Computer-Aided Assessment of Tuberculosis with Radiological Imaging: From rule-based methods to Deep Learning

Abstract

Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis (Mtb.) that produces pulmonary damage due to its airborne nature. This fact facilitates the disease fast-spreading, which, according to the World Health Organization (WHO), in 2021 caused 1.2 million deaths and 9.9 million new cases. Traditionally, TB has been considered a binary disease (latent/active) due to the limited specificity of the traditional diagnostic tests. Such a simple model causes difficulties in the longitudinal assessment of pulmonary affectation needed for the development of novel drugs and to control the spread of the disease. Fortunately, X-Ray Computed Tomography (CT) images enable capturing specific manifestations of TB that are undetectable using regular diagnostic tests, which suffer from limited specificity. In conventional workflows, expert radiologists inspect the CT images. However, this procedure is unfeasible to process the thousands of volume images belonging to the different TB animal models and humans required for a suitable (pre-)clinical trial. To achieve suitable results, automatization of different image analysis processes is a must to quantify TB. It is also advisable to measure the uncertainty associated with this process and model causal relationships between the specific mechanisms that characterize each animal model and its level of damage. Thus, in this thesis, we introduce a set of novel methods based on the state of the art Artificial Intelligence (AI) and Computer Vision (CV). Initially, we present an algorithm to assess Pathological Lung Segmentation (PLS) employing an unsupervised rule-based model which was traditionally considered a needed step before biomarker extraction. This procedure allows robust segmentation in a Mtb. infection model (Dice Similarity Coefficient, DSC, 94%±4%, Hausdorff Distance, HD, 8.64mm±7.36mm) of damaged lungs with lesions attached to the parenchyma and affected by respiratory movement artefacts. Next, a Gaussian Mixture Model ruled by an Expectation-Maximization (EM) algorithm is employed to automatically quantify the burden of Mtb.using biomarkers extracted from the segmented CT images. This approach achieves a strong correlation (R2 ≈ 0.8) between our automatic method and manual extraction. Consequently, Chapter 3 introduces a model to automate the identification of TB lesions and the characterization of disease progression. To this aim, the method employs the Statistical Region Merging algorithm to detect lesions subsequently characterized by texture features that feed a Random Forest (RF) estimator. The proposed procedure enables a selection of a simple but powerful model able to classify abnormal tissue. The latest works base their methodology on Deep Learning (DL). Chapter 4 extends the classification of TB lesions. Namely, we introduce a computational model to infer TB manifestations present in each lung lobe of CT scans by employing the associated radiologist reports as ground truth. We do so instead of using the classical manually delimited segmentation masks. The model adjusts the three-dimensional architecture, V-Net, to a multitask classification context in which loss function is weighted by homoscedastic uncertainty. Besides, the method employs Self-Normalizing Neural Networks (SNNs) for regularization. Our results are promising with a Root Mean Square Error of 1.14 in the number of nodules and F1-scores above 0.85 for the most prevalent TB lesions (i.e., conglomerations, cavitations, consolidations, trees in bud) when considering the whole lung. In Chapter 5, we present a DL model capable of extracting disentangled information from images of different animal models, as well as information of the mechanisms that generate the CT volumes. The method provides the segmentation mask of axial slices from three animal models of different species employing a single trained architecture. It also infers the level of TB damage and generates counterfactual images. So, with this methodology, we offer an alternative to promote generalization and explainable AI models. To sum up, the thesis presents a collection of valuable tools to automate the quantification of pathological lungs and moreover extend the methodology to provide more explainable results which are vital for drug development purposes. Chapter 6 elaborates on these conclusions.