THREECOND: An Automated and Unsupervised Three Colour Fuzzy-Based Algorithm for Detecting Nuclei in Cervical Pap Smear Images

Abstract

Visual examination and interpretation of microscopic images taken from the cervix are at the core for the detection and prevention of cervical cancer. However these visual processes are tedious and in many cases error-prone. This is why automated screening systems, interacting with the technologist, would be a tremendous improvement for reducing the likelihood of human errors. In this work we propose THREECOND, a three colour-based algorithm that integrates colour information, cyto-pathologists knowledge and fuzzy systems. This algorithm is designed to be integrated into the previously developed system [23], with the aim of improving its accuracy and efficiency for detecting and segmenting the nuclei of Pap smear images.

A multiscale algorithm for nuclei extraction in pap smear images

“…A two-group object enhancement technique is then used to reinforce this object according to rough pixels Finally, an edge detection like Sobel filter with some post processing, and noise elimination in the results is done. In (Vaschetto et al, 2009) a fuzzy system which integrates colour information and cytopatologists knowledge is developed for the nuclei segmentation. The hue, saturation and intensity (HSI) colour space is used.…”

A Detection Method of Ectocervical Cell Nuclei for Pap test Images, Based on Adaptive Thresholds and Local Derivatives

“…As for the illumination problem, there is a grey reescalation based on the gray weighted barycenter in [8], and a HSI color model approach in [9]. In [10], part of the preprocessing is edge sharpening and contrast enhancement, within the three RGB layers, using h-minima transform.…”

“…Finally, the area, elliptical shape, and texture/granularity are considered for artifact rejection in [13]. Regarding the detection algorithms previously developed, there have been several approaches, such as global and adaptive thresholds [8,14], the watershed transform [11][12][13] and even a fuzzy logic based algorithm [9]. However, the thresholding algorithms lack robustness when faced to problems such as noise, uneven illumination and variations in staining intensity.…”

Methods for cytological image analysis

“…Then, the nuclei detection in images of higher magnication follows, which is also based on fuzzy rules. Moreover, in [38], a three-color based algorithm that combines colour information, experts knowledge and fuzzy systems is proposed, aiming at the improvement of the accuracy of the method proposed in [37] for the detection and the segmentation of the nuclei in Pap smear images.…”