Classification of HEp-2 Cells Using Fluorescent Image Analysis and Data Mining

Abstract

Abstract. The cells that are considered in this application for an automated image analysis are Hep-2 cells which are used for the identification of antinuclear autoantibodies (ANA). Hep-2 cells allow for recognition of over 30 different nuclear and cytoplasmic patterns, which are given by upwards of 100 different autoantibodies. The identification of the patterns has recently been done manually by a human inspecting the slides with a microscope. In this paper we present results on image analysis, feature extraction, and classification. Starting from a knowledge acquisition process with a human operator, we developed an image analysis and feature extraction algorithm. A data set containing 162 features for each entry was set up and given to a data mining algorithm to find out the relevant features among this large feature set and to construct the classification knowledge. The classifier was evaluated by cross validation. The results show the feasibility of an automated inspection system.

Algorithmic framework for HEp-2 fluorescence pattern classification to aid auto-immune diseases diagnosis

“…Due to the automated measurement the system improves diagnosis accuracy by simultaneously increasing the throughput. The system has an overall error rate of 9.75% which outperforms other similar studies, that stated error rates of 13.33% [4], 16.9% [9] and 25.6% [10]. Additionally, in contrast to our approach, these studies focus on i-cells only.…”

“…Although easier to use, they do not have the same discrimination power as iIFT tests. [4] One study concluded that iIFT diagnosis using automatically acquired digital images is more reliable than iIFT diagnosis performed using the microscope's eye pieces directly [5].…”

A Hybrid Method for Automatic Counting of Microorganisms in Microscopic Images

“…, (11) When the structuring element B has a center and this center is located on the origin of E, then the erosion of A by B is expressed as: Figure 2: Probing of an image with a structuring element (white and grey pixels have zero and non-zero values, respectively).…”

“…Bacterial cell classification using data mining techniques is employed for the classification of HE p -2 cells in [11], which uses a simple set of shape features for the classification. A new image analysis tool to study biomass and morphotypes of three major bacterioplankton groups in an alpine lake based on geometric features is defined in Thomas Posch et al [12].…”

Spiral Bacterial Cell Image Analysis using Active Contour Method

“…The artificial neural network approach for bacterial classification has been investigated by Nicholas Blackburn, et al [9]. The data mining techniques are employed for the classification of HEp-2 cells by Petra Perner [11], in which a simple set of shape features are used for classification of bacterial cells. Hiremath and Parashuram [4,9] have investigated the automatic classification of cocci and spiral bacterial cells and its sub groups using digital microscopic images using geometric shape features.…”