Inflammatory Cell Extraction and Nuclei Detection in Pap Smear Images (original) (raw)
Related papers
TELKOMNIKA (Telecommunication Computing Electronics and Control), 2018
In order to obtain a diagnosis of cervical cancer information, the characteristics of each cell nucleus must be identified and evaluated properly through a Pap smear test. The presence of inflammatory cells in Pap smear images can complicate the process of identification of cell nuclei in the early detection of cervical cancer. Inflammatory cells need to be eliminated to assist pathologists in reading Pap smear slides. In this work, we developed a novel method to extract the inflammatory cells that allow detection of cell nuclei more accuracy. The proposed algorithm consists of two stages: extraction of inflammatory cells using the distance criterion and image transformation. This experiment applied to the 1358 cells comprising 378 nuclei cells and 980 inflammatory cells from 25 Pap smear images. The results showed that our method can significantly reduce the amount of inflammation that can disrupt the cell nuclei in the detection process. The proposed method has promising results with a sensitivity level of 97% and a specificity of 84.38%.
Extraction and Classification Texture of Inflammatory Cells and Nuclei in Normal Pap smear Images
The presence of inflammatory cells complicates the process of identifying the nuclei in the early detection of cervical cancer. Inflammatory cells need to be eliminated to assist pathologists in reading Pap smear slides. The texture of Grey-Level Run-Length Matrix (GLRLM) for inflammatory cells and nuclei types are investigated. The inflammatory cells and nuclei have different texture, and it can be used to differentiate them. To extract all of the features, firstly manual cropping of inflammatory cells and nuclei needs to be done. All of extracted features have been analyzed and selected by Decision Tree classifier (J48). Originally there have been eleven features in the direction of 135ยบ which are extracted to classify cropping cells into inflammatory cells and nuclei. Then the eleven features are reduced into eight, namely low gray level run emphasis, gray level non uniformity, run length non-uniformity, long run low gray-level emphasis, short run high gray-level emphasis, short run low gray-level emphasis, long run high gray-level emphasis and run percentage based on the rule of classification. This experiment is applied into 957 cells which were from 50 images. The compositions of these cells were 122 cells of nuclei and 837 cells of inflammatory. The proposed algorithm applied to all of the cells and the result of classification by using these eight texture features obtains the sensitivity rates which show that there are still nuclei of cells that were considered as inflammatory cells. It was in accordance with the conditions of the difficulties faced by the pathologist while the specificity rate suggests that inflammatory cells detected properly and few inflammatory cells are considered as nucleus.
CommIT (Communication and Information Technology) Journal, 2017
The automatic interpretation of Pap Smear image is one of challenging issues in some aspects. Accurate segmentation for each cell is an important procedurethat must be done so that no information is lost during the evaluation process. However, the presence of overlapping cells in Pap Smear image make the automated analysis of these cytology images become more difficult. In most ofthe studies, cytoplasm segmentation is the difficult stage because the boundaries between cells are very thin. In this study, we propose an algorithm that can segment the overlapping cytoplasm. First, the morphology operation and global thresholding to segment cytoplasm is done. Second, the overlapping area on cytoplasm region is separated using morphological operation and distance criteria on each pixel. The proposed method has been evaluated against the results of manual tracing by experts. The experiment results show that the proposed method can segment the overlapping cytoplasm as similar as experts do,...
Pap Smear Images Segmentation for Automatic Detection of Cervical Cancer
This work focuses on segmentation of Pap smear cervical cell image for automatic screening and detection of cervical cancer at early stage. This paper proposed linear contrast enhancement and median filter for removing of noise, sharpens and preserving edges and boundary of cytoplasm and nucleus. Canny detector algorithm was preferred and applied to a cervical cell images with the value of sensitivity of 0.634 and value of sigma was 6.56. We obtained the gradient images with smooth edges and boundary of cytoplasm and nucleus. Otsu's algorithm was used to separate cytoplasm from the background. Maximum gray gradient difference (MGLGD) method adopted to extract nucleus contour. The results shows that segmentation gives impressive performance which will help further steps of automatic screening and detection of cervical cancer from Pap smear cervical cells image.
Automated segmentation of cell nuclei in PAP smear images
In this paper an automated method for cell nucleus segmentation in PAP smear images is presented. The method combines the global knowledge about the cells and nuclei appearance and the local characteristics of the area of the nuclei, in order to achieve an accurate nucleus boundary. Filters and morphological operators in all three channels of a color image result in the determination of the locations of nuclei in the image, even in cases where cell overlapping occurs. The nucleus boundary is determined by a deformable model. The results are very promising, even when images with high degree of overlapping are used.
Inflammation Detection in Cervical Cytology Images
Journal of Network and Information Security, 2017
Cervical cancer is a leading cause of cancer-related deaths in women worldwide. If detected at a precancerous condition it is completely curable. Several screening methods are available and Pap smear test is a preliminary screening method. Hence an automatic detection method for cervical cancer will be preferred. Cervical Screening System is a computer assisted screening solution, where the digitized images of the PAP-Smear are analyzed and classified through advanced image processing and classification algorithms. The LBC slides are analyzed for the detection of normal and abnormal cells. But some slides will be inflammatory, that are neither normal nor abnormal, but existing systems categorize them as abnormal and will go for further review. The inflammatory slides should be identified and categorized as Inflammatory so that they will not go for further review, instead they will go for a repap (preliminary) test after 6-9 months. The identification of Inflammatory slides inturn increases the system accuracy which increases specificity and sensitivity.
International Journal of Computer Applications, 2013
In this paper, a novel method for automated diagnosis of cervical cancer by extracting cytoplasm and nuclei from cervical cytology images is described. The background is removed by preprocessing methods like Edge sharpening and Adaptive Histogram Equalization. Fuzzy thresholding and Active contours are used for extracting the region of interest containing the cytoplasm and nuclei. The nuclei are separated from the cytoplasm using linear contrast stretching. The nucleus to cytoplasm ratio is used to determine the stage of cancer.
A fast and reliable approach to cell nuclei segmentation in PAP stained cervical smears
CSI Transactions on ICT, 2013
Fast and reliable segmentation of cervical cell nuclei is one of the crucial steps of an automated screening system that aims early detection of cervical cancer. In this paper, we propose an edge based approach using customized Laplacian of Gaussian (LoG) filter to segment free lying cell nuclei in bright-field microscope images of Pap smear. The LoG is generally employed as a second order edge detector in image processing. The images may have the challenges of inconsistent staining, overlapping and folded cells. Experimenting proposed method over all types of cervical images including sufficient number of high grade lesions of cervical cancer shows that our method performs well for stain varied images containing focused nuclei.