Sandeep Bodduluri

Background: Chronic obstructive pulmonary disease (COPD) is characterized by airway remodeling, which may affect tracheal morphology. However, the relationship between tracheal morphometry and COPD severity, quality of life, functional capacity, and mortality remains poorly understood. Objective: To investigate the associations between CT-derived tracheal lumen eccentricity and clinical outcomes in COPD. Methods: We analyzed data from 8,383 participants in the multicenter COPDGene study. Tracheal lumen eccentricity (ε) was calculated at each cross-section using the major and minor axes lengths and deriving final value using the arithmetic mean across all tracheal slices, where ε = 0 represents a circle and ε > 0 indicates an ellipse. Baseline assessments included spirometry measurements, 6-minute walk distance (6MWD), St. George’s Respiratory Questionnaire (SGRQ), and the modified Medical Research Council (mMRC) dyspnea score. Longitudinal assessments included annualized lung function change and all-cause mortality. Multivariable models were used to evaluate associations between tracheal eccentricity and clinical outcomes. Results: Tracheal eccentricity increased with severity of airflow obstruction (0.60±0.07, 0.61±0.07, 0.62±0.07, 0.64±0.08, and 0.64±0.08 in GOLD stages 0 through 4, respectively). Higher tracheal eccentricity was independently associated with lower FEV ₁ (β = −0.30 L, 95% CI: −0.47 to −0.14, p1 /FVC (β = −0.06, 95% CI: −0.09 to −0.04, p<0.001), lower 6MWD (β = −15.7 m, 95% CI: −25.2 to −6.2, p=0.001), higher SGRQ score (β = 16.9, 95% CI: 11.2 to 22.5, p<0.001), higher mMRC dyspnea score (β = 0.4, 95% CI: 0.1 to 0.6, p=0.007), and accelerated lung function decline (β = −23.8 ml/year, 95% CI: −2.48 to −45.13, p=0.029). Increased tracheal eccentricity is associated with increased all-cause mortality (adjusted HR: 1.81 [95% CI, 1.01-3.26]; p = 0.047). Conclusions: These findings suggest that tracheal morphology may serve as an imaging biomarker for COPD outcomes, supported by significant associations with lower quality of life, lung function decline, and all-cause mortality.

Rationale: Conventional CT-derived pulmonary vascular metrics quantify vascular pruning but do not assess spatial heterogeneity of vascular architecture. In COPD, peripheral microvascular pruning coexists with compensatory central vessel dilation, paradoxically preserving total vessel volume while reducing effective vascular penetration into lung parenchyma. Objectives: To develop and validate Vascular Proximity Coverage (VPC), a novel distance-based CT biomarker quantifying spatial efficiency of pulmonary vascular distribution. Methods: This retrospective analysis included 7,881 COPDGene participants with complete vascular segmentations. VPC is estimated by integrating the area under the cumulative lung tissue coverage curve at distances 0–10 mm from segmented vessel voxels. Multivariable models were used to assess associations with lung function, six-minute walk distance (6MWD), St. George’s Respiratory Questionnaire (SGRQ), mMRC dyspnea score and all-cause mortality adjusting for demographics, smoking, emphysema, scanner type, and BV5. We stratified the cohort into four groups defined by the median values of BV5 and VPC, yielding discordant (high-BV5/low-VPC, low-BV5/high-VPC) and concordant (high/high, low/low) vascular phenotypes. Results: VPC declined across disease severity (5.82 ± 0.50 in non-smokers to 5.21 ± 0.64 in GOLD 4; p5 ) and total vessel volume, quantify the amount of visible vasculature but do not assess how effectively vessels reach the lung parenchyma for efficient gas exchange. In COPD, peripheral microvascular pruning commonly coexists with compensatory central vessel dilation, leading to preserved or increased total vascular volume despite compromised functional vascular distribution. What This Study Adds to the Field: Vascular Proximity Coverage (VPC) is a novel distance-based CT biomarker that quantifies the spatial efficiency of pulmonary vascular distribution by measuring cumulative lung tissue coverage across distances from vessel walls. In 7,881 COPDGene participants, including non-smokers and PRISm subjects, lower VPC was independently associated with decreased lung function, reduced exercise capacity, worsened quality of life, and increased all-cause mortality over a median 10.8-year follow-up after adjusting for BV ₅ and emphysema. VPC identified a high-risk phenotype with preserved vessel volume but impaired distribution (high-BV5/low-VPC) that carried 24% increased mortality risk and detected subclinical vascular dysfunction in smokers with normal spirometry.

Shrinks a failing R script to the smallest subset of statements that still triggers the same error, using the delta debugging algorithm of Zeller and Hildebrandt (2002) . Each candidate reduction is evaluated in a separate R process, so dependencies between statements and their side effects are respected. The result is a one-minimal example, in which removing any remaining statement makes the error disappear; this is the form most useful for bug reports and for questions on community forums. When no statement can be removed, because the failure is nested inside a function body, reduction continues within the surviving statements. A general delta debugging routine and a helper for reducing data frames to the rows that reproduce a failure are also provided.

BACKGROUND: Nontuberculous mycobacterial lung disease (NTM-LD) is highly heterogenous, geographically and etiologically, hindering effective timely identification. Prior CT radiomics studies require manual segmentation of pathology. We developed a whole-lung CT radiomics-based machine learning approach and identified common features across two geographically distinct NTM-LD cohorts. STUDY DESIGN AND METHODS: 1,300 chest CT scans from China (871 TB; 429 NTM, Dataset 1) and 173 independent NTM cohort from UAB, US. Whole-lung regions were automatically segmented on each scan, and 85 quanti-tative radiomic features were extracted using a standardized image-processing pipeline. We eval-uated two frameworks to assess model performance and generalizability: (1) training on Dataset 1 with external validation on Dataset 2, and (2) training on the combined cohort. Linear discriminant analysis (LDA) was used as the primary classification method. Cross-cohort concordance analysis was performed to evaluate the reproducibility of radiomic features across datasets. RESULTS: In Scenario 1, the LDA classifier trained on Dataset 1 achieved an AUC of 0.79 (95% CI, 0.73–0.84) with high specificity (0.91). On the external UAB cohort, the model achieved an AUC of 0.94 (95% CI, 0.90–0.97). In Scenario 2, the combined cohort model achieved an AUC of 0.81 (95% CI, 0.76–0.85) with improved sensitivity (0.61) and precision (0.82). Feature importance analysis identified 16 features consistently ranked among the top 20 in both scenarios, predominantly texture-based descriptors reflecting distinct parenchymal patterns between myco-bacterial species. CONCLUSION: Whole-lung CT radiomics enables interpretable NTM-LD classification across geographically dis-tinct populations without manual annotation. Suggesting population-independent parenchymal signatures of NTM-LD.

Optimizing radiotherapy dose distributions remain a resource-intensive bottleneck. Existing AI-based dose prediction methods often have limited generalizability because they rely on small, heterogeneous datasets. We present nnDoseNetv2, an auto-configured, end-to-end framework for dose prediction across diverse disease sites (head and neck, prostate, breast, and lung), prescription levels (1.5–84 Gy), and treatment modalities (IMRT, VMAT, and 3D-CRT). By integrating machine-specific beam geometry with 3D structural information, the framework is designed to generalize across varied clinical scenarios. A single multi-site model was trained on 1,000 clinical plans. On sites seen during training, performance was comparable to specialized site-specific models. On unseen sites (liver and whole brain), the model outperformed site-specific models, with mean absolute errors of 2.46% and 6.97% of prescription, respectively. These results suggest that geometric awareness can bridge disparate anatomical domains while eliminating the need for site-specific model maintenance, providing a scalable and high-fidelity approach for personalized radiotherapy planning.

Background: Approximately 70% of adults with chronic obstructive pulmonary disease (COPD) remain undiagnosed. Opportunistic screening using chest computed tomography (CT) scans, commonly acquired in clinical practice, may be used to improve COPD detection through simple, clinically applicable deep-learning models. We developed a lightweight, convolutional neural network (COPDxNet) that utilizes minimally processed chest CT scans to detect COPD. Methods: We analyzed 13,043 inspiratory chest CT scans from the COPDGene participants, (9,675 standard-dose and 3,368 low-dose scans), which we randomly split into training (70%) and test (30%) sets at the participant level to no individual contributed to both sets. COPD was defined by postbronchodilator FEV /FVC < 0.70. We constructed a simple, four-block convolutional model that was trained on pooled data and validated on the held-out standard- and low-dose test sets. External validation was performed using standard-dose CT scans from 2,890 SPIROMICS participants and low-dose CT scans from 7,893 participants in the National Lung Screening Trial (NLST). We evaluated performance using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, Brier scores, and calibration curves. Findings: On COPDGene standard-dose CT scans, COPDxNet achieved an AUC of 0.92 (95% CI: 0.91 to 0.93), sensitivity of 80.2%, and specificity of 89.4%. On low-dose scans, AUC was 0.88 (95% CI: 0.86 to 0.90). When the COPDxNet model was applied to external validation datasets, it showed an AUC of 0.92 (95% CI: 0.91 to 0.93) in SPIROMICS and 0.82 (95% CI: 0.81 to 0.83) on NLST. The model was well-calibrated, with Brier scores of 0.11 for standard- dose and 0.13 for low-dose CT scans in COPDGene, 0.12 in SPIROMICS, and 0.17 in NLST. Interpretation: COPDxNet demonstrates high discriminative accuracy and generalizability for detecting COPD on standard- and low-dose chest CT scans, supporting its potential for clinical and screening applications across diverse populations.

Importance: Obtaining spirometry requires repeated testing and using the maximal values based on quality control criteria. Whether the suboptimal efforts are useful for the prediction of respiratory outcomes is not clear. Objective: To determine whether a machine learning model could predict respiratory outcomes and mortality based on suboptimal spirometry. Design: Observational cohorts (UK Biobank and COPDGene). Setting: Multi-center; population, and disease-enriched. Participants: UK aged 40-69; US aged 45-80, >10 pack-years smoking, without respiratory diseases other than COPD or asthma. Exposures: Raw spirograms (volume-time). Main outcomes and measures: To create a combined representation of lung function we implemented a contrastive learning approach, Spirogram-based Contrastive Learning Framework (Spiro-CLF), which utilized all recorded volume-time curves per participant and applied different transformations (e.g. flow-volume, flow-time). We defined “maximal” efforts as those passing quality control (QC) with the maximum FVC; all other efforts, including submaximal and QC-failing efforts, were defined as “suboptimal”. We trained the Spiro-CLF model using both maximal and suboptimal efforts from the UK Biobank. We tested the model in a held-out 20% testing UK Biobank subset and COPDGene, on 1) binary predictions of FEV1/FVC <0.7, and FEV1 Percent Predicted (FEV1PP) <80%, 2) Cox regression for all-cause mortality, and 3) prediction of respiratory phenotypes. Results: We trained Spiro-CLF on 940,705 volume-time curves from 352,684 UKB participants with 2-3 spirometry efforts per individual (66.7% with 3 efforts) and at least one QC-passing spirometry effort. Of all spirometry efforts, 61.6% were suboptimal (37.5% submaximal and 24.1% QC-failing). In the UK Biobank, Spiro-CLF using QC-failing and submaximal efforts predicted FEV1/FVC < 0.7 with an Area under the Receiver Operating Characteristics (AUROC) of 0.956, mortality with a concordance index of 0.647, and asthma with a 9-42% improvement versus baseline models. In COPDGene (n=10,110 participants), adding QC-passing, submaximal efforts did not improve the prediction of lung function or mortality; however, Spiro-CLF representations predicted asthma and respiratory phenotypes (joint test P ≤ 2 × 10−3). Conclusions and Relevance: A machine-learning model can predict respiratory phenotypes using suboptimal spirometry; results from all spirometry efforts may contain valuable data. Additional studies are required to determine performance and utility in specific clinical scenarios.

The new CT metric PiSlope quantified the amount of remodeling along the entire visualized airway and was associated with dyspnea, quality of life, functional capacity, exacerbations, lung function decline, and mortality.