Publication: Computer-Aided Assessment of Tuberculosis with Radiological Imaging: From rule-based methods to Deep Learning
Loading...
Identifiers
Publication date
2022-02
Defense date
2022-05-06
Authors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
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.
Description
Mención Internacional en el título de doctor
Keywords
Biomedical engineering, Artificial intelligence, Lung segmentation, Imaging biomarker, Tuberculosis, Experimental models of disease, Infectious-disease epidemiology