Monitoring of Wild Pseudomonas Biofilm Strain Conditions Using Statistical Characterisation of Scanning Electron Microscopy Images

by   Suparna Dutta Sinha, et al.

The present paper proposes a novel method of quantification of the variation in biofilm architecture, in correlation with the alteration of growth conditions that include, variations of substrate and conditioning layer. The polymeric biomaterial serving as substrates are widely used in implants and indwelling medical devices, while the plasma proteins serve as the conditioning layer. The present method uses descriptive statistics of FESEM images of biofilms obtained during a variety of growth conditions. We aim to explore here the texture and fractal analysis techniques, to identify the most discriminatory features which are capable of predicting the difference in biofilm growth conditions. We initially extract some statistical features of biofilm images on bare polymer surfaces, followed by those on the same substrates adsorbed with two different types of plasma proteins, viz. Bovine serum albumin (BSA) and Fibronectin (FN), for two different adsorption times. The present analysis has the potential to act as a futuristic technology for developing a computerized monitoring system in hospitals with automated image analysis and feature extraction, which may be used to predict the growth profile of an emerging biofilm on surgical implants or similar medical applications.



There are no comments yet.


page 8

page 10

page 11

page 12

page 13

page 23


Predicting growth fluctuation in network economy

This study presents a method to predict the growth fluctuation of firms ...

A Review of Visual Descriptors and Classification Techniques Used in Leaf Species Identification

Plants are fundamentally important to life. Key research areas in plant ...

Self Organization Map based Texture Feature Extraction for Efficient Medical Image Categorization

Texture is one of the most important properties of visual surface that h...

Automated quantification of one-dimensional nanostructure alignment on surfaces

A method for automated quantification of the alignment of one-dimensiona...

Segmentation of Scanning Tunneling Microscopy Images Using Variational Methods and Empirical Wavelets

In the fields of nanoscience and nanotechnology, it is important to be a...

Classification of Motorcycles using Extracted Images of Traffic Monitoring Videos

Due to the great growth of motorcycles in the urban fleet and the growth...

4D-MultispectralNet: Multispectral Stereoscopic Disparity Estimation using Human Masks

Multispectral stereoscopy is an emerging field. A lot of work has been d...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.