Multiple Feature Extraction from Cervical Cytology Images by Gaussian Mixture Model

Abstract

In this paper, methods for automated extraction of multiple features of cytoplasm and nuclei from cervical cytology images are described. Edges of the image are enhanced by Edge Sharpening filter. Then Gaussian mixture model using Expectation Maximization and K-means clustering is used to segment the image into its components as background, nucleus and cytoplasm. Features have been identified for both multiple and single cervical cytology cells. For multiple cell images, nucleus to cytoplasm ratio is calculated. A mixture of features like center, perimeter, area, mean intensity of nucleus and cytoplasm are extracted from cells with single nucleus. These features may be used to determine the stage of cancer.

A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification

“…Many authors have proposed solutions to this problem of detecting cervical cells, using synthetic databases or working with databases that do not represent the reality of conventional Pap smear images, in which there are many cells, often overlapping, in a single image [16][17][18][19][20][21][22][23][24]. Therefore, the investigation of methodologies capable of being applied in the real context of cervical cancer screening is still a great challenge.…”

“…They used 20 morphologic features and found that the combinations of algorithms Bagging + MultilayerPerceptron and AdaBoostM1 + LMT were the best scenarios analyzed by them. [20] presented a method to extract nuclei and cytoplasm features of Pap smear images. Attributes such as center, perimeter, area, and average intensity were considered.…”

Complete three‐phase detection framework for identifying abnormal cervical cells

“…So for a detection system of cervical cell images, representations of cells seek to capture the differences between normal and abnormal classes. Several studies have investigated methods for feature representation [16][17][18][19], and previous methods perform well in different aims of the cervical cell analysis. In particular, textural features were ever used to extract nuclei characteristics [19].…”

“…Several studies have investigated methods for feature representation [16][17][18][19], and previous methods perform well in different aims of the cervical cell analysis. In particular, textural features were ever used to extract nuclei characteristics [19]. The chromatin texture of the nucleus exhibits the essential pre-cancerous changes and can be applied to detect abnormal cells too.…”

Serviks Kanserinin Erken Teşhisi için Çok Katmanlı Sitoloji Küplerinde Çekirdek ve Sitoplazma Bölütlenmesi

“…Örnek olarak, hücre çekirdeklerinin bölütlenmesi için alçak geçirgen gürültü giderici filtrenin ardından iteratif eşikleme [5], yıldız şekil öncülleri temelinde yönlü türevler yardımıyla görüntü işleme tabanlı yaklaşımla bölütlenmesi [6], çok-adımlı aşama seviye kümesi yöntemi yaklaşımları kullanılmıştır [7]. Hücre çekirdeği ve sitoplazmasının bölütlenmesi için piksel yoğunluklarına bağlı Gauss karışım modeli çoklu özellik çıkarım yöntemleri kullanılarak uygulanmıştır [8]. Ayrıca, hücre çekirdeği ile sitoplazmasını birbirinden ayırmak için gradyan vektör alanı (GVF) yılan yöntemi [9], hücre kümesi ile görüntü arka planını birbirinden ayırmak için minimum hata eşiklemesi [10] ve şekil-bilimsel geriçatım ve kümeleme yöntemlerinden yararlanılmıştır [11].…”