Generative-based airway and vessel morphology quantification on chest CT images

Abstract

Accurately and precisely characterizing the morphology of small pulmonary structures from Computed Tomography (CT) images, such as airways and vessels, is becoming of great importance for diagnosis of pulmonary diseases. The smaller conducting airways are the major site of increased airflow resistance in chronic obstructive pulmonary disease (COPD), while accurately sizing vessels can help identify arterial and venous changes in lung regions that may determine future disorders. However, traditional methods are often limited due to image resolution and artifacts. We propose a Convolutional Neural Regressor (CNR) that provides cross-sectional measurement of airway lumen, airway wall thickness, and vessel radius. CNR is trained with data created by a generative model of synthetic structures which is used in combination with Simulated and Unsupervised Generative Adversarial Network (SimGAN) to create simulated and refined airways and vessels with known ground-truth. For validation, we first use synthetically generated airways and vessels produced by the proposed generative model to compute the relative error and directly evaluate the accuracy of CNR in comparison with traditional methods. Then, in-vivo validation is performed by analyzing the association between the percentage of the predicted forced expiratory volume in one second (FEV1%) and the value of the Pi10 parameter, two well-known measures of lung function and airway disease, for airways. For vessels, we assess the correlation between our estimate of the small-vessel blood volume and the lungs' diffusing capacity for carbon monoxide (DLCO). The results demonstrate that Convolutional Neural Networks (CNNs) provide a promising direction for accurately measuring vessels and airways on chest CT images with physiological correlates.A PREPRINT -MARCH 16, 2020 Additionally, several studies have demonstrated that small pulmonary arteries become smaller and shrink at subsegmental levels in patients with COPD [7,8], and endothelial dysfunction may be caused by both pulmonary and extra-pulmonary vascular alterations in COPD [2,3]. Therefore, having an automated method for airway and vessel morphology assessment will help precise measurements of the geometrical properties of bronchial and venous trees which, in turn, may lead to improved diagnosis and open the door to new studies on lung disorders.While in the past several methods have been proposed with the aim of helping physicians accurately locate small pulmonary airways and veins on chest CT images [9, 10], up to date not much work has been proposed for sub-voxel morphology assessment. Traditional approaches for airway wall thickness detection are based on edge-detection methods, that, although limited by the Nyquist theorem, use the reconstructed CT signal to analyze properties of the structure directly. Among them, the full width at half max (FWHM) [11], for which the true edge of an ideal step function undergoing low-pass filtering is located at the FWHM location, is one of the most typical algorithms. In [1...

Automation of surgical skill assessment using a three-stage machine learning algorithm

“…Numerous studies have shown that CNNs can be successfully applied to real-world laparoscopic videos 22 . Examples include procedural phase and instrument presence detection 23 as well as surgical instrument segmentation 24 . So far only one previous study analyzed surgical skill based on laparoscopic videos 25 .…”

Artificial Intelligence in COPD: New Venues to Study a Complex Disease

“…Arterial and venous separation of the pulmonary vessels have been challenging and initial attempts were based on graph matching and partitioning techniques 56,57 . Nardelli et al 58 proposed a CNN to compute an "arterialness" probability for each vessel location based on cropped image sections of a vessel. Those probabilities were used to further divide the vascular tree in a connected arterial and venous size.…”

“…The definition of vascular phenotypes in COPD that can be potentially sensible to remodeling relies on an accurate estimation of the vessel size, particularly in small vessels. This is technically challenging as the CT scanner's resolution compromises the ability to resolve 59 to synthesize real looking CT scans of airway and vessel with known characteristics have been employed to train accurate regressors of vessel and airway morphometric characteristics 60 . This approach has been shown to provide accurate airway and vessel metrics while preserving high precision to variations in imaging protocol (Fig.…”

Accurate Point Cloud Registration with Robust Optimal Transport

“…We extracted the lung vascular geometry in both inspiratory and expiratory CT scans using a scale-space particle system [34,62] that is implemented in the Teem library [61]. We used the pipeline that is defined in the chest imaging platform [83,102].…”