A deep learning-based algorithm improves radiology residents' diagnoses of acute pulmonary embolism on CT pulmonary angiograms.

PURPOSE: To compare radiology residents' diagnostic performances to detect pulmonary emboli (PEs) on CT pulmonary angiographies (CTPAs) with deep-learning (DL)-based algorithm support and without. METHODS: Fully anonymized CTPAs (n = 207) of patients suspected of having acute PE served as input for PE detection using a previously trained and validated DL-based algorithm. Three residents in their first three years of training, blinded to the index report and clinical history, read the CTPAs first without, and 2 months later with the help of artificial intelligence (AI) output, to diagnose PE as present, absent or indeterminate. We evaluated concordances and discordances with the consensus-reading results of two experts in chest imaging. RESULTS: Because the AI algorithm failed to analyze 11 CTPAs, 196 CTPAs were analyzed; 31 (15.8 %) were PE-positive. Good-classification performance was higher for residents with AI-algorithm support than without (AUROCs: 0.958 [95 % CI: 0.921-0.979] vs. 0.894 [95 % CI: 0.850-0.931], p < 0.001, respectively). The main finding was the increased sensitivity of residents' diagnoses using the AI algorithm (92.5 % vs. 81.7 %, respectively). Concordance between residents (kappa: 0.77 [95 % CI: 0.76-0.78]; p < 0.001) improved with AI-algorithm use (kappa: 0.88 [95 % CI: 0.87-0.89]; p < 0.001). CONCLUSION: The AI algorithm we used improved between-resident agreements to interpret CTPAs for suspected PE and, hence, their diagnostic performances.

Primary immunodeficiency diseases of adults: a review of pulmonary complication imaging findings.

Our objective in this review is to familiarize radiologists with the spectrum of initial and progressive CT manifestations of pulmonary complications observed in adult patients with primary immunodeficiency diseases, including primary antibody deficiency (PAD), hyper-IgE syndrome (HIES), and chronic granulomatous disease (CGD). In patients with PAD, recurrent pulmonary infections may lead to airway remodeling with bronchial wall-thickening, bronchiectasis, mucus-plugging, mosaic perfusion, and expiratory air-trapping. Interstitial lung disease associates pulmonary lymphoid hyperplasia, granulomatous inflammation, and organizing pneumonia and is called granulomatous-lymphocytic interstitial lung disease (GLILD). The CT features of GLILD are solid and semi-solid pulmonary nodules and areas of air space consolidation, reticular opacities, and lymphadenopathy. These features may overlap those of mucosa-associated lymphoid tissue (MALT) lymphoma, justifying biopsies. In patients with HIES, particularly the autosomal dominant type (Job syndrome), recurrent pyogenic infections lead to permanent lung damage. Secondary infections with aspergillus species develop in pre-existing pneumatocele and bronchiectasis areas, leading to chronic airway infection. The complete spectrum of CT pulmonary aspergillosis may be seen including aspergillomas, chronic cavitary pulmonary aspergillosis, allergic bronchopulmonary aspergillosis (ABPA)-like pattern, mixed pattern, and invasive. Patients with CGD present with recurrent bacterial and fungal infections leading to parenchymal scarring, traction bronchiectasis, cicatricial emphysema, airway remodeling, and mosaicism. Invasive aspergillosis, the major cause of mortality, manifests as single or multiple nodules, areas of airspace consolidation that may be complicated by abscess, empyema, or contiguous extension to the pleura or chest wall. CLINICAL RELEVANCE STATEMENT: Awareness of the imaging findings spectrum of pulmonary complications that can occur in adult patients with primary immunodeficiency diseases is important to minimize diagnostic delay and improve patient outcomes. KEY POINTS: • Unexplained bronchiectasis, associated or not with CT findings of obliterative bronchiolitis, should evoke a potential diagnosis of primary autoantibody deficiency. • The CT evidence of various patterns of aspergillosis developed in severe bronchiectasis or pneumatocele in a young adult characterizes the pulmonary complications of hyper-IgE syndrome. • In patients with chronic granulomatous disease, invasive aspergillosis is relatively frequent, often asymptomatic, and sometimes mimicking or associated with non-infectious inflammatory pulmonary lesions.

Deep Learning-Based Algorithm for Automatic Detection of Pulmonary Embolism in Chest CT Angiograms.

PURPOSE: Since the prompt recognition of acute pulmonary embolism (PE) and the immediate initiation of treatment can significantly reduce the risk of death, we developed a deep learning (DL)-based application aimed to automatically detect PEs on chest computed tomography angiograms (CTAs) and alert radiologists for an urgent interpretation. Convolutional neural networks (CNNs) were used to design the application. The associated algorithm used a hybrid 3D/2D UNet topology. The training phase was performed on datasets adequately distributed in terms of vendors, patient age, slice thickness, and kVp. The objective of this study was to validate the performance of the algorithm in detecting suspected PEs on CTAs. METHODS: The validation dataset included 387 anonymized real-world chest CTAs from multiple clinical sites (228 U.S. cities). The data were acquired on 41 different scanner models from five different scanner makers. The ground truth (presence or absence of PE on CTA images) was established by three independent U.S. board-certified radiologists. RESULTS: The algorithm correctly identified 170 of 186 exams positive for PE (sensitivity 91.4% [95% CI: 86.4-95.0%]) and 184 of 201 exams negative for PE (specificity 91.5% [95% CI: 86.8-95.0%]), leading to an accuracy of 91.5%. False negative cases were either chronic PEs or PEs at the limit of subsegmental arteries and close to partial volume effect artifacts. Most of the false positive findings were due to contrast agent-related fluid artifacts, pulmonary veins, and lymph nodes. CONCLUSIONS: The DL-based algorithm has a high degree of diagnostic accuracy with balanced sensitivity and specificity for the detection of PE on CTAs.

The Potential Role of Artificial Intelligence in Lung Cancer Screening Using Low-Dose Computed Tomography.

Two large randomized controlled trials of low-dose CT (LDCT)-based lung cancer screening (LCS) in high-risk smoker populations have shown a reduction in the number of lung cancer deaths in the screening group compared to a control group. Even if various countries are currently considering the implementation of LCS programs, recurring doubts and fears persist about the potentially high false positive rates, cost-effectiveness, and the availability of radiologists for scan interpretation. Artificial intelligence (AI) can potentially increase the efficiency of LCS. The objective of this article is to review the performances of AI algorithms developed for different tasks that make up the interpretation of LCS CT scans, and to estimate how these AI algorithms may be used as a second reader. Despite the reduction in lung cancer mortality due to LCS with LDCT, many smokers die of comorbid smoking-related diseases. The identification of CT features associated with these comorbidities could increase the value of screening with minimal impact on LCS programs. Because these smoking-related conditions are not systematically assessed in current LCS programs, AI can identify individuals with evidence of previously undiagnosed cardiovascular disease, emphysema or osteoporosis and offer an opportunity for treatment and prevention.

Idiopathic inflammatory myopathies: CT characteristics of interstitial lung disease and their association(s) with myositis-specific autoantibodies.

OBJECTIVES: Interstitial lung disease (ILD), one of the most common extramuscular manifestations of idiopathic inflammatory myopathies (IIMs), carries a poor prognosis. Myositis-specific autoantibody (MSA)-positivity is a key finding for IIM diagnosis. We aimed to identify IIM-associated lung patterns, evaluate potential CT-ILD finding-MSA relationships, and assess intra- and interobserver reproducibility in a large IIM population. METHODS: All consecutive IIM patients (2003-2019) were included. Two chest radiologists retrospectively assessed all chest CT scans. Multiple correspondence and hierarchical cluster analyses of CT findings identified and characterized ILD-patient subgroups. Classification and regression-tree analyses highlighted CT-scan variables predicting three patterns. Three independent radiologists read CT scans twice to assign patients according to CT-ILD-pattern clusters. RESULTS: Among 257 IIM patients, 94 (36.6%) had ILDs; 87 (93%) of them were MSA-positive. ILD-IIM distribution was 54 (57%) ASyS, 21 (22%) DM, 15 (16%) IMNM, and 4 (4%) IBM. Cluster analysis identified three ILD-patient subgroups. Consolidation characterized cluster 1, with significantly (p < 0.05) more frequent anti-MDA5-autoantibody-positivity. Significantly more cluster-2 patients had a reticular pattern, without cysts and with few consolidations. All cluster-3 patients had cysts and anti-PL12 autoantibodies. Clusters 2 and 3 included significantly more ASyS patients. Intraobserver concordances to classify patients into those three clusters were good-to-excellent (Cohen κ 0.64-0.81), with good interobserver reliability (Fleiss's κ 0.56). CONCLUSION: Despite the observed IIM heterogeneity, CT-scan criteria enabled ILD assignment to the three clusters, which were associated with MSAs. Radiologist identification of those clusters could facilitate diagnostic screening and therapeutics. Interstitial lung disease in patients with idiopathic inflammatory myopathy could be classified into three clusters according to CT-scan criteria, and these clusters were significantly associated with myositis-specific autoantibodies. KEY POINTS: • Cluster analysis discerned three homogeneous groups of interstitial lung disease (ILD) for which cysts, consolidations, and reticular pattern were discriminatory, and associated with myositis-specific autoantibodies. • Like muscle- and extramuscular-specific phenotypes, myositis-specific autoantibodies are also associated with specific ILD patterns in patients with idiopathic inflammatory myopathies.

X-ray dark-field chest imaging for detection and quantification of emphysema in patients with chronic obstructive pulmonary disease: a diagnostic accuracy study.

BACKGROUND: Although advanced medical imaging technologies give detailed diagnostic information, a low-dose, fast, and inexpensive option for early detection of respiratory diseases and follow-ups is still lacking. The novel method of x-ray dark-field chest imaging might fill this gap but has not yet been studied in living humans. Enabling the assessment of microstructural changes in lung parenchyma, this technique presents a more sensitive alternative to conventional chest x-rays, and yet requires only a fraction of the dose applied in CT. We studied the application of this technique to assess pulmonary emphysema in patients with chronic obstructive pulmonary disease (COPD). METHODS: In this diagnostic accuracy study, we designed and built a novel dark-field chest x-ray system (Technical University of Munich, Munich, Germany)-which is also capable of simultaneously acquiring a conventional thorax radiograph (7 s, 0·035 mSv effective dose). Patients who had undergone a medically indicated chest CT were recruited from the department of Radiology and Pneumology of our site (Klinikum rechts der Isar, Technical University of Munich, Munich, Germany). Patients with pulmonary pathologies, or conditions other than COPD, that might influence lung parenchyma were excluded. For patients with different disease stages of pulmonary emphysema, x-ray dark-field images and CT images were acquired and visually assessed by five readers. Pulmonary function tests (spirometry and body plethysmography) were performed for every patient and for a subgroup of patients the measurement of diffusion capacity was performed. Individual patient datasets were statistically evaluated using correlation testing, rank-based analysis of variance, and pair-wise post-hoc comparison. FINDINGS: Between October, 2018 and December, 2019 we enrolled 77 patients. Compared with CT-based parameters (quantitative emphysema ρ=-0·27, p=0·089 and visual emphysema ρ=-0·45, p=0·0028), the dark-field signal (ρ=0·62, p<0·0001) yields a stronger correlation with lung diffusion capacity in the evaluated cohort. Emphysema assessment based on dark-field chest x-ray features yields consistent conclusions with findings from visual CT image interpretation and shows improved diagnostic performance than conventional clinical tests characterising emphysema. Pair-wise comparison of corresponding test parameters between adjacent visual emphysema severity groups (CT-based, reference standard) showed higher effect sizes. The mean effect size over the group comparisons (absent-trace, trace-mild, mild-moderate, and moderate-confluent or advanced destructive visual emphysema grades) for the COPD assessment test score is 0·21, for forced expiratory volume in 1 s (FEV1)/functional vital capacity is 0·25, for FEV1% of predicted is 0·23, for residual volume % of predicted is 0·24, for CT emphysema index is 0·35, for dark-field signal homogeneity within lungs is 0·38, for dark-field signal texture within lungs is 0·38, and for dark-field-based emphysema severity is 0·42. INTERPRETATION: X-ray dark-field chest imaging allows the diagnosis of pulmonary emphysema in patients with COPD because this technique provides relevant information representing the structural condition of lung parenchyma. This technique might offer a low radiation dose alternative to CT in COPD and potentially other lung disorders. FUNDING: European Research Council, Deutsche Forschungsgemeinschaft, Royal Philips, and Karlsruhe Nano Micro Facility.

Automated AI-Driven CT Quantification of Lung Disease Predicts Adverse Outcomes in Patients Hospitalized for COVID-19 Pneumonia.

The purpose of our work was to assess the independent and incremental value of AI-derived quantitative determination of lung lesions extent on initial CT scan for the prediction of clinical deterioration or death in patients hospitalized with COVID-19 pneumonia. 323 consecutive patients (mean age 65 ± 15 years, 192 men), with laboratory-confirmed COVID-19 and an abnormal chest CT scan, were admitted to the hospital between March and December 2020. The extent of consolidation and all lung opacities were quantified on an initial CT scan using a 3D automatic AI-based software. The outcome was known for all these patients. 85 (26.3%) patients died or experienced clinical deterioration, defined as intensive care unit admission. In multivariate regression based on clinical, biological and CT parameters, the extent of all opacities, and extent of consolidation were independent predictors of adverse outcomes, as were diabetes, heart disease, C-reactive protein, and neutrophils/lymphocytes ratio. The association of CT-derived measures with clinical and biological parameters significantly improved the risk prediction (p = 0.049). Automated quantification of lung disease at CT in COVID-19 pneumonia is useful to predict clinical deterioration or in-hospital death. Its combination with clinical and biological data improves risk prediction.

Lung Transplantation: CT Assessment of Chronic Lung Allograft Dysfunction (CLAD).

Chronic lung allograft rejection remains one of the major causes of morbi-mortality after lung transplantation. The term Chronic Lung Allograft Dysfunction (CLAD) has been proposed to describe the different processes that lead to a significant and persistent deterioration in lung function without identifiable causes. The two main phenotypes of CLAD are Bronchiolitis Obliterans Syndrome (BOS) and Restrictive Allograft Syndrome (RAS), each of them characterized by particular functional and imaging features. These entities can be associated (mixed phenotype) or switched from one to the other. If CLAD remains a clinical diagnosis based on spirometry, computed tomography (CT) scan plays an important role in the diagnosis and follow-up of CLAD patients, to exclude identifiable causes of functional decline when CLAD is first suspected, to detect early abnormalities that can precede the diagnosis of CLAD (particularly RAS), to differentiate between the obstructive and restrictive phenotypes, and to detect exacerbations and evolution from one phenotype to the other. Recognition of early signs of rejection is crucial for better understanding of physiopathologic pathways and optimal management of patients.

Vascular Ehlers-Danlos syndrome (vEDS): CT and histologic findings of pleural and lung parenchymal damage.

OBJECTIVES: To describe CT features of lung involvement in patients with vascular Ehlers-Danlos syndrome (vEDS), a rare genetic condition caused by pathogenic variants within the COL3A1 gene, characterized by recurrent arterial, digestive, and pulmonary events. MATERIAL AND METHODS: All consecutive vEDS patients referred to the national tertiary referral center for vEDS, between 2004 and 2016, were included. Chest CT scans obtained during the initial vascular work-up were reviewed retrospectively by two chest radiologists for lung involvement. Five surgical samples underwent histologic examination. RESULTS: Among 136 enrolled patients (83 women, 53 men; mean age 37 years) with molecularly confirmed vEDS, 24 (17.6%) had a history of respiratory events: 17 with pneumothorax, 4 with hemothorax, and 3 with hemoptysis that required thoracic surgery in 11. CT scans detected lung parenchymal abnormalities in 78 (57.3%) patients: emphysema (mostly centrilobular and paraseptal) in 44 (32.3%), comparable for smokers and non-smokers; clusters of calcified small pulmonary nodules in 9 (6.6%); and cavitated nodules in 4 (2.9%). Histologic examination of surgical samples found arterial abnormalities, emphysema with alveolar ruptures in 3, accompanied by diffuse hemorrhage and increased hemosiderin resorption. CONCLUSION: In vEDS patients, identification of lung parenchymal abnormalities is common on CT. The most frequently observed CT finding was emphysema suggesting alveolar wall rupture which might facilitate the diagnostic screening of the disease in asymptomatic carriers of a genetic COL3A1 gene mutation. The prognostic value and evolution of these parenchymal abnormalities remain to be evaluated. KEY POINTS: • Patients with vEDS can have lung parenchymal changes on top of or next to thoracal vascular abnormalities and that these changes can be present in asymptomatic cases. • The presence of these parenchymal changes is associated with a slightly higher incidence of respiratory events (although not statistically significant). • Identification of the described CT pattern by radiologists and chest physicians may facilitate diagnostic screening.

COVID-19 pneumonia: high diagnostic accuracy of chest CT in patients with intermediate clinical probability.

OBJECTIVES: To assess inter-reader agreements and diagnostic accuracy of chest CT to identify COVID-19 pneumonia in patients with intermediate clinical probability during an acute disease outbreak. METHODS: From March 20 to April 8, 319 patients (mean age 62.3 years old) consecutive patients with an intermediate clinical probability of COVID-19 pneumonia underwent a chest CT scan. Two independent chest radiologists blinded to clinical information and RT-PCR results retrospectively reviewed and classified images on a 1-5 confidence level scale for COVID-19 pneumonia. Agreements between radiologists were assessed with kappa statistics. Diagnostic accuracy of chest CT compared with RT-PCR assay and patient outcomes was measured using receiver operating characteristics (ROC). Positive predictive value (PPV) and negative predictive value (NPV) for COVID-19 pneumonia were calculated. RESULTS: Inter-observer agreement for highly probable (kappa: 0.83 [p < .001]) and highly probable or probable (kappa: 0.82 [p < .001]) diagnosis of COVID-19 pneumonia was very good. RT-PCR tests performed in 307 patients were positive in 174 and negative in 133. The areas under the curve (AUC) were 0.94 and 0.92 respectively. With a disease prevalence of 61.2%, PPV were 95.9% and 94.3%, and NPV 84.4% and 77.1%. CONCLUSION: During acute COVID-19 outbreak, chest CT scan may be used for triage of patients with intermediate clinical probability with very good inter-observer agreements and diagnostic accuracy. KEY POINTS: • Concordances between two chest radiologists to diagnose or exclude a COVID-19 pneumonia in 319 consecutive patients with intermediate clinical probability were very good (kappa: 0.82; p < .001). • When compared with RT-PCR results and patient outcomes, the diagnostic accuracy of CT to identify COVID-19 pneumonia was high for both radiologists (AUC: 0.94 and 0.92). • With a disease prevalence of 61.2% in the studied population, the positive predictive values of CT for diagnosing COVID-19 pneumonia were 95.9% and 94.3% with negative predictive values of 84.4% and 77.1%.

COPDGene® 2019: Redefining the Diagnosis of Chronic Obstructive Pulmonary Disease.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) remains a major cause of morbidity and mortality. Present-day diagnostic criteria are largely based solely on spirometric criteria. Accumulating evidence has identified a substantial number of individuals without spirometric evidence of COPD who suffer from respiratory symptoms and/or increased morbidity and mortality. There is a clear need for an expanded definition of COPD that is linked to physiologic, structural (computed tomography [CT]) and clinical evidence of disease. Using data from the COPD Genetic Epidemiology study (COPDGene®), we hypothesized that an integrated approach that includes environmental exposure, clinical symptoms, chest CT imaging and spirometry better defines disease and captures the likelihood of progression of respiratory obstruction and mortality. METHODS: Four key disease characteristics - environmental exposure (cigarette smoking), clinical symptoms (dyspnea and/or chronic bronchitis), chest CT imaging abnormalities (emphysema, gas trapping and/or airway wall thickening), and abnormal spirometry - were evaluated in a group of 8784 current and former smokers who were participants in COPDGene® Phase 1. Using these 4 disease characteristics, 8 categories of participants were identified and evaluated for odds of spirometric disease progression (FEV1 > 350 ml loss over 5 years), and the hazard ratio for all-cause mortality was examined. RESULTS: Using smokers without symptoms, CT imaging abnormalities or airflow obstruction as the reference population, individuals were classified as Possible COPD, Probable COPD and Definite COPD. Current Global initiative for obstructive Lung Disease (GOLD) criteria would diagnose 4062 (46%) of the 8784 study participants with COPD. The proposed COPDGene® 2019 diagnostic criteria would add an additional 3144 participants. Under the new criteria, 82% of the 8784 study participants would be diagnosed with Possible, Probable or Definite COPD. These COPD groups showed increased risk of disease progression and mortality. Mortality increased in patients as the number of their COPD characteristics increased, with a maximum hazard ratio for all cause-mortality of 5.18 (95% confidence interval [CI]: 4.15-6.48) in those with all 4 disease characteristics. CONCLUSIONS: A substantial portion of smokers with respiratory symptoms and imaging abnormalities do not manifest spirometric obstruction as defined by population normals. These individuals are at significant risk of death and spirometric disease progression. We propose to redefine the diagnosis of COPD through an integrated approach using environmental exposure, clinical symptoms, CT imaging and spirometric criteria. These expanded criteria offer the potential to stimulate both current and future interventions that could slow or halt disease progression in patients before disability or irreversible lung structural changes develop.

Inter-observer agreement in identifying traction bronchiectasis on computed tomography: its improvement with the use of the additional criteria for chronic fibrosing interstitial pneumonia.

PURPOSE: To assess inter-observer variability in identifying traction bronchiectasis on computed tomography (CT) using additional criteria for chronic fibrosing interstitial pneumonia. METHODS: Seven experts categorized CT image set representing 39 patients into three groups on the basis of the presence of traction bronchiectasis, using a three-point scale: 3-definitely/probably yes; 2-possibly yes; and 1-definitely/probably no. This scale served as a reference standard. The image set included cases of chronic fibrosing interstitial pneumonia, non-interstitial lung disease, and difficult-to-determine cases. Forty-eight observers similarly assessed the same image set, first according to the Fleischner Society definition, and second with additional criteria, in which traction bronchiectasis was observed exclusively in chronic fibrosing interstitial pneumonia. The agreement level between the reference standard and each observer's evaluation in each session was calculated using weighted kappa values which were compared between the two sessions using a paired t test. RESULTS: The mean weighted kappa value for all observers was significantly higher in the second reading session (mean 0.75) than in the first reading session (mean 0.62) (p < 0.001). CONCLUSION: Inter-observer agreement in identifying traction bronchiectasis improves when using the additional criteria which specify chronic fibrosing interstitial pneumonia as the underlying disease.

Relationship of spirometric, body plethysmographic, and diffusing capacity parameters to emphysema scores derived from CT scans.

Phenotyping of chronic obstructive pulmonary disease (COPD) with computed tomography (CT) is used to distinguish between emphysema- and airway-dominated type. The phenotype is reflected in correlations with lung function measures. Among these, the relative value of body plethysmography has not been quantified. We addressed this question using CT scans retrospectively collected from clinical routine in a large COPD cohort. Three hundred and thirty five patients with baseline data of the German COPD cohort COPD and Systemic Consequences-Comorbidities Network were included. CT scans were primarily evaluated using a qualitative binary emphysema score. The binary score was positive for emphysema in 52.5% of patients, and there were significant differences between the positive/negative groups regarding forced expiratory volume in 1 second (FEV1), FEV1/forced vital capacity (FVC), intrathoracic gas volume (ITGV), residual volume (RV), specific airway resistance (sRaw), transfer coefficient (KCO), transfer factor for carbon monoxide (TLCO), age, pack-years, and body mass index (BMI). Stepwise discriminant analyses revealed the combination of FEV1/FVC, RV, sRaw, and KCO to be significantly related to the binary emphysema score. The additional positive predictive value of body plethysmography, however, was only slightly higher than that of the conventional combination of spirometry and diffusing capacity, which if taken alone also achieved high predictive values, in contrast to body plethysmography. The additional information on the presence of CT-diagnosed emphysema as conferred by body plethysmography appeared to be minor compared to the well-known combination of spirometry and CO diffusing capacity.