Lung tuberculosis detection using anti-aliased convolutional networks

A bacterial infection named Tuberculosis is a persistent disease that has caused a large number of deaths worldwide according to WHO’s data. This disease is caused by a particular bacteria called Mycobacterium which usually affects the lungs. If early treatments are not provided to the patients it may result in fatality. So, early diagnosis and treatment are crucial. In this paper, we present a new and better way of automated detection of tuberculosis using a Deep Learning method known as the Antialiased Convolution Neural Networks proposed by Richard Zhang in his Research Paper titled “Making Convolution Neural Networks Shift-Invariant Again”. The objective of this task is the detection of tuberculosis lesions in the lungs using Image Segmentation and then using the trained models and the metadata the patient cases were classified to tuberculosis of low or high severity. The data in consideration here is the ImageCLEF med Tuberculosis 2019 data set. The data set comprises of 3D CT images. So, here the 3D images were split into 2D slices and segmentation was applied to each slicing using UNet, FPN, and LinkNet architecture. For better accuracy and predictions Antialiased Convolution Neural Networks based on shift-invariant pooling is applied instead of the conventional Convolution Neural Networks. Here the Antialiased Convolution Neural Networks provided better results. This is a generalized attempt on our end which can be applied for other similar and related datasets as well.