Prevalence of lung cysts in adolescents and adults with a germline DICER1 pathogenic/likely pathogenic variant: a report from the National Institutes of Health and International Pleuropulmonary Blastoma/DICER1 Registry.

BACKGROUND: Pleuropulmonary blastoma (PPB), the hallmark tumour associated with DICER1-related tumour predisposition, is characterised by an age-related progression from a cystic lesion (type I) to a high-grade sarcoma with mixed cystic and solid features (type II) or purely solid lesion (type III). Not all cystic PPBs progress; type Ir (regressed), hypothesised to represent regressed or non-progressed type I PPB, is an air-filled, cystic lesion lacking a primitive sarcomatous component. This study aims to evaluate the prevalence of non-progressed lung cysts detected by CT scan in adolescents and adults with germline DICER1 pathogenic/likely pathogenic (P/LP) variants. METHODS: Individuals were enrolled in the National Cancer Institute Natural History of DICER1 Syndrome study, the International PPB/DICER1 Registry and/or the International Ovarian and Testicular Stromal Tumor Registry. Individuals with a germline DICER1 P/LP variant with first chest CT at 12 years of age or older were selected for this analysis. RESULTS: In the combined databases, 110 individuals with a germline DICER1 P/LP variant who underwent first chest CT at or after the age of 12 were identified. Cystic lung lesions were identified in 38% (42/110) with a total of 72 cystic lesions detected. No demographic differences were noted between those with lung cysts and those without lung cysts. Five cysts were resected with four centrally reviewed as type Ir PPB. CONCLUSION: Lung cysts are common in adolescents and adults with germline DICER1 variation. Further study is needed to understand the mechanism of non-progression or regression of lung cysts in childhood to guide judicious intervention.

Increasing the scan-efficiency of pulmonary imaging at 0.55 T using iterative concomitant field and motion-corrected reconstruction.

PURPOSE: To develop an iterative concomitant field and motion corrected (iCoMoCo) reconstruction for isotropic high-resolution UTE pulmonary imaging at 0.55 T. METHODS: A free-breathing golden-angle stack-of-spirals UTE sequence was used to acquire data for 8 min with prototype and commercial 0.55 T MRI scanners. The data was binned into 12 respiratory phases based on superior-inferior navigator readouts. The previously published iterative motion corrected (iMoCo) reconstruction was extended to include concomitant field correction directly in the cost function. The reconstruction was implemented within the Gadgetron framework for inline reconstruction. Data were retrospectively reconstructed to simulate scan times of 2, 4, 6, and 8 min. Image quality was assessed using apparent SNR and image sharpness. The technique was evaluated in healthy volunteers and patients with known lung pathology including coronavirus disease 2019 infection, chronic granulomatous disease, lymphangioleiomyomatosis, and lung nodules. RESULTS: The technique provided diagnostic-quality images, and image quality was maintained with a slight loss in SNR for simulated scan times down to 4 min. Parenchymal apparent SNR was 4.33 ± 0.57, 5.96 ± 0.65, 7.36 ± 0.64, and 7.87 ± 0.65 using iCoMoCo with scan times of 2, 4, 6, and 8 min, respectively. Image sharpness at the diaphragm was comparable between iCoMoCo and reference images. Concomitant field corrections visibly improved the sharpness of anatomical structures away from the isocenter. Inline image reconstruction and artifact correction were achieved in <5 min. CONCLUSION: The proposed iCoMoCo pulmonary imaging technique can generate diagnostic quality images with 1.75 mm isotropic resolution in less than 5 min using a 6-min acquisition, on a 0.55 T scanner.

Combining lung ultrasound and oscillatory mechanics for assessing lung disease in very preterm infants.

BACKGROUND: We investigated whether combining lung ultrasound scores (LUSs) and respiratory system reactance (Xrs) measured by respiratory oscillometry explains the severity of lung disease better than individual parameters alone. METHODS: We performed a prospective observational study in very preterm infants. Forced oscillations (10 Hz) were applied using a neonatal mechanical ventilator (Fabian HFOi, Vyaire). We used the simultaneous respiratory severity score (RSS = mean airway pressure × FIO2) as a primary outcome. We built linear mixed-effect models to assess the relationship between Xrs z-score, LUS and RSS and compared nested models using the likelihood ratio test (LRT). RESULTS: We enrolled 61 infants (median (Q1, Q3) gestational age = 30.00 (26.86, 31.00) weeks) and performed 243 measurements at a postnatal age of 26 (13, 41) days and postmenstrual age of 33.14 (30.46, 35.86) weeks. Xrs z-score and LUS were independently associated with simultaneous RSS (p < 0.001 for both). The model including Xrs and LUS explained the RSS significantly better than Xrs (p value LRT < 0.001) or LUS alone (p value LRT < 0.001). CONCLUSIONS: Combining LUS and Xrs z-score explains the severity of lung disease better than each parameter alone and has the potential to improve the understanding of the underlying pathophysiology. IMPACT: Combining respiratory system reactance by oscillometry and lung ultrasound score explains the respiratory support requirement (e.g., proxy of the severity of lung disease) significantly better than each parameter alone. We assessed the relationship between lung ultrasound and respiratory system reactance in very preterm infants for the first time. Combining respiratory oscillometry and lung ultrasound has the potential to improve the understanding of respiratory pathophysiology.

Conventional and Contrast-enhanced US of the Lung: From Performance to Diagnosis.

In recent years, lung US has evolved from a marginal tool to an integral component of diagnostic chest imaging. Contrast-enhanced US (CEUS) can improve routine gray-scale imaging of the lung and chest, particularly in diagnosis of peripheral lung diseases (PLDs). Although an underused tool in many centers, and despite inherent limitations in evaluation of central lung disease caused by high acoustic impedance between air and soft tissues, lung CEUS has emerged as a valuable tool in diagnosis of PLDs. Owing to the dual arterial supply to the lungs via pulmonary and bronchial (systemic) arteries, different enhancement patterns can be observed at lung CEUS, thereby enabling accurate differential diagnoses in various PLDs. Lung CEUS also assists in identifying patients who may benefit from complementary diagnostic tests, including image-guided percutaneous biopsy. Moreover, lung CEUS-guided percutaneous biopsy has shown feasibility in accessible subpleural lesions, enabling higher histopathologic performance without significantly increasing either imaging time or expenses compared with conventional US. The authors discuss the technique of and basic normal and pathologic findings at conventional lung US, followed by a more detailed discussion of lung CEUS applications, emphasizing specific aspects of pulmonary physiology, basic concepts in lung US enhancement, and the most commonly encountered enhancement patterns of different PLDs. Finally, they discuss the benefits of lung CEUS in planning and guidance of US-guided lung biopsy. ©RSNA, 2024 Supplemental material is available for this article.

Lung ultrasound for the sick child: less harm and more information than a radiograph.

In the realm of emergency medicine, the swift adoption of lung ultrasound (LU) has extended from the adult population to encompass pediatric and neonatal intensivists. LU stands out as a bedside, replicable, and cost-effective modality, distinct in its avoidance of ionizing radiations, a departure from conventional chest radiography. Recent years have witnessed a seamless adaptation of experiences gained in the adult setting to the neonatal and pediatric contexts, underscoring the versatility of bedside Point of care ultrasound (POCUS). This adaptability has proven reliable in diagnosing common pathologies and executing therapeutic interventions, including chest drainage, and central and peripheral vascular cannulation. The surge in POCUS utilization among neonatologists and pediatric intensivists is notable, spanning economically advanced Western nations with sophisticated, high-cost intensive care facilities and extending to low-income countries. Within the neonatal and pediatric population, POCUS has become integral for diagnosing and monitoring respiratory infections and chronic and acute lung pathologies. This, in turn, contributes to a reduction in radiation exposure during critical periods of growth, thereby mitigating oncological risks. Collaboration among various national and international societies has led to the formulation of guidelines addressing both the clinical application and regulatory aspects of operator training. Nevertheless, unified guidelines specific to the pediatric and neonatal population remain lacking, in contrast to the well-established protocols for adults. The initial application of POCUS in neonatal and pediatric settings centered on goal-directed echocardiography. Pivotal developments include expert statements in 2011, the UK consensus statement on echocardiography by neonatologists, and European training recommendations. The Australian Clinician Performed Ultrasound (CPU) program has played a crucial role, providing a robust academic curriculum tailored for training neonatologists in cerebral and cardiac assessment. Notably, the European Society for Paediatric and Neonatal Intensive Care (ESPNIC) recently disseminated evidence-based guidelines through an international panel, delineating the use and applications of POCUS in the pediatric setting. These guidelines are pertinent to any professional tending to critically ill children in routine or emergency scenarios. In light of the burgeoning literature, this paper will succinctly elucidate the methodology of performing an LU scan and underscore its primary indications in the neonatal and pediatric patient cohort. The focal points of this review comprise as follows: (1) methodology for conducting a lung ultrasound scan, (2) key ultrasonographic features characterizing a healthy lung, and (3) the functional approach: Lung Ultrasound Score in the child and the neonate.  Conclusion: the aim of this review is to discuss the following key points: 1. How to perform a lung ultrasound scan 2. Main ultrasonographic features of the healthy lung 3. The functional approach: Lung Ultrasound Score in the child and the neonate What is Known: • Lung Ultrasound (LUS) is applied in pediatric and neonatal age for the diagnosis of pneumothorax, consolidation, and pleural effusion. • Recently, LUS has been introduced into clinical practice as a bedside diagnostic method for monitoring surfactant use in NARDS and lung recruitment in PARDS. What is New: • Lung Ultrasound (LUS) has proven to be useful in confirming diagnoses of pneumothorax, consolidation, and pleural effusion. • Furthermore, it has demonstrated effectiveness in monitoring the response to surfactant therapy in neonates, in staging the severity of bronchiolitis, and in PARDS.

Metastatic Pulmonary Calcification: Single-Center Review of Typical and Atypical Imaging Features.

PURPOSE: The purpose of this study is to bring attention to an atypical form of metastatic pulmonary calcification, which is conventionally described as a metabolic process with upper lobe predominance in patients with a specific clinical history, which has not been reported as a distinct entity. METHODS: Patients with metastatic pulmonary calcification (MPC) were first identified with mPower keyword search, including MPC or metastatic calcifications on computed tomography chest radiological reports. Patients were then filtered on likelihood of MPC based off imaging reports. Images were then reviewed by three senior radiologists for pertinent characteristics such as location of MPC, degree of calcifications and pleural effusions. Based on the predominant location of MPC, cases were labeled as either typical or atypical. Clinical and imaging characteristics relevant to MPC were noted and compared across typical and atypical cases. RESULTS: In our study, we describe 25 patients with MPC, 13 defined as typical MPC and 12 with atypical MPC. Through consensus of senior radiologists, MPC was deemed to be mild (52%), moderate (44%), or severe (4%). Twenty-three patients (92%) had underlying renal disease including 21 requiring dialysis at the time of diagnosis. Outside of age at diagnosis, there was no significant clinical difference between the two groups. Evaluation of imaging characteristics (average HU attenuation, 267; range, 186-295), pattern and distribution of calcification, and clinical history strongly supported a diagnosis of atypical MPC. CONCLUSION: This study presents several cases of lower lobe subpleural MPC associated with pleural effusions, which has not been reported as a distinct entity, despite comprising a significant portion of MPC cases at our institution.

A methodical exploration of imaging modalities from dataset to detection through machine learning paradigms in prominent lung disease diagnosis: a review.

BACKGROUND: Lung diseases, both infectious and non-infectious, are the most prevalent cause of mortality overall in the world. Medical research has identified pneumonia, lung cancer, and Corona Virus Disease 2019 (COVID-19) as prominent lung diseases prioritized over others. Imaging modalities, including X-rays, computer tomography (CT) scans, magnetic resonance imaging (MRIs), positron emission tomography (PET) scans, and others, are primarily employed in medical assessments because they provide computed data that can be utilized as input datasets for computer-assisted diagnostic systems. Imaging datasets are used to develop and evaluate machine learning (ML) methods to analyze and predict prominent lung diseases. OBJECTIVE: This review analyzes ML paradigms, imaging modalities' utilization, and recent developments for prominent lung diseases. Furthermore, the research also explores various datasets available publically that are being used for prominent lung diseases. METHODS: The well-known databases of academic studies that have been subjected to peer review, namely ScienceDirect, arXiv, IEEE Xplore, MDPI, and many more, were used for the search of relevant articles. Applied keywords and combinations used to search procedures with primary considerations for review, such as pneumonia, lung cancer, COVID-19, various imaging modalities, ML, convolutional neural networks (CNNs), transfer learning, and ensemble learning. RESULTS: This research finding indicates that X-ray datasets are preferred for detecting pneumonia, while CT scan datasets are predominantly favored for detecting lung cancer. Furthermore, in COVID-19 detection, X-ray datasets are prioritized over CT scan datasets. The analysis reveals that X-rays and CT scans have surpassed all other imaging techniques. It has been observed that using CNNs yields a high degree of accuracy and practicability in identifying prominent lung diseases. Transfer learning and ensemble learning are complementary techniques to CNNs to facilitate analysis. Furthermore, accuracy is the most favored metric for assessment.

Pneumothorax and pulmonary hemorrhage after C-arm cone-beam computed tomography-guided percutaneous transthoracic lung biopsy: incidence, clinical significance, and correlation.

OBJECTIVE: This study aimed to assess the incidence and clinical significance of pneumothorax (PTX) and pulmonary hemorrhage (PH) after percutaneous transthoracic lung biopsy (PTLB) guided by C-arm cone-beam computed tomography (CBCT). Furthermore, this study aimed to examine the relationships between PTX and PH with demographics, clinical characteristics, imaging, and PTLB parameters. METHODS: A retrospective analysis was conducted on 192 patients who underwent PTLB at our hospital between January 2019 and October 2022. Incidences of PTX and PH were recorded. PTX was considered clinically significant if treated with chest tube insertion (CTI), and PH if treated with bronchoscopes or endovascular treatments. The various factors on PTX and PH were analyzed using the Chi-squared test and Student t-test. Logistic regression analyses were then used to determine these factors on the correlation to develop PTX and PH. RESULTS: PTX occurred in 67/192 cases (34.9%); CTI was required in 5/67 (7.5%). PH occurred in 63/192 cases (32.8%) and none of these cases required bronchoscopes or endovascular treatments. Lesion diameter (ORPTX = 0.822; ORPH = 0.785), presence of pulmonary emphysema (ORPH = 2.148), the number of samples (ORPH = 1.834), the use of gelfoam (ORPTX = 0.474; ORPH = 0.341) and ablation (ORPTX = 2.351; ORPH = 3.443) showed statistically significant correlation to PTX and PH. CONCLUSIONS: CBCT-guided PTLB is a safe and effective method for performing lung biopsies. The use of gelfoam has been shown to reduce the occurrence of PTX and PH. However, caution should be exercised when combining radiofrequency ablation with PTLB, as it may increase the risk of PTX and PH.

Lung Ultrasound Signs: The Beginning. Part 3-An Accademia di Ecografia Toracica Comprehensive Review on Ultrasonographic Signs and Real Needs.

Over the last 20 years, scientific literature and interest on chest/lung ultrasound (LUS) have exponentially increased. Interpreting mixed-anatomical and artifactual-pictures determined the need of a proposal of a new nomenclature of artifacts and signs to simplify learning, spread, and implementation of this technique. The aim of this review is to collect and analyze different signs and artifacts reported in the history of chest ultrasound regarding normal lung, pleural pathologies, and lung consolidations. By reviewing the possible physical and anatomical interpretation of these artifacts and signs reported in the literature, this work aims to present the AdET (Accademia di Ecografia Toracica) proposal of nomenclature and to bring order between published studies.

Connective tissue disease-associated lung disease in children.

Connective tissue diseases are a heterogeneous group of autoimmune diseases that can affect a variety of organ systems. Lung parenchymal involvement is an important contributor to morbidity and mortality in children with connective tissue disease. Connective tissue disease-associated lung disease in children often manifests as one of several radiologic-pathologic patterns of disease, with certain patterns having a propensity to occur in association with certain connective tissue diseases. In this article, key clinical, histopathologic, and computed tomography (CT) features of typical patterns of connective tissue disease-associated lung disease in children are reviewed, with an emphasis on radiologic-pathologic correlation, to improve recognition of these patterns of lung disease at CT and to empower the pediatric radiologist to more fully contribute to the care of pediatric patients with these conditions.

Unusual pediatric lung infections: imaging findings.

Pediatric lung infections continue to be a leading cause of pediatric morbidity and mortality. Although both pediatric and general radiologists are familiar with typical lung infections and their imaging findings in children, relatively rare lung infections continue to present a diagnostic challenge. In addition, the advances in radiological imaging and emergence of several new lung infections in recent years facilitated the need for up-to-date knowledge on this topic. In this review article, we discuss the imaging findings of pediatric lung infections caused by unusual/uncommon and new pathogens. We review the epidemiological, clinical, and radiological imaging findings of viral (coronavirus disease 2019, Middle East respiratory syndrome, bird flu), bacterial (Streptococcus anginosus, Francisella tularensis, Chlamydia psittaci), and parasitic lung infections (echinococcosis, paragonimiasis, amoebiasis). Additional disorders whose clinical course and imaging findings may mimic lung infections in children (hypersensitivity pneumonitis, pulmonary hemorrhage, eosinophilic pneumonia) are also presented, to aid in differential diagnosis. As the clinical presentation of children with new and unusual lung infections is often non-specific, imaging evaluation plays an important role in initial detection, follow-up for disease progression, and assessment of potential complications.

Comparative Analysis of CT Findings and Clinical Outcomes in Adult Patients With Disseminated and Localized Pulmonary Nocardiosis.

BACKGROUND: Pulmonary nocardiosis is a rare opportunistic infection with occasional systemic dissemination. This study aimed to investigate the computed tomography (CT) findings and prognosis of pulmonary nocardiosis associated with dissemination. METHODS: We conducted a retrospective analysis of patients diagnosed with pulmonary nocardiosis between March 2001 and September 2023. We reviewed the chest CT findings and categorized them based on the dominant CT findings as consolidation, nodules and/or masses, consolidation with multiple nodules, and nodular bronchiectasis. We compared chest CT findings between localized and disseminated pulmonary nocardiosis and identified significant prognostic factors associated with 12-month mortality using multivariate Cox regression analysis. RESULTS: Pulmonary nocardiosis was diagnosed in 75 patients, of whom 14 (18.7%) had dissemination, including involvement of the brain in 9 (64.3%) cases, soft tissue in 3 (21.4%) cases and positive blood cultures in 3 (21.4%) cases. Disseminated pulmonary nocardiosis showed a higher frequency of cavitation (64.3% vs. 32.8%, P = 0.029) and pleural effusion (64.3% vs. 29.5%, P = 0.014) compared to localized infection. The 12-month mortality rate was 25.3%. The presence of dissemination was not a significant prognostic factor (hazard ratio [HR], 0.80; confidence interval [CI], 0.23-2.75; P = 0.724). Malignancy (HR, 9.73; CI, 2.32-40.72; P = 0.002), use of steroid medication (HR, 3.72; CI, 1.33-10.38; P = 0.012), and a CT pattern of consolidation with multiple nodules (HR, 4.99; CI, 1.41-17.70; P = 0.013) were associated with higher mortality rates. CONCLUSION: Pulmonary nocardiosis with dissemination showed more frequent cavitation and pleural effusion compared to cases without dissemination, but dissemination alone did not affect the mortality rate of pulmonary nocardiosis.

DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features.

Lung diseases are the third-leading cause of mortality in the world. Due to compromised lung function, respiratory difficulties, and physiological complications, lung disease brought on by toxic substances, pollution, infections, or smoking results in millions of deaths every year. Chest X-ray images pose a challenge for classification due to their visual similarity, leading to confusion among radiologists. To imitate those issues, we created an automated system with a large data hub that contains 17 datasets of chest X-ray images for a total of 71,096, and we aim to classify ten different disease classes. For combining various resources, our large datasets contain noise and annotations, class imbalances, data redundancy, etc. We conducted several image pre-processing techniques to eliminate noise and artifacts from images, such as resizing, de-annotation, CLAHE, and filtering. The elastic deformation augmentation technique also generates a balanced dataset. Then, we developed DeepChestGNN, a novel medical image classification model utilizing a deep convolutional neural network (DCNN) to extract 100 significant deep features indicative of various lung diseases. This model, incorporating Batch Normalization, MaxPooling, and Dropout layers, achieved a remarkable 99.74% accuracy in extensive trials. By combining graph neural networks (GNNs) with feedforward layers, the architecture is very flexible when it comes to working with graph data for accurate lung disease classification. This study highlights the significant impact of combining advanced research with clinical application potential in diagnosing lung diseases, providing an optimal framework for precise and efficient disease identification and classification.

Breast ultrasound: An opportunity to detect unsuspected pleural and pulmonary abnormalities.

PURPOSE: While scanning women for breast US, is possible to observe changes in the appearance of the pleural line or in the most superficial portion of the lung. The objective of this single-center, prospective study was to determine the prevalence of a variety of pleural and pulmonary US findings during routine breast US. METHODS: In this study, there were 200 women undergoing standard breast US examination. The presence of pleural and pulmonary abnormalities in these cases was recorded. Two off-site reviewers confirmed the presence of pleura and lung changes. RESULTS: There was no abnormal finding in 168 out of 200 cases (84%) while there were one or more abnormal findings in 32 cases (16%). Pleural effusion was observed in 0.5% of cases, thickening of the pleural line 5% of cases, irregularity of the pleural line in 6% of cases, increased number of vertical artifacts in 9% of cases, subpleural nodulations in 2% of cases, and lung consolidation in 0.5%. CONCLUSION: Pleural and lung changes are not uncommon during breast US. Operators performing breast US examinations should be aware of the possibility to identify unsuspected pleuro-pulmonary abnormalities.

Computer tomography measurements of the airway and thoracic cavity do not provide support for bronchial conformation as a predisposing factor of left cranial lung lobe torsion in pugs.

The objective of this retrospective clinical study was to determine if airway or thoracic cavity measurements in pugs, particularly the left cranial lung lobe, were significantly different from brachycephalic and mesocephalic control. Thoracic computed tomographic studies of 10 pugs, French bulldogs (FB), and Jack Russell Terriers (JRT) were analyzed. Thoracic height: width ratio (H:W), cross-sectional areas of the left mainstem bronchus (CSA LMB), left cranial lung lobe bronchus (CSA LCrBr), left caudal lung lobe bronchus (CSA LCauBr), CSA LCrBr relative to length (CSA LCrBr/length) and CSA LCauBr/length were measured and adjusted to body weight (/kg). CSA LMB/kg, CSA LCauBr/length/kg, and CSA LCrBr/length /kg were smaller in pugs and FB compared with JRT (P < .05), but no differences were found between pugs and FB. Cross-sectional areas of left cranial lung lobe bronchus /kg and CSA LCauBr/kg were smaller in pugs than JRT (P < .05), but no differences were found between pugs and FB or FB and JRT. No difference was found in thoracic H:W between any breeds. This demonstrated that pugs and FB had significantly narrower bronchi CSA/lengths ratios compared with JRT, but this was not limited to the LCBr. Airway measurements were not significantly different between brachycephalic breeds; therefore, the pugs' predisposition to left cranial lung lobe torsion cannot be solely explained by narrower lower airways.

[Diffuse cystic lung disease]. / Cystische Lungenerkrankungen.

INTRODUCTION: Diffuse cystic lung disease (DCLD) represents a heterogeneous group of conditions, typically characterized by the presence of multiple thin-walled, predominantly round parenchymal lucencies. The increased accessibility of computed tomography (CT) underscores the growing relevance of a relatively rare group of diseases as more clinicians are confronted with the presence of multiple lung cysts on the chest CT scan. Although the etiology of these conditions is very diverse, the focus of the differential diagnosis revolves around four primary causative factors - Lymphangioleiomyomatosis (LAM), Pulmonary Langerhanscell histiocytosis (PLCH), Birt-Hogg-Dubé (BHD) and lymphoid interstitial pneumonia (LIP). Achieving an accurate diagnosis poses a challenge and typically necessitates lung biopsies; however, it is crucial for ensuring proper management.

Ultra-low-dose CT versus chest X-ray for patients suspected of pulmonary disease at the emergency department: a multicentre randomised clinical trial.

BACKGROUND: Chest CT displays chest pathology better than chest X-ray (CXR). We evaluated the effects on health outcomes of replacing CXR by ultra-low-dose chest-CT (ULDCT) in the diagnostic work-up of patients suspected of non-traumatic pulmonary disease at the emergency department. METHODS: Pragmatic, multicentre, non-inferiority randomised clinical trial in patients suspected of non-traumatic pulmonary disease at the emergency department. Between 31 January 2017 and 31 May 2018, every month, participating centres were randomly allocated to using ULDCT or CXR. Primary outcome was functional health at 28 days, measured by the Short Form (SF)-12 physical component summary scale score (PCS score), non-inferiority margin was set at 1 point. Secondary outcomes included hospital admission, hospital length of stay (LOS) and patients in follow-up because of incidental findings. RESULTS: 2418 consecutive patients (ULDCT: 1208 and CXR: 1210) were included. Mean SF-12 PCS score at 28 days was 37.0 for ULDCT and 35.9 for CXR (difference 1.1; 95% lower CI: 0.003). After ULDCT, 638/1208 (52.7%) patients were admitted (median LOS of 4.8 days; IQR 2.1-8.8) compared with 659/1210 (54.5%) patients after CXR (median LOS 4.6 days; IQR 2.1-8.8). More ULDCT patients were in follow-up because of incidental findings: 26 (2.2%) versus 4 (0.3%). CONCLUSIONS: Short-term functional health was comparable between ULDCT and CXR, as were hospital admissions and LOS, but more incidental findings were found in the ULDCT group. Our trial does not support routine use of ULDCT in the work-up of patients suspected of non-traumatic pulmonary disease at the emergency department. TRIAL REGISTRATION NUMBER: NTR6163.

Advances in bronchoscopic optical coherence tomography and confocal laser endomicroscopy in pulmonary diseases.

PURPOSE OF REVIEW: Imaging techniques play a crucial role in the diagnostic work-up of pulmonary diseases but generally lack detailed information on a microscopic level. Optical coherence tomography (OCT) and confocal laser endomicroscopy (CLE) are imaging techniques which provide microscopic images in vivo during bronchoscopy. The purpose of this review is to describe recent advancements in the use of bronchoscopic OCT- and CLE-imaging in pulmonary medicine. RECENT FINDINGS: In recent years, OCT- and CLE-imaging have been evaluated in a wide variety of pulmonary diseases and demonstrated to be complementary to bronchoscopy for real-time, near-histological imaging. Several pulmonary compartments were visualized and characteristic patterns for disease were identified. In thoracic malignancy, OCT- and CLE-imaging can provide characterization of malignant tissue with the ability to identify the optimal sampling area. In interstitial lung disease (ILD), fibrotic patterns were detected by both (PS-) OCT and CLE, complementary to current HRCT-imaging. For obstructive lung diseases, (PS-) OCT enables to detect airway wall structures and remodelling, including changes in the airway smooth muscle and extracellular matrix. SUMMARY: Bronchoscopic OCT- and CLE-imaging allow high resolution imaging of airways, lung parenchyma, pleura, lung tumours and mediastinal lymph nodes. Although investigational at the moment, promising clinical applications are on the horizon.

Multicentre external validation of a commercial artificial intelligence software to analyse chest radiographs in health screening environments with low disease prevalence.

OBJECTIVES: To externally validate the performance of a commercial AI software program for interpreting CXRs in a large, consecutive, real-world cohort from primary healthcare centres. METHODS: A total of 3047 CXRs were collected from two primary healthcare centres, characterised by low disease prevalence, between January and December 2018. All CXRs were labelled as normal or abnormal according to CT findings. Four radiology residents read all CXRs twice with and without AI assistance. The performances of the AI and readers with and without AI assistance were measured in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. RESULTS: The prevalence of clinically significant lesions was 2.2% (68 of 3047). The AUROC, sensitivity, and specificity of the AI were 0.648 (95% confidence interval [CI] 0.630-0.665), 35.3% (CI, 24.7-47.8), and 94.2% (CI, 93.3-95.0), respectively. AI detected 12 of 41 pneumonia, 3 of 5 tuberculosis, and 9 of 22 tumours. AI-undetected lesions tended to be smaller than true-positive lesions. The readers' AUROCs ranged from 0.534-0.676 without AI and 0.571-0.688 with AI (all p values < 0.05). For all readers, the mean reading time was 2.96-10.27 s longer with AI assistance (all p values < 0.05). CONCLUSIONS: The performance of commercial AI in these high-volume, low-prevalence settings was poorer than expected, although it modestly boosted the performance of less-experienced readers. The technical prowess of AI demonstrated in experimental settings and approved by regulatory bodies may not directly translate to real-world practice, especially where the demand for AI assistance is highest. KEY POINTS: • This study shows the limited applicability of commercial AI software for detecting abnormalities in CXRs in a health screening population. • When using AI software in a specific clinical setting that differs from the training setting, it is necessary to adjust the threshold or perform additional training with such data that reflects this environment well. • Prospective test accuracy studies, randomised controlled trials, or cohort studies are needed to examine AI software to be implemented in real clinical practice.

A self-supervised feature-standardization-block for cross-domain lung disease classification.

With the advance of deep learning technology, convolutional neural network (CNN) has been wildly used and achieved the state-of-the-art performances in the area of medical image classification. However, most existing medical image classification methods conduct their experiments on only one public dataset. When applying a well-trained model to a different dataset selected from different sources, the model usually shows large performance degradation and needs to be fine-tuned before it can be applied to the new dataset. The goal of this work is trying to solve the cross-domain image classification problem without using data from target domain. In this work, we designed a self-supervised plug-and-play feature-standardization-block (FSB) which consisting of image normalization (INB), contrast enhancement (CEB) and boundary detection blocks (BDB), to extract cross-domain robust feature maps for deep learning framework, and applied the network for chest x-ray-based lung diseases classification. Three classic deep networks, i.e. VGG, Xception and DenseNet and four chest x-ray lung diseases datasets were employed for evaluating the performance. The experimental result showed that when employing feature-standardization-block, all three networks showed better domain adaption performance. The image normalization, contrast enhancement and boundary detection blocks achieved in average 2%, 2% and 5% accuracy improvement, respectively. By combining all three blocks, feature-standardization-block achieved in average 6% accuracy improvement.