Using Capsule Neural Network to predict Tuberculosis in lens-free microscopic images
This work addresses the problem of tuberculosis diagnosis for public health by enabling easier, automated prediction with untrained personnel, though it is incremental as it applies an existing method to a new dataset.
The paper tackled automating tuberculosis prediction from lens-free microscopic images using the MODS method, achieving better accuracy than traditional CNNs with the CapsNet architecture.
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.