Deep CNN frameworks comparison for malaria diagnosis

TL;DR

This paper compares AlexNet and VGGNet deep learning frameworks for classifying healthy and malaria-infected cells in challenging microscopic images with limited training data, aiming for rapid and accurate diagnosis.

Contribution

It provides a comparative analysis of two CNN architectures for malaria detection in low-quality images with small datasets, highlighting their effectiveness.

Findings

Promising classification accuracy achieved

Deep CNNs can be effective with limited training data

Potential for rapid malaria diagnosis

Abstract

We compare Deep Convolutional Neural Networks (DCNN) frameworks, namely AlexNet and VGGNet, for the classification of healthy and malaria-infected cells in large, grayscale, low quality and low resolution microscopic images, in the case only a small training set is available. Experimental results deliver promising results on the path to quick, automatic and precise classification in unstained images.