Using Capsule Neural Network to predict Tuberculosis in lens-free microscopic images

TL;DR

This paper presents a capsule neural network approach to predict tuberculosis from lens-free microscopic images, aiming to improve accuracy and facilitate diagnosis by untrained personnel.

Contribution

The study introduces the use of CapsNet architecture for tuberculosis prediction in lens-free microscopy images, demonstrating superior accuracy over traditional CNNs.

Findings

CapsNet outperforms traditional CNNs in accuracy.

Lens-free microscopy enables easier, accessible TB diagnosis.

Automated prediction can assist untrained personnel.

Abstract

Tuberculosis, caused by a bacteria called Mycobacterium tuberculosis, is one of the most serious public health problems worldwide. This work seeks to facilitate and automate the prediction of tuberculosis by the MODS method and using lens-free microscopy, which is easy to use by untrained personnel. We employ the CapsNet architecture in our collected dataset and show that it has a better accuracy than traditional CNN architectures.