Human Epithelial Type-2 Cell Image Classification Using an Artificial Neural Network with Hybrid Descriptors

ABSTRACT

Antinuclear antibody (ANA) testing is best performed using the indirect immunofluorescence (IIF) method with human epithelial type-2 (HEp-2) cells as the substrate. IIF is a subjective procedure in which HEp-2 patterns are analyzed manually from the microscope. Therefore, ANA test results greatly rely on the experience and expertise of pathologists. Hence, complete automation of the ANA test is required to avoid incorrect diagnoses. This paper represents an algorithm for the complex HEp-2 cell classification problem. The proposed algorithm used a small hybrid feature set that characterizes the texture and morphology of the HEp-2 cells along with artificial neural network (ANN). The hybrid features were extracted by breaking up the image into eight binary images. The proposed hybrid descriptors were more efficient than the popular co-occurrence matrix descriptor and local binary pattern descriptors for texture analysis. The proposed algorithm was evaluated on the ICPR 2016 IIF HEp-2 cell image dataset. The results indicated that the hybrid descriptor with an ANN approach achieved improved performance, with “96.8%” mean class accuracy.

KEYWORDS:

• Artificial neural network
• ANA
• Classification
• Fractals
• HEp-2
• IIF

ACKNOWLEDGEMENT

The authors would like to thank the ICPR 2016 contest chair Gennaro Percannella, University of Salerno, Italy, for making the test dataset and contest results available for the research. The authors presented a research paper on HEp-2 cell classification in the contest organized by the International Conference on Pattern Recognition (ICPR 2016) and the research work secured second place for their design.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

B. S. Divya

B S Divya worked as an assistant professor in the ECE Department with Acharya Institute of Technology, Bengaluru, from August 2005 to December 2015. Currently, she is pursuing her PhD from Karpagam University. Her research interests are image processing, pattern recognition, and neural networks.

Kamalraj Subramaniam

Kamalraj Subramaniam is an associate professor in the Electronics and Communication Engineering Department at Karpagam University. His research interests are biosignal processing, medical image analysis, fractal set analysis, artificial neural networks, and swarm algorithms. Email: [email protected]

H.R. Nanjundaswamy

H R Nanjundaswamy is working as a Senior Manager, IP engineering with Microsemi India Private Ltd. His research interests are image and signal processing, neural networks, machine learning, and digital filter design. Email: [email protected]