Local heterogeneity of normal lung parenchyma and small airways disease are associated with COPD severity and progression.

BACKGROUND: Small airways disease (SAD) is a major cause of airflow obstruction in COPD patients and has been identified as a precursor to emphysema. Although the amount of SAD in the lungs can be quantified using our Parametric Response Mapping (PRM) approach, the full breadth of this readout as a measure of emphysema and COPD progression has yet to be explored. We evaluated topological features of PRM-derived normal parenchyma and SAD as surrogates of emphysema and predictors of spirometric decline. METHODS: PRM metrics of normal lung (PRMNorm) and functional SAD (PRMfSAD) were generated from CT scans collected as part of the COPDGene study (n = 8956). Volume density (V) and Euler-Poincaré Characteristic (χ) image maps, measures of the extent and coalescence of pocket formations (i.e., topologies), respectively, were determined for both PRMNorm and PRMfSAD. Association with COPD severity, emphysema, and spirometric measures were assessed via multivariable regression models. Readouts were evaluated as inputs for predicting FEV1 decline using a machine learning model. RESULTS: Multivariable cross-sectional analysis of COPD subjects showed that V and χ measures for PRMfSAD and PRMNorm were independently associated with the amount of emphysema. Readouts χfSAD (ß of 0.106, p < 0.001) and VfSAD (ß of 0.065, p = 0.004) were also independently associated with FEV1% predicted. The machine learning model using PRM topologies as inputs predicted FEV1 decline over five years with an AUC of 0.69. CONCLUSIONS: We demonstrated that V and χ of fSAD and Norm have independent value when associated with lung function and emphysema. In addition, we demonstrated that these readouts are predictive of spirometric decline when used as inputs in a ML model. Our topological PRM approach using PRMfSAD and PRMNorm may show promise as an early indicator of emphysema onset and COPD progression.

Computed tomography-based machine learning for donor lung screening before transplantation.

BACKGROUND: Assessment and selection of donor lungs remain largely subjective and experience based. Criteria to accept or decline lungs are poorly standardized and are not compliant with the current donor pool. Using ex vivo computed tomography (CT) images, we investigated the use of a CT-based machine learning algorithm for screening donor lungs before transplantation. METHODS: Clinical measures and ex situ CT scans were collected from 100 cases as part of a prospective clinical trial. Following procurement, donor lungs were inflated, placed on ice according to routine clinical practice, and imaged using a clinical CT scanner before transplantation while stored in the icebox. We trained and tested a supervised machine learning method called dictionary learning, which uses CT scans and learns specific image patterns and features pertaining to each class for a classification task. The results were evaluated with donor and recipient clinical measures. RESULTS: Of the 100 lung pairs donated, 70 were considered acceptable for transplantation (based on standard clinical assessment) before CT screening and were consequently implanted. The remaining 30 pairs were screened but not transplanted. Our machine learning algorithm was able to detect pulmonary abnormalities on the CT scans. Among the patients who received donor lungs, our algorithm identified recipients who had extended stays in the intensive care unit and were at 19 times higher risk of developing chronic lung allograft dysfunction within 2 years posttransplant. CONCLUSIONS: We have created a strategy to ex vivo screen donor lungs using a CT-based machine learning algorithm. As the use of suboptimal donor lungs rises, it is important to have in place objective techniques that will assist physicians in accurately screening donor lungs to identify recipients most at risk of posttransplant complications.

Topologic Parametric Response Mapping Identifies Tissue Subtypes Associated with Emphysema Progression.

RATIONALE AND OBJECTIVES: Small airways disease (SAD) and emphysema are significant components of chronic obstructive pulmonary disease (COPD), a heterogenous disease where predicting progression is difficult. SAD, a principal cause of airflow obstruction in mild COPD, has been identified as a precursor to emphysema. Parametric Response Mapping (PRM) of chest computed tomography (CT) can help distinguish SAD from emphysema. Specifically, topologic PRM can define local patterns of both diseases to characterize how and in whom COPD progresses. We aimed to determine if distribution of CT-based PRM of functional SAD (fSAD) is associated with emphysema progression. MATERIALS AND METHODS: We analyzed paired inspiratory-expiratory chest CT scans at baseline and 5-year follow up in 1495 COPDGene subjects using topological analyses of PRM classifications. By spatially aligning temporal scans, we mapped local emphysema at year five to baseline lobar PRM-derived topological readouts. K-means clustering was applied to all observations. Subjects were subtyped based on predominant PRM cluster assignments and assessed using non-parametric statistical tests to determine differences in PRM values, pulmonary function metrics, and clinical measures. RESULTS: We identified distinct lobar imaging patterns and classified subjects into three radiologic subtypes: emphysema-dominant (ED), fSAD-dominant (FD), and fSAD-transition (FT: transition from healthy lung to fSAD). Relative to year five emphysema, FT showed rapid local emphysema progression (-57.5% ± 1.1) compared to FD (-49.9% ± 0.5) and ED (-33.1% ± 0.4). FT consisted primarily of at-risk subjects (roughly 60%) with normal spirometry. CONCLUSION: The FT subtype of COPD may allow earlier identification of individuals without spirometrically-defined COPD at-risk for developing emphysema.

Quantitative CT of Normal Lung Parenchyma and Small Airways Disease Topologies are Associated With COPD Severity and Progression.

Objectives: Small airways disease (SAD) is a major cause of airflow obstruction in COPD patients, and has been identified as a precursor to emphysema. Although the amount of SAD in the lungs can be quantified using our Parametric Response Mapping (PRM) approach, the full breadth of this readout as a measure of emphysema and COPD progression has yet to be explored. We evaluated topological features of PRM-derived normal parenchyma and SAD as surrogates of emphysema and predictors of spirometric decline. Materials and Methods: PRM metrics of normal lung (PRMNorm) and functional SAD (PRMfSAD) were generated from CT scans collected as part of the COPDGene study (n=8956). Volume density (V) and Euler-Poincaré Characteristic (χ) image maps, measures of the extent and coalescence of pocket formations (i.e., topologies), respectively, were determined for both PRMNorm and PRMfSAD. Association with COPD severity, emphysema, and spirometric measures were assessed via multivariable regression models. Readouts were evaluated as inputs for predicting FEV1 decline using a machine learning model. Results: Multivariable cross-sectional analysis of COPD subjects showed that V and χ measures for PRMfSAD and PRMNorm were independently associated with the amount of emphysema. Readouts χfSAD (ß of 0.106, p<0.001) and VfSAD (ß of 0.065, p=0.004) were also independently associated with FEV1% predicted. The machine learning model using PRM topologies as inputs predicted FEV1 decline over five years with an AUC of 0.69. Conclusions: We demonstrated that V and χ of fSAD and Norm have independent value when associated with lung function and emphysema. In addition, we demonstrated that these readouts are predictive of spirometric decline when used as inputs in a ML model. Our topological PRM approach using PRMfSAD and PRMNorm may show promise as an early indicator of emphysema onset and COPD progression.

Lung cancer lesion detection in histopathology images using graph-based sparse PCA network.

Early detection of lung cancer is critical for improvement of patient survival. To address the clinical need for efficacious treatments, genetically engineered mouse models (GEMM) have become integral in identifying and evaluating the molecular underpinnings of this complex disease that may be exploited as therapeutic targets. Assessment of GEMM tumor burden on histopathological sections performed by manual inspection is both time consuming and prone to subjective bias. Therefore, an interplay of needs and challenges exists for computer-aided diagnostic tools, for accurate and efficient analysis of these histopathology images. In this paper, we propose a simple machine learning approach called the graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E). Our method comprises four steps: 1) cascaded graph-based sparse PCA, 2) PCA binary hashing, 3) block-wise histograms, and 4) support vector machine (SVM) classification. In our proposed architecture, graph-based sparse PCA is employed to learn the filter banks of the multiple stages of a convolutional network. This is followed by PCA hashing and block histograms for indexing and pooling. The meaningful features extracted from this GS-PCA are then fed to an SVM classifier. We evaluate the performance of the proposed algorithm on H&E slides obtained from an inducible K-rasG12D lung cancer mouse model using precision/recall rates, Fß-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC) and show that our algorithm is efficient and provides improved detection accuracy compared to existing algorithms.

Machine learning for screening of at-risk, mild and moderate COPD patients at risk of FEV1 decline: results from COPDGene and SPIROMICS.

Purpose: The purpose of this study was to train and validate machine learning models for predicting rapid decline of forced expiratory volume in 1 s (FEV1) in individuals with a smoking history at-risk-for chronic obstructive pulmonary disease (COPD), Global Initiative for Chronic Obstructive Lung Disease (GOLD 0), or with mild-to-moderate (GOLD 1-2) COPD. We trained multiple models to predict rapid FEV1 decline using demographic, clinical and radiologic biomarker data. Training and internal validation data were obtained from the COPDGene study and prediction models were validated against the SPIROMICS cohort. Methods: We used GOLD 0-2 participants (n = 3,821) from COPDGene (60.0 ± 8.8 years, 49.9% male) for variable selection and model training. Accelerated lung function decline was defined as a mean drop in FEV1% predicted of > 1.5%/year at 5-year follow-up. We built logistic regression models predicting accelerated decline based on 22 chest CT imaging biomarker, pulmonary function, symptom, and demographic features. Models were validated using n = 885 SPIROMICS subjects (63.6 ± 8.6 years, 47.8% male). Results: The most important variables for predicting FEV1 decline in GOLD 0 participants were bronchodilator responsiveness (BDR), post bronchodilator FEV1% predicted (FEV1.pp.post), and CT-derived expiratory lung volume; among GOLD 1 and 2 subjects, they were BDR, age, and PRMlower lobes fSAD. In the validation cohort, GOLD 0 and GOLD 1-2 full variable models had significant predictive performance with AUCs of 0.620 ± 0.081 (p = 0.041) and 0.640 ± 0.059 (p < 0.001). Subjects with higher model-derived risk scores had significantly greater odds of FEV1 decline than those with lower scores. Conclusion: Predicting FEV1 decline in at-risk patients remains challenging but a combination of clinical, physiologic and imaging variables provided the best performance across two COPD cohorts.

CT-based Machine Learning for Donor Lung Screening Prior to Transplantation.

Background: Assessment and selection of donor lungs remains largely subjective and experience based. Criteria to accept or decline lungs are poorly standardized and are not compliant with the current donor pool. Using ex vivo CT images, we investigated the use of a CT-based machine learning algorithm for screening donor lungs prior to transplantation. Methods: Clinical measures and ex-situ CT scans were collected from 100 cases as part of a prospective clinical trial. Following procurement, donor lungs were inflated, placed on ice according to routine clinical practice, and imaged using a clinical CT scanner prior to transplantation while stored in the icebox. We trained and tested a supervised machine learning method called dictionary learning , which uses CT scans and learns specific image patterns and features pertaining to each class for a classification task. The results were evaluated with donor and recipient clinical measures. Results: Of the 100 lung pairs donated, 70 were considered acceptable for transplantation (based on standard clinical assessment) prior to CT screening and were consequently implanted. The remaining 30 pairs were screened but not transplanted. Our machine learning algorithm was able to detect pulmonary abnormalities on the CT scans. Among the patients who received donor lungs, our algorithm identified recipients who had extended stays in the ICU and were at 19 times higher risk of developing CLAD within 2 years post-transplant. Conclusions: We have created a strategy to ex vivo screen donor lungs using a CT-based machine learning algorithm. As the use of suboptimal donor lungs rises, it is important to have in place objective techniques that will assist physicians in accurately screening donor lungs to identify recipients most at risk of post-transplant complications.

Quantitative CT Correlates with Local Inflammation in Lung of Patients with Subtypes of Chronic Lung Allograft Dysfunction.

Chronic rejection of lung allografts has two major subtypes, bronchiolitis obliterans syndrome (BOS) and restrictive allograft syndrome (RAS), which present radiologically either as air trapping with small airways disease or with persistent pleuroparenchymal opacities. Parametric response mapping (PRM), a computed tomography (CT) methodology, has been demonstrated as an objective readout of BOS and RAS and bears prognostic importance, but has yet to be correlated to biological measures. Using a topological technique, we evaluate the distribution and arrangement of PRM-derived classifications of pulmonary abnormalities from lung transplant recipients undergoing redo-transplantation for end-stage BOS (N = 6) or RAS (N = 6). Topological metrics were determined from each PRM classification and compared to structural and biological markers determined from microCT and histopathology of lung core samples. Whole-lung measurements of PRM-defined functional small airways disease (fSAD), which serves as a readout of BOS, were significantly elevated in BOS versus RAS patients (p = 0.01). At the core-level, PRM-defined parenchymal disease, a potential readout of RAS, was found to correlate to neutrophil and collagen I levels (p < 0.05). We demonstrate the relationship of structural and biological markers to the CT-based distribution and arrangement of PRM-derived readouts of BOS and RAS.

Improved detection of air trapping on expiratory computed tomography using deep learning.

BACKGROUND: Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression. OBJECTIVE: To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques. MATERIALS AND METHODS: Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model. RESULTS: QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach. CONCLUSION: The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients.