Automatic identification of subcellular phenotypes on human cell arrays

Light microscopic analysis of cell morphology provides a high-content readout of cell function and protein localization. Cell arrays and microwell transfection assays on cultured cells have made cell phenotype analysis accessible to high-throughput experiments. Both the localization of each protein in the proteome and the effect of RNAi knock-down of individual genes on cell morphology can be assayed by manual inspection of microscopic images. However, the use of morphological readouts for functional genomics requires fast and automatic identification of complex cellular phenotypes. Here, we present a fully automated platform for high-throughput cell phenotype screening combining human live cell arrays, screening microscopy, and machine-learning-based classification methods. Efficiency of this platform is demonstrated by classification of eleven subcellular patterns marked by GFP-tagged proteins. Our classification method can be adapted to virtually any microscopic assay based on cell morphology, opening a wide range of applications including large-scale RNAi screening in human cells.     

A new automatic image analysis method for assessing estrogen receptors’ status in breast tissue specimens

Manual assessment of estrogen receptors′ (ER) status from breast tissue microscopy images is a subjective, time consuming and error prone process. Automatic image analysis methods offer the possibility to obtain consistent, objective and rapid diagnoses of histopathology specimens. In breast cancer biopsies immunohistochemically (IHC) stained for ER, cancer cell nuclei present a large variety in their characteristics that bring various difficulties for traditional image analysis methods. In this paper, we propose a new automatic method to perform both segmentation and classification of breast cell nuclei in order to give quantitative assessment and uniform indicators of IHC staining that will help pathologists in their diagnostic. Firstly, a color geometric active contour model incorporating a spatial fuzzy clustering algorithm is proposed to detect the contours of all cell nuclei in the image. Secondly, overlapping and touching nuclei are separated using an improved watershed algorithm based on a concave vertex graph. Finally, to identify positive and negative stained nuclei, all the segmented nuclei are classified into five categories according to their staining intensity and morphological features using a trained multilayer neural network combined with Fisher's linear discriminant preprocessing. The proposed method is tested on a large dataset containing several breast tissue images with different levels of malignancy. The experimental results show high agreement between the results of the method and ground-truth from the pathologist panel. Furthermore, a comparative study versus existing techniques is presented in order to demonstrate the efficiency and the superiority of the proposed method.     

基于超声图像的乳腺钙化点自动检测技术

当前乳腺钙化点检测方法多基于X光片,难以应用于超声图像,本研究提出基于超声图像的乳腺钙化点自动检测技术,首先将乳腺超声图像中的肿瘤区域通过勾画模板提取出来,基于简单线性迭代聚类算法进行超像素分割;然后提取表征各超像素的特征量来计算显著性图,基于钙化区域显著性进行粗钙化点分割;最终对分割后的粗钙化点进行形态学检测,达到对超声图像中的细钙化点自动检测。该方法取得了较好的分割效果,具有较强的鲁棒性,为形成具有普适性的肿瘤自动诊断方案奠定了研究基础。     

基于活动轮廓模型的彩色白细胞图像自动分割方法研究

为解决血液白细胞显微图像自动识别中的图像分割问题,提出了一种基于活动轮廓的彩色白细胞图像自动分割方法,首先在Hue,Saturation,Intensitv（HSI）彩色空间中运用聚类分割得到细胞核,从而得到细胞所在的位置,然后用流域算法得到细胞大致的轮廓,最后将此轮廓作为初始轮廓,用梯度矢量流（GVF）外力及来自全局信息的区域力驱动,结合彩色信息,使得轮廓收敛于真实的细胞边界。实验结果表明,此方法能精确、有效地分割出单个以及部分重叠白细胞区域。     

Development of a fully automatic scheme for detection of masses in whole breast ultrasound images

Ultrasonography has been used for breast cancer screening in Japan. Screening using a conventional hand-held probe is operator dependent and thus it is possible that some areas of the breast may not be scanned. To overcome such problems, a mechanical whole breast ultrasound (US) scanner has been proposed and developed for screening purposes. However, another issue is that radiologists might tire while interpreting all images in a large-volume screening; this increases the likelihood that masses may remain undetected. Therefore, the aim of this study is to develop a fully automatic scheme for the detection of masses in whole breast US images in order to assist the interpretations of radiologists and potentially improve the screening accuracy. The authors database comprised 109 whole breast US imagoes, which include 36 masses (16 malignant masses, 5 fibroadenomas, and 15 cysts). A whole breast US image with 84 slice images (interval between two slice images: 2 mm) was obtained by the ASU-1004 US scanner (ALOKA Co., Ltd., Japan). The feature based on the edge directions in each slice and a method for subtracting between the slice images were used for the detection of masses in the authors proposed scheme. The Canny edge detector was applied to detect edges in US images; these edges were classified as near-vertical edges or near-horizontal edges using a morphological method. The positions of mass candidates were located using the near-vertical edges as a cue. Then, the located positions were segmented by the watershed algorithm and mass candidate regions were detected using the segmented regions and the low-density regions extracted by the slice subtraction method. For the removal of false positives (FPs), rule-based schemes and a quadratic discriminant analysis were applied for the distribution between masses and FPs. As a result, the sensitivity of the authors scheme for the detection of masses was 80.6% (29/36) with 3.8 FPs per whole breast image. The authors scheme for a computer-aided detection may be useful in improving the screening performance and efficiency.     

Automated live cell screening system based on a 24-well-microplate with integrated micro fluidics

In research, pharmacologic drug-screening and medical diagnostics, the trend towards the utilization of functional assays using living cells is persisting. Research groups working with living cells are confronted with the problem, that common endpoint measurement methods are not able to map dynamic changes. With consideration of time as a further dimension, the dynamic and networked molecular processes of cells in culture can be monitored. These processes can be investigated by measuring several extracellular parameters. This paper describes a high-content system that provides real-time monitoring data of cell parameters (metabolic and morphological alterations), e.g., upon treatment with drug compounds. Accessible are acidification rates, the oxygen consumption and changes in adhesion forces within 24 cell cultures in parallel. Addressing the rising interest in biomedical and pharmacological high-content screening assays, a concept has been developed, which integrates multi-parametric sensor readout, automated imaging and probe handling into a single embedded platform. A life-maintenance system keeps important environmental parameters (gas, humidity, sterility, temperature) constant.     

基于特征点的人体红外图像自动分割技术

目的医学红外人体图像区域分割是大规模医学红外图像处理的关键步骤。为快速有效地获取医学红外图像中的人体信息,本文提出一种在医学红外图像中自动提取并划分人体区域的方法。方法由红外热像仪在静室中采集人的裸体红外图像,然后通过对红外人体图像灰度分布特征分析而取得的阈值来获取人体区域,以人体横向距离(宽度)函数结合人体红外图像中的特殊方向亮带的识别,提取人体的特征点,并通过特征点对人体区域进行分割。结果对来自8人的72幅图像进行验证,其中64幅可以正确分割,证明该方法可以对直立姿势的红外人体图像进行自动区域分割与提取。结论该红外人体图像区域自动分割算法可为基于红外图像的疾病筛查及计算机辅助诊断提供技术基础。     

Automatic multiscale enhancement and segmentation of pulmonary vessels in CT pulmonary angiography images for CAD applications

The authors are developing a computerized pulmonary vessel segmentation method for a computer-aided pulmonary embolism (PE) detection system on computed tomographic pulmonary angiography (CTPA) images. Because PE only occurs inside pulmonary arteries, an automatic and accurate segmentation of the pulmonary vessels in 3D CTPA images is an essential step for the PE CAD system. To segment the pulmonary vessels within the lung, the lung regions are first extracted using expectation-maximization (EM) analysis and morphological operations. The authors developed a 3D multiscale filtering technique to enhance the pulmonary vascular structures based on the analysis of eigenvalues of the Hessian matrix at multiple scales. A new response function of the filter was designed to enhance all vascular structures including the vessel bifurcations and suppress nonvessel structures such as the lymphoid tissues surrounding the vessels. An EM estimation is then used to segment the vascular structures by extracting the high response voxels at each scale. The vessel tree is finally reconstructed by integrating the segmented vessels at all scales based on a "connected component" analysis. Two CTPA cases containing PEs were used to evaluate the performance of the system. One of these two cases also contained pleural effusion disease. Two experienced thoracic radiologists provided the gold standard of pulmonary vessels including both arteries and veins by manually tracking the arterial tree and marking the center of the vessels using a computer graphical user interface. The accuracy of vessel tree segmentation was evaluated by the percentage of the "gold standard" vessel center points overlapping with the segmented vessels. The results show that 96.2% (2398/2494) and 96.3% (1910/1984) of the manually marked center points in the arteries overlapped with segmented vessels for the case without and with other lung diseases. For the manually marked center points in all vessels including arteries and veins, the segmentation accuracy are 97.0% (4546/4689) and 93.8% (4439/4732) for the cases without and with other lung diseases, respectively. Because of the lack of ground truth for the vessels, in addition to quantitative evaluation of the vessel segmentation performance, visual inspection was conducted to evaluate the segmentation. The results demonstrate that vessel segmentation using our method can extract the pulmonary vessels accurately and is not degraded by PE occlusion to the vessels in these test cases.     

Laser scanning cytometry for automation of the micronucleus assay

Laser scanning cytometry (LSC) provides a novel approach for automated scoring of micronuclei (MN) in different types of mammalian cells, serving as a biomarker of genotoxicity and mutagenicity. In this review, we discuss the advances to date in measuring MN in cell lines, buccal cells and erythrocytes, describe the advantages and outline potential challenges of this distinctive approach of analysis of nuclear anomalies. The use of multiple laser wavelengths in LSC and the high dynamic range of fluorescence and absorption detection allow simultaneous measurement of multiple cellular and nuclear features such as cytoplasmic area, nuclear area, DNA content and density of nuclei and MN, protein content and density of cytoplasm as well as other features using molecular probes. This high-content analysis approach allows the cells of interest to be identified (e.g. binucleated cells in cytokinesis-blocked cultures) and MN scored specifically in them. MN assays in cell lines (e.g. the CHO cell MN assay) using LSC are increasingly used in routine toxicology screening. More high-content MN assays and the expansion of MN analysis by LSC to other models (i.e. exfoliated cells, dermal cell models, etc.) hold great promise for robust and exciting developments in MN assay automation as a high-content high-throughput analysis procedure.     

Visualisation and modelling of renal capillaries from confocal images

A computer aided design was developed to support three-dimensional visualisation and modelling of vascular networks. Volume data comprised a series of images obtained using a Zeiss confocal laser scanning microscope. The profiles of vessels were automatically segmented using two-dimensional morphological filters. Segmented contours of the vessels were used to form a spatial model of the network. The centre points of segmented contours were used to derive a three-dimensional graph representing the vascular network. The proposed method was applied to renal capillary networks of normal rats, and showed well the lobular structure of glomeruli. The average length of renal capillary networks was 6.09 mm. Three-dimensional models based on confocal data require much less effort than reconstructions based on serial sections, and can be adapted for any vascular patterns.     

Visualisation and modelling of renal capillaries from confocal images

A computer aided design was developed to support three-dimensional visualisation and modelling of vascular networks. Volume data comprised a series of images obtained using a Zeiss confocal laser scanning microscope. The profiles of vessels were automatically segmented using two-dimensional morphological filters. Segmented contours of the vessels were used to form a spatial model of the network. The centre points of segmented contours were used to derive a three-dimensional graph representing the vascular network. The proposed method was applied to renal capillary networks of normal rats, and showed well the lobular structure of glomeruli. The average length of renal capillary networks was 6.09 mm. Three-dimensional models based on confocal data require much less effort than reconstructions based on serial sections, and can be adapted for any vascular patterns.     

肌肉组织背景下的微血管分割方法研究

微血管的分割提取是微循环网络特征参数分析与功能障碍评估的关键性图像处理技术基础之一。目前尚缺乏有效的专门针对肌肉组织来源图像的微血管分割方法,使用现有的血管分割算法难以取得理想的分割效果。本研究依据该类图像的特点,针对性地提出了一种基于多技术组合联用的分割方案—TOSC分割法。首先以阈值法进行初次分割,然后通过形态学开运算截断背景与微血管间连接区,再以种子填充法对微血管区域进行二次识别与分割,最后通过形态学闭运算填充分割区域中的孔洞和缺刻,实现了微血管的分割提取以及在此基础上的功能微血管面积密度测量。分割测试结果表明TOSC分割法能够准确地将微血管区域从复杂的肌纤维组织背景中提取出来,可满足基础研究与临床处理的要求。     

A silicon-glass microwell platform for high-resolution imaging and high-content screening with single cell resolution

We present a novel microwell array platform suited for various cell-imaging assays where single cell resolution is important. The platform consists of an exchangeable silicon-glass microchip for cell biological applications and a custom made holder that fits in conventional microscopes. The microchips presented here contain arrays of miniature wells, where the well sizes and layout have been designed for different applications, including single cell imaging, studies of cell-cell interactions or ultrasonic manipulation of cells. The device has been designed to be easy to use, to allow long-term assays (spanning several days) with read-outs based on high-resolution imaging or high-content screening. This study is focused on screening applications and an automatic cell counting protocol is described and evaluated. Finally, we have tested the device and automatic counting by studying the selective survival and clonal expansion of 721.221 B cells transfected to express HLA Cw6-GFP compared to untransfected 721.221 B cells when grown under antibiotic selection for 3 days. The device and automated analysis protocol make up the foundation for development of several novel cellular imaging assays.     

基于形态学的均值平移算法的神经元干细胞图像的自动分割

在神经元干细胞的图像分析中,准确快速的图像分割是干细胞分化增值自动追踪系统的基础。为了准确地分割低对比度的灰度神经元干细胞图像,本研究提出一种基于形态学运算和均值平移算法的神经元干细胞分割方法,称其为形态学的均值平移算法。此算法可以快速地获得任意形状细胞的图像,并且能检测到图像中多连接边缘不封闭的细胞。将此方法应用于神经元干细胞序列图像分割中并且将其与门限分割、水线分割和活动轮廓进行对比。实验结果证明,与其它的方法相比,此方法获得的细胞分割形状更接近于真实细胞的形状,并且能获得或接近于原始图像中准确的独立细胞数目。此方法可以获得正确的分割结果,为进一步图像处理奠定了良好的基础。     

Identification of compounds that enhance the anti-lymphoma activity of rituximab using flow cytometric high-content screening

In this report, we describe a new flow cytometry technique termed flow cytometric high-content screening (FC-HCS) which involves semi-automated processing and analysis of multiparameter flow cytometry samples. As a first test of the FC-HCS technique, we used it to screen a 2000-compound library, called the National Cancer Institute (NCI) Diversity Set, to identify agents that would enhance the anti-lymphoma activity of the therapeutic monoclonal antibody rituximab. FC-HCS identified 15 compounds from the Diversity Set that significantly enhanced the ability of rituximab to inhibit cell cycle progression and induce apoptosis in lymphoma cells. The validity of the screening results was confirmed for several compounds using additional assays of cell proliferation, apoptosis and cell growth. The FC-HCS technique was relatively simple and reliable and could process up to 1000 samples/day on a single flow cytometer. The FC-HCS technique may be useful for a variety of applications including drug discovery, immunologic monitoring of patients, functional genomics studies and tissue engineering efforts.     

Detection of Hard Exudates in Colour Fundus Images Using Fuzzy Support Vector Machine-Based Expert System

Diabetic retinopathy is a major cause of vision loss in diabetic patients. Currently, there is a need for making decisions using intelligent computer algorithms when screening a large volume of data. This paper presents an expert decision-making system designed using a fuzzy support vector machine (FSVM) classifier to detect hard exudates in fundus images. The optic discs in the colour fundus images are segmented to avoid false alarms using morphological operations and based on circular Hough transform. To discriminate between the exudates and the non-exudates pixels, colour and texture features are extracted from the images. These features are given as input to the FSVM classifier. The classifier analysed 200 retinal images collected from diabetic retinopathy screening programmes. The tests made on the retinal images show that the proposed detection system has better discriminating power than the conventional support vector machine. With the best combination of FSVM and features sets, the area under the receiver operating characteristic curve reached 0.9606, which corresponds to a sensitivity of 94.1 % with a specificity of 90.0 %. The results suggest that detecting hard exudates using FSVM contribute to computer-assisted detection of diabetic retinopathy and as a decision support system for ophthalmologists.     

一种对混养细胞基于形态的细胞分选方法

目的通过对采集的细胞图像的定量识别,并结合基于机器学习的聚类分析,实现对混合培养的多种细胞基于形态的快速识别分选。方法对体外混合培养的A549和3T3两种细胞进行免疫荧光染色以表征其形态轮廓,利用CellProfiler对采集的荧光图片进行细胞形态特征的提取,再通过CellProfiler Analyst对提取的数据进行机器学习,训练出一种规则,形成一种泛化能力,以达到对混合培养的两种细胞进行识别分选的目的。结果训练分类器准确率为81.24%,可以实现A549和3T3细胞的二分类。结论机器学习有助于提升数据聚类分析的准确率,将其应用于细胞图像的识别,可为临床对组织切片进行快速病理检测提供预判断,从而减轻医生的工作量,提高诊断的准确率。     

Automatic recognition of small cell carcinoma based on the self-organizing neural network

In this paper the recognition of Small Cell Carcinoma (SCC) is studied. For each type we select 128 samples for training, and randomly measure 200 cells in each sample. We introduce multi-scale morphology based on centroid coordinates to extract the boundaries of nuclei and obtain feature images of nuclei. The features of lung cancer cells are described by morphological and colorimetrical parameters, which is valuable to recognize SCC. Then the architecture of self-organizing feature mapping (SOFM) neural network is studied for recognition of SCC. The weights of the network are adjusted by self-organizing competition, and finally inputted patterns are classified. This algorithm has the advantage of parallelism and fast-convergence, and may simplify the analysis of SCC. Clinical experiment results show that the correctness ratio of this system may reach 95.3% while recognizing lung cancer cell types. Our work is significant to the pathological researches of lung cancer, assistant clinic diagnosis, and assessment of therapeutic effects. Meanwhile a software system named as SCC.LUNG is established for automatic analysis.     

Automated detection of exudates for diabetic retinopathy screening

Automated image analysis is being widely sought to reduce the workload required for grading images resulting from diabetic retinopathy screening programmes. The recognition of exudates in retinal images is an important goal for automated analysis since these are one of the indicators that the disease has progressed to a stage requiring referral to an ophthalmologist. Candidate exudates were detected using a multi-scale morphological process. Based on local properties, the likelihoods of a candidate being a member of classes exudate, drusen or background were determined. This leads to a likelihood of the image containing exudates which can be thresholded to create a binary decision. Compared to a clinical reference standard, images containing exudates were detected with sensitivity 95.0% and specificity 84.6% in a test set of 13,219 images of which 300 contained exudates. Depending on requirements, this method could form part of an automated system to detect images showing either any diabetic retinopathy or referable diabetic retinopathy.