Anna Korzynska

Segmentation of microscope images of living cells

This paper describes a segmentation method combining a texture based technique with a contour based method. The technique is designed to enable the study of cell behaviour over time by segmenting brightfield microscope image sequences. The technique was tested on artificial images, based on images of living cells and on real sequences acquired from microscope observations of neutrophils and lymphocytes as well as on a sequence of MRI images. The results of the segmentation are compared with the results of the watershed and snake segmentation methods. The results show that the method is both effective and practical.

Validation of various adaptive threshold methods of segmentation applied to follicular lymphoma digital images stained with 3,3’-Diaminobenzidine&Haematoxylin

AbstractThe comparative study of the results of various segmentation methods for the digital images of the follicular lymphoma cancer tissue section is described in this paper. The sensitivity and specificity and some other parameters of the following adaptive threshold methods of segmentation: the Niblack method, the Sauvola method, the White method, the Bernsen method, the Yasuda method and the Palumbo method, are calculated. Methods are applied to three types of images constructed by extraction of the brown colour information from the artificial images synthesized based on counterpart experimentally captured images. This paper presents usefulness of the microscopic image synthesis method in evaluation as well as comparison of the image processing results. The results of thoughtful analysis of broad range of adaptive threshold methods applied to: (1) the blue channel of RGB, (2) the brown colour extracted by deconvolution and (3) the ’brown component’ extracted from RGB allows to select some pairs: method and type of image for which this method is most efficient considering various criteria e.g. accuracy and precision in area detection or accuracy in number of objects detection and so on. The comparison shows that the White, the Bernsen and the Sauvola methods results are better than the results of the rest of the methods for all types of monochromatic images. All three methods segments the immunopositive nuclei with the mean accuracy of 0.9952, 0.9942 and 0.9944 respectively, when treated totally. However the best results are achieved for monochromatic image in which intensity shows brown colour map constructed by colour deconvolution algorithm. The specificity in the cases of the Bernsen and the White methods is 1 and sensitivities are: 0.74 for White and 0.91 for Bernsen methods while the Sauvola method achieves sensitivity value of 0.74 and the specificity value of 0.99. According to Bland-Altman plot the Sauvola method selected objects are segmented without undercutting the area for true positive objects but with extra false positive objects. The Sauvola and the Bernsen methods gives complementary results what will be exploited when the new method of virtual tissue slides segmentation be develop.Virtual SlidesThe virtual slides for this article can be found here: slide 1: http://diagnosticpathology.slidepath.com/dih/webViewer.php?snapshotId=13617947952577 and slide 2: http://diagnosticpathology.slidepath.com/dih/webViewer.php?snapshotId=13617948230017.

Segmentation of Stained Lymphoma Tissue Section Images

In order to obtain supporting tool for the pathologists who are investigating prognostic factors in folicular lymphoma a new method of color images segmentation is proposed. The method works on images acquired from immunohistochemically stained thin tissue sections of lymph nodes coming from patients with folicular lymphoma diagnosis. The proposed method of segmentation consists of: pre-processing, adaptive threshold, watershed segmentation and post-processing. The method is tested on a set of 50 images. Its results are compared with results of manual counting. It has been found that difference between the traditional method results and the proposed method is small for images with up to 100 nuclei while in more complicated images with more then 100 nuclei and with nuclei clusters this difference increases.

Comparison of the Manual, Semiautomatic, and Automatic Selection and Leveling of Hot Spots in Whole Slide Images for Ki-67 Quantification in Meningiomas

Background. This paper presents the study concerning hot-spot selection in the assessment of whole slide images of tissue sections collected from meningioma patients. The samples were immunohistochemically stained to determine the Ki-67/MIB-1 proliferation index used for prognosis and treatment planning. Objective. The observer performance was examined by comparing results of the proposed method of automatic hot-spot selection in whole slide images, results of traditional scoring under a microscope, and results of a pathologists manual hot-spot selection. Methods. The results of scoring the Ki-67 index using optical scoring under a microscope, software for Ki-67 index quantification based on hot spots selected by two pathologists (resp., once and three times), and the same software but on hot spots selected by proposed automatic methods were compared using Kendalls tau-b statistics. Results. Results show intra- and interobserver agreement. The agreement between Ki-67 scoring with manual and automatic hot-spot selection is high, while agreement between Ki-67 index scoring results in whole slide images and traditional microscopic examination is lower. Conclusions. The agreement observed for the three scoring methods shows that automation of area selection is an effective tool in supporting physicians and in increasing the reliability of Ki-67 scoring in meningioma.

Equalisation of archival microscopic images from immunohistochemically stained tissue sections

A method of image equalisation that reduces non-uniformity of light distribution caused by optical devices and dust on camera sensors is presented. The method explores non-uniformity which occurs in archival images captured by a typical optical set which consists of a light microscope and a digital camera. A sufficient number of images with low density of foreground objects has been used to extract a global map of non-uniformity of the particular microscope and camera. The proposed method consists of two steps: – (1) extraction of the map of non-uniformity based upon a set of chosen images and – (2) correction of images acquired by the optical set. The global map is created based upon a modified value layer, the third layer of HSV colour space. The proposed method has been tested on images of immunohistochemically (IHC) stained samples of a biopsy tissue, and it has been validated using an image segmentation method developed earlier. The results of the light distribution equalization, as well as the equalized images segmentation turn out to be more similar to the reference method results (namely the manual counting results), than the results of the original images segmentation. The equalization method can be used for other types of images, but all of them should be acquired by the same optical set.

The Method of Immunohistochemical Images Standardization

The standardization method of immunohistchemically staining tissue section images prior to the image processing and analysis is described in this paper. The effectiveness of the proposed standardization method is examined on thin tissue slices of breast cancer stained with DAB & H. The image analysis results after the initial image standardization are more closer to the results of traditional methods of cells nuclei quantification than for original images.

Evaluation of cytokeratin-19 in breast cancer tissue samples: a comparison of automatic and manual evaluations of scanned tissue microarray cylinders

BackgroundDigital image (DI) analysis avoids visual subjectivity in interpreting immunohistochemical stains and provides more reproducible results. An automated procedure consisting of two variant methods for quantifying the cytokeratin-19 (CK19) marker in breast cancer tissues is presented.MethodsThe first method (A) excludes the holes inside selected CK19 stained areas, and the second (B) includes them. 93 DIs scanned from complete cylinders of tissue microarrays were evaluated visually by two pathologists and by the automated procedures.Results and conclusionsThere was good concordance between the two automated methods, both of which tended to identify a smaller CK19-positive area than did the pathologists. The results obtained with method B were more similar to those of the pathologists; probably because it takes into account the entire positive tumoural area, including the holes. However, the pathologists overestimated the positive area of CK19. Further studies are needed to confirm the utility of this automated procedure in prognostic studies.

Influence of the measurement method of features in ultrasound images of the thyroid in the diagnosis of Hashimoto’s disease

IntroductionThis paper shows the influence of a measurement method of features in the diagnosis of Hashimoto’s disease. Sensitivity of the algorithm to changes in the parameters of the ROI, namely shift, resizing and rotation, has been presented. The obtained results were also compared to the methods known from the literature in which decision trees or average gray level thresholding are used.MaterialIn the study, 288 images obtained from patients with Hashimoto’s disease and 236 images from healthy subjects have been analyzed. For each person, an ultrasound examination of the left and right thyroid lobe in transverse and longitudinal sections has been performed.MethodWith the use of the developed algorithm, a discriminant analysis has been conducted for the following five options: linear, diaglinear, quadratic, diagquadratic and mahalanobis. The left and right thyroid lobes have been analyzed both together and separately in transverse and longitudinal sections. In addition, the algorithm enabled to analyze specificity and sensitivity as well as the impact of sensitivity of ROI shift, repositioning and rotation on the measured features.Results and summaryThe analysis has shown that the highest accuracy was obtained for the longitudinal section (LD) with the method of linear, yielding sensitivity = 76%, specificity = 95% and accuracy ACC = 84%. The conducted sensitivity assessment confirms that changes in the position and size of the ROI have little effect on sensitivity and specificity. The analysis of all cases, that is, images of the left and right thyroid lobes in transverse and longitudinal sections, has shown specificity ranging from 60% to 95% and sensitivity from 62% to 89%. Additionally, it was shown that the value of ACC for the method using decision trees as a classifier is equal to 84% for the analyzed data. Thresholding of average brightness of the ROI gave ACC equal to 76%.

Automatic Counting of Neural Stem Cells Growing in Cultures

Stem cells are a potential source of cells for use in the regenerative medicine. Automation of monitoring and analysis is crucial for reliable and fast optimization of culturing methods. The goal of the first step in this investigation is to find a method of automatic cell counting on microscopic static images. In our method, an image is divided into two types of regions: the regions covered by cells and the background regions. Next the cell regions are classified into three categories: converged cells,the flatten cells and the transitional cells regions. For each type of region, the adjusted procedure estimates a quantity of cells. The quantity of cells in image has been obtained for randomly chosen images from certain sequences captured from cells which growth has been monitored using laser scanner confocal microscopy. The results of the automatic cell counting are compared with results obtained by an operator and the difference has been admissible. When a lot of frames and cells are counted, the accuracy of the proposed method has been similar to the accuracy of an expert.

A multistep image analysis method to increase automated identification efficiency in immunohistochemical nuclear markers with a high background level

The “removal” of background from digital images (DIs) to identify only the objects of interest is difficult due to the overlapping color values of pixels of the nuclei and background. We outline a new automated procedure to quantify only immunohistochemically stained nuclear markers, despite the similar color of the background. This procedure was compared with the gold standard manual method and a previous method developed for low-background DIs.