Automated Segmentation of Drosophila RNAi Fluorescence Cellular Images Using Deformable Models

Image-based high-throughput genome-wide RNA interference (RNAi) experiments are increasingly carried out to facilitate the understanding of gene functions in intricate biological processes. Robust automated segmentation of the large volumes of output images generated from image-based screening is much needed for data analyses. In this paper, we propose a new automated segmentation technique to fill the void. The technique consists of two steps: nuclei and cytoplasm segmentation. In the former step, nuclei are extracted, labeled, and used as starting points for the latter step. A new force obtained from rough segmentation is introduced into the classical level set curve evolution to improve the performance for odd shapes, such as spiky or ruffly cells. A scheme of preventing curve intersection is proposed to treat the difficulty of segmenting touching cells. Synthetic images are generated to test the capabilities of our approach. Then, we apply it to three types of Drosophila cells in RNAi fluorescence images. In all cases, accuracy of greater than 92% is obtained     

SAR图像的自动分割方法研究

由于存在相干斑噪声的影响,给SAR图像分割造成很大的困难,该文提出了一种SAR图像的自动分割方法。首先在特征提取阶段,通过计算小波能量提取纹理信息,用邻域统计量提取灰度信息,用保边缘平均灰度提取边缘信息,以确保边缘准确。然后提出一种改进的完全无监督的聚类算法进行图像分割,该算法可以自动确定分割的类型数目。由于该方法充分考虑了SAR图像的纹理、灰度和边缘信息,因而极大地提高了其最终分割性能。实验结果证明了该方法的有效性。     

一种参数自适应的PCNN图像分割算法

文章利用用粒子群优化(PSO)算法优化脉冲耦合神经网络(PCNN)的参数,其中将从训练图像中提取熵和能量的比值作为PSO的适应度函数,提出了一种参数自适应的PCNN图像分割方法。最终通过Matlab仿真实验证明了该方法具有较好的分割性能,该方法不但能够正确地完成图像分割,而且也省去了人为设置PCNN参数的麻烦。     

Informatics challenges of high-throughput microscopy

In this article, we discussed the emerging informatics issues of high-throughput screening (HTS) using automated fluorescence microscopy technology, otherwise known as high-content screening (HCS) in the pharmaceutical industry. Optimal methods of scoring biomarkers and identifying candidate hits have been actively studied in academia and industry, with the exception of data modeling topics. To find candidate hits, we need to score the images associated with different compound interventions. In the application example of RNAi genome-wide screening, we aim to find the candidate effectors or genes which correspond to the images acquired using the three channels. Scoring the effectors is equivalent to scoring the images based on the number of phenotypes existing in those images. Our ultimate objective of studying HTS is to model the relationship between gene networks and cellular phenotypes, investigate cellular communication via protein interaction, and study the disease mechanism beyond the prediction based on the molecular structure of the compound. Finally, computational image analysis has become a powerful tool in cellular and molecular biology studies. Signal processing and modeling for high-throughput image screening is an emerging filed that requires novel algorithms for dynamical system analysis, image processing, and statistical modeling. We hope that this article will motivate the signal processing communities to address challenging data modeling and other informatics issues of HTS.     

融合层次聚类的高分辨率遥感影像超像素分割方法

为解决遥感影像分割尺度自动选取难的问题,提出了融合层次聚类的高分辨率遥感影像超像素分割方法。首先采用自适应形态重建的分水岭分割算法将影像分割成多个超像素;然后提取各超像素的灰度特征向量;最后利用层次聚类方法进行超像素合并,实现高分辨率遥感影像的精确分割。实验选用4组景遥感影像;采用定性和定量相结合的方法评价实验结果。实验结果表明,该方法有效提高了遥感影像分割精度,并取得了较好的分割视觉效果。     

基于改进Lazy Snapping算法的红外图像分割方法研究

针对红外图像含大量噪声以及对比度低等特点,提出一种结合快速模糊C均值聚类的改进Lazy Snapping分割方法.对红外图像使用快速模糊C均值聚类算法进行预分割,通过形态学骨架提取的方法在图像中标记出目标和背景种子点,将Lazy Snapping算法由全局分割转化为聚类区域分割,并构造能量函数,通过最小割算法求解能量函...     

基于面向对象的极化雷达影像分类

有效的PolSAR影像分类技术是PolSAR成功应用的基础,然而相比于比较成熟的PolSAR成像技术与系统设计,PolSAR影像分类技术的发展相对滞后,针对PolSAR影像面向对象分类研究中存在的问题,提出了一种新的结合多种目标极化分解、ReliefF-PSO_SVM和集成学习的PolSAR影像面向对象分类方法。该方法首先采用多种方法对PolSAR影像进行目标极化分解;然后将利用不同极化分解方法提取的极化参数组合成一幅多通道影像;接下来对多通道影像进行分割、特征提取;采用ReliefF-PSO_SVM算法进行特征选择,并保留适应度最高的N个特征子集进行分类,每一个特征子集对应一个分类结果;最后利用集成学习技术对各分类结果进行集成。以吉林省长春市部分区域为研究区,Radarsat2影像为数据源,将提出的方法应用于土地利用分类中,取得了较好的分类效果,总体精度和Kappa系数分别达到了85.06%和0.8006。此外,还构建了3种对比方法用于分类,对比结果进一步证明了所提方法在PolSAR影像分类中的优越性。     

基于元胞自动机的红外弱小目标图像分割

针对红外成像制导中弱小日标图像分割,提出了基于元胞自动机的自动分割方法.首先使用元胞自动机增强图像的对比度,状态转移函数采用了冯.诺伊曼邻域和一致的演化规则,然后采用边缘双阈值策略二值化图像,最后标记形成目标块,并依据种子点和目标复杂度进行滤波,得到精确的图像分割结果.在实拍的3幅不同类型的红外图像上进行分割实验,其结果表明:提出的方法均能够有效地分割出多个弱小目标区域,有利于下一步的目标识别和跟踪.     

A fast multichannel SAR raw data simulator of clutter and moving targets

Accessibility of a fast and accurate multichannel synthetic aperture radar raw data generator of stationary clutter and moving targets has high importance, especially in the application of ground moving target indication. In this paper, a fast four-stage algorithm for generating the raw data of each channel stationary clutter and moving targets, has been proposed respectively in the frequency and the hybrid time–frequency domain. Using this simulator, in different conditions in terms of target motion speed, acceleration and direction, for each of the channels, after generating the raw data, its final image has been extracted by the range-Doppler algorithm. Then, using clutter suppression techniques such as DPCA, ATI and hybrid DPCA–ATI, the multichannel SAR final image has been obtained in ideal and nonideal conditions. Finally, the obtained images of the first channel have been studied using the extracted formulas for predicting the effects of target motion parameters on the SAR images as well as analyzing the multichannel SAR final image. The results show that the proposed algorithm for generating the raw data of each channel stationary clutter and moving targets has better performance in terms of speed and accuracy than the other existing simulators and the proposed multichannel SAR simulation method has high quality.     

Automatic detection of abnormalities in chest radiographs using local texture analysis

A fully automatic method is presented to detect abnormalities in frontal chest radiographs which are aggregated into an overall abnormality score. The method is aimed at finding abnormal signs of a diffuse textural nature, such as they are encountered in mass chest screening against tuberculosis (TB). The scheme starts with automatic segmentation of the lung fields, using active shape models. The segmentation is used to subdivide the lung fields into overlapping regions of various sizes. Texture features are extracted from each region, using the moments of responses to a multiscale filter bank. Additional "difference features" are obtained by subtracting feature vectors from corresponding regions in the left and right lung fields. A separate training set is constructed for each region. All regions are classified by voting among the k nearest neighbors, with leave-one-out. Next, the classification results of each region are combined, using a weighted multiplier in which regions with higher classification reliability weigh more heavily. This produces an abnormality score for each image. The method is evaluated on two databases. The first database was collected from a TB mass chest screening program, from which 147 images with textural abnormalities and 241 normal images were selected. Although this database contains many subtle abnormalities, the classification has a sensitivity of 0.86 at a specificity of 0.50 and an area under the receiver operating characteristic (ROC) curve of 0.820. The second database consist of 100 normal images and 100 abnormal images with interstitial disease. For this database, the results were a sensitivity of 0.97 at a specificity of 0.90 and an area under the ROC curve of 0.986.     

Computer-aided kidney segmentation on abdominal CT images.

In this paper, an effective model-based approach for computer-aided kidney segmentation of abdominal CT images with anatomic structure consideration is presented. This automatic segmentation system is expected to assist physicians in both clinical diagnosis and educational training. The proposed method is a coarse to fine segmentation approach divided into two stages. First, the candidate kidney region is extracted according to the statistical geometric location of kidney within the abdomen. This approach is applicable to images of different sizes by using the relative distance of the kidney region to the spine. The second stage identifies the kidney by a series of image processing operations. The main elements of the proposed system are: 1) the location of the spine is used as the landmark for coordinate references; 2) elliptic candidate kidney region extraction with progressive positioning on the consecutive CT images; 3) novel directional model for a more reliable kidney region seed point identification; and 4) adaptive region growing controlled by the properties of image homogeneity. In addition, in order to provide different views for the physicians, we have implemented a visualization tool that will automatically show the renal contour through the method of second-order neighborhood edge detection. We considered segmentation of kidney regions from CT scans that contain pathologies in clinical practice. The results of a series of tests on 358 images from 30 patients indicate an average correlation coefficient of up to 88% between automatic and manual segmentation.     

基于深度卷积神经网络的宫颈细胞病理智能辅助诊断方法

针对宫颈细胞病理自动筛查问题,提出一种基于深度卷积神经网络的智能辅助诊断方法。首先采用基于改进UNet深度卷积神经网络模型的语义分割方法,检测出宫颈细胞病理涂片扫描图像中的细胞(粘连簇团)区域。接着,利用VGG 16深度卷积神经网络模型,结合迁移学习技术,对检测出的细胞(粘连簇团)区域进行精确识别。为了提高深度卷积神经网络模型的性能,在进行细胞(粘连簇团)区域检测、识别的过程中,采用了数据增强技术。同时,针对该领域相关研究缺乏宫颈细胞病理液基涂片扫描图像数据集的问题,我们收集四川大学华西附二院的典型LCT筛查病例,建立了宫颈细胞病理图像HXLCT数据集,并由资深病理医生完成数据标注。实验表明,本文方法能够较好地完成宫颈细胞病理涂片扫描图像中的细胞(粘连簇团)区域检测(正确率为91.33%),并能对检测出的区域完成正常、疑似病变二分类识别(正确率为91.6%,召回率为92.3%,ROC曲线线下面积为0.914)。本文工作将有助于宫颈细胞病理自动筛查系统的开发,对于宫颈癌早期防治具有重要意义。     

Automated cell nuclei segmentation for breast fine needle aspiration cytology

Breast cancer detection and segmentation of cytological images is the standard clinical practice for the diagnosis and prognosis of breast cancer. This paper presents a fully automated method for cell nuclei detection and segmentation in breast cytological images. The images are enhanced with histogram stretching and contrast-limited adaptive histogram equalization (CLAHE). The locations of the cell nuclei in the image are detected with circular Hough transform (CHT) and local maximum filtering. The elimination of false positive findings (noisy circles and blood cells) is achieved using Otsu’s thresholding method and fuzzy C-means clustering technique. The segmentation of the nuclei boundaries is accomplished with the application of the marker controlled watershed transform in the gradient image, using the nuclei markers extracted in the detection step. The proposed method is evaluated using 92 breast cytological images containing 11,502 cell nuclei. Experimental evidence shows that the proposed method has very effective results even in the case of images with high degree of blood cells, noisy circles.     

基于Mumford-Shah模型的参数估计和两阶段图像分割方法

Mumford-Shah两相分片常数模型是一个有效的图像分割模型,但当模型用于带有噪声的图像时,其水平集解法存在对初始解和长度参数敏感这两个问题.文中给出一种两阶段分割方法,首先利用传统的简单分割方法获得一个粗分割,再将其作为变分模型的初始解,从而实现自动选取初始解.文中还给出一个有效的自适应长度参数估计模型,该模型依据图像中噪声方差大小来确定参数.两阶段分割方法和自适应参数估计结合起来使得算法大大减弱了对参量的敏感性,而且可以正确、快速地分割.针对一些计算机生成图像和实际图像的实验结果验证了算法是有效的.     

利用局部离散度活动轮廓模型的强度非均匀图像分割

强度非均匀现象在真实图像中普遍存在,采用常规基于强度的分割算法会导致严重的误分割。针对强度非均匀图像分割,提出了基于局部离散度的活动轮廓模型分割算法。首先定义基于类内类间距离的离散度,然后利用核函数提取局部区域信息,同时加入边缘指示函数加权的轮廓线长度项能量,建立基于局部离散度的活动轮廓模型。最后引入水平集函数惩罚项,避免水平集方法在演化求解时需要不断初始化的问题。合成图像和真实图像实验结果证明本文算法性能稳定,适应于强度非均匀图像的分割。      

基于多尺度多方向Gabor变换的Tsallis熵阈值分割方法

为了能在统一框架内处理无模态、单模态、双模态或者多模态直方图情形下的自动阈值选取问题,该文提出一种基于多尺度多方向Gabor变换的Tsallis熵阈值分割方法(MGTE)。该方法先通过Gabor变换得到多尺度乘积图像,然后利用内外轮廓图像从多尺度乘积图像中重构1维直方图,并在重构1维直方图上采用Tsallis熵计算模型来选取4个方向Tsallis熵取最大值时对应的阈值,最后对4个方向的阈值进行加权求和作为最终分割阈值。将提出的方法和5个分割方法在4幅合成图像和40幅真实世界图像上进行了实验。结果表明提出的方法虽然计算效率不占优势,但它的分割适应性和分割精度有明显的提高。     

一种基于中心矩特征的SAR图像目标识别方法

合成孔径雷达自动目标识别是目前国内外模式识别领域的重点研究课题之一.本文给出了一种内存需求小,低计算复杂度且具有较好识别性能的SAR图像目标识别方法,先通过自适应阈值分割来获得目标图像,然后提取其中心矩特征,采用SVM来进行识别.基于美国MSTAR实测数据的识别试验验证了该方法的有效性.     

Medical image segmentation using minimal path deformable models with implicit shape priors.

This paper presents a new method for segmentation of medical images by extracting organ contours, using minimal path deformable models incorporated with statistical shape priors. In our approach, boundaries of structures are considered as minimal paths, i.e., paths associated with the minimal energy, on weighted graphs. Starting from the theory of minimal path deformable models, an intelligent "worm" algorithm is proposed for segmentation, which is used to evaluate the paths and finally find the minimal path. Prior shape knowledge is incorporated into the segmentation process to achieve more robust segmentation. The shape priors are implicitly represented and the estimated shapes of the structures can be conveniently obtained. The worm evolves under the joint influence of the image features, its internal energy, and the shape priors. The contour of the structure is then extracted as the worm trail. The proposed segmentation framework overcomes the short-comings of existing deformable models and has been successfully applied to segmenting various medical images.     

Segmentation of kidney from ultrasound images based on texture and shape priors

This paper presents a novel texture and shape priors based method for kidney segmentation in ultrasound (US) images. Texture features are extracted by applying a bank of Gabor filters on test images through a two-sided convolution strategy. The texture model is constructed via estimating the parameters of a set of mixtures of half-planed Gaussians using the expectation-maximization method. Through this texture model, the texture similarities of areas around the segmenting curve are measured in the inside and outside regions, respectively. We also present an iterative segmentation framework to combine the texture measures into the parametric shape model proposed by Leventon and Faugeras. Segmentation is implemented by calculating the parameters of the shape model to minimize a novel energy function. The goal of this energy function is to partition the test image into two regions, the inside one with high texture similarity and low texture variance, and the outside one with high texture variance. The effectiveness of this method is demonstrated through experimental results on both natural images and US data compared with other image segmentation methods and manual segmentation.