different levels of noise so as to evaluate their effects on the performance. Each approach combines a feature extraction method, either multi-way principal component analysis (MPCA) or multi-way independent component analysis (MICA), with a classification method, either artificial neural network (ANN) or support vector machines (SVM). The performance obtained by the different approaches is assessed and discussed for a set of simulated faults under different scenarios. One of the faults (a loss in mixing power) could not be detected due to the minimal effect of mixing on the simulated data. The remaining faults could be easily diagnosed and the subsequent discussion provides practical insight into the selection and use of the available techniques to specific applications. Irrespective of the classification algorithm, MPCA renders better results than MICA, hence the diagnosis performance proves to be more sensitive to the selection of the feature extraction technique.     

Automated Multi-Lesion Detection for Referable Diabetic Retinopathy in Indigenous Health Care

Diabetic Retinopathy (DR) is a complication of diabetes mellitus that affects more than one-quarter of the population with diabetes, and can lead to blindness if not discovered in time. An automated screening enables the identification of patients who need further medical attention. This study aimed to classify retinal images of Aboriginal and Torres Strait Islander peoples utilizing an automated computer-based multi-lesion eye screening program for diabetic retinopathy. The multi-lesion classifier was trained on 1,014 images from the São Paulo Eye Hospital and tested on retinal images containing no DR-related lesion, single lesions, or multiple types of lesions from the Inala Aboriginal and Torres Strait Islander health care centre. The automated multi-lesion classifier has the potential to enhance the efficiency of clinical practice delivering diabetic retinopathy screening. Our program does not necessitate image samples for training from any specific ethnic group or population being assessed and is independent of image pre- or post-processing to identify retinal lesions. In this Aboriginal and Torres Strait Islander population, the program achieved 100% sensitivity and 88.9% specificity in identifying bright lesions, while detection of red lesions achieved a sensitivity of 67% and specificity of 95%. When both bright and red lesions were present, 100% sensitivity with 88.9% specificity was obtained. All results obtained with this automated screening program meet WHO standards for diabetic retinopathy screening.