Objective.Deep learning has demonstrated strong potential for magnetic resonance imaging (MRI) reconstruction. However, conventional supervised learning requires high-quality, high-signal-to-noise-ratio (SNR) reference data for network training, which are often difficult or impossible to obtain, particularly in low-field MRI. Self-supervised learning (SSL) eliminates the need for reference training data but may suffer from degraded performance under low-SNR conditions. To address these limitations, we propose hybrid learning, a new training framework that integrates self-supervised and supervised learning for joint MRI reconstruction and denoising when only low-SNR training data are available.Approach.Hybrid learning is implemented in two sequential stages. In the first stage, SSL is applied to fully sampled low-SNR data to generate higher-quality pseudo-references. In the second stage, these pseudo-references are then used as targets for supervised learning to reconstruct and denoise undersampled, noisy data. The proposed method was evaluated in four experiments using simulated and real noisy MRI data of the breast, lung, and brain across different field strengths (0.3 T to 3 T), sampling trajectories (Cartesian, spiral, and radial), noise levels, and undersampling ratios.Main Results.Hybrid learning consistently improved reconstruction quality relative to both supervised and self-supervised baselines under different acceleration rates, noise levels, and sampling patterns in all experiments. Compared with standard supervised learning using noisy references, it achieved up to 167.70% higher structural similarity index measure (SSIM), 95.41% lower normalized mean squared error (NMSE), and 90.70% lower high-frequency error norm (HFEN). Compared with standard SSL, it achieved up to 23.88% higher SSIM, 60.85% lower NMSE, and 49.13% lower HFEN.Significance.Hybrid learning enables improved MRI reconstruction under low-SNR imaging conditions by jointly addressing noise and undersampling. It provides a practical solution for robust deep learning-based reconstruction and is particularly well suited for applications such as low-field MRI, where image quality is limited by reduced SNR.

PURPOSE:To improve 0.55T T2-weighted PROPELLER lung MRI by developing a self-supervised framework for joint reconstruction and denoising. METHODS:T2-weighted 0.55T lung MRI datasets from 44 patients with prior COVID-19 infection were used. Each PROPELLER blade was split along the readout direction into two disjoint subsets: one subset for training an unrolled network, and the other for loss calculation. Following the Noise2Noise paradigm, this framework split k-space into two subsets with independent, matched noise but identical underlying signal, enabling joint reconstruction and denoising without external training references. For comparison, coil-wise Marchenko-Pastur Principal Component Analysis (MPPCA) denoising followed by parallel imaging reconstruction was performed. The reconstructed images were evaluated by two experienced chest radiologists. RESULTS:The self-supervised model generated lung images with improved clarity, better delineation of parenchymal and airway structures, and maintained high fidelity in cases with available CT references. In addition, the proposed framework also enabled further reduction of scan time by reconstructing images with adequate diagnostic quality from only half the number of blades. The reader study confirmed that the proposed method outperformed MPPCA across all categories (Wilcoxon signed-rank test, p < 0.001), with moderate inter-reader agreement (weighted Cohen's kappa = 0.55; percentage of exact and within ±1 point agreement = 91%). CONCLUSION:By leveraging the intrinsic data redundancy in PROPELLER sampling and extending the Noise2Noise concept, the proposed self-supervised framework enabled simultaneous reconstruction and denoising of lung images at 0.55T to address the low-SNR challenge at low-field. It holds great potential for broad use in other low-field MRI applications.

Imaging plays a major role in the care of the intensive care unit (ICU) patients. An understanding of the monitoring devices is essential for the interpretation of imaging studies. An awareness of their expected locations aids in identifying complications in a timely manner. This review describes the imaging of ICU monitoring and support catheters, tubes, and pulmonary and cardiac devices, some more commonly encountered and others that have been introduced into clinical patient care more recently. Special focus will be placed on chest radiography and potential pitfalls encountered.

A strong understanding of radiation techniques, including CRT and SBRT, and the expected posttherapy imaging manifestations enables more confident and accurate interpretations of surveillance CT imaging studies in patients with prior RT. Knowledge of common complications and corresponding CT imaging appearances, particularly tumor recurrence and infection, leads to more accurate diagnoses, timely treatment, and avoidance of pitfalls in interpretation.

OBJECTIVES:To evaluate the clinical significance of low-field MRI lung opacity severity. METHODS:Retrospective cross-sectional analysis of post-acute Covid-19 patients imaged with low-field MRI from 9/2020 through 9/2022, and within 1 month of pulmonary function tests (PFTs), 6-min walk test (6mWT), and symptom inventory (SI), and/or within 3 months of St. George Respiratory Questionnaire (SGRQ) was performed. Univariate and correlative analyses were performed with Wilcoxon, Chi-square, and Spearman tests. The association between disease and demographic factors and MR opacity severity, PFTs, 6mWT, SI, and SGRQ, and association between MR opacity severity with functional and patient-reported outcomes (PROs), was evaluated with mixed model analysis of variance, covariance and generalized estimating equations. Two-sided 5 % significance level was used, with Bonferroni multiple comparison correction. RESULTS:81 MRI exams in 62 post-acute Covid-19 patients (median age 57, IQR 41-64; 25 women) were included. Exams were a median of 8 months from initial illness. Univariate analysis showed lung opacity severity was associated with decreased %DLCO (ρ = -0.55, P = .0125), and lung opacity severity quartile was associated with decreased %DLCO, predicted TLC, FVC, and increased FEV1/FVC. Multivariable analysis adjusting for sex, initial disease severity, and interval from Covid-19 diagnosis showed MR lung opacity severity was associated with decreased %DLCO (P < .001). Lung opacity severity was not associated with PROs. CONCLUSION:Low-field MRI lung opacity severity correlated with decreased %DLCO in post-acute Covid-19 patients, but was not associated with PROs.

RATIONALE AND OBJECTIVES:To determine factors influencing low-field MRI lung opacity severity 6-24 months after acute Covid-19 pneumonia. MATERIALS AND METHODS:104 post-acute Covid-19 patients with 167 MRI exams were included. 32 patients had more than one exam, and 63 exams were serial exams. Pulmonary findings were graded on a scale of 0-4 by quadrant, total score ranging from 0 (no opacity) to 16 (opacity > 75%), and score >8 considered moderate and >12 severe opacity. Kruskal-Wallis, Mann-Whitney, and Spearman rank correlation was used to assess the association of clinical and demographic factors with MR opacity severity at time intervals from acute infection. Random coefficients regression was used to assess whether opacity score changed over time. RESULTS:Severity of initial illness was associated with increased MR opacity score at timeframes up to 24 months (p < .05). Among the 167 exams, moderate to severe MR opacities (total opacity score >8) were identified in 33% of exams beyond 6 months: 37% at 6 - <12 months (n = 23/63); 31% at 12- < 18 months (n = 13/42); 25% at 18- < 24 months (n = 6/24); and 50% at > 24 months (n = 3/6). No significant change in total opacity score over time was identified by random coefficients regression. Among the 32 patients with serial exams, 11 demonstrated no change in opacity score from initial to final exam, 10 decrease in score (mean 2.3, stdev 1.25, range 1-4), and 11 increase in score (average 2.8, stdev 1.48, range 1-7). CONCLUSION:Initial Covid-19 disease severity was associated with increased MRI total opacity score at time intervals up to 24 months, and moderate to severe opacities were commonly identified by low-field MRI beyond 6 months from acute illness.

Purpose To determine the performance of volumetric dual energy low kV and iodine radiomic features for the differentiation of intrathoracic lymph node histopathology, and influence of contrast protocol. Materials and methods Intrathoracic lymph nodes with histopathologic correlation (neoplastic, granulomatous sarcoid, benign) within 90 days of DECT chest imaging were volumetrically segmented. 1691 volumetric radiomic features were extracted from iodine maps and low-kV images, totaling 3382 features. Univariate analysis was performed using 2-sample t-test and filtered for false discoveries. Multivariable analysis was used to compute AUCs for lymph node classification tasks. Results 129 lymph nodes from 72 individuals (mean age 61 ± 15 years) were included, 52 neoplastic, 51 benign, and 26 granulomatous-sarcoid. Among all contrast enhanced DECT protocol exams (routine, PE and CTA), univariable analysis demonstrated no significant differences in iodine and low kV features between neoplastic and non-neoplastic lymph nodes; in the subset of neoplastic versus benign lymph nodes with routine DECT protocol, 199 features differed (p = .01- < 0.05).Multivariable analysis using both iodine and low kV features yielded AUCs >0.8 for differentiating neoplastic from non-neoplastic lymph nodes (AUC 0.86), including subsets of neoplastic from granulomatous (AUC 0.86) and neoplastic from benign (AUC 0.9) lymph nodes, among all contrast protocols. Conclusions Volumetric DECT radiomic features demonstrate strong collective performance in differentiation of neoplastic from non-neoplastic intrathoracic lymph nodes, and are influenced by contrast protocol.

Sepsis is defined as a life-threatening organ dysfunction caused by a dysregulated host response to infection. A search for the underlying cause of infection typically includes radiological imaging as part of this investigation. This document focuses on thoracic and abdominopelvic causes of sepsis. In 2017, the global incidence of sepsis was estimated to be 48.9 million cases, with 11 million sepsis-related deaths (accounting for nearly 20% of all global deaths); therefore, understanding which imaging modalities and types of studies are acceptable or not acceptable is imperative. The 5 variants provided include the most commonly encountered scenarios in the setting of sepsis along with recommendations and data for each imaging study.The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

PURPOSE:Apical pleuroparenchymal scarring (APPS) is commonly seen on chest computed tomography (CT), though the imaging and clinical features, to the best of our knowledge, have never been studied. The purpose was to understand APPS's typical morphologic appearance and associated clinical features. PATIENTS AND METHODS:A random generator selected 1000 adult patients from all 21516 chest CTs performed at urban outpatient centers from January 1, 2016 to December 31, 2016. Patients with obscuring apical diseases were excluded to eliminate confounding factors. After exclusions, 780 patients (median age: 64 y; interquartile range: 56 to 72 y; 55% males) were included for analysis. Two radiologists evaluated the lung apices of each CT for the extent of abnormality in the axial plane (mild: <5 mm, moderate: 5 to 10 mm, severe: >10 mm), craniocaudal plane (extension halfway to the aortic arch, more than halfway, vs below the arch), the predominant pattern (nodular vs reticular and symmetry), and progression. Cohen kappa coefficient was used to assess radiologists' agreement in scoring. Ordinal logistic regression was used to determine associations of clinical and imaging variables with APPS. RESULTS:APPS was present on 65% (507/780) of chest CTs (54% mild axial; 80% mild craniocaudal). The predominant pattern was nodular and symmetric. Greater age, female sex, lower body mass index, greater height, and white race were associated with more extensive APPS. APPS was not found to be associated with lung cancer in this cohort. CONCLUSION:Classifying APPS by the extent of disease in the axial or craniocaudal planes, in addition to the predominant pattern, enabled statistically significant associations to be determined, which may aid in understanding the pathophysiology of apical scarring and potential associated risks.

TOPIC IMPORTANCE: Chest CT imaging holds a major role in the diagnosis of lung diseases, many of which affect the peribronchovascular region. Identification and categorization of peribronchovascular abnormalities on CT imaging can assist in formulating a differential diagnosis and directing further diagnostic evaluation. REVIEW FINDINGS: The peribronchovascular region of the lung encompasses the pulmonary arteries, airways, and lung interstitium. Understanding disease processes associated with structures of the peribronchovascular region and their appearances on CT imaging aids in prompt diagnosis. This article reviews current knowledge in anatomic and pathologic features of the lung interstitium composed of intercommunicating prelymphatic spaces, lymphatics, collagen bundles, lymph nodes, and bronchial arteries; diffuse lung diseases that present in a peribronchovascular distribution; and an approach to classifying diseases according to patterns of imaging presentations. Lung peribronchovascular diseases can appear on CT imaging as diffuse thickening, fibrosis, masses or masslike consolidation, ground-glass or air space consolidation, and cysts, acknowledging that some diseases may have multiple presentations. SUMMARY: A category approach to peribronchovascular diseases on CT imaging can be integrated with clinical features as part of a multidisciplinary approach for disease diagnosis.

Radiation therapy is part of a multimodality treatment approach to lung cancer. The radiologist must be aware of both the expected and the unexpected imaging findings of the post–radiation therapy patient, including the time course for development of post– radiation therapy pneumonitis and fibrosis. In this review, a brief discussion of radiation therapy techniques and indications is presented, followed by an image-heavy differential diagnostic approach. The review focuses on computed tomography imaging examples to help distinguish normal postradiation pneumonitis and fibrosis from alternative complications, such as infection, local recurrence, or radiation-induced malignancy.

PURPOSE: COVID-19 has had a severe impact on force readiness across all branches of the United States military.Personnel that were symptomatic and tested positive for COVID-19 were significantly more likely to report persistent dyspnea and exercise limitation that impacted PFT scores for longer than 12 months.Symptoms in prior studies did not always correlate with imaging findings, which prompted expansion of testing to better qualify the cause of persistent cardiopulmonary symptoms. METHODS:A prospective analysis of active duty service members with persistent symptoms for 3 months after contracting COVID-19 were evaluated.Testing included full pulmonary function testing with bronchodilator (PFTs with BD), impulse oscillometry (IOS), methacholine challenge testing (MCT), high resolution computed tomography (HRCT), echocardiogram and electrocardiogram (EKG), laboratory testing, and cardiopulmonary exercise testing (CPET).RESULTS: A total of 105 AD service members with a median age of 35.9 AE 8.0 and median BMI of 28.8 AE 4.6 with persistent symptoms after COVID-19 were enrolled to further evaluate the cause of their persistent dyspnea.Ten of these participants had been hospitalized between 1-12 days.Significant pulmonary function test findings included MCT positivity in 12 patients (11.4%),FEV 1 below the lower limit of normal in 12 patients (11.4%),TLC below the lower limit of normal in 9 patients (8.6%), residual volume above the upper limit of normal in 4 patients (3.8%) and low diffusion capacity in 15 patients (14%).Significant imaging findings included air trapping in 24 of patients (22.3%), ground glass opacities in 10 patients (9.5%), and reticulation in 4 patients (3.8%).IOS data was significant for R5 below predicted in 53 patients (50.5%) and R20 below predicted in 70 patients (66.7%).No significant reduction in VO 2 max was noted on CPET and there were no significant echocardiographic findings.CONCLUSIONS: This prospective study of non-hospitalized active duty service members with persistent symptoms after contracting COVID-19 found a predominant pattern of obstructive airway disease and isolated reduction in DLCO.No respiratory abnormalities in exercise capacity were noted and echocardiographic findings were unremarkable.Additional enrollment may allow for more subset analysis based on time since diagnosis and improvements in exercise capacity.CLINICAL IMPLICATIONS: Persistent symptoms associated with COVID 19 infection continue to be investigated extensively and have evolved as the severity of infection has changed.In this study, the predominant etiolgoy of ongoing dyspnea on exertion is obstruction with reduced DLCO as a close second.This understanding may help target therapies that may offer more symptom relief.

A variety of thoracic imaging modalities and techniques have been used to evaluate diseases of the trachea and central bronchi. This document evaluates evidence for the use of thoracic imaging in the evaluation of tracheobronchial disease, including clinically suspected tracheal or bronchial stenosis, tracheomalacia or bronchomalacia, and bronchiectasis. Appropriateness guidelines for initial imaging evaluation of tracheobronchial disease and for pretreatment planning or posttreatment evaluation are included. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

PURPOSE:The purpose of this study was to identify differences in imaging features between patients with confirmed right middle lobe (RML) torsion compared to those suspected yet without torsion. MATERIALS AND METHODS:This retrospective study entailing a search of radiology reports from April 1, 2014, to April 15, 2021, resulted in 52 patients with suspected yet without lobar torsion and 4 with confirmed torsion, supplemented by 2 additional cases before the search period for a total of 6 confirmed cases. Four thoracic radiologists (1 an adjudicator) evaluated chest radiographs and computed tomography (CT) examinations, and Fisher exact and Mann-Whitney tests were used to identify any significant differences in imaging features ( P <0.05). RESULTS:A reversed halo sign was more frequent for all readers ( P= 0.001) in confirmed RML torsion than patients without torsion (83.3% vs. 0% for 3 readers, one the adjudicator). The CT coronal bronchial angle between RML bronchus and bronchus intermedius was larger ( P= 0.035) in torsion (121.28 degrees) than nontorsion cases (98.26 degrees). Patients with torsion had a higher percentage of ground-glass opacity in the affected lobe ( P= 0.031). A convex fissure towards the adjacent lobe on CT ( P= 0.009) and increased lobe volume on CT ( P= 0.001) occurred more often in confirmed torsion. CONCLUSION:A reversed halo sign, larger CT coronal bronchial angle, greater proportion of ground-glass opacity, fissural convexity, and larger lobe volume on CT may aid in early recognition of the rare yet highly significant diagnosis of lobar torsion.

Routine chest imaging has been used to identify unknown or subclinical cardiothoracic abnormalities in the absence of symptoms. Various imaging modalities have been suggested for routine chest imaging. We review the evidence for or against the use of routine chest imaging in different clinical scenarios. This document aims to determine guidelines for the use of routine chest imaging as initial imaging for hospital admission, initial imaging prior to noncardiothoracic surgery, and surveillance imaging for chronic cardiopulmonary disease. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

PURPOSE: Interstitial lung diseases (ILD) are a unique group of lung disease that carries significant morbidity and mortality with increased incidence and prevalence with age.The heterogeneity and evolution of diagnosis has made defining true incidence and characteristics of disease difficult.This study aims to describe the etiology and characteristic in a young healthy military population with various deployment exposures. METHODS:A retrospective chart review was conducted using the electronic medical record for active duty service members with a diagnosis of ILD.Basic demographic data, diagnosis, pulmonary function testing, chest imaging, and pathologic results were reviewed.The groups were then subdivided for further analysis based on exposure and deployment history.Further subgroup analysis was performed on the major idiopathic interstitial pneumonias (IIP) and connective tissue disease related ILD (CTD-ILD) within this cohort.RESULTS: Initial review of medical records identified 323 individuals with a diagnosis of ILD of which only 158 were analyzed.The cohort was 70.9% male with a mean age of 38.9 years.Chest imaging was performed in 158 (100%) patients while PFTs were done in 147 (93%) patients.Average FVC 3.52 L (77% predicted), FEV1 2.75 L (75% predicted), FEV1/FVC 79%, TLC 6.32 L (78% predicted), and DLCO 18.8 mL/Hg/min (63% predicted).Tissue diagnosis was made in 39.2 % of patients.BAL was performed in 20.9% of patients.Notably, 82 (51.9%) individuals were under the age of 40 while the remaining 76 (48.1%) over 40 years old.32.3% had a diagnosis characterized as a major IIP, 29.7% with CTD-ILD, and 38% alternative diagnosis.There was a notable higher proportion of females in CTD-ILD subgroup when compared to Major IIPs (44.7% vs 21.6%). CONCLUSIONS:In this study we describe the etiology and characteristics of active duty military members diagnosed with ILD during military service.Despite a young population a variety of causes were found for underlying ILD.A higher proportion of females were noted to have CTD-ILD when compared to other subgroups.PFT data reviewed showed more subtle changes suggestive of early ILD.Further characterization based on military occupation and deployment is ongoing.CLINICAL IMPLICATIONS: This study aims to help further describe the incidence and distribution of ILD in an otherwise healthy population.ILD is typically diagnosed later in life and early detection may help decrease long term morbidity and mortality.Further investigation should be performed to evaluate any relationship of ILD to deployment or other exposures during military service.

Purpose: The aim of this study was to evaluate the association between census tract-level measures of social vulnerability and residential segregation and incidental pulmonary nodule (IPN) follow-up.Methods: This retrospective cohort study included patients with IPNs >= 6 mm in size or multiple subsolid or ground-glass IPNs <6 mm (with nonoptional follow-up recommendations) diagnosed between January 1, 2018, and December 30, 2019, at a large urban tertiary center and followed for >= 2 years. Geographic sociodemographic context was characterized by the 2018 Centers for Disease Control and Prevention Social Vulnerability Index (SVI) and the index of concentration at the extremes (ICE), categorized in quartiles. Multivariable binomial regression models were used, with a primary outcome of inappropriate IPN follow-up (late or no follow-up). Models were also stratified by nodule risk.Results: The study consisted of 2,492 patients (mean age, 65.6 +/- 12.6 years; 1,361 women). Top-quartile SVI patients were more likely to have inappropriate follow-up (risk ratio [RR], 1.24; 95% confidence interval [CI], 1.12-1.36) compared with the bottom quartile; risk was also elevated in top-quartile SVI subcategories of socioeconomic status (RR, 1.23; 95% CI, 1.13-1.34), Minority status and language (RR, 1.24; 95% CI, 1.03-1.48), housing and transportation (RR, 1.13; 95% CI, 1.02-1.26), and ICE (RR, 1.20; 95% CI, 1.11-1.30). Furthermore, top-quartile ICE was associated with greater risk for inappropriate follow-up among high-risk versus lower risk IPNs (RR, 1.33 [95% CI, 1.18-1.50] versus 1.13 [95% CI, 1.02-1.25]), respectively; P for interaction = .017).Conclusions: Local social vulnerability and residential segregation are associated with inappropriate IPN follow-up and may inform policy or interventions tailored for neighborhoods.