Particle Method Computation of the Red Blood Cell Motion in Malaria Infection

Malaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red blood cell images using deep learning. Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders. We provide probabilistic analysis on the impact of misclassification rates on compression performance in terms of the information-theoretic measure of entropy. We then use malaria infection image datasets to evaluate the relations between misclassification rates and actually obtainable compressed bit rates using Golomb–Rice codes. Simulation results show that the joint pattern classification/compression method provides more efficient compression than several mainstream lossless compression techniques, such as JPEG2000, JPEG-LS, CALIC, and WebP, by exploiting common features extracted by deep learning on large datasets. This study provides new insight into the interplay between classification accuracy and compression bitrates. The proposed compression method can find useful telemedicine applications where efficient storage and rapid transfer of large image datasets is desirable.

Download Full-text

Numerical Modeling of the Red Blood Cell Motion/Deformation in the Capillary

XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016 - IFMBE Proceedings ◽

10.1007/978-3-319-32703-7_121 ◽

2016 ◽

pp. 624-633

Author(s):

Kamran Hassani ◽

Alireza Karimi ◽

Ali Tavakoli Golpaygani

Keyword(s):

Numerical Modeling ◽

Blood Cell ◽

Red Blood Cell ◽

Cell Motion

Download Full-text

Simulation of Red Blood Cell Deformation in Microvessels Using a New Rapid Modified Particle Method

Volume 6: Fluids and Thermal Systems; Advances for Process Industries, Parts A and B ◽

10.1115/imece2011-63540 ◽

2011 ◽

Author(s):

K. Firoozbakhsh ◽

M. T. Ahmadian ◽

M. Hasanian ◽

S. Samiezadeh

Keyword(s):

Blood Cell ◽

Red Blood Cell ◽

Complex Geometry ◽

Fluid Pressure ◽

Real Life ◽

Particle Method ◽

Original Method ◽

Discrete Models ◽

Mps Method ◽

Long Time

The deformation of human red blood cell has been a topic of considerable scientific interest and real-life significance. Several methods have been improved to simulate the behavior of red blood cells motion and deformation in micro-capillaries. Since in microscopic scales, using discrete models are more preferred than continuum methods, moving particle semi-implicit method (MPS) which is one of the recent innovative particle based methods, can simulate micro-fluidic flows based on Navier-Stocks equations. It has been shown that original MPS method has a lack of rapid calculation which leads to massive calculations and long time simulation. Quite a few studies have been done to improve MPS method. But the main problem, calculation of viscosity effect in conjunction with fluid pressure distribution, is still under discussion. In this paper a new algorithm is proposed that is to say by this method simulation duration decreases by the factor of 20 while the accuracy of the results remains constant. The results indicate that while the velocity precision is as well as original method, the duration of simulation is reduced more than 20 times. This significant novel MPS algorithm can be implemented in future studies for simulation of multi-fluid flows, complex geometry flows and micro-scale biomedical phenomena.

Download Full-text