Revealing Lung Affections from CTs. A Comparative Analysis of Various Deep Learning Approaches for Dealing with Volumetric Data

TL;DR

This paper compares various deep learning methods for detecting tuberculosis lesions in lung CT scans, analyzing their effectiveness in classifying volumetric data with extensive experiments and achieving top results in a competition.

Contribution

It provides a comprehensive comparison of three different approaches to process volumetric CT data using deep learning, including architectures, segmentation, and data augmentation.

Findings

Best performing approach achieved top results in the ImageClef 2020 Tuberculosis task.

Different input handling methods significantly impact classification accuracy.

Extensive experimental analysis highlights effective neural network configurations.

Abstract

The paper presents and comparatively analyses several deep learning approaches to automatically detect tuberculosis related lesions in lung CTs, in the context of the ImageClef 2020 Tuberculosis task. Three classes of methods, different with respect to the way the volumetric data is given as input to neural network-based classifiers are discussed and evaluated. All these come with a rich experimental analysis comprising a variety of neural network architectures, various segmentation algorithms and data augmentation schemes. The reported work belongs to the SenticLab.UAIC team, which obtained the best results in the competition.