Automatic diagnosis of mammographic abnormalities based on hybrid features with learning classifier

Breast cancer screening is currently performed by mammography, which is limited by overlying anatomy and dense breast tissue. Computer-aided detection (CAD) systems can serve as a double reader to improve radiologist performance. In this paper, we have applied a novel approach to segmentation of suspicious region by mammogram and classification based on hybrid features with learning classifier. We formulated differentiation of lesion from normal tissue as a supervised learning problem, and applied this learning method to develop the classification algorithm. The algorithm has been verified with 164 mammograms in the mini Mammographic Image Analysis Society database. The experimental results show that the detection method has a sensitivity of 94.5% at 0.26 false positives per image. The efficiency of algorithm is measured using free receiver operating characteristics curve and the results are highlighted. We conclude that CAD technology with learning classifier has the potential to help radiologists with the task of discriminating between lesion and normal tissues.     

Directionlet transform based sharpening and enhancement of mammographic X-ray images

Due to difficulty in detecting the low contrast and noisy nature of X-ray mammography images, they have to be enhanced to obtain a clear and good view. Though Sharpening Technique (ST) is used to enhance the contrast, it introduces noise in the enhancement process, and they do not include anisotropic features. This paper proposes a ST, which uses multiscale linear and anisotropic geometrical features obtained from directionlet transform (DT). The newly formulated method that combines multidirectional geometrical information has various tunable parameters and improved noise control by means of multiscale features. The DT that uses skewed and elongated directional basis functions not only captures the point singularities, but also links them into linear structure. The performance of the proposed DT ST is compared with non-linear unsharp masking (NLUSM). While the DT and LoG based sharpened images are given to the input of standard AHE, their performance is improved. Enhancement Measure and structural similarity measure are used to analyze the performance of the proposed method. Though the images are enhanced, the quality of the image is not degraded. As a specific application, the enhanced images are used to detect the microcalcification and spiculated masses in mammograms.     

A computer-aided diagnosis scheme of breast lesion classification using GLGLM and shape features: Combined-view and multi-classifiers

PurposeTo address high false-positive results of FFDM issue, we make the first effort to develop a computer-aided diagnosis (CAD) scheme to analyze and distinguish breast lesions.MethodThe breast lesion regions were first segmented and depicted on FFDM images from 106 patients. In this work, 11 gray-level gap-length matrix texture features and 12 shape features were extracted form craniocaudal view and mediolateral oblique view, and then Student’s t-test, Fisher-score and Relief-F were introduced to select features. We also investigated the effect of three factors, i.e., discretisation, selection methods and classifier methods, of the classification performance via analysis of variance. Finally, a classification model was constructed. Spearman’s correlation coefficient analysis was conducted to assess the internal relevance of features.ResultsThe proposed scheme using Student’s t-test achieved an area under the receiver operating characteristic curve (AUC) value of 0.923 at 512 bins. The AUC values are 0.884, 0.867, 0.874 and 0.901 for the low gray-level gaps emphasis (LGGE), solidity, extent, and the combined set, respectively. Solidity and extent depicts the correlation coefficient of 0.86 (P < 0.05).ConclusionsWe present a new CAD scheme based on the contribution of the significant factors. The experimental results demonstrate that the presented scheme can be used to successfully distinguish breast carcinoma lesions and benign fibroadenoma lesions in our FFDM dataset and the MIAS dataset, which may provide a CAD method to assist radiologists in diagnosing and interpreting screening mammograms. Moreover, we found that LGGE, solidity and extent features show great potential for breast lesion classification.     

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.     

An exact test for detecting inconsistency in readers interpretation over time in screening mammograms

Radiologists' interpretation on screening mammograms is measured by accuracy indices such as sensitivity and specificity. The hypothesis that radiologists' interpretation on screening mammograms is constant across time can be tested by measuring overdispersion. However, small sample sizes are problematic for the accuracy of asymptotic approaches. In this article, we propose an exact conditional distribution for testing overdispersion of the binomial assumption that is assumed for the accuracy indices. An exact p -value can be defined from the developed distribution. We also describe an algorithm for computing this exact test. This proposed method is applied to data from a study in reading screening mammograms in a population of US radiologists (Beam et al., 2003). The exact method is compared analytically with a currently available method based on large sample approximations.     

三维肺部图像中疑似肺结节结构的自动提取

本文提出了一种肺部CT图像三维数据中自动提取疑似结节区域的方法。首先结合阈值分割、种子填充等方法,在三维体数据上分割出肺实质。进而利用改进的模糊C均值聚类,提取出结节及具有结节特征的血管、支气管等感兴趣区域。该工作对感兴趣区域的特征提取有重要意义,是早期肺癌计算机辅助诊断重要的一步。     

LeukocyteMask: An automated localization and segmentation method for leukocyte in blood smear images using deep neural networks

Digital pathology and microscope image analysis is widely used in comprehensive studies of cell morphology. Identification and analysis of leukocytes in blood smear images, acquired from bright field microscope, are vital for diagnosing many diseases such as hepatitis, leukaemia and acquired immune deficiency syndrome (AIDS). The major challenge for robust and accurate identification and segmentation of leukocyte in blood smear images lays in the large variations of cell appearance such as size, colour and shape of cells, the adhesion between leukocytes (white blood cells, WBCs) and erythrocytes (red blood cells, RBCs), and the emergence of substantial dyeing impurities in blood smear images. In this paper, an end‐to‐end leukocyte localization and segmentation method is proposed, named LeukocyteMask, in which pixel‐level prior information is utilized for supervisor training of a deep convolutional neural network, which is then employed to locate the region of interests (ROI) of leukocyte, and finally segmentation mask of leukocyte is obtained based on the extracted ROI by forward propagation of the network. Experimental results validate the effectiveness of the propose method and both the quantitative and qualitative comparisons with existing methods indicate that LeukocyteMask achieves a state‐of‐the‐art performance for the segmentation of leukocyte in terms of robustness and accuracy .     

Patient oriented graph-based image segmentation

Despite increased image quality including medical imaging, image segmentation continues to represent a major bottleneck in practical applications due to noise and lack of contrast. In this paper, we present a new methodology to segment noisy, low contrast medical images, with a view to developing practical applications. Firstly, the contrast of the image is enhanced and then a modified graph-based method is followed. This paper has mainly two contributions: (1) a contrast enhancement stage performed by suitably utilizing the noise present in the medical data. This step is achieved through stochastic resonance theory applied in the wavelet domain and (2) a new weighting function is proposed for traditional graph-based approaches. Both qualitative (by our clinicians/radiologists) and quantitative evaluation performed on publicly available computed tomography (CT) (MICCAI 2007 Grand Challenge workshop database) and cardiac magnetic resonance (CMR) databases reflect the potential of the proposed method even in the presence of tumors/papillary muscles.     

Tumor morphology and phenotypic evolution driven by selective pressure from the microenvironment

Emergence of invasive behavior in cancer is life-threatening, yet ill-defined due to its multifactorial nature. We present a multiscale mathematical model of cancer invasion, which considers cellular and microenvironmental factors simultaneously and interactively. Unexpectedly, the model simulations predict that harsh tumor microenvironment conditions (e.g., hypoxia, heterogenous extracellular matrix) exert a dramatic selective force on the tumor, which grows as an invasive mass with fingering margins, dominated by a few clones with aggressive traits. In contrast, mild microenvironment conditions (e.g., normoxia, homogeneous matrix) allow clones with similar aggressive traits to coexist with less aggressive phenotypes in a heterogeneous tumor mass with smooth, noninvasive margins. Thus, the genetic make-up of a cancer cell may realize its invasive potential through a clonal evolution process driven by definable microenvironmental selective forces. Our mathematical model provides a theoretical/experimental framework to quantitatively characterize this selective pressure for invasion and test ways to eliminate it.     

A Combinational Clustering Based Method for cDNA Microarray Image Segmentation

Microarray technology plays an important role in drawing useful biological conclusions by analyzing thousands of gene expressions simultaneously. Especially, image analysis is a key step in microarray analysis and its accuracy strongly depends on segmentation. The pioneering works of clustering based segmentation have shown that k-means clustering algorithm and moving k-means clustering algorithm are two commonly used methods in microarray image processing. However, they usually face unsatisfactory results because the real microarray image contains noise, artifacts and spots that vary in size, shape and contrast. To improve the segmentation accuracy, in this article we present a combination clustering based segmentation approach that may be more reliable and able to segment spots automatically. First, this new method starts with a very simple but effective contrast enhancement operation to improve the image quality. Then, an automatic gridding based on the maximum between-class variance is applied to separate the spots into independent areas. Next, among each spot region, the moving k-means clustering is first conducted to separate the spot from background and then the k-means clustering algorithms are combined for those spots failing to obtain the entire boundary. Finally, a refinement step is used to replace the false segmentation and the inseparable ones of missing spots. In addition, quantitative comparisons between the improved method and the other four segmentation algorithms--edge detection, thresholding, k-means clustering and moving k-means clustering--are carried out on cDNA microarray images from six different data sets. Experiments on six different data sets, 1) Stanford Microarray Database (SMD), 2) Gene Expression Omnibus (GEO), 3) Baylor College of Medicine (BCM), 4) Swiss Institute of Bioinformatics (SIB), 5) Joe DeRisi’s individual tiff files (DeRisi), and 6) University of California, San Francisco (UCSF), indicate that the improved approach is more robust and sensitive to weak spots. More importantly, it can obtain higher segmentation accuracy in the presence of noise, artifacts and weakly expressed spots compared with the other four methods.     

FogBank: a single cell segmentation across multiple cell lines and image modalities

Background

Many cell lines currently used in medical research, such as cancer cells or stem cells, grow in confluent sheets or colonies. The biology of individual cells provide valuable information, thus the separation of touching cells in these microscopy images is critical for counting, identification and measurement of individual cells. Over-segmentation of single cells continues to be a major problem for methods based on morphological watershed due to the high level of noise in microscopy cell images. There is a need for a new segmentation method that is robust over a wide variety of biological images and can accurately separate individual cells even in challenging datasets such as confluent sheets or colonies.

Results

We present a new automated segmentation method called FogBank that accurately separates cells when confluent and touching each other. This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images. The method is based on morphological watershed principles with two new features to improve accuracy and minimize over-segmentation.First, FogBank uses histogram binning to quantize pixel intensities which minimizes the image noise that causes over-segmentation. Second, FogBank uses a geodesic distance mask derived from raw images to detect the shapes of individual cells, in contrast to the more linear cell edges that other watershed-like algorithms produce.We evaluated the segmentation accuracy against manually segmented datasets using two metrics. FogBank achieved segmentation accuracy on the order of 0.75 (1 being a perfect match). We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets. FogBank outperformed all related algorithms. The accuracy has also been visually verified on data sets with 14 cell lines across 3 imaging modalities leading to 876 segmentation evaluation images.

Conclusions

FogBank produces single cell segmentation from confluent cell sheets with high accuracy. It can be applied to microscopy images of multiple cell lines and a variety of imaging modalities. The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0431-x) contains supplementary material, which is available to authorized users.     

Nuclear localization and mitogen-activated protein kinase phosphorylation of the multifunctional protein CAD

CAD is a multifunctional protein that initiates and regulates mammalian de novo pyrimidine biosynthesis. The activation of the pathway required for cell proliferation is a consequence of the phosphorylation of CAD Thr-456 by mitogen-activated protein (MAP) kinase. Although most of the CAD in the cell was cytosolic, cell fractionation and fluorescence microscopy showed that Thr(P)-456 CAD was primarily localized within the nucleus in association with insoluble nuclear substructures, including the nuclear matrix. CAD in resting cells was cytosolic and unphosphorylated. Upon epidermal growth factor stimulation, CAD moved to the nucleus, and Thr-456 was found to be phosphorylated. Mutation of the CAD Thr-456 and inhibitor studies showed that nuclear import is not mediated by MAP kinase phosphorylation. Two fluorescent CAD constructs, NLS-CAD and NES-CAD, were prepared that incorporated strong nuclear import and export signals, respectively. NLS-CAD was exclusively nuclear and extensively phosphorylated. In contrast, NES-CAD was confined to the cytoplasm, and Thr-456 remained unphosphorylated. Although alternative explanations can be envisioned, it is likely that phosphorylation occurs within the nucleus where much of the activated MAP kinase is localized. Trapping CAD in the nucleus had a minimal effect on pyrimidine metabolism. In contrast, when CAD was excluded from the nucleus, the rate of pyrimidine biosynthesis, the nucleotide pools, and the growth rate were reduced by 21, 36, and 60%, respectively. Thus, the nuclear import of CAD appears to promote optimal cell growth. UMP synthase, the bifunctional protein that catalyzes the last two steps in the pathway, was also found in both the cytoplasm and nucleus.     

Improved and Robust Detection of Cell Nuclei from Four Dimensional Fluorescence Images

Segmentation-free direct methods are quite efficient for automated nuclei extraction from high dimensional images. A few such methods do exist but most of them do not ensure algorithmic robustness to parameter and noise variations. In this research, we propose a method based on multiscale adaptive filtering for efficient and robust detection of nuclei centroids from four dimensional (4D) fluorescence images. A temporal feedback mechanism is employed between the enhancement and the initial detection steps of a typical direct method. We estimate the minimum and maximum nuclei diameters from the previous frame and feed back them as filter lengths for multiscale enhancement of the current frame. A radial intensity-gradient function is optimized at positions of initial centroids to estimate all nuclei diameters. This procedure continues for processing subsequent images in the sequence. Above mechanism thus ensures proper enhancement by automated estimation of major parameters. This brings robustness and safeguards the system against additive noises and effects from wrong parameters. Later, the method and its single-scale variant are simplified for further reduction of parameters. The proposed method is then extended for nuclei volume segmentation. The same optimization technique is applied to final centroid positions of the enhanced image and the estimated diameters are projected onto the binary candidate regions to segment nuclei volumes.Our method is finally integrated with a simple sequential tracking approach to establish nuclear trajectories in the 4D space. Experimental evaluations with five image-sequences (each having 271 3D sequential images) corresponding to five different mouse embryos show promising performances of our methods in terms of nuclear detection, segmentation, and tracking. A detail analysis with a sub-sequence of 101 3D images from an embryo reveals that the proposed method can improve the nuclei detection accuracy by 9 over the previous methods, which used inappropriate large valued parameters. Results also confirm that the proposed method and its variants achieve high detection accuracies ( 98 mean F-measure) irrespective of the large variations of filter parameters and noise levels.     

Computer-aided detection of pulmonary nodules using dynamic self-adaptive template matching and a FLDA classifier

Improving the performance of computer-aided detection (CAD) system for pulmonary nodules is still an important issue for its future clinical applications. This study aims to develop a new CAD scheme for pulmonary nodule detection based on dynamic self-adaptive template matching and Fisher linear discriminant analysis (FLDA) classifier. We first segment and repair lung volume by using OTSU algorithm and three-dimensional (3D) region growing. Next, the suspicious regions of interest (ROIs) are extracted and filtered by applying 3D dot filtering and thresholding method. Then, pulmonary nodule candidates are roughly detected with 3D dynamic self-adaptive template matching. Finally, we optimally select 11 image features and apply FLDA classifier to reduce false positive detections. The performance of the new method is validated by comparing with other methods through experiments using two groups of public datasets from Lung Image Database Consortium (LIDC) and ANODE09. By a 10-fold cross-validation experiment, the new CAD scheme finally has achieved a sensitivity of 90.24% and a false-positive (FP) of 4.54 FP/scan on average for the former dataset, and a sensitivity of 84.1% with 5.59 FP/scan for the latter. By comparing with other previously reported CAD schemes tested on the same datasets, the study proves that this new scheme can yield higher and more robust results in detecting pulmonary nodules.     

ROI-Based Compression Strategy of 3D MRI Brain Datasets for Wireless Communications

ObjectivesBecause of the large amount of medical imaging data, the transmission process becomes complicated in telemedicine applications. Thus, in order to adapt the data bit streams to the constraints related to the limitation of the bandwidths a reduction of the size of the data by compression of the images is essential. Despite the improvements in the field of compression, the transmission itself can also introduce errors. For this reason, it is important to develop an adequate strategy which will help reduce this volume of data without having to introduce some distortion and resist the errors introduced by the channel noise during transmission. Thus, in this paper, we propose a ROI-based coding strategy and unequal bit stream protection to meet this dual constraint.Material and methodsThe proposed ROI-based compression strategy with unequal bit stream protection is composed of three parts: the first one allows the extraction of the ROI region, the second one consists of a ROI-based coding and the third one allows an unequal protection of the ROI bit stream.First, the Regions Of Interest (ROI) are extracted by hierarchical segmentation of these regions according to a segmentation method based on the technique of Marker-based-watershed combined with the technique of active contours by level set. The resulting regions are selectively encoded by a 3D coder based on a shape adaptive discrete wavelet transform 3D-BISK, where the compression ratio of each region depends on its relevance in diagnosis. These obtained regions of interest are protected with an error-correcting code of Reed-Solomon type with a code rate that varies according to the relevance of the region by an unequal protection strategy (UEP).ResultsThe performance of the proposed compression scheme is evaluated in several ways. First, tests are performed to study the impact of errors on the different bit streams. In the first place, these tests are carried out in order to study the effect of the variation of the compression rates on the different bit streams. Secondly, different Reed Solomon error-correcting codes of different code rates are tested at different compression rates on a BSC channel. Finally, the performances of this coding strategy are compared with those of SPIHT 3D in the case of transmission on a BSC channel.ConclusionThe obtained results show that the proposed method is quite efficient in transmission time reduction. Therefore, our proposed scheme will reduce the volume of data without having to introduce some distortion and resist the errors introduced by the channel noise in the case of telemedicine.     

GPCALMA: Implementation in Italian hospitals of a computer aided detection system for breast lesions by mammography examination

We describe the implementation in several Italian hospitals of a computer aided detection (CAD) system, named GPCALMA (grid platform for a computer aided library in mammography), for the automatic search of lesions in X-ray mammographies. GPCALMA has been under development since 1999 by a community of physicists of the Italian National Institute for Nuclear Physics (INFN) in collaboration with radiologists. This CAD system was tested as a support to radiologists in reading mammographies. The main system components are: (i) the algorithms implemented for the analysis of digitized mammograms to recognize suspicious lesions, (ii) the database of digitized mammographic images, and (iii) the PC-based digitization and analysis workstation and its user interface. The distributed nature of data and resources and the prevalence of geographically remote users suggested the development of the system as a grid application: the design of this networked version is also reported. The paper describes the system architecture, the database of digitized mammographies, the clinical workstation and the medical applications carried out to characterize the system. A commercial CAD was evaluated in a comparison with GPCALMA by analysing the medical reports obtained with and without the two different CADs on the same dataset of images: with both CAD a statistically significant increase in sensitivity was obtained. The sensitivity in the detection of lesions obtained for microcalcification and masses was 96% and 80%, respectively. An analysis in terms of receiver operating characteristic (ROC) curve was performed for massive lesion searches, achieving an area under the ROC curve of A_z = 0.783 ± 0.008. Results show that the GPCALMA CAD is ready to be used in the radiological practice, both for screening mammography and clinical studies. GPCALMA is a starting point for the development of other medical imaging applications such as the CAD for the search of pulmonary nodules, currently under development in the framework of an INFN-funded project.     

Design of Orthopedic Plates and Its Modification Based on Feature

To quickly construct the orthopedic plates and to conveniently edit it, a novel method for designing the plates is put forward based on feature idea and parameterization. Firstly, attached to the existing or repaired bone model, the region of interest (ROI) is selected as the abutted surface of orthopedic plate, and the ROI is reconstructed to form a CAD surface. Secondly, the CAD surface is to be defined as a surface feature (SF) and then some semantic parameters are configured for it. Lastly, the plate body is constructed through thickening, and some higher parameters are defined for it so as to produce a volumetric feature (VF). In the above process, there exist two main problems: one is parameterization of the abutted surface, and the other is construction of the outer surface. Besides, the mapping relationship has to be built between surface feature parameters and volumetric feature parameters. This method supports the modification of high-level parameters, consequently promoting the quality and efficiency of orthopedic plate design.     

Automatic Detection and Classification of Mammograms Using Improved Extreme Learning Machine with Deep Learning

Background and objectiveBreast cancer, the most intrusive form of cancer affecting women globally. Next to lung cancer, breast cancer is the one that provides a greater number of cancer deaths among women. In recent times, several intelligent methodologies were come into existence for building an effective detection and classification of such noxious type of cancer. For further improving the rate of early diagnosis and for increasing the life span of victims, optimistic light of research is essential in breast cancer classification. Accordingly, a new customized method of integrating the concept of deep learning with the extreme learning machine (ELM), which is optimized using a simple crow-search algorithm (ICS-ELM). Thus, to enhance the state-of-the-art workings, an improved deep feature-based crow-search optimized extreme learning machine is proposed for addressing the health-care problem. The paper pours a light-of-research on detecting the input mammograms as either normal or abnormal. Subsequently, it focuses on further classifying the type of abnormal severities i.e., benign type or malignant.Materials and methodsThe digital mammograms for this work are taken from the Curated Breast Imaging Subset of DDSM (CBIS-DDSM), Mammographic Image Analysis Society (MIAS), and INbreast datasets. Herein, the work employs 570 digital mammograms (250 normal, 200 benign and 120 malignant cases) from CBIS-DDSM dataset, 322 digital mammograms (207 normal, 64 benign and 51 malignant cases) from MIAS database and 179 full-field digital mammograms (66 normal, 56 benign and 57 malignant cases) from INbreast dataset for its evaluation. The work utilizes ResNet-18 based deep extracted features with proposed Improved Crow-Search Optimized Extreme Learning Machine (ICS-ELM) algorithm.ResultsThe proposed work is finally compared with the existing Support Vector Machines (RBF kernel), ELM, particle swarm optimization (PSO) optimized ELM, and crow-search optimized ELM, where the maximum overall classification accuracy is obtained for the proposed method with 97.193% for DDSM, 98.137% for MIAS and 98.266% for INbreast datasets, respectively.ConclusionThe obtained results reveal that the proposed Computer-Aided-Diagnosis (CAD) tool is robust for the automatic detection and classification of breast cancer.     

Segmentation of the Clustered Cells with Optimized Boundary Detection in Negative Phase Contrast Images

Cell image segmentation plays a central role in numerous biology studies and clinical applications. As a result, the development of cell image segmentation algorithms with high robustness and accuracy is attracting more and more attention. In this study, an automated cell image segmentation algorithm is developed to get improved cell image segmentation with respect to cell boundary detection and segmentation of the clustered cells for all cells in the field of view in negative phase contrast images. A new method which combines the thresholding method and edge based active contour method was proposed to optimize cell boundary detection. In order to segment clustered cells, the geographic peaks of cell light intensity were utilized to detect numbers and locations of the clustered cells. In this paper, the working principles of the algorithms are described. The influence of parameters in cell boundary detection and the selection of the threshold value on the final segmentation results are investigated. At last, the proposed algorithm is applied to the negative phase contrast images from different experiments. The performance of the proposed method is evaluated. Results show that the proposed method can achieve optimized cell boundary detection and highly accurate segmentation for clustered cells.     

一种新的中心定位算法在细胞分割中的应用

以模糊数学为基础,提出了一种新的寻找细胞核中心的方法。该方法能有效地对同一图中多个不同大小的细胞核进行定位,并且其抗噪能力较强,正确率较高。文中采用该定位算法确定细胞核的中心位置后,再应用水平集的方法对细胞显微图像进行分割。分割的结果进一步表明了这种中心定位算法是有效的和鲁棒的,能辅助其他分割算法一起完成复杂图像的分割任务。