Incidence and Risk Factors for Pneumonitis Associated With Checkpoint Inhibitors in Advanced Non-Small Cell Lung Cancer: A Single Center Experience.

INTRODUCTION: Immune checkpoint inhibitor (ICI) pneumonitis causes substantial morbidity and mortality. Estimates of real-world incidence and reported risk factors vary substantially. METHODS: We conducted a retrospective review of 419 patients with advanced non-small cell lung cancer (NSCLC) who were treated with anti-PD-(L)1 with or without anti-CTLA-4 therapy. Clinical, imaging, and microbiological data were evaluated by multidisciplinary adjudication teams. The primary outcome of interest was grade ≥2 (CTCAEv5) pneumonitis. Clinicopathologic variables, tobacco use, cancer therapies, and preexisting lung disease were assessed for univariate effects using Cox proportional hazards models. We created multivariate Cox proportional hazards models to assess risk factors for pneumonitis and mortality. Pneumonitis, pneumonia, and progression were modeled as time-dependent variables in mortality models. RESULTS: We evaluated 419 patients between 2013 and 2021. The cumulative incidence of pneumonitis was 9.5% (40/419). In a multivariate model, pneumonitis increased the risk for mortality (HR 1.6, 95% CI, 1.0-2.5), after adjustment for disease progression (HR 1.6, 95% CI, 1.4-1.8) and baseline shortness of breath (HR 1.5, 95% CI, 1.2-2.0). Incomplete resolution was more common with more severe pneumonitis. Interstitial lung disease was associated with higher risk for pneumonitis (HR 5.4, 95% CI, 1.1-26.6), particularly in never smokers (HR 26.9, 95% CI, 2.8-259.0). CONCLUSION: Pneumonitis occurred at a high rate and significantly increased mortality. Interstitial lung disease, particularly in never smokers, increased the risk for pneumonitis.

Pneumonitis after immune checkpoint inhibitor therapies in patients with acute myeloid leukemia: A retrospective cohort study.

BACKGROUND: Immune checkpoint inhibitors (ICI), combined with hypomethylating agents, can be used to treat acute myeloid leukemia (AML), but this strategy results in a high rate of pneumonitis. The authors sought to determine risk factors for pneumonitis development and whether pneumonitis increased mortality. METHODS: The authors conducted a retrospective review of 258 AML patients who received ICI-containing regimens from 2016 to 2018. A multidisciplinary adjudication committee diagnosed pneumonia and pneumonitis by reviewing symptoms, imaging, microbiology, and response to therapies. To measure risk factors for pneumonitis and mortality, multivariate Cox proportional hazards models were constructed. Pneumonia, pneumonitis, and disease progression were modeled as a time-dependent variable and incorporated a standard risk set modifying variables into the models. RESULTS: Thirty patients developed pneumonitis (12%). Of these, 17 had partial or complete resolution, whereas 13 patients died from pneumonitis. Increasing age (hazard ratio [HR], 1.04 per year; 95% confidence interval [CI], 1.00-1.08), and baseline shortness of breath increased pneumonitis risk (HR, 2.51; 95% CI, 1.13-5.55). Female sex (HR, 0.33; 95% CI, 0.15-0.70) and increasing platelet count (HR, 0.52 per log-unit increase; 95% CI, 0.30-0.92) decreased pneumonitis risk. In adjusted models, ICI-related pneumonitis significantly increased mortality (HR, 2.84; 95% CI, 1.84-4.37). CONCLUSIONS: ICI-related pneumonitis occurs at a high rate in AML patients and increases mortality. LAY SUMMARY: Immune checkpoint inhibitors (ICIs) remove inhibitory signals that reduce T-cell function and allow T-cells to better attack cancer cells. In acute myeloid leukemia (AML), the effectiveness of ICIs is limited in part by inflammation of the lung, called pneumonitis. This study reviewed 258 patients with AML who received ICIs and identified 30 patients who developed pneumonitis, nearly half of whom died. Older age and baseline shortness of breath increased pneumonitis risk, whereas female sex and higher baseline platelet counts decreased pneumonitis risk. Pneumonitis increased mortality by nearly 3-fold. This work highlights the significant harm imposed by pneumonitis after ICI therapies.

Imaging of Lung Cancer Staging.

Lung cancer is a leading cause of cancer-related mortality worldwide. Imaging is integral in accurate clinical staging to stratify patients into groups to predict survival and determine treatment. The eighth edition of the tumor, node, and metastasis (TNM-8) staging system proposed by the International Association for the Study of Lung Cancer in 2016, accepted by both the Union for International Cancer Control and the American Joint Committee on Cancer, is the current standard method of staging lung cancer. This single TNM staging is used for all histologic subtypes of lung cancer, including nonsmall cell lung cancer, small cell lung cancer, and bronchopulmonary carcinoid tumor, and it addresses both clinical and pathologic staging. Familiarity with the strengths and limitations of imaging modalities used in staging, the nuances of TNM-8, its correct nomenclature, and potential pitfalls are important to optimize patient care. In this article, we discuss the role of computed tomography (CT) and positron emission tomography/CT in lung cancer staging, as well as current imaging recommendations pertaining to TNM-8.

18F-fluorodeoxyglucose positron emission tomography correlates with tumor immunometabolic phenotypes in resected lung cancer.

Enhanced tumor glycolytic activity is a mechanism by which tumors induce an immunosuppressive environment to resist adoptive T cell therapy; therefore, methods of assessing intratumoral glycolytic activity are of considerable clinical interest. In this study, we characterized the relationships among tumor 18F-fluorodeoxyglucose (FDG) retention, tumor metabolic and immune phenotypes, and survival in patients with resected non-small cell lung cancer (NSCLC). We retrospectively analyzed tumor preoperative positron emission tomography (PET) 18F-FDG uptake in 59 resected NSCLCs and investigated correlations between PET parameters (SUVMax, SUVTotal, SUVMean, TLG), tumor expression of glycolysis- and immune-related genes, and tumor-associated immune cell densities that were quantified by immunohistochemistry. Tumor glycolysis-associated immune gene signatures were analyzed for associations with survival outcomes. We found that each 18F-FDG PET parameter was positively correlated with tumor expression of glycolysis-related genes. Elevated 18F-FDG SUVMax was more discriminatory of glycolysis-associated changes in tumor immune phenotypes than other 18F-FDG PET parameters. Increased SUVMax was associated with multiple immune factors characteristic of an immunosuppressive and poorly immune infiltrated tumor microenvironment, including elevated PD-L1 expression, reduced CD57+ cell density, and increased T cell exhaustion gene signature. Elevated SUVMax identified immune-related transcriptomic signatures that were associated with enhanced tumor glycolytic gene expression and poor clinical outcomes. Our results suggest that 18F-FDG SUVMax has potential value as a noninvasive, clinical indicator of tumor immunometabolic phenotypes in patients with resectable NSCLC and warrants investigation as a potential predictor of therapeutic response to immune-based treatment strategies.

Crowdsourcing pneumothorax annotations using machine learning annotations on the NIH chest X-ray dataset.

Pneumothorax is a potentially life-threatening condition that requires prompt recognition and often urgent intervention. In the ICU setting, large numbers of chest radiographs are performed and must be interpreted on a daily basis which may delay diagnosis of this entity. Development of artificial intelligence (AI) techniques to detect pneumothorax could help expedite detection as well as localize and potentially quantify pneumothorax. Open image analysis competitions are useful in advancing state-of-the art AI algorithms but generally require large expert annotated datasets. We have annotated and adjudicated a large dataset of chest radiographs to be made public with the goal of sparking innovation in this space. Because of the cumbersome and time-consuming nature of image labeling, we explored the value of using AI models to generate annotations for review. Utilization of this machine learning annotation (MLA) technique appeared to expedite our annotation process with relatively high sensitivity at the expense of specificity. Further research is required to confirm and better characterize the value of MLAs. Our adjudicated dataset is now available for public consumption in the form of a challenge.

Refinement of estimates of mortality risk using the Radiologic Severity Index in hematologic malignancy patients with respiratory syncytial virus infection.

BACKGROUND: Immunocompromised hematologic malignancy (HM) patients experience high mortality after respiratory syncytial virus (RSV) lower respiratory tract infection (LRTI). We measured radiologic severity to determine whether it could improve the performance of 60-day mortality models based only upon immunodeficiency severity. METHODS: We studied 155 HM patients, including 84 hematopoietic cell transplant recipients, who developed RSV LRTI from 2001 to 2013. We measured immunodeficiency using lymphopenia (lymphocyte count <200 cells/mm3 ), Immunodeficiency Severity Index (ISI), and Severe Immunodeficiency (SID) criteria. Radiologic severity was measured by the Radiologic Severity Index (RSI, range 0-72) at time of LRTI (baseline-RSI) and peak severity (peak-RSI). Delta-RSI was defined as the difference between baseline-RSI and peak-RSI. We used logistic regression models to measure the association of immunodeficiency and RSI with 60-day all-cause mortality, and measured model discrimination using areas under the receiver-operating characteristics curves, calibration using Brier scores, and explained variance using pseudo-R2 values. RESULTS: Forty-one patients died within 60 days of RSV LRTI. Severe immunodeficiency was associated with higher mortality. Peak-RSI (odds ratio [OR] 1.06/point, 95% confidence interval [CI] 1.04-1.08), and delta-RSI (OR 1.07/point, 95% CI 1.05-1.10) were associated with 60-day mortality after RSV LRTI, but not baseline-RSI. Addition of peak-RSI or delta-RSI to baseline immunodeficiency improved the discrimination, calibration, and explained variance (P < 0.001) of 60-day mortality models. CONCLUSIONS: Although baseline immunodeficiency in HM patients helps predict 60-day mortality after RSV LRTI, mortality risk estimates can be further refined by also measuring LRTI progression using RSI. RSI is well-suited as a marker of LRTI severity in RSV infection.

Intermanufacturer Comparison of Dual-Energy CT Iodine Quantification and Monochromatic Attenuation: A Phantom Study.

Purpose To determine the accuracy of dual-energy computed tomographic (CT) quantitation in a phantom system comparing fast kilovolt peak-switching, dual-source, split-filter, sequential-scanning, and dual-layer detector systems. Materials and Methods A large elliptical phantom containing iodine (2, 5, and 15 mg/mL), simulated contrast material-enhanced blood, and soft-tissue inserts with known elemental compositions was scanned three to five times with seven dual-energy CT systems and a total of 10 kilovolt peak settings. Monochromatic images (50, 70, and 140 keV) and iodine concentration images were created. Mean iodine concentration and monochromatic attenuation for each insert and reconstruction energy level were recorded. Measurement bias was assessed by using the sum of the mean signed errors measured across relevant inserts for each monochromatic energy level and iodine concentration. Iodine and monochromatic errors were assessed by using the root sum of the squared error of all measurements. Results At least one acquisition paradigm per scanner had iodine biases (range, -2.6 to 1.5 mg/mL) with significant differences from zero. There were no significant differences in iodine error (range, 0.44-1.70 mg/mL) among the top five acquisition paradigms (one fast kilovolt peak switching, three dual source, and one sequential scanning). Monochromatic bias was smallest for 70 keV (-12.7 to 15.8 HU) and largest for 50 keV (-80.6 to 35.2 HU). There were no significant differences in monochromatic error (range, 11.4-52.0 HU) among the top three acquisition paradigms (one dual source and two fast kilovolt peak switching). The lowest accuracy for both measures was with a split-filter system. Conclusion Iodine and monochromatic accuracy varies among systems, but dual-source and fast kilovolt-switching generally provided the most accurate results in a large phantom. © RSNA, 2017 Online supplemental material is available for this article.

IASLC/ITMIG Staging System and Lymph Node Map for Thymic Epithelial Neoplasms.

Thymic epithelial neoplasms are rare malignancies that arise from the thymus and include thymoma, thymic carcinoma, and thymic neuroendocrine tumors. At least 15 different stage classifications have been proposed for thymic epithelial neoplasms and used to varying degrees in clinical practice, many of which have been constructed from small groups of patients. Traditionally, the Masaoka and Masaoka-Koga staging systems have been the schemes most commonly employed, and the latter has been recommended for use by the International Thymic Malignancy Interest Group (ITMIG). An official, consistent stage classification system has recently been recognized by the American Joint Committee on Cancer (AJCC) and the Union for International Cancer Control (UICC), which are responsible for defining stage classifications for neoplasms. To establish this stage classification system, the International Association for the Study of Lung Cancer (IASLC) and ITMIG amassed a large retrospective database and evaluated this group of cases to develop proposals for the eighth edition of the stage classification manuals. For this endeavor, IASLC provided funding and statistical analysis and ITMIG provided the involvement of the clinicians and researchers actively participating in the study of thymic epithelial neoplasms. To accomplish this, a Thymic Domain of the Staging and Prognostic Factors Committee (TD-SPFC) was established to formulate the rationale, methodology, and definitions of this tumor-node-metastasis (TNM) staging system, which is presented in this article. © RSNA, 2017.

ITMIG Classification of Mediastinal Compartments and Multidisciplinary Approach to Mediastinal Masses.

Division of the mediastinum into specific compartments is beneficial for a number of reasons, including generation of a focused differential diagnosis for mediastinal masses identified on imaging examinations, assistance in planning for biopsies and surgical procedures, and facilitation of communication between clinicians in a multidisciplinary setting. Several classification schemes for the mediastinum have been created and used to varying degrees in clinical practice. Most radiology classifications have been based on arbitrary landmarks outlined on the lateral chest radiograph. A new scheme based on cross-sectional imaging, principally multidetector computed tomography (CT), has been developed by the International Thymic Malignancy Interest Group (ITMIG) and accepted as a new standard. This clinical division scheme defines unique prevascular, visceral, and paravertebral compartments based on boundaries delineated by specific anatomic structures at multidetector CT. This new definition plays an important role in identification and characterization of mediastinal abnormalities, which, although uncommon and encompassing a wide variety of entities, can often be diagnosed with confidence based on location and imaging features alone. In other scenarios, a diagnosis may be suggested when radiologic features are combined with specific clinical information. In this article, the authors present the new multidetector CT-based classification of mediastinal compartments introduced by ITMIG and a structured approach to imaging evaluation of mediastinal abnormalities. ©RSNA, 2017.

Pulmonary Legionellosis in Oncologic Patients: Findings on Chest CT.

OBJECTIVE: The purpose of this study was to report the computed tomography (CT) findings of non-pneumophila Legionella pneumonia and to compare these CT findings to those caused by Legionella pneumophila in oncologic patients. METHODS: Chest CT scans of 34 oncologic patients with culture-proven Legionella infection (16 L. pneumophila and 18 non-pneumophila Legionella) were retrospectively reviewed. Radiologic checkpoints included consolidation, ground-glass opacities, cavitation, nodules, tree-in-bud opacities, septal thickening, pleural effusions, and adenopathy, as well as the halo, reversed halo, and bulging fissure signs. RESULTS: The most common imaging feature of Legionella pneumonia was consolidation, seen in 94% of patients. Ground-glass opacities were the next most common abnormality. The halo sign was present in 26% of patients, in both immunocompetent and immunosuppressed hosts. Most features occurred with similar frequency between L. pneumophila and non-pneumophila Legionella. CONCLUSIONS: Findings in L. pneumophila pneumonia and non-pneumophila Legionella pneumonia are similar but nonspecific. Airspace consolidation is almost always present; the halo sign is not uncommon.

Tuberous Sclerosis Complex: State-of-the-Art Review with a Focus on Pulmonary Involvement.

Tuberous sclerosis complex (TSC) is an autosomal-dominant neurocutaneous disease with high phenotypic variability. The incidence is approximately one in 5000-10,000 births. TSC is characterized by widespread hamartomas and benign or rarely malignant neoplasms affecting various organs, most commonly the brain, skin, retinas, kidneys, heart, and lungs. The wide range of organs affected reflects the roles of TSC1 and TSC2 genes in the regulation of cell proliferation and differentiation. Clinical diagnostic criteria are important because genetic testing does not identify the mutation in up to 25% of patients. Imaging is pivotal, as it allows a presumptive diagnosis of TSC and definition of the extent of the disease. Common manifestations of TSC include cortical tubers, subependymal nodules, white matter abnormalities, retinal abnormalities, cardiac rhabdomyoma, lymphangioleiomyomatosis (LAM), renal angiomyolipoma, and skin lesions. Pulmonary involvement consists of LAM and, less commonly, multifocal micronodular pneumocyte hyperplasia (MMPH), which causes cystic and nodular diseases, respectively. Recent reports indicate that pulmonary LAM is found by computed tomography in up to 35% of the female patients with TSC. MMPH is rare and may be associated with LAM or, less frequently, occurs as an isolated pulmonary manifestation in women with TSC. Dyspnea and pneumothorax are common clinical presentations of LAM, whereas MMPH is usually asymptomatic. The aim of this review is to describe the main clinical, imaging, and pathological aspects of TSC, with a focus on pulmonary involvement.

Multidetector CT evaluation of airway stents: what the radiologist should know.

Airway stents are increasingly used to treat symptomatic patients with obstructive tracheobronchial diseases who are not amenable to surgical resection or who have poor performance status, precluding them from resection. The most common conditions that are treated with tracheobronchial stents are primary lung cancer and metastatic disease. However, stents have also been used to treat patients with airway stenosis related to a variety of benign conditions, such as tracheobronchomalacia, relapsing polychondritis, postintubation tracheal stenosis, postoperative anastomotic stenosis, and granulomatous diseases. Additionally, airway stents can be used as a barrier method in the management of esophagorespiratory fistulas. Many types of stents are available from different manufacturers. Principally, they are classified as silicone; covered and uncovered metal; or hybrid, which are made of silicone and reinforced by metal rings. The advantages and disadvantages of each type of airway stent are carefully considered when choosing the most appropriate stent for each patient. Multidetector computed tomography plays an important role in determining the cause and assessing the location and extent of airway obstruction. Moreover, it is very accurate in its depiction of complications after airway stent placement.

Differentiating pericardial recesses from mediastinal adenopathy: potential pitfalls in oncological imaging.

In oncological imaging, staging with computed tomography (CT) is widely used to determine treatment. Misinterpretation of fluid in pericardial recesses as mediastinal adenopathy can lead to inaccurate clinical staging and inappropriate management. In this review, we describe normal pericardial anatomy and illustrate imaging features to differentiate fluid in pericardial sinuses and recesses from mediastinal adenopathy.

Lung cancer imaging.

Lung cancer remains the leading cause of cancer-related deaths in the US. Imaging plays an important role in the diagnosis, staging, and follow-up evaluation of patients with lung cancer. With recent advances in technology, it is important to update and standardize the radiological practices in lung cancer evaluation. In this article, the authors review the main clinical applications of different imaging modalities and the most common radiological presentations of lung cancer.

Fungal diseases mimicking primary lung cancer: radiologic-pathologic correlation.

A variety of fungal pulmonary infections can produce radiologic findings that mimic lung cancers. Distinguishing these infectious lesions from lung cancer remains challenging for radiologists and clinicians. In such cases, radiographic findings and clinical manifestations can be highly suggestive of lung cancer, and misdiagnosis can significantly delay the initiation of appropriate treatment. Likewise, the findings of imaging studies cannot replace the detection of a species as the aetiological agent. A biopsy is usually required to diagnose the infectious nature of the lesions. In this article, we review the clinical, histologic and radiologic features of the most common fungal infections that can mimic primary lung cancers, including paracoccidioidomycosis, histoplasmosis, cryptococcosis, coccidioidomycosis, aspergillosis, mucormycosis and blastomycosis.

Functional imaging with diffusion-weighted MRI for lung biopsy planning: initial experience.

BACKGROUND: The purpose of this study was to evaluate the usefulness of diffusion-weighted magnetic resonance imaging (DW-MRI) and positron emission tomography/computed tomography (PET/CT) in planning transthoracic CT-guided biopsies of lung lesions. METHODS: Thirteen patients with lung lesions suspicious for malignancy underwent CT-guided biopsy. Chest DW-MRI and apparent diffusion coefficient (ADC) calculation were performed to aid biopsy planning with fused images. MRI was indicated due to large heterogeneous masses, association with lung atelectasis/consolidation/necrosis, and/or divergent results of other biopsy type and histopathology versus clinical/radiological suspicion. Eight patients underwent PET/CT to identify appropriate areas for biopsy. RESULTS: Mean patient (n = 9 males) age was 59 (range, 30 to 78) years. Based on DW-MRI results, biopsies targeted the most suspicious areas within lesions. All biopsied areas showed higher DW signal intensity and lower ADCs (mean, 0.79 (range, 0.54 to 1.2) × 10(-3) mm2/s), suggesting high cellularity. In patients who underwent PET/CT, areas with higher 18-fluorodeoxyglucose concentrations (standard uptake value mean, 7.7 (range, 3.6 to 13.7)) corresponded to areas of higher DW signal intensity and lower ADCs. All biopsies yielded adequate material for histopathological diagnosis. CONCLUSIONS: Functional imaging is useful for lung biopsy planning. DW-MRI and PET/CT increase overall performance and enable the collection of adequate material for specific diagnosis.

Radiation dose reduction for CT lung cancer screening using ASIR and MBIR: a phantom study.

The purpose of this study was to reduce the radiation dosage associated with computed tomography (CT) lung cancer screening while maintaining overall diagnostic image quality and definition of ground-glass opacities (GGOs). A lung screening phantom and a multipurpose chest phantom were used to quantitatively assess the performance of two iterative image reconstruction algorithms (adaptive statistical iterative reconstruction (ASIR) and model-based iterative reconstruction (MBIR)) used in conjunction with reduced tube currents relative to a standard clinical lung cancer screening protocol (51 effective mAs (3.9 mGy) and filtered back-projection (FBP) reconstruction). To further assess the algorithms' performances, qualitative image analysis was conducted (in the form of a reader study) using the multipurpose chest phantom, which was implanted with GGOs of two densities. Our quantitative image analysis indicated that tube current, and thus radiation dose, could be reduced by 40% or 80% from ASIR or MBIR, respectively, compared with conventional FBP, while maintaining similar image noise magnitude and contrast-to-noise ratio. The qualitative portion of our study, which assessed reader preference, yielded similar results, indicating that dose could be reduced by 60% (to 20 effective mAs (1.6 mGy)) with either ASIR or MBIR, while maintaining GGO definition. Additionally, the readers' preferences (as indicated by their ratings) regarding overall image quality were equal or better (for a given dose) when using ASIR or MBIR, compared with FBP. In conclusion, combining ASIR or MBIR with reduced tube current may allow for lower doses while maintaining overall diagnostic image quality, as well as GGO definition, during CT lung cancer screening.

Prognostic value of tumor volume doubling time in lung-metastatic adenoid cystic carcinoma.

OBJECTIVES: Lung metastases in adenoid cystic carcinoma (ACC) usually have indolent growth and the optimal timing to start systemic therapy is not established. We assessed ACC lung metastasis tumor growth dynamics and compared the prognostic value of time to progression (TTP) and tumor volume doubling time (TVDT). METHODS: The study included ACC patients with ≥1 pulmonary metastasis (≥5 mm) and at least 2 chest computed tomography scans. Radiology assessment was performed from the first scan showing metastasis until treatment initiation or death. Up to 5 lung nodules per patient were segmented for TVDT calculation. To assess tumor growth rate (TGR), the correlation coefficient (r) and coefficient of determination (R2) were calculated for measured lung nodules. TTP was assessed per RECIST 1.1; TVDT was calculated using the Schwartz formula. Overall survival was analyzed using the Kaplan-Meier method. RESULTS: The study included 75 patients. Sixty-seven patients (89%) had lung-only metastasis on first CT scan. The TGR was overall constant (median R2 = 0.974). Median TTP and TVDT were 11.2 months and 7.5 months. Shorter TVDT (<6 months) was associated with poor overall survival (HR = 0.48; p = 0.037), but TTP was not associated with survival (HR = 1.02; p = 0.96). Cox regression showed that TVDT but not TTP significantly correlated with OS. TVDT calculated using estimated tumor volume correlated with TVDT obtained by segmentation. CONCLUSION: Most ACC lung metastases have a constant TGR. TVDT may be a better prognostic indicator than TTP in lung-metastatic ACC. TVDT can be estimated by single longitudinal measurement in clinical practice.

CT strain metrics allow for earlier diagnosis of bronchiolitis obliterans syndrome after hematopoietic cell transplant.

Bronchiolitis obliterans syndrome (BOS) after hematopoietic cell transplantation (HCT) is associated with substantial morbidity and mortality. Quantitative CT (qCT) can help diagnose advanced BOS meeting National Institutes of Health (NIH) criteria (NIH-BOS) but has not been used to diagnose early, often asymptomatic BOS (early BOS), limiting the potential for early intervention and improved outcomes. Using Pulmonary Function Tests (PFT) to define NIH-BOS, early BOS, and mixed BOS (NIH-BOS with restrictive lung disease) in patients from two large cancer centers, we applied qCT to identify early BOS and distinguish between types of BOS. Patients with transient impairment or healthy lungs were included for comparison. PFT were done at month 0, 6, and 12. Analysis was performed with association statistics, principal component analysis, conditional inference trees (CIT), and machine learning (ML) classifier models. Our cohort included 84 allogeneic HCT recipients -- 66 BOS (NIH-defined, early, or mixed) and 18 without BOS. All qCT metrics had moderate correlation with Forced Expiratory Volume in 1 second, and each qCT metric differentiated BOS from those without BOS (non-BOS) (P < 0.0001). CIT's distinguished 94% of participants with BOS versus non-BOS, 85% early BOS versus non-BOS, 92% early BOS versus NIH-BOS. ML models diagnosed BOS with area under the curve (AUC) 0.84 (95% confidence interval [CI] 0.74-0.94) and early BOS with AUC 0.84 (95% CI 0.69 - 0.97). Quantitative CT metrics can identify individuals with early BOS, paving the way for closer monitoring and earlier treatment in this vulnerable population.