Increased respiratory morbidity in individuals with interstitial lung abnormalities.

BACKGROUND: Interstitial lung abnormalities (ILA) are common in participants of lung cancer screening trials and broad population-based cohorts. They are associated with increased mortality, but less is known about disease specific morbidity and healthcare utilisation in individuals with ILA. METHODS: We included all participants from the screening arm of the Danish Lung Cancer Screening Trial with available baseline CT scan data (n = 1990) in this cohort study. The baseline scan was scored for the presence of ILA and patients were followed for up to 12 years. Data about all hospital admissions, primary healthcare visits and medicine prescriptions were collected from the Danish National Health Registries and used to determine the participants' disease specific morbidity and healthcare utilisation using Cox proportional hazards models. RESULTS: The 332 (16.7%) participants with ILA were more likely to be diagnosed with one of several respiratory diseases, including interstitial lung disease (HR: 4.9, 95% CI: 1.8-13.3, p = 0.008), COPD (HR: 1.7, 95% CI: 1.2-2.3, p = 0.01), pneumonia (HR: 2.0, 95% CI: 1.4-2.7, p <  0.001), lung cancer (HR: 2.7, 95% CI: 1.8-4.0, p <  0.001) and respiratory failure (HR: 1.8, 95% CI: 1.1-3.0, p = 0.03) compared with participants without ILA. These findings were confirmed by increased hospital admission rates with these diagnoses and more frequent prescriptions for inhalation medicine and antibiotics in participants with ILA. CONCLUSIONS: Individuals with ILA are more likely to receive a diagnosis and treatment for several respiratory diseases, including interstitial lung disease, COPD, pneumonia, lung cancer and respiratory failure during long-term follow-up.

Classification of Volumetric Images Using Multi-Instance Learning and Extreme Value Theorem.

Volumetric imaging is an essential diagnostic tool for medical practitioners. The use of popular techniques such as convolutional neural networks (CNN) for analysis of volumetric images is constrained by the availability of detailed (with local annotations) training data and GPU memory. In this paper, the volumetric image classification problem is posed as a multi-instance classification problem and a novel method is proposed to adaptively select positive instances from positive bags during the training phase. This method uses the extreme value theory to model the feature distribution of the images without a pathology and use it to identify positive instances of an imaged pathology. The experimental results, on three separate image classification tasks (i.e. classify retinal OCT images according to the presence or absence of fluid build-ups, emphysema detection in pulmonary 3D-CT images and detection of cancerous regions in 2D histopathology images) show that the proposed method produces classifiers that have similar performance to fully supervised methods and achieves the state of the art performance in all examined test cases.

Learning to Quantify Emphysema Extent: What Labels Do We Need?

Accurate assessment of pulmonary emphysema is crucial to assess disease severity and subtype, to monitor disease progression, and to predict lung cancer risk. However, visual assessment is time-consuming and subject to substantial inter-rater variability while standard densitometry approaches to quantify emphysema remain inferior to visual scoring. We explore if machine learning methods that learn from a large dataset of visually assessed CT scans can provide accurate estimates of emphysema extent and if methods that learn from emphysema extent scoring can outperform algorithms that learn only from emphysema presence scoring. Four Multiple Instance Learning classifiers, trained on emphysema presence labels, and five Learning with Label Proportions classifiers, trained on emphysema extent labels, are compared. Performance is evaluated on 600 low-dose CT scans from the Danish Lung Cancer Screening Trial and we find that learning from emphysema presence labels, which are much easier to obtain, gives equally good performance to learning from emphysema extent labels. The best performing Multiple Instance Learning and Learning with Label Proportions classifiers, achieve intra-class correlation coefficients around 0.90 and average overall agreement with raters of 78% and 79% compared to an inter-rater agreement of 83%.

Interstitial lung abnormalities are associated with increased mortality in smokers.

OBJECTIVE: The aim of this study was to investigate whether smokers with incidental findings of interstitial lung abnormalities have an increased mortality during long-term follow-up, and review the contributing causes of death. METHODS: Baseline CT scans of 1990 participants from the Danish Lung Cancer Screening Trial were qualitatively assessed for predefined interstitial lung abnormalities of any severity. Inclusion criteria for this lung cancer screening trial included current or former smoking, > 20 pack-years, and age 50-70 years. Patients were followed up for up to 12 years. RESULTS: We found interstitial lung abnormalities in 332 participants (16.7%). Interstitial lung abnormalities were associated with increased all-cause mortality in the full cohort (HR: 2.0, 95% CI: 1.4-2.7, P < 0.001) and in lung cancer-free participants (HR: 1.6, 95% CI: 1.1-2.4, P = 0.007). The findings were associated with death from lung cancer (HR: 3.2, 95% CI: 1.7-6.2, P < 0.001) and non-pulmonary malignancies (HR: 2.1, 95% CI: 1.1-4.0, P = 0.02). Participants with fibrotic and non-fibrotic interstitial lung abnormalities had similar survival. CONCLUSION: Interstitial lung abnormalities were common in this lung cancer screening population of relatively healthy smokers and were associated with mortality regardless of the interstitial morphological phenotype. The increased mortality was partly due to an association with lung cancer and non-pulmonary malignancies.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Computed Tomography-based Subclassification of Chronic Obstructive Pulmonary Disease.

Computed tomography (CT) is an obvious modality for subclassification of COPD. Traditionally, the pulmonary involvement of chronic obstructive pulmonary disease (COPD) in smokers is understood as a combination of deleterious effects of smoking on small airways (chronic bronchitis and small airways disease) and distal to the airways with destruction and loss of lung parenchyma (emphysema). However, segmentation of airways is still experimental; with contemporary high-resolution CT (HRCT) we can just see the "entrance" of small airways, and until now changes in airway morphology that have been observed in COPD are subtle. Furthermore, recent results indicate that emphysema may also be the essential pathophysiologic mechanism behind the airflow limitation of COPD. The definition of COPD excludes bronchiectasis as a symptomatic subtype of COPD, and CT findings in chronic bronchitis and exacerbations of COPD are rather unspecific. This leaves emphysema as the most obvious candidate for subclassification of COPD. Both chest radiologists and pulmonary physicians are quite familiar with the appearance of various patterns of emphysema on HRCT, such as centrilobular, panlobular, and paraseptal emphysema. However, it has not yet been possible to develop operational definitions of these patterns that can be used by computer software to automatically classify CT scans into distinct patterns. In conclusion, even though various emphysema patterns can be recognized visually, CT has not yet demonstrated a great potential for automated subclassification of COPD, and it is an open question whether it will ever be possible to achieve success equivalent to that obtained by HRCT in the area of interstitial lung diseases.

Results of the Randomized Danish Lung Cancer Screening Trial with Focus on High-Risk Profiling.

RATIONALE: As of April 2015, participants in the Danish Lung Cancer Screening Trial had been followed for at least 5 years since their last screening. OBJECTIVES: Mortality, causes of death, and lung cancer findings are reported to explore the effect of computed tomography (CT) screening. METHODS: A total of 4,104 participants aged 50-70 years at the time of inclusion and with a minimum 20 pack-years of smoking were randomized to have five annual low-dose CT scans (study group) or no screening (control group). MEASUREMENTS AND MAIN RESULTS: Follow-up information regarding date and cause of death, lung cancer diagnosis, cancer stage, and histology was obtained from national registries. No differences between the two groups in lung cancer mortality (hazard ratio, 1.03; 95% confidence interval, 0.66-1.6; P = 0.888) or all-cause mortality (hazard ratio, 1.02; 95% confidence interval, 0.82-1.27; P = 0.867) were observed. More cancers were found in the screening group than in the no-screening group (100 vs. 53, respectively; P < 0.001), particularly adenocarcinomas (58 vs. 18, respectively; P < 0.001). More early-stage cancers (stages I and II, 54 vs. 10, respectively; P < 0.001) and stage IIIa cancers (15 vs. 3, respectively; P = 0.009) were found in the screening group than in the control group. Stage IV cancers were nonsignificantly more frequent in the control group than in the screening group (32 vs. 23, respectively; P = 0.278). For the highest-stage cancers (T4N3M1, 21 vs. 8, respectively; P = 0.025), this difference was statistically significant, indicating an absolute stage shift. Older participants, those with chronic obstructive pulmonary disease, and those with more than 35 pack-years of smoking had a significantly increased risk of death due to lung cancer, with nonsignificantly fewer deaths in the screening group. CONCLUSIONS: No statistically significant effects of CT screening on lung cancer mortality were found, but the results of post hoc high-risk subgroup analyses showed nonsignificant trends that seem to be in good agreement with the results of the National Lung Screening Trial. Clinical trial registered with www.clinicaltrials.gov (NCT00496977).

Visual assessment of early emphysema and interstitial abnormalities on CT is useful in lung cancer risk analysis.

OBJECTIVES: Screening for lung cancer should be limited to a high-risk-population, and abnormalities in low-dose computed tomography (CT) screening images may be relevant for predicting the risk of lung cancer. Our aims were to compare the occurrence of visually detected emphysema and interstitial abnormalities in subjects with and without lung cancer in a screening population of smokers. METHODS: Low-dose chest CT examinations (baseline and latest possible) of 1990 participants from The Danish Lung Cancer Screening Trial were independently evaluated by two observers who scored emphysema and interstitial abnormalities. Emphysema (lung density) was also measured quantitatively. RESULTS: Emphysema was seen more frequently and its extent was greater among participants with lung cancer on baseline (odds ratio (OR), 1.8, p = 0.017 and p = 0.002) and late examinations (OR 2.6, p < 0.001 and p < 0.001). No significant difference was found using quantitative measurements. Interstitial abnormalities were more common findings among participants with lung cancer (OR 5.1, p < 0.001 and OR 4.5, p < 0.001).There was no association between presence of emphysema and presence of interstitial abnormalities (OR 0.75, p = 0.499). CONCLUSIONS: Even early signs of emphysema and interstitial abnormalities are associated with lung cancer. Quantitative measurements of emphysema-regardless of type-do not show the same association. KEY POINTS: • Visually detected emphysema on CT is more frequent in individuals who develop lung cancer. • Emphysema grading is higher in those who develop lung cancer. • Interstitial abnormalities, including discrete changes, are associated with lung cancer. • Quantitative lung density measurements are not useful in lung cancer risk prediction. • Early CT signs of emphysema and interstitial abnormalities can predict future risk.

Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images.

We present a novel descriptor for the characterization of pulmonary nodules in computed tomography (CT) images. The descriptor encodes information on nodule morphology and has scale-invariant and rotation-invariant properties. Information on nodule morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created and labeled via unsupervised clustering, obtaining a Bag-of-Frequencies, which is used to assign each spectra a label. The descriptor is obtained as the histogram of labels along all the spheres. Additional contributions are a technique to estimate the nodule size, based on the sampling strategy, as well as a technique to choose the most informative plane to cut a 2-D view of the nodule in the 3-D image. We evaluate the descriptor on several nodule morphology classification problems, namely discrimination of nodules versus vascular structures and characterization of spiculation. We validate the descriptor on data from European screening trials NELSON and DLCST and we compare it with state-of-the-art approaches for 3-D shape description in medical imaging and computer vision, namely SPHARM and 3-D SIFT, outperforming them in all the considered experiments.

Effect of inspiration on airway dimensions measured in maximal inspiration CT images of subjects without airflow limitation.

OBJECTIVES: To study the effect of inspiration on airway dimensions measured in voluntary inspiration breath-hold examinations. METHODS: 961 subjects with normal spirometry were selected from the Danish Lung Cancer Screening Trial. Subjects were examined annually for five years with low-dose CT. Automated software was utilized to segment lungs and airways, identify segmental bronchi, and match airway branches in all images of the same subject. Inspiration level was defined as segmented total lung volume (TLV) divided by predicted total lung capacity (pTLC). Mixed-effects models were used to predict relative change in lumen diameter (ALD) and wall thickness (AWT) in airways of generation 0 (trachea) to 7 and segmental bronchi (R1-R10 and L1-L10) from relative changes in inspiration level. RESULTS: Relative changes in ALD were related to relative changes in TLV/pTLC, and this distensibility increased with generation (p < 0.001). Relative changes in AWT were inversely related to relative changes in TLV/pTLC in generation 3--7 (p < 0.001). Segmental bronchi were widely dispersed in terms of ALD (5.7 ± 0.7 mm), AWT (0.86 ± 0.07 mm), and distensibility (23.5 ± 7.7%). CONCLUSIONS: Subjects who inspire more deeply prior to imaging have larger ALD and smaller AWT. This effect is more pronounced in higher-generation airways. Therefore, adjustment of inspiration level is necessary to accurately assess airway dimensions. KEY POINTS: Airway lumen diameter increases and wall thickness decreases with inspiration. The effect of inspiration is greater in higher-generation (more peripheral) airways. Airways of generation 5 and beyond are as distensible as lung parenchyma. Airway dimensions measured from CT should be adjusted for inspiration level.

Tree-space statistics and approximations for large-scale analysis of anatomical trees.

Statistical analysis of anatomical trees is hard to perform due to differences in the topological structure of the trees. In this paper we define statistical properties of leaf-labeled anatomical trees with geometric edge attributes by considering the anatomical trees as points in the geometric space of leaf-labeled trees. This tree-space is a geodesic metric space where any two trees are connected by a unique shortest path, which corresponds to a tree deformation. However, tree-space is not a manifold, and the usual strategy of performing statistical analysis in a tangent space and projecting onto tree-space is not available. Using tree-space and its shortest paths, a variety of statistical properties, such as mean, principal component, hypothesis testing and linear discriminant analysis can be defined. For some of these properties it is still an open problem how to compute them; others (like the mean) can be computed, but efficient alternatives are helpful in speeding up algorithms that use means iteratively, like hypothesis testing. In this paper, we take advantage of a very large dataset (N = 8016) to obtain computable approximations, under the assumption that the data trees parametrize the relevant parts of tree-space well. Using the developed approximate statistics, we illustrate how the structure and geometry of airway trees vary across a population and show that airway trees with Chronic Obstructive Pulmonary Disease come from a different distribution in tree-space than healthy ones. Software is available from http://image.diku.dk/aasa/software.php.

A hierarchical scheme for geodesic anatomical labeling of airway trees.

We present a fast and robust supervised algorithm for labeling anatomical airway trees, based on geodesic distances in a geometric tree-space. Possible branch label configurations for a given tree are evaluated based on distances to a training set of labeled trees. In tree-space, the tree topology and geometry change continuously, giving a natural way to automatically handle anatomical differences and noise. The algorithm is made efficient using a hierarchical approach, in which labels are assigned from the top down. We only use features of the airway centerline tree, which are relatively unaffected by pathology. A thorough leave-one-patient-out evaluation of the algorithm is made on 40 segmented airway trees from 20 subjects labeled by 2 medical experts. We evaluate accuracy, reproducibility and robustness in patients with chronic obstructive pulmonary disease (COPD). Performance is statistically similar to the inter- and intra-expert agreement, and we found no significant correlation between COPD stage and labeling accuracy.