Bartholmai, Brian J.

Abstract Rationale In fungal endemic regions, differentiating benign from malignant pulmonary nodules on CT scans remains a major diagnostic challenge. Coccidioides nodules frequently resemble malignant lesions on CT and PET imaging, presenting significant challenges for differentiation, even among radiologists. Consequently, the benign biopsy and resection rate, especially in the Southwestern US, remains high. We previously developed [DOI:10.1371/journal.pone.0196910] and externally validated [DOI:10.1183/13993003.02485-2020] the Benign versus aggRessive nODule Evaluation using Radiomic Stratification (BRODERS) machine learning (ML) classifier to non-invasively distinguish between benign and malignant pulmonary nodules with an AUC of 0.87. However, its performance in certain benign nodules with malignant surface and texture characteristics like in coccidioidomycosis had a suboptimal AUC of 0.65. In this study, we redesigned our radiomics model by including numerous clinical features. Methods In this retrospective study, 113 pulmonary nodules (66 Coccidioides and 47 adenocarcinoma spectrum) detected on CTs with ground truth pathology diagnosis were identified by screening for key terms like “nodule”, “cocci”, and “adenocarcinoma” from both CT and pathology reports using a large language model trained on clinical textual data (Illuminate®). Clinical features such as demographics, smoking history, and laboratory studies were extracted by trained clinicians from the electronic medical record. All nodules were segmented and radiomic features extracted using a semi-automated seed growing algorithm previously described [DOI: 10.1097/JTO.0b013e3182843721]. The database was randomly split into an 80%-20% development and hold-out set prior to ML modeling. Feature selection for variables was conducted utilizing Elastic Net Regression, which provides a balanced approach between Lasso and Ridge regression. A logistic regression model was developed using the selected features and ground truth information of the training cohort. The true performance of the model was tested on the hold-out set. Results 160 radiomics and 22 clinical features were extracted. Elastic Net regression identified 44 features that contributed the most. Some of these clinical features include presence of satellite lesions, smoking history, and presence of positive IgG coccidiomycosis serology. The AUC of the ROC curve for the hold-out test set was 0.86. Conclusions The clinical features of significance that emerged during multimodal modeling are explainable. Designing explainable ML models is important, especially in the Southwestern US where Coccidioides nodules can appear to be malignant to both human experts and ML models. Although coccidioidomycosis serologies alone lack sensitivity and specificity to diagnose Coccidioides nodules, integrating them with a multimodal ML model can improve differentiation between benign Coccidioides and malignant adenocarcinoma nodules. This abstract is funded by: None

Abstract Rationale Interstitial lung disease (ILD) affects ∼50% of patients with systemic sclerosis (SSc) and is a leading cause of mortality. Visual assessment of ILD extent and morphologies, including ground-glass opacities (GGO) and reticular densities (RD), suffers from poor interobserver agreement, limiting prognostic consistency. CALIPER Quantitative CT (QCT) provides reproducible volumetric measures of parenchymal and vascular features. This study evaluated baseline QCT-derived lung features for association with transplant/mortality risk in SSc-ILD. Methods A retrospective cohort of SSc patients (≥18 years) seen at an academic center from 2007-2018 was identified using ICD codes, with ACR/EULAR 2013 SSc criteria confirmed by chart review. Inclusion required ILD on high-resolution CT (HRCT) ±2 years of SSc diagnosis, and PFTs ±6 months of HRCT. CALIPER quantified volumes of normal lung, GGO, RD, hyperlucency, honeycombing (HC), and pulmonary vascular-related structures (PVRS), which are expressed as percentages of total lung volume. Right heart catheterization confirmed pulmonary hypertension (PH) defined by 2022 ESC/ERS criteria (Eur Heart J, 2022). Cox hazards models assessed associations with combined mortality/transplant outcome, a priori adjusted for age, sex, diffuse SSc subtype, ILD duration, and PH (Column B), and further adjusted for baseline percent predicted FVC (ppFVC) and ppDLCO (Column C)(Table 1). Results Of 132 SSc-ILD patients, median SSc and ILD disease durations at HRCT were 1.4 (0.6, 2.4) and 0.0 (0.0, 0.5) years. Median feature percentages: total ILD 13.0% (IQR: 6.4, 21.0), GGO 10.2% (4.6, 16.9), RD 1.9% (0.8, 3.7), HC 0.03% (0.00, 0.09), PVRS 3.2% (2.3, 4.1). Median ppFVC was 81.1% (69.4, 92.6), and ppDLCO 60.0% (46.0, 75.7); 21 patients had PH. There were 2 transplants and 45 deaths. Every 5% increase in baseline total ILD and GGO associated with 22% (HR 1.22; 95% CI 1.12-1.33) and 24% (1.24; 1.12-1.36) higher risk of transplant/mortality on unadjusted models (Column A), respectively, remaining significant after a priori (CB) and full adjustment (CC)(Table 1). Every 1% increase in RD and PVRS conferred 19% (1.19; 1.08-1.31) and 33% (1.33; 1.08-1.63) higher risk of transplant/mortality in unadjusted models (CA); RD retained significance after a priori adjustment (1.17; 1.03-1.33), while PVRS trended non-significant in adjusted models. Conclusions In early SSc-ILD, QCT-derived GGO, RD, and PVRS provide robust prognostic value for mortality/transplant risk assessment, with small increases in baseline severity—at or below visual detection thresholds—associating with clinically meaningful risk increases. These findings support integrating baseline QCT biomarkers into risk stratification beyond clinical and PFT measures. This abstract is funded by: Rheumatology Research Foundation

Introduction Bronchoscopic lung volume reduction with endobronchial valves (EBV) is an effective procedure for patient with severe emphysema to improve lung function, exercise tolerance, dyspnoea and quality of life. Optimisation of patient and treatment lobe selection is essential for successful EBV outcomes. While clinical selection criteria are rigorous, many centres use a multidisciplinary team and rely on previous clinical experience for the selection process. To aid objective clinical decision making, we present a mathematical model to facilitate patient and target lobe selection. Methods A multidisciplinary team reviewed quantitative high-resolution computed tomography (HRCT) analysis from 119 patients to select candidates for EBV and to select a treatment lobe. Two logistic regression models, (1) candidacy for EBV placement and (2) target-lobe selection, were developed based on the normalised distributions of the four quantitative HRCT variables (fissure completeness score, per cent of voxel density with HU < −910 and HU < −950, and lobar volumes) across all five lung lobes. An external cohort of 50 patients (25 candidates and 25 non-candidates) was used to validate the prediction model. Results Performance measures of the training cohort demonstrated an area under the curve (AUC) of 0.91, accuracy of 81%, sensitivity of 93% and specificity of 78% compared with the multidisciplinary teams’ target lobe selection. The validation cohort demonstrated an AUC of 0.89, accuracy of 84%, sensitivity of 88% and specificity of 83% compared with the multidisciplinary team decision making. Conclusions Endobronchial valve lung volume reduction remains a potent palliative measure to improve quality of life in patients with hyperinflated emphysema. Our model for target lobe selection harnesses the multidisciplinary experience at a tertiary care centre to objectively select candidates and target lobes to assist clinicians’ decision making. Future studies investigating prediction of lobar collapse and functional improvement after target lobe selection using our model are needed.

Abstract Rationale Immune checkpoint inhibitors (ICI) have become standard care for many cancers. Their mechanism of action mediates immune related adverse events including ICI pneumonitis. Diagnosis of this is difficult to differentiate from infectious and radiation pneumonitis as it is a diagnosis of exclusion often requiring bronchoscopy and imaging interpreted by expert radiologists. This study investigates the use of CALIPER, a computer-aided lung informatics program, in identifying differences between Computed Tomography (CT) patterns in ICI, radiation, and infectious pneumonitis that may aid in diagnosis noninvasively. Methods CT images of ten patients with ICI pneumonitis, ten patients with infectious pneumonitis, and nine patients with radiation pneumonitis, all diagnosed by clinical expertise and evaluation with bronchoalveolar lavage, were analyzed with CALIPER. CALIPER classified each CT voxel into either vessel-related structures (VRS), normal, mild low-attenuation area (LAA), moderate LAA, severe LAA, reticular (R), honeycomb (HC) or ground-glass (GG) features. Each lung was divided into upper, middle, and lower lobes. Exploratory analyses explored the relationship between CALIPER components and diagnosis, comparing ICI and radiation pneumonitis with infectious pneumonitis. Diagnosis was analyzed using multinomial logistic regression adjusted for presence of pleural effusion. Additionally, diagnosis was assessed as infectious versus a pooled group of radiation and ICI pneumonitis and analyzed using logistic regression adjusted for pleural effusion. Due to the exploratory nature of analysis, no correction was applied for multiplicity of testing. Results Twenty-nine patients were analyzed. ICI pneumonitis patients had less moderate low attenuation in the left upper (p = 0.016) and middle peripheral lung (p = 0.038), and radiation pneumonitis patients had less moderate low attenuation in the left upper peripheral lung (p = 0.031). When comparing the pooled group of ICI and radiation pneumonitis images with infectious pneumonitis, there was more moderate LAA in left upper (0.012) and middle (0.034) peripheral lung in the pooled group compared to infectious pneumonitis. There was no association with VRS, GG, HC, R, mild, or severe LAA patterns. Conclusions Although areas of moderate low attenuation were more prevalent for infectious pneumonitis, these results taken in the context of low sample size, exploratory analysis, and lack of clinical reasoning to support these findings make them likely insignificant. Based on this limited exploratory analysis, it is unlikely that we can solely use CALIPER as noninvasive evaluation to differentiate radiation and ICI pneumonitis from infectious pneumonitis. This highlights the need for a more robust program to aid in noninvasive diagnosis.

Abstract Rationale Stereotactic body radiation therapy (SBRT) represents an effective therapeutic strategy for early-stage non–small cell lung cancer (NSCLC); however, local and systemic recurrences represent ongoing challenges. Computed tomography (CT) radiomics-based risk models can potentially be used to predict the risk of local recurrence on pretreatment CT scans. Objective Development of a radiomics model to predict local recurrence after SBRT in patients with NSCLC. Methods This single-institution study includes a retrospective case-control training set (20 patients with local recurrence and 40 control subjects) and an independent validation set (198 consecutive cases) of patients with early-stage NSCLC treated with SBRT. Tumors were semiautomatically segmented, and 102 quantitative radiomic features, including texture, landscape, spatial, nodule shape, and nodule surface features, were extracted. These features were included in three separate multivariable models to predict the risk of recurrence on the basis of pre-SBRT, post-SBRT, and the difference between the pre-SBRT and post-SBRT scans (Delta model). The pre-SBRT model was subsequently validated in an independent validation set. Results Thirteen independent variables were selected for the models using the Boruta algorithm. The sensitivity, specificity, and area under the curve of the pre-SBRT, post-SBRT, and Delta models were 85%, 90%, and 0.91; 85%, 92.5%, and 0.92; and 85%, 92.5%, and 0.94, respectively. The pre-SBRT model was validated in the independent validation set (area under the curve, 0.89; confidence interval, 0.83–0.92), because this model was believed to be the most useful to assist in individualized treatment planning. Conclusions Radiomic analysis facilitated the development of three high-performing models predicting local recurrence using either pre-SBRT CT, post-SBRT CT, or the change between these two. We successfully validated the most clinically relevant model, the pre-SBRT model. Although this model needs further validation, it may facilitate individualized surveillance, treatment planning, and selection of adjuvant therapy.

ABSTRACT Background Several hematological and biochemical parameters have been related to the COVID‐19 infection severity and outcomes. However, less is known about clinical indicators reflecting lung involvement of COVID‐19 patients at hospital admission. Computed tomography (CT) represents an established imaging tool for the detection of lung injury, and the quantitative analysis software CALIPER has been used to assess lung involvement in COVID‐19 patients. Herein, the relationship between the lung involvement expressed by CALIPER interstitial lung disease (ILD) percentage and a set of blood parameters related to tissue oxygenation and damage in COVID‐19 patients at hospital admission was evaluated. Methods We performed a retrospective and a prospective study involving 321 and 75, respectively, COVID‐19‐positive patients recruited from Pisa University Hospital. The association between CALIPER ILD percentages and selected blood parameters was investigated by a regression tree approach, after multiple imputations of the dataset missing values. Results High serum lactate dehydrogenase (LDH) values appeared to be predictive of high CALIPER ILD percentages at hospital admission in both retrospective and prospective datasets, even if the predictive performance of the algorithm was not optimal. Conclusions LDH levels could be evaluated as a tool for early identification of COVID‐19 patients at risk of extensive lung injury, as well as in fast screening procedures before hospitalization.

Abstract Background: Tracheobronchomalacia (TBM) presents diagnostic challenges due to its nonspecific symptoms and variability in diagnostic methods. This study evaluates physician concordance in TBM diagnosis and phenotyping using chest computed tomography (CT) scans with dynamic expiratory views. Methods: We conducted a retrospective cross-sectional study at Mayo Clinic Rochester, analyzing 150 patients with dynamic expiratory CT scans. Three specialists—a thoracic radiologist, a bronchoscopist, and a pulmonologist—reviewed identical CT scans, blinded to prior interpretations. Inter-rater agreement was assessed using Fleiss's Kappa for TBM diagnosis and Cohen's Kappa for TBM phenotype classification into six categories: No TBM, Excessive Dynamic Airway Collapse (EDAC), Crescent Type, Circumferential Type, Saber-Sheath Type, and Mixed Type. Results: Among the 150 patients, 54 (36%) were diagnosed with TBM or EDAC. TBM was more prevalent in males, older individuals, and smokers. Agreement among specialists was substantial for TBM diagnosis (Fleiss’s Kappa = 0.61, p < 0.001) but moderate for phenotype classification (Fleiss’s Kappa = 0.52, p < 0.001). The highest concordance was between the thoracic radiologist and the pulmonologist (Cohen's Kappa = 0.68), while the lowest was between the bronchoscopist and other specialists. Conclusion: There is substantial agreement in TBM diagnosis using chest CT scans with dynamic expiratory views, but moderate variability in phenotyping. Standardizing criteria and integrating pulmonary function testing could enhance diagnostic consistency and clinical relevance.

Objectives: To investigate the relationship between COVID-19 pneumonia outcomes and three chest CT analysis approaches. Methods: Patients with COVID-19 pneumonia who underwent chest CT were included and divided into survivors/non-survivors and intubated/not-intubated. Chest CTs were analyzed through a (1) Total Severity Score visually quantified by an emergency (TSS1) and a thoracic radiologist (TSS2); (2) density mask technique quantifying normal parenchyma (DM_Norm 1) and ground glass opacities (DM_GGO1) repeated after the manual delineation of consolidations (DM_Norm2, DM_GGO2, DM_Consolidation); (3) texture analysis quantifying normal parenchyma (TA_Norm) and interstitial lung disease (TA_ILD). Association with outcomes was assessed through Chi-square and the Mann–Whitney test. The TSS inter-reader variability was assessed through intraclass correlation coefficient (ICC) and Bland–Altman analysis. The relationship between quantitative variables and outcomes was investigated through multivariate logistic regression analysis. Variables correlation was investigated using Spearman analysis. Results: Overall, 192 patients (mean age, 66.8 ± 15.4 years) were included. TSS was significantly higher in intubated patients but only TSS1 in survivors. TSS presented an ICC of 0.83 (0.76; 0.88) and a bias (LOA) of 1.55 (−4.69, 7.78). DM_Consolidation showed the greatest median difference between survivors/not survivors (p = 0.002). The strongest independent predictor for mortality was DM_Consolidation (AUC 0.688), while the strongest independent predictor for the intensity of care was TSS2 (0.7498). DM_Norm 2 was the singular feature independently associated with both the outcomes. DM_GGO1 strongly correlated with TA_ILD (ρ = 0.977). Conclusions: The DM technique and TA achieved consistent measurements and a better correlation with patient outcomes.

Three-dimensional reconstruction of airways has shown increased luminal area in patients with COVID-19 and post-acute sequelae of COVID-19 when compared with healthy controls. These findings suggest the role of large conducting airways in the pathogenesis of post-acute sequelae of COVID 19.

Abstract Rationale Although many studies have examined gene expression in lung tissue, the gene regulatory processes underlying emphysema are still not well understood. Finding efficient nonimaging screening methods and disease-modifying therapies has been challenging, but knowledge of the transcriptomic features of emphysema may help in this effort. Objectives Our goals were to identify emphysema-associated biological pathways through transcriptomic analysis of bulk lung tissue, to determine the lung cell types in which these emphysema-associated pathways are altered, and to detect unique and overlapping transcriptomic signatures in blood and lung samples. Methods Using RNA-sequencing data from 446 samples in the Lung Tissue Research Consortium and 3,606 blood samples from the COPDGene study, we examined the transcriptomic features of chest computed tomography–quantified emphysema. We also leveraged publicly available lung single-cell RNA-sequencing data to identify cell types showing chronic obstructive pulmonary disease–associated differential expression of the emphysema pathways found in the bulk analyses. Measurements and Main Results In the bulk lung RNA-sequencing analysis, 1,087 differentially expressed genes and 34 dysregulated pathways were significantly associated with emphysema. We observed alternative splicing of several genes and increased activity in pluripotency and cell barrier function pathways. Lung tissue and blood samples shared differentially expressed genes and biological pathways. Multiple lung cell types displayed dysregulation of epithelial barrier function pathways, and distinct pathway activities were observed among various macrophage subpopulations. Conclusions This study identified emphysema-related changes in gene expression and alternative splicing, cell type–specific dysregulated pathways, and instances of shared pathway dysregulation between blood and lung.