Texture-based analysis of COPD: a data-driven approach

Quantitative Imaging Metrics for the Assessment of Pulmonary Pathophysiology: An Official American Thoracic Society and Fleischner Society Joint Workshop Report

Multiple thoracic imaging modalities have been developed to link structure to function in the diagnosis and monitoring of lung disease. Volumetric computed tomography (CT) renders three-dimensional maps of lung structures and may be combined with positron emission tomography (PET) to obtain dynamic physiological data. Magnetic resonance imaging (MRI) using ultrashort-echo time (UTE) sequences has improved signal detection from lung parenchyma; contrast agents are used to deduce airway function, ventilation-perfusion-diffusion, and mechanics. Proton MRI can measure regional ventilation-perfusion ratio. Quantitative imaging (QI)-derived endpoints have been developed to identify structure-function phenotypes, including air-blood-tissue volume partition, bronchovascular remodeling, emphysema, fibrosis, and textural patterns indicating architectural alteration. Coregistered landmarks on paired images obtained at different lung volumes are used to infer airway caliber, air trapping, gas and blood transport, compliance, and deformation. This document summarizes fundamental "good practice" stereological principles in QI study design and analysis; evaluates technical capabilities and limitations of common imaging modalities; and assesses major QI endpoints regarding underlying assumptions and limitations, ability to detect and stratify heterogeneous, overlapping pathophysiology, and monitor disease progression and therapeutic response, correlated with and complementary to, functional indices. The goal is to promote unbiased quantification and interpretation of in vivo imaging data, compare metrics obtained using different QI modalities to ensure accurate and reproducible metric derivation, and avoid misrepresentation of inferred physiological processes. The role of imaging-based computational modeling in advancing these goals is emphasized. Fundamental principles outlined herein are critical for all forms of QI irrespective of acquisition modality or disease entity.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Transferability of radiomic signatures from experimental to human interstitial lung disease

Background

Interstitial lung disease (ILD) defines a group of parenchymal lung disorders, characterized by fibrosis as their common final pathophysiological stage. To improve diagnosis and treatment of ILD, there is a need for repetitive non-invasive characterization of lung tissue by quantitative parameters. In this study, we investigated whether CT image patterns found in mice with bleomycin induced lung fibrosis can be translated as prognostic factors to human patients diagnosed with ILD.

Methods

Bleomycin was used to induce lung fibrosis in mice (n_control = 36, n_experimental = 55). The patient cohort consisted of 98 systemic sclerosis (SSc) patients (n_ILD = 65). Radiomic features (n_histogram = 17, n_texture = 137) were extracted from microCT (mice) and HRCT (patients) images. Predictive performance of the models was evaluated with the area under the receiver-operating characteristic curve (AUC). First, predictive performance of individual features was examined and compared between murine and patient data sets. Second, multivariate models predicting ILD were trained on murine data and tested on patient data. Additionally, the models were reoptimized on patient data to reduce the influence of the domain shift on the performance scores.

Results

Predictive power of individual features in terms of AUC was highly correlated between mice and patients (r = 0.86). A model based only on mean image intensity in the lung scored AUC = 0.921 ± 0.048 in mice and AUC = 0.774 (CI95% 0.677-0.859) in patients. The best radiomic model based on three radiomic features scored AUC = 0.994 ± 0.013 in mice and validated with AUC = 0.832 (CI95% 0.745-0.907) in patients. However, reoptimization of the model weights in the patient cohort allowed to increase the model’s performance to AUC = 0.912 ± 0.058.

Conclusion

Radiomic signatures of experimental ILD derived from microCT scans translated to HRCT of humans with SSc-ILD. We showed that the experimental model of BLM-induced ILD is a promising system to test radiomic models for later application and validation in human cohorts.

Early detection of COPD based on graph convolutional network and small and weakly labeled data

Chronic obstructive pulmonary disease (COPD) is a common disease with high morbidity and mortality, where early detection benefits the population. However, the early diagnosis rate of COPD is low due to the absence or slight early symptoms. In this paper, a novel method based on graph convolution network (GCN) for early detection of COPD is proposed, which uses small and weakly labeled chest computed tomography image data from the publicly available Danish Lung Cancer Screening Trial database. The key idea is to construct a graph using regions of interest randomly selected from the segmented lung parenchyma and then input it into the GCN model for COPD detection. In this way, the model can not only extract the feature information of each region of interest but also the topological structure information between regions of interest, that is, graph structure information. The proposed GCN model achieves an acceptable performance with an accuracy of 0.77 and an area under a curve of 0.81, which is higher than the previous studies on the same dataset. GCN model also outperforms several state-of-the-art methods trained at the same time. As far as we know, it is also the first time using the GCN model on this dataset for COPD detection.

Emotion Processing Dysfunction in Alzheimer's Disease: An Overview of Behavioral Findings, Systems Neural Correlates, and Underlying Neural Biology

We described behavioral studies to highlight emotional processing deficits in Alzheimer's disease (AD). The findings suggest prominent deficit in recognizing negative emotions, pronounced effect of positive emotion on enhancing memory, and a critical role of cognitive deficits in manifesting emotional processing dysfunction in AD. We reviewed imaging studies to highlight morphometric and functional markers of hippocampal circuit dysfunction in emotional processing deficits. Despite amygdala reactivity to emotional stimuli, hippocampal dysfunction conduces to deficits in emotional memory. Finally, the reviewed studies implicating major neurotransmitter systems in anxiety and depression in AD supported altered cholinergic and noradrenergic signaling in AD emotional disorders. Overall, the studies showed altered emotions early in the course of illness and suggest the need of multimodal imaging for further investigations. Particularly, longitudinal studies with multiple behavioral paradigms translatable between preclinical and clinical models would provide data to elucidate the time course and underlying neurobiology of emotion processing dysfunction in AD.

Unpaired data empowers association tests

Motivation

There is growing interest in the biomedical research community to incorporate retrospective data, available in healthcare systems, to shed light on associations between different biomarkers. Understanding the association between various types of biomedical data, such as genetic, blood biomarkers, imaging, etc. can provide a holistic understanding of human diseases. To formally test a hypothesized association between two types of data in Electronic Health Records (EHRs), one requires a substantial sample size with both data modalities to achieve a reasonable power. Current association test methods only allow using data from individuals who have both data modalities. Hence, researchers cannot take advantage of much larger EHR samples that includes individuals with at least one of the data types, which limits the power of the association test.

Results

We present a new method called the Semi-paired Association Test (SAT) that makes use of both paired and unpaired data. In contrast to classical approaches, incorporating unpaired data allows SAT to produce better control of false discovery and to improve the power of the association test. We study the properties of the new test theoretically and empirically, through a series of simulations and by applying our method on real studies in the context of Chronic Obstructive Pulmonary Disease. We are able to identify an association between the high-dimensional characterization of Computed Tomography chest images and several blood biomarkers as well as the expression of dozens of genes involved in the immune system.

Availability and implementation

Code is available on https://github.com/batmanlab/Semi-paired-Association-Test.

Supplementary information

Supplementary data are available at Bioinformatics online.

Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach

PURPOSE

To develop and evaluate a deep learning (DL) approach to extract rich information from high-resolution computed tomography (HRCT) of patients with chronic obstructive pulmonary disease (COPD).

METHODS

We develop a DL-based model to learn a compact representation of a subject, which is predictive of COPD physiologic severity and other outcomes. Our DL model learned: (a) to extract informative regional image features from HRCT; (b) to adaptively weight these features and form an aggregate patient representation; and finally, (c) to predict several COPD outcomes. The adaptive weights correspond to the regional lung contribution to the disease. We evaluate the model on 10 300 participants from the COPDGene cohort.

RESULTS

Our model was strongly predictive of spirometric obstruction ( r 2  =  0.67) and grouped 65.4% of subjects correctly and 89.1% within one stage of their GOLD severity stage. Our model achieved an accuracy of 41.7% and 52.8% in stratifying the population-based on centrilobular (5-grade) and paraseptal (3-grade) emphysema severity score, respectively. For predicting future exacerbation, combining subjects' representations from our model with their past exacerbation histories achieved an accuracy of 80.8% (area under the ROC curve of 0.73). For all-cause mortality, in Cox regression analysis, we outperformed the BODE index improving the concordance metric (ours: 0.61 vs BODE: 0.56).

CONCLUSIONS

Our model independently predicted spirometric obstruction, emphysema severity, exacerbation risk, and mortality from CT imaging alone. This method has potential applicability in both research and clinical practice.

Incorporating External Information in Tissue Subtyping: A Topic Modeling Approach

Probabilistic topic models, have been widely deployed for various applications such as learning disease or tissue subtypes. Yet, learning the parameters of such models is usually an ill-posed problem and may result in losing valuable information about disease severity. A common approach is to add a discriminative loss term to the generative model's loss in order to learn a representation that is also predictive of disease severity. However, finding a balance between these two losses is not straightforward. We propose an alternative way in this paper. We develop a framework which allows for incorporating external covariates into the generative model's approximate posterior. These covariates can have more discriminative power for disease severity compared to the representation that we extract from the posterior distribution. For instance, they can be features extracted from a neural network which predicts disease severity from CT images. Effectively, we enforce the generative model's approximate posterior to reside in the subspace of these discriminative covariates. We illustrate our method's application on a large-scale lung CT study of Chronic Obstructive Pulmonary Disease (COPD), a highly heterogeneous disease. We aim at identifying tissue subtypes by using a variant of topic model as a generative model. We quantitatively evaluate the predictive performance of the inferred subtypes and demonstrate that our method outperforms or performs on par with some reasonable baselines. We also show that some of the discovered subtypes are correlated with genetic measurements, suggesting that the identified subtypes may characterize the disease's underlying etiology.

Relative Regional Air Volume Change Maps at the Acinar Scale Reflect Variable Ventilation in Low Lung Attenuation of COPD patients

OBJECTIVES

The purpose of this study was to investigate regional air volume changes at the acinar scale of the lung in chronic obstructive pulmonary disease (COPD) patients using an image registration technique.

MATERIALS AND METHODS

Thirty-four emphysema patients and 24 subjects with normal chest CT and pulmonary function test (PFT) results were included in this retrospective study for which informed consent was waived by the institutional review board. After lung segmentation, a mass-preserving image registration technique was used to compute relative regional air volume changes (RRAVCs) between inspiration and expiration CT scans. After determining the appropriate thresholds of RRAVCs for low ventilation areas (LVAs), they were displayed and analyzed using color maps on the background inspiration CT image, and compared with the low attenuation area (LAA) map. Correlations between quantitative CT parameters and PFTs were assessed using Pearson's correlation test, and parameters were compared between emphysema and normal-CT patients using the Student's t-test.

RESULTS

LVA percentage with an RRAVC threshold of 0.5 (%LVA_0.5) showed the strongest correlations with FEV₁/FVC (r = -0.566), FEV₁ (r = -0.534), %LAA_-950insp (r = 0.712), and %LAA_-856exp (r = 0.775). %LVA_0.5 was significantly higher (P < 0.001) in COPD patients than normal subjects. Despite the identical appearance of emphysematous lesions on the LAA_-950insp map, the RRAVC map depicted a wide range of ventilation differences between these LAA clusters.

CONCLUSION

RRAVC-based %LVA_0.5 correlated well with FEV₁/FVC, FEV₁, %LAA_-950insp and %LAA_-856exp. RRAVC holds the potential for providing additional acinar scale functional information for emphysematous LAAs in inspiratory CT images, providing the basis for a novel set for emphysematous phenotypes.

Applicability of radiomics in interstitial lung disease associated with systemic sclerosis: proof of concept

Objective

To retrospectively evaluate if texture-based radiomics features are able to detect interstitial lung disease (ILD) and to distinguish between the different disease stages in patients with systemic sclerosis (SSc) in comparison with mere visual analysis of high-resolution computed tomography (HRCT).

Methods

Sixty patients (46 females, median age 56 years) with SSc who underwent HRCT of the thorax were retrospectively analyzed. Visual analysis was performed by two radiologists for the presence of ILD features. Gender, age, and pulmonary function (GAP) stage was calculated from clinical data (gender, age, pulmonary function test). Data augmentation was performed and the balanced dataset was split into a training (70%) and a testing dataset (30%). For selecting variables that allow classification of the GAP stage, single and multiple logistic regression models were fitted and compared by using the Akaike information criterion (AIC). Diagnostic accuracy was evaluated from the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, and diagnostic sensitivity and specificity were calculated.

Results

Values for some radiomics features were significantly lower (p < 0.05) and those of other radiomics features were significantly higher (p = 0.001) in patients with GAP2 compared with those in patients with GAP1. The combination of two specific radiomics features in a multivariable model resulted in the lowest AIC of 10.73 with an AUC of 0.96, 84% sensitivity, and 99% specificity. Visual assessment of fibrosis was inferior in predicting individual GAP stages (AUC 0.86; 83% sensitivity; 74% specificity).

Conclusion

The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features indicating severity of SSc-ILD on HRCT, which are not recognized by visual analysis.

Key Points

• Radiomics features can predict GAP stage with a sensitivity of 84% and a specificity of almost 100%.

• Extent of fibrosis on HRCT and a combined model of different visual HRCT-ILD features perform worse in predicting GAP stage.

• The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features on HRCT, which are not recognized by visual analysis.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-07293-8) contains supplementary material, which is available to authorized users.

Prospects and Challenges of Radiomics by Using Nononcologic Routine Chest CT

Chest CT scans are one of the most common medical imaging procedures. The automatic extraction and quantification of imaging features may help in diagnosis, prognosis of, or treatment decision in cardiovascular, pulmonary, and metabolic diseases. However, an adequate sample size as a statistical necessity for radiomics studies is often difficult to achieve in prospective trials. By exploiting imaging data from clinical routine, a much larger amount of data could be used than in clinical trials. Still, there is only little literature on the implementation of radiomics in clinical routine chest CT scans. Reasons are heterogeneous CT scanning protocols and the resulting technical variability (eg, different slice thicknesses, reconstruction kernels or timings after contrast material administration) in routine CT imaging data. This review summarizes the recent state of the art of studies aiming to develop quantifiable imaging biomarkers at chest CT, such as for osteoporosis, chronic obstructive pulmonary disease, interstitial lung disease, and coronary artery disease. This review explains solutions to overcome heterogeneity in routine data such as the use of imaging repositories, the standardization of radiomic features, algorithmic approaches to improve feature stability, test-retest studies, and the evolution of deep learning for modeling radiomics features. Supplemental material is available for this article. © RSNA, 2020 See also the commentary by Kay in this issue.

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.

Deep learning for screening of interstitial lung disease patterns in high-resolution CT images

AIM

To develop a screening tool for the detection of interstitial lung disease (ILD) patterns using a deep-learning method.

MATERIALS AND METHODS

A fully convolutional network was used for semantic segmentation of several ILD patterns. Improved segmentation of ILD patterns was achieved using multi-scale feature extraction. Dilated convolution was used to maintain the resolution of feature maps and to enlarge the receptive field. The proposed method was evaluated on a publicly available ILD database (MedGIFT) and a private clinical research database. Several metrics, such as success rate, sensitivity, and false positives per section were used for quantitative evaluation of the proposed method.

RESULTS

Sections with fibrosis and emphysema were detected with a similar success rate and sensitivity for both databases but the performance of detection was lower for consolidation compared to fibrosis and emphysema.

CONCLUSION

Automatic identification of ILD patterns in a high-resolution computed tomography (CT) image was implemented using a deep-learning framework. Creation of a pre-trained model with natural images and subsequent transfer learning using a particular database gives acceptable results.

Quantitative CT Analysis of Diffuse Lung Disease

Quantitative analysis of thin-section CT of the chest has a growing role in the clinical evaluation and management of diffuse lung diseases. This heterogeneous group includes diseases with markedly different prognoses and treatment options. Quantitative tools can assist in both accurate diagnosis and longitudinal management by improving characterization and quantification of disease and increasing the reproducibility of disease severity assessment. Furthermore, a quantitative index of disease severity may serve as a useful tool or surrogate endpoint in evaluating treatment efficacy. The authors explore the role of quantitative imaging tools in the evaluation and management of diffuse lung diseases. Lung parenchymal features can be classified with threshold, histogram, morphologic, and texture-analysis-based methods. Quantitative CT analysis has been applied in obstructive, infiltrative, and restrictive pulmonary diseases including emphysema, cystic fibrosis, asthma, idiopathic pulmonary fibrosis, hypersensitivity pneumonitis, connective tissue-related interstitial lung disease, and combined pulmonary fibrosis and emphysema. Some challenges limiting the development and practical application of current quantitative analysis tools include the quality of training data, lack of standard criteria to validate the accuracy of the results, and lack of real-world assessments of the impact on outcomes. Artifacts such as patient motion or metallic beam hardening, variation in inspiratory effort, differences in image acquisition and reconstruction techniques, or inaccurate preprocessing steps such as segmentation of anatomic structures may lead to inaccurate classification. Despite these challenges, as new techniques emerge, quantitative analysis is developing into a viable tool to supplement the traditional visual assessment of diffuse lung diseases and to provide decision support regarding diagnosis, prognosis, and longitudinal evaluation of disease. ^©RSNA, 2019.

Personalized medicine for patients with COPD: where are we?

Chronic airflow limitation is the common denominator of patients with chronic obstructive pulmonary disease (COPD). However, it is not possible to predict morbidity and mortality of individual patients based on the degree of lung function impairment, nor does the degree of airflow limitation allow guidance regarding therapies. Over the last decades, understanding of the factors contributing to the heterogeneity of disease trajectories, clinical presentation, and response to existing therapies has greatly advanced. Indeed, diagnostic assessment and treatment algorithms for COPD have become more personalized. In addition to the pulmonary abnormalities and inhaler therapies, extra-pulmonary features and comorbidities have been studied and are considered essential components of comprehensive disease management, including lifestyle interventions. Despite these advances, predicting and/or modifying the course of the disease remains currently impossible, and selection of patients with a beneficial response to specific interventions is unsatisfactory. Consequently, non-response to pharmacologic and non-pharmacologic treatments is common, and many patients have refractory symptoms. Thus, there is an ongoing urgency for a more targeted and holistic management of the disease, incorporating the basic principles of P4 medicine (predictive, preventive, personalized, and participatory). This review describes the current status and unmet needs regarding personalized medicine for patients with COPD. Also, it proposes a systems medicine approach, integrating genetic, environmental, (micro)biological, and clinical factors in experimental and computational models in order to decipher the multilevel complexity of COPD. Ultimately, the acquired insights will enable the development of clinical decision support systems and advance personalized medicine for patients with COPD.

Artificial intelligence in diagnosis of obstructive lung disease: current status and future potential

PURPOSE OF REVIEW

The application of artificial intelligence in the diagnosis of obstructive lung diseases is an exciting phenomenon. Artificial intelligence algorithms work by finding patterns in data obtained from diagnostic tests, which can be used to predict clinical outcomes or to detect obstructive phenotypes. The purpose of this review is to describe the latest trends and to discuss the future potential of artificial intelligence in the diagnosis of obstructive lung diseases.

RECENT FINDINGS

Machine learning has been successfully used in automated interpretation of pulmonary function tests for differential diagnosis of obstructive lung diseases. Deep learning models such as convolutional neural network are state-of-the art for obstructive pattern recognition in computed tomography. Machine learning has also been applied in other diagnostic approaches such as forced oscillation test, breath analysis, lung sound analysis and telemedicine with promising results in small-scale studies.

SUMMARY

Overall, the application of artificial intelligence has produced encouraging results in the diagnosis of obstructive lung diseases. However, large-scale studies are still required to validate current findings and to boost its adoption by the medical community.

Automatic emphysema detection using weakly labeled HRCT lung images

PURPOSE

A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented.

METHODS

HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs).

RESULTS

The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist.

CONCLUSIONS

The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.

Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector

We propose an attention-based method that aggregates local image features to a subject-level representation for predicting disease severity. In contrast to classical deep learning that requires a fixed dimensional input, our method operates on a set of image patches; hence it can accommodate variable length input image without image resizing. The model learns a clinically interpretable subject-level representation that is reflective of the disease severity. Our model consists of three mutually dependent modules which regulate each other: (1) a discriminative network that learns a fixed-length representation from local features and maps them to disease severity; (2) an attention mechanism that provides interpretability by focusing on the areas of the anatomy that contribute the most to the prediction task; and (3) a generative network that encourages the diversity of the local latent features. The generative term ensures that the attention weights are non-degenerate while maintaining the relevance of the local regions to the disease severity. We train our model end-to-end in the context of a large-scale lung CT study of Chronic Obstructive Pulmonary Disease (COPD). Our model gives state-of-the art performance in predicting clinical measures of severity for COPD.The distribution of the attention provides the regional relevance of lung tissue to the clinical measurements.

Functional respiratory imaging (FRI) for optimizing therapy development and patient care

Functional imaging techniques offer the possibility of improved visualization of anatomical structures such as; airways, lobe volumes and blood vessels. Computer-based flow simulations with a three-dimensional element add functionality to the images. By providing valuable detailed information about airway geometry, internal airflow distribution and inhalation profile, functional respiratory imaging can be of use routinely in the clinic. Three dimensional visualization allows for highly detailed follow-up in terms of disease progression or in assessing effects of interventions. Here, we explore the usefulness of functional respiratory imaging in different respiratory diseases. In patients with asthma and COPD, functional respiratory imaging has been used for phenotyping these patients, to predict the responder and non-responder phenotype and to evaluate different innovative therapeutic interventions.

Digital liver biopsy: Bio-imaging of fatty liver for translational and clinical research

The rapidly growing field of functional, molecular and structural bio-imaging is providing an extraordinary new opportunity to overcome the limits of invasive liver biopsy and introduce a "digital biopsy" for in vivo study of liver pathophysiology. To foster the application of bio-imaging in clinical and translational research, there is a need to standardize the methods of both acquisition and the storage of the bio-images of the liver. It can be hoped that the combination of digital, liquid and histologic liver biopsies will provide an innovative synergistic tri-dimensional approach to identifying new aetiologies, diagnostic and prognostic biomarkers and therapeutic targets for the optimization of personalized therapy of liver diseases and liver cancer. A group of experts of different disciplines (Special Interest Group for Personalized Hepatology of the Italian Association for the Study of the Liver, Institute for Biostructures and Bio-imaging of the National Research Council and Bio-banking and Biomolecular Resources Research Infrastructure) discussed criteria, methods and guidelines for facilitating the requisite application of data collection. This manuscript provides a multi-Author review of the issue with special focus on fatty liver.

Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography

RATIONALE

Deep learning is a powerful tool that may allow for improved outcome prediction.

OBJECTIVES

To determine if deep learning, specifically convolutional neural network (CNN) analysis, could detect and stage chronic obstructive pulmonary disease (COPD) and predict acute respiratory disease (ARD) events and mortality in smokers.

METHODS

A CNN was trained using computed tomography scans from 7,983 COPDGene participants and evaluated using 1,000 nonoverlapping COPDGene participants and 1,672 ECLIPSE participants. Logistic regression (C statistic and the Hosmer-Lemeshow test) was used to assess COPD diagnosis and ARD prediction. Cox regression (C index and the Greenwood-Nam-D'Agnostino test) was used to assess mortality.

MEASUREMENTS AND MAIN RESULTS

In COPDGene, the C statistic for the detection of COPD was 0.856. A total of 51.1% of participants in COPDGene were accurately staged and 74.95% were within one stage. In ECLIPSE, 29.4% were accurately staged and 74.6% were within one stage. In COPDGene and ECLIPSE, the C statistics for ARD events were 0.64 and 0.55, respectively, and the Hosmer-Lemeshow P values were 0.502 and 0.380, respectively, suggesting no evidence of poor calibration. In COPDGene and ECLIPSE, CNN predicted mortality with fair discrimination (C indices, 0.72 and 0.60, respectively), and without evidence of poor calibration (Greenwood-Nam-D'Agnostino P values, 0.307 and 0.331, respectively).

CONCLUSIONS

A deep-learning approach that uses only computed tomography imaging data can identify those smokers who have COPD and predict who are most likely to have ARD events and those with the highest mortality. At a population level CNN analysis may be a powerful tool for risk assessment.

Transfer Learning for Multicenter Classification of Chronic Obstructive Pulmonary Disease

Chronic obstructive pulmonary disease (COPD) is a lung disease that can be quantified using chest computed tomography scans. Recent studies have shown that COPD can be automatically diagnosed using weakly supervised learning of intensity and texture distributions. However, up till now such classifiers have only been evaluated on scans from a single domain, and it is unclear whether they would generalize across domains, such as different scanners or scanning protocols. To address this problem, we investigate classification of COPD in a multicenter dataset with a total of 803 scans from three different centers, four different scanners, with heterogenous subject distributions. Our method is based on Gaussian texture features, and a weighted logistic classifier, which increases the weights of samples similar to the test data. We show that Gaussian texture features outperform intensity features previously used in multicenter classification tasks. We also show that a weighting strategy based on a classifier that is trained to discriminate between scans from different domains can further improve the results. To encourage further research into transfer learning methods for the classification of COPD, upon acceptance of this paper we will release two feature datasets used in this study on http://bigr.nl/research/projects/copd.

A Likelihood-Free Approach for Characterizing Heterogeneous Diseases in Large-Scale Studies

We propose a non-parametric approach for characterizing heterogeneous diseases in large-scale studies. We target diseases where multiple types of pathology present simultaneously in each subject and a more severe disease manifests as a higher level of tissue destruction. For each subject, we model the collection of local image descriptors as samples generated by an unknown subject-specific probability density. Instead of approximating the probability density via a parametric family, we propose to side step the parametric inference by directly estimating the divergence between subject densities. Our method maps the collection of local image descriptors to a signature vector that is used to predict a clinical measurement. We are able to interpret the prediction of the clinical variable in the population and individual levels by carefully studying the divergences. We illustrate an application this method on simulated data as well as on a large-scale lung CT study of Chronic Obstructive Pulmonary Disease (COPD). Our approach outperforms classical methods on both simulated and COPD data and demonstrates the state-of-the-art prediction on an important physiologic measure of airflow (the forced respiratory volume in one second, FEV1).

Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures

Quantitative analysis of tumour characteristics based on medical imaging is an emerging field of research. In recent years, quantitative imaging features derived from CT, positron emission tomography and MR scans were shown to be of added value in the prediction of outcome parameters in oncology, in what is called the radiomics field. However, results might be difficult to compare owing to a lack of standardized methodologies to conduct quantitative image analyses. In this review, we aim to present an overview of the current challenges, technical routines and protocols that are involved in quantitative imaging studies. The first issue that should be overcome is the dependency of several features on the scan acquisition and image reconstruction parameters. Adopting consistent methods in the subsequent target segmentation step is evenly crucial. To further establish robust quantitative image analyses, standardization or at least calibration of imaging features based on different feature extraction settings is required, especially for texture- and filter-based features. Several open-source and commercial software packages to perform feature extraction are currently available, all with slightly different functionalities, which makes benchmarking quite challenging. The number of imaging features calculated is typically larger than the number of patients studied, which emphasizes the importance of proper feature selection and prediction model-building routines to prevent overfitting. Even though many of these challenges still need to be addressed before quantitative imaging can be brought into daily clinical practice, radiomics is expected to be a critical component for the integration of image-derived information to personalize treatment in the future.

Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry

This paper presents a brain T1-weighted structural magnetic resonance imaging (MRI) biomarker that combines several individual MRI biomarkers (cortical thickness measurements, volumetric measurements, hippocampal shape, and hippocampal texture). The method was developed, trained, and evaluated using two publicly available reference datasets: a standardized dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the imaging arm of the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL). In addition, the method was evaluated by participation in the Computer-Aided Diagnosis of Dementia (CADDementia) challenge. Cross-validation using ADNI and AIBL data resulted in a multi-class classification accuracy of 62.7% for the discrimination of healthy normal controls (NC), subjects with mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD). This performance generalized to the CADDementia challenge where the method, trained using the ADNI and AIBL data, achieved a classification accuracy 63.0%. The obtained classification accuracy resulted in a first place in the challenge, and the method was significantly better (McNemar's test) than the bottom 24 methods out of the total of 29 methods contributed by 15 different teams in the challenge. The method was further investigated with learning curve and feature selection experiments using ADNI and AIBL data. The learning curve experiments suggested that neither more training data nor a more complex classifier would have improved the obtained results. The feature selection experiment showed that both common and uncommon individual MRI biomarkers contributed to the performance; hippocampal volume, ventricular volume, hippocampal texture, and parietal lobe thickness were the most important. This study highlights the need for both subtle, localized measurements and global measurements in order to discriminate NC, MCI, and AD simultaneously based on a single structural MRI scan. It is likely that additional non-structural MRI features are needed to further improve the obtained performance, especially to improve the discrimination between NC and MCI.

•

The algorithm that won the CADDementia challenge is described and analyzed.

•

Evaluation on data from ADNI, AIBL and the CADDementia challenge.

•

Hippocampal texture is shown to be an important feature in the algorithm.

•

Structural MRI intensity variations may include so far unused information.

•

It is conjectured that additional features are needed in order to improve diagnostic performance.

Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images

The World Health Organization estimates that 300 million people have asthma, 210 million people have Chronic Obstructive Pulmonary Disease (COPD), and, according to WHO, COPD will become the third major cause of death worldwide in 2030. Computational Vision systems are commonly used in pulmonology to address the task of image segmentation, which is essential for accurate medical diagnoses. Segmentation defines the regions of the lungs in CT images of the thorax that must be further analyzed by the system or by a specialist physician. This work proposes a novel and powerful technique named 3D Adaptive Crisp Active Contour Method (3D ACACM) for the segmentation of CT lung images. The method starts with a sphere within the lung to be segmented that is deformed by forces acting on it towards the lung borders. This process is performed iteratively in order to minimize an energy function associated with the 3D deformable model used. In the experimental assessment, the 3D ACACM is compared against three approaches commonly used in this field: the automatic 3D Region Growing, the level-set algorithm based on coherent propagation and the semi-automatic segmentation by an expert using the 3D OsiriX toolbox. When applied to 40 CT scans of the chest the 3D ACACM had an average F-measure of 99.22%, revealing its superiority and competency to segment lungs in CT images.

Machine learning approaches in medical image analysis: From detection to diagnosis

Machine learning approaches are increasingly successful in image-based diagnosis, disease prognosis, and risk assessment. This paper highlights new research directions and discusses three main challenges related to machine learning in medical imaging: coping with variation in imaging protocols, learning from weak labels, and interpretation and evaluation of results.

Early detection of Alzheimer's disease using MRI hippocampal texture

Cognitive impairment in patients with Alzheimer's disease (AD) is associated with reduction in hippocampal volume in magnetic resonance imaging (MRI). However, it is unknown whether hippocampal texture changes in persons with mild cognitive impairment (MCI) that does not have a change in hippocampal volume. We tested the hypothesis that hippocampal texture has association to early cognitive loss beyond that of volumetric changes. The texture marker was trained and evaluated using T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and subsequently applied to score independent data sets from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL) and the Metropolit 1953 Danish Male Birth Cohort (Metropolit). Hippocampal texture was superior to volume reduction as predictor of MCI-to-AD conversion in ADNI (area under the receiver operating characteristic curve [AUC] 0.74 vs. 0.67; DeLong test, p = 0.005), and provided even better prognostic results in AIBL (AUC 0.83). Hippocampal texture, but not volume, correlated with Addenbrooke's cognitive examination score (Pearson correlation, r = -0.25, p < 0.001) in the Metropolit cohort. The hippocampal texture marker correlated with hippocampal glucose metabolism as indicated by fluorodeoxyglucose-positron emission tomography (Pearson correlation, r = -0.57, p < 0.001). Texture statistics remained significant after adjustment for volume in all cases, and the combination of texture and volume did not improve diagnostic or prognostic AUCs significantly. Our study highlights the presence of hippocampal texture abnormalities in MCI, and the possibility that texture may serve as a prognostic neuroimaging biomarker of early cognitive impairment.

Influence of COPD Assessment Text (CAT) evaluation and rehabilitation education guidance on the respiratory and motor functions of COPD patients

The study aimed to evaluate the influence of the COPD Assessment Test (CAT) evaluation and rehabilitation education guidance on the respiratory and motor functions of patients with chronic obstructive pulmonary disease (COPD). Forty-five patients with COPD admitted from Nov. 2012 to Nov. 2013 were treated with combined bronchodilators and inhaled corticosteroids. Thirty-five patients admitted from Nov. 2012 to Nov. 2013 and classified as a study group received rehabilitation education guidance on the basis of the treatment of the control group to compare the quality-of-life-scale score, dyspnea index score, and motor function of the two groups of patients after 48 weeks of treatment. After treatment, the CAT score of both groups of patients was significantly lowered. After 48 weeks of treatment, the respiratory function of both groups was significantly improved, but the Medical Research Council (MRC) scale for the study group after treatment was significantly lower than that for the control group. After 48 weeks of rehabilitation exercises, the 6-minute walk test (6MWT) for patients with COPD was significantly prolonged, but the test results were significantly higher for the study group after treatment than for the control group. After receiving CAT rehabilitation education, COPD patients had significantly improved life quality and significantly enhanced exercise tolerance. The treatment mode may be gradually introduced in future clinic and nursing work.

Large Margin Local Estimate With Applications to Medical Image Classification

Medical images usually exhibit large intra-class variation and inter-class ambiguity in the feature space, which could affect classification accuracy. To tackle this issue, we propose a new Large Margin Local Estimate (LMLE) classification model with sub-categorization based sparse representation. We first sub-categorize the reference sets of different classes into multiple clusters, to reduce feature variation within each subcategory compared to the entire reference set. Local estimates are generated for the test image using sparse representation with reference subcategories as the dictionaries. The similarity between the test image and each class is then computed by fusing the distances with the local estimates in a learning-based large margin aggregation construct to alleviate the problem of inter-class ambiguity. The derived similarities are finally used to determine the class label. We demonstrate that our LMLE model is generally applicable to different imaging modalities, and applied it to three tasks: interstitial lung disease (ILD) classification on high-resolution computed tomography (HRCT) images, phenotype binary classification and continuous regression on brain magnetic resonance (MR) imaging. Our experimental results show statistically significant performance improvements over existing popular classifiers.

Machine learning algorithms and forced oscillation measurements to categorise the airway obstruction severity in chronic obstructive pulmonary disease

The purpose of this study was to develop automatic classifiers to simplify the clinical use and increase the accuracy of the forced oscillation technique (FOT) in the categorisation of airway obstruction level in patients with chronic obstructive pulmonary disease (COPD). The data consisted of FOT parameters obtained from 168 volunteers (42 healthy and 126 COPD subjects with four different levels of obstruction). The first part of this study showed that FOT parameters do not provide adequate accuracy in identifying COPD subjects in the first levels of obstruction, as well as in discriminating between close levels of obstruction. In the second part of this study, different supervised machine learning (ML) techniques were investigated, including k-nearest neighbour (KNN), random forest (RF) and support vector machines with linear (SVML) and radial basis function kernels (SVMR). These algorithms were applied only in situations where high categorisation accuracy [area under the Receiver Operating Characteristic curve (AUC)≥0.9] was not achieved with the FOT parameter alone. It was observed that KNN and RF classifiers improved categorisation accuracy. Notably, in four of the six cases studied, an AUC≥0.9 was achieved. Even in situations where an AUC≥0.9 was not achieved, there was a significant improvement in categorisation performance (AUC≥0.83). In conclusion, machine learning classifiers can help in the categorisation of COPD airway obstruction. They can assist clinicians in tracking disease progression, evaluating the risk of future disease exacerbations and guiding therapy.

A Feature-Based Approach to Big Data Analysis of Medical Images

This paper proposes an inference method well-suited to large sets of medical images. The method is based upon a framework where distinctive 3D scale-invariant features are indexed efficiently to identify approximate nearest-neighbor (NN) feature matches-in O (log N) computational complexity in the number of images N. It thus scales well to large data sets, in contrast to methods based on pair-wise image registration or feature matching requiring O(N) complexity. Our theoretical contribution is a density estimator based on a generative model that generalizes kernel density estimation and K-nearest neighbor (KNN) methods.. The estimator can be used for on-the-fly queries, without requiring explicit parametric models or an off-line training phase. The method is validated on a large multi-site data set of 95,000,000 features extracted from 19,000 lung CT scans. Subject-level classification identifies all images of the same subjects across the entire data set despite deformation due to breathing state, including unintentional duplicate scans. State-of-the-art performance is achieved in predicting chronic pulmonary obstructive disorder (COPD) severity across the 5-category GOLD clinical rating, with an accuracy of 89% if both exact and one-off predictions are considered correct.

Modelling the dynamics of expiratory airflow to describe chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease (COPD) is characterized by expiratory airflow limitation, but current diagnostic criteria only consider flow till the first second and are therefore strongly debated. We aimed to develop a data-based individualized model for flow decline and to explore the relationship between model parameters and COPD presence. A second-order transfer function model was chosen and the model parameters (namely the two poles and the steady state gain (SSG)) from 474 individuals were correlated with COPD presence. The capability of the model to predict disease presence was explored using 5 machine learning classifiers and tenfold cross-validation. Median (95% CI) poles in subjects without disease were 0.9868 (0.9858-0.9878) and 0.9333 (0.9256-0.9395), compared with 0.9929 (0.9925-0.9933) and 0.9082 (0.9004-0.9140) in subjects with COPD (p < 0.001 for both poles). A significant difference was also found when analysing the SSG, being lower in COPD group 3.8 (3.5-4.2) compared with 8.2 (7.8-8.7) in subjects without (p < 0.0001). A combination of all three parameters in a support vector machines corresponded with highest sensitivity of 85%, specificity of 98.1% and accuracy of 88.2% to COPD diagnosis. The forced expiration of COPD can be modelled by a second-order system which parameters identify most COPD cases. Our approach offers an additional tool in case FEV1/FVC ratio-based diagnosis is doubted.

Adaptive quantification and longitudinal analysis of pulmonary emphysema with a hidden Markov measure field model

The extent of pulmonary emphysema is commonly estimated from CT scans by computing the proportional area of voxels below a predefined attenuation threshold. However, the reliability of this approach is limited by several factors that affect the CT intensity distributions in the lung. This work presents a novel method for emphysema quantification, based on parametric modeling of intensity distributions and a hidden Markov measure field model to segment emphysematous regions. The framework adapts to the characteristics of an image to ensure a robust quantification of emphysema under varying CT imaging protocols, and differences in parenchymal intensity distributions due to factors such as inspiration level. Compared to standard approaches, the presented model involves a larger number of parameters, most of which can be estimated from data, to handle the variability encountered in lung CT scans. The method was applied on a longitudinal data set with 87 subjects and a total of 365 scans acquired with varying imaging protocols. The resulting emphysema estimates had very high intra-subject correlation values. By reducing sensitivity to changes in imaging protocol, the method provides a more robust estimate than standard approaches. The generated emphysema delineations promise advantages for regional analysis of emphysema extent and progression.

Extended Gabor approach applied to classification of emphysematous patterns in computed tomography

Chronic obstructive pulmonary disease (COPD) is a progressive and irreversible lung condition typically related to emphysema. It hinders air from passing through airpaths and causes that alveolar sacs lose their elastic quality. Findings of COPD may be manifested in a variety of computed tomography (CT) studies. Nevertheless, visual assessment of CT images is time-consuming and depends on trained observers. Hence, a reliable computer-aided diagnosis system would be useful to reduce time and inter-evaluator variability. In this paper, we propose a new emphysema classification framework based on complex Gabor filters and local binary patterns. This approach simultaneously encodes global characteristics and local information to describe emphysema morphology in CT images. Kernel Fisher analysis was used to reduce dimensionality and to find the most discriminant nonlinear boundaries among classes. Finally, classification was performed using the k-nearest neighbor classifier. The results have shown the effectiveness of our approach for quantifying lesions due to emphysema and that the combination of descriptors yields to a better classification performance.

Registration-based lung mechanical analysis of chronic obstructive pulmonary disease (COPD) using a supervised machine learning framework

RATIONALE AND OBJECTIVES

This study evaluated the performance of computed tomography (CT)-derived biomechanical based features of lung function and the presence and severity of chronic obstructive pulmonary disease (COPD). It performed well when compared to CT-derived density and textural features of lung function and the presence and severity of COPD.

MATERIALS AND METHODS

A total of 162 subjects (Global Initiative for Chronic Obstructive Lung Disease [GOLD] stages 0-4 and nonsmokers) subjects with CT scan performed at total lung capacity or expiration to functional residual capacity were evaluated. CT-derived biomechanical, density, and textural feature sets were compared to forced expiratory volume in 1 second (FEV1)%, FEV1/forced vital capacity, and total St. George's respiratory questionnaire scores. The ability of these feature sets to assess the presence and severity of COPD was also evaluated. Optimal features are selected by linear forward feature selection and the classification is done using k nearest neighbor learning algorithm.

RESULTS

The proposed biomechanical features showed good correlations with the pulmonary function tests and health status metrics. In COPD versus non-COPD classification, biomechanical feature set achieved an area under the curve (AUC) of 0.85 performing well in comparison to density (AUC = 0.83) and texture (AUC = 0.89) feature sets. Classifying the subjects into the severity of GOLD stage using biomechanical features (AUC = 0.81) performed better than the density- and texture-based feature sets, AUC = 0.76 and 0.73, respectively. The biomechanical features performed better alone than in combination with the other two feature sets.

CONCLUSION

This study shows the effectiveness of CT-derived biomechanical measures in the assessment of airflow obstruction and quality of life in subjects with COPD. CT-derived biomechanical features performed well in assessing the presence and severity of COPD.

Feature-based image patch approximation for lung tissue classification

In this paper, we propose a new classification method for five categories of lung tissues in high-resolution computed tomography (HRCT) images, with feature-based image patch approximation. We design two new feature descriptors for higher feature descriptiveness, namely the rotation-invariant Gabor-local binary patterns (RGLBP) texture descriptor and multi-coordinate histogram of oriented gradients (MCHOG) gradient descriptor. Together with intensity features, each image patch is then labeled based on its feature approximation from reference image patches. And a new patch-adaptive sparse approximation (PASA) method is designed with the following main components: minimum discrepancy criteria for sparse-based classification, patch-specific adaptation for discriminative approximation, and feature-space weighting for distance computation. The patch-wise labelings are then accumulated as probabilistic estimations for region-level classification. The proposed method is evaluated on a publicly available ILD database, showing encouraging performance improvements over the state-of-the-arts.