Novel Methods for Microglia Segmentation, Feature Extraction, and Classification

• Published in: IEEE/ACM transactions on computational biology and bioinformatics Vol. 14; no. 6; pp. 1366 - 1377
• Main Authors: Yuchun Ding, Pardon, Marie Christine, Agostini, Alessandra, Faas, Henryk, Jinming Duan, Ward, Wil O. C., Easton, Felicity, Auer, Dorothee, Li Bai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2017
• Subjects: Alzheimer Disease - diagnostic imaging; Animals; Brain - diagnostic imaging; Data analysis; Diseases; fast Fourier transform; Fast Fourier transforms; fast split Bregman; Feature extraction; Fourier Analysis; Fractals; Histocytochemistry - methods; histology data analysis; Image Processing, Computer-Assisted - methods; Image segmentation; Mathematical model; Mice; Microglia - cytology; Microglia analysis; Morphology; multifractal analysis; Mumford-Shah
• ISSN: 1545-5963; 1557-9964
• DOI: 10.1109/TCBB.2016.2591520

Segmentation and analysis of histological images provides a valuable tool to gain insight into the biology and function of microglial cells in health and disease. Common image segmentation methods are not suitable for inhomogeneous histology image analysis and accurate classification of microglial activation states has remained a challenge. In this paper, we introduce an automated image analysis framework capable of efficiently segmenting microglial cells from histology images and analyzing their morphology. The framework makes use of variational methods and the fast-split Bregman algorithm for image denoising and segmentation, and of multifractal analysis for feature extraction to classify microglia by their activation states. Experiments show that the proposed framework is accurate and scalable to large datasets and provides a useful tool for the study of microglial biology.