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.

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.