Mining textural knowledge in biological images: Applications, methods and trends

Abstract

Texture analysis is a major task in many areas of computer vision and pattern recognition, including biological imaging. Indeed, visual textures can be exploited to distinguish specific tissues or cells in a biological sample, to highlight chemical reactions between molecules, as well as to detect subcellular patterns that can be evidence of certain pathologies. This makes automated texture analysis fundamental in many applications of biomedicine, such as the accurate detection and grading of multiple types of cancer, the differential diagnosis of autoimmune diseases, or the study of physiological processes. Due to their specific characteristics and challenges, the design of texture analysis systems for biological images has attracted ever-growing attention in the last few years. In this paper, we perform a critical review of this important topic. First, we provide a general definition of texture analysis and discuss its role in the context of bioimaging, with examples of applications from the recent literature. Then, we review the main approaches to automated texture analysis, with special attention to the methods of feature extraction and encoding that can be successfully applied to microscopy images of cells or tissues. Our aim is to provide an overview of the state of the art, as well as a glimpse into the latest and future trends of research in this area.

Keywords: Bioimaging; Deep learning; Feature encoding; Textural analysis; Textural features extraction; Texture classification.

Fig. 1

Visual textures with corresponding subpatterns.

Fig. 2

Different textures in H&E pulmonary tissues: (a) Sarcomatoid mesothelioma (cancerous). (b) Active fibrosis (non-cancerous).

Fig. 3

Textures categories in HEp-2 cell images for the differential diagnosis of autoimmune diseases.

Fig. 4

Computation of a normalised co-occurrence matrix with d = 1 and θ = 0.

Fig. 5

Computation of local binary patterns.

Fig. 6

Kernel of a Gabor filter (real part).

Fig. 7

Simplified scheme of BoW feature encoding model.

Fig. 8

Deep neural network framework.

Fig. 9

Structure of a deep autoencoder with 5 hidden layers.