Expert Thoracic Radiologists Research Articles

Meta-Analysis of Interobserver Agreement in Assessment of Interstitial Lung Disease Using High-Resolution CT.

Background High-resolution CT (HRCT) is central to the assessment of interstitial lung disease (ILD), and accurate classification of disease has important implications for patients. Evaluation of imaging features can be challenging, even for experienced thoracic radiologists. Previous work has provided equivocal evidence on the interpretation of HRCT features at ILD-related imaging. Purpose To perform a meta-analysis to assess the level of agreement among expert thoracic radiologists in interpreting ILD-related imaging. Materials and Methods A systematic literature search from January 2000 to October 2023 of the Ovid MEDLINE, Embase, and Cochrane Central Register of Controlled Trials databases was performed for articles reporting assessments of interobserver agreement between thoracic radiologists for evaluation of ILD findings, such as severity and progression of disease, presence of features such as honeycombing and ground-glass opacification, and classification based on the 2011 and 2018 American Thoracic Society/European Respiratory Society/Japanese Respiratory Society/Asociación Latinoamericana del Tórax (ATS/ERS/JRS/ALAT) guidelines for idiopathic pulmonary fibrosis (IPF). Meta-analysis was performed using a random-effects model to obtain pooled κ or intraclass correlation coefficient (ICC) values as measures of interobserver agreement. Results The final analysis included 13 studies consisting of 6943 images and 146 radiologists. In 10 studies assessing agreement of specific radiologic findings in ILD, the pooled κ value was 0.56 (95% CI: 0.43, 0.70). In eight studies, the assessed interobserver agreement of the ATS/ERS/JRS/ALAT diagnostic guidelines for IPF based on usual interstitial pneumonia (UIP) patterns, the pooled κ value was 0.61 (95% CI: 0.48, 0.74). One study reported a κ value of 0.87 for ILD progression. Seven studies assessing ILD severity could not be pooled; the individual κ values for ILD severity ranged from 0.64 to 0.90, and ICC values ranged from 0.63 to 0.96. Conclusion There was moderate agreement between thoracic radiologists when assessing ILD features and UIP pattern diagnosis but little evidence on agreement of disease severity, extent, or progression. Meta-analysis registry no. PROSPERO CRD42022361803 © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Humbert in this issue.

Usar una herramienta comercial de inteligencia artificial no entrenada para COVID-19 mejora ligeramente la interpretación de las radiografías con neumonía COVID-19, especialmente entre lectores inexpertos

IntroductionOur objective is to evaluate how useful an artificial intelligence (AI) tool is to chest radiograph readers with various levels of expertise for the diagnosis of COVID-19 pneumonia when the tool has been trained on a non-COVID-19 pneumonia pathology. MethodsData was collected for patients who had previously undergone a chest radiograph and digital tomosynthesis due to suspected COVID-19 pneumonia. The gold standard consisted of the readings of two expert radiologists who assessed the presence and distribution of COVID-19 pneumonia on the images. Six medical students, two radiology trainees, and two other expert thoracic radiologists participated as additional readers. Two radiograph readings and a third supported by the AI Thoracic Care Suite tool were performed. COVID-19 pneumonia distribution and probability were assessed along with the contribution made by AI. Agreement and diagnostic performance were analysed. ResultsThe sample consisted of 113 cases, of which 56 displayed lung opacities, 52.2% were female, and the mean age was 50.70±14.9. Agreement with the gold standard differed between students, trainees, and radiologists. There was a non-significant improvement for four of the six students when AI was used. The use of AI by students did not improve the COVID-19 pneumonia diagnostic performance but it did reduce the difference in diagnostic performance with the more expert radiologists. Furthermore, it had more influence on the interpretation of mild pneumonia than severe pneumonia and normal radiograph findings. AI resolved more doubts than it generated, especially among students (31.30 vs 8.32%), followed by trainees (14.45 vs 5.7%) and radiologists (10.05% vs 6.15%). ConclusionFor expert and lesser experienced radiologists, this commercial AI tool has shown no impact on chest radiograph readings of patients with suspected COVID-19 pneumonia. However, it aided the assessment of inexperienced readers and in cases of mild pneumonia.

A validation of register-derived diagnoses of interstitial lung disease in patients with inflammatory arthritis: data from the NOR-DMARD study

Objective There is a lack of knowledge concerning the validity of the interstitial lung disease (ILD) diagnoses used in epidemiological studies on rheumatic diseases. This paper seeks to verify register-derived ILD diagnoses using chest computed tomography (CT) and medical records as a gold standard. Method The Norwegian Anti-Rheumatic Drug Register (NOR-DMARD) is a multicentre prospective observational study of patients with inflammatory arthritis who start treatment with disease-modifying anti-rheumatic drugs. NOR-DMARD is linked to the Norwegian Patient Registry (NPR) and Cause of Death Registry. We searched registers for ILD coded by ICD-10 J84 or J99 among patients with rheumatoid arthritis, psoriatic arthritis, or spondyloarthritis. We extracted chest CT reports and medical records from participating hospitals. Two expert thoracic radiologists scored examinations to confirm the ILD diagnosis. We also searched medical records to find justifications for the diagnosis following multidisciplinary evaluations. We calculated the positive predictive values (PPVs) for ILD across subsets. Results We identified 71 cases with an ILD diagnosis. CT examinations were available in 65/71 patients (91.5%), of whom ILD was confirmed on CT in 29/65 (44.6%). In a further 10 patients, medical records confirmed the diagnosis, giving a total of 39/71 verified cases. The PPV of a register-derived ILD diagnosis was thus 54.9%. In a subset of patients who had received an ILD code at two or more time-points and had a CT scan taken within a relevant period, the PPV was 72.2%. Conclusion The validity of register-based diagnoses of ILD must be carefully considered in epidemiological studies.

Utility of artificial intelligence for detection of pneumothorax on chest radiopgraphs done after transthoracic percutaneous transthoracic biopsy guided by computed tomography

ObjetiveTo assess the ability of an artificial intelligence software to detect pneumothorax in chest radiographs done after percutaneous transthoracic biopsy. Material and methodsWe included retrospectively in our study adult patients who underwent CT-guided percutaneous transthoracic biopsies from lung, pleural or mediastinal lesions from June 2019 to June 2020, and who had a follow-up chest radiograph after the procedure. These chest radiographs were read to search the presence of pneumothorax independently by an expert thoracic radiologist and a radiodiagnosis resident, whose unified lecture was defined as the gold standard, and the result of each radiograph after interpretation by the artificial intelligence software was documented for posterior comparison with the gold standard. ResultsA total of 284 chest radiographs were included in the study and the incidence of pneumothorax was 14.4%. There were no discrepancies between the two readers’ interpretation of any of the postbiopsy chest radiographs. The artificial intelligence software was able to detect 41/41 of the present pneumothorax, implying a sensitivity of 100% and a negative predictive value of 100%, with a specificity of 79.4% and a positive predictive value of 45%. The accuracy was 82.4%, indicating that there is a high probability that an individual will be adequately classified by the software. It has also been documented that the presence of Port-a-cath is the cause of 8 of the 50 of false positives by the software. ConclusionsThe software has detected 100% of cases of pneumothorax in the postbiopsy chest radiographs. A potential use of this software could be as a prioritisation tool, allowing radiologists not to read immediately (or even not to read) chest radiographs classified as non-pathological by the software, with the confidence that there are no pathological cases.

Inter-rater reliability of a novel objective endpoint for benign central airway stenosis interventions: Segmentation-based volume rendering of computed tomography scans.

To evaluate the reliability of a novel segmentation-based volume rendering approach for quantification of benign central airway obstruction (BCAO). A retrospective single-center cohort study. Data were ascertained using electronic health records at a tertiary academic medical center in the United States. Patients with airway stenosis located within the trachea on two-dimensional (2D) computed tomography (CT) imaging and documentation of suspected benign etiology were included. Four readers with varying expertise in quantifying tracheal stenosis severity were selected to manually segment each CT using a volume rendering approach with the available free tools in the medical imaging viewing software OsiriX (Bernex, Switzerland). Three expert thoracic radiologists were recruited to quantify the same CTs using traditional subjective methods on a continuous and categorical scale. The interrater reliability for continuous variables was calculated by the intraclass correlation coefficient (ICC) using a two-way mixed model with 95% confidence intervals (CI). Thirty-eight patients met the inclusion criteria, and fifty CT scans were selected for measurement. The most common etiology of BCAO was iatrogenic in 22 patients (58%). There was an even distribution of chest and neck CT imaging within our cohort. The average ICC across all four readers for the volume rendering approach was 0.88 (95% CI, 0.84 to 0.93), suggesting good to excellent agreement. The average ICC for thoracic radiologists for subjective methods on the continuous scale was 0.38 (95% CI, 0.20 to 0.55), suggesting poor to fair agreement. The kappa for the categorical approach was 0.26, suggesting a slight to fair agreement amongst the raters. In this retrospective cohort study, agreement was good to excellent for raters with varying expertise in airway cross-sectional imaging using a novel segmentation-based volume rendering approach to quantify BCAO. This proposed measurement outperformed our expert thoracic radiologists using conventional subjective grading methods.

Utilidad de la inteligencia artificial para la detección de neumotórax en radiografías de tórax de control tras punción percutánea transtorácica guiada por tomografía computarizada

ObjectiveTo assess the ability of an artificial intelligence software to detect pneumothorax in chest radiographs done after percutaneous transthoracic biopsy. Material and methodsWe included retrospectively in our study adult patients who underwent CT-guided percutaneous transthoracic biopsies from lung, pleural or mediastinal lesions from June 2019 to June 2020, and who had a follow-up chest radiograph after the procedure. These chest radiographs were read to search the presence of pneumothorax independently by an expert thoracic radiologist and a radiodiagnosis resident, whose unified lecture was defined as the gold standard, and the result of each radiograph after interpretation by the artificial intelligence software was documented for posterior comparison with the gold standard. ResultsA total of 284 chest radiographs were included in the study and the incidence of pneumothorax was 14.4%. There were no discrepancies between the two readers’ interpretation of any of the postbiopsy chest radiographs. The artificial intelligence software was able to detect 41/41 of the present pneumothorax, implying a sensitivity of 100% and a negative predictive value of 100%, with a specificity of 79.4% and a positive predictive value of 45%. The accuracy was 82.4%, indicating that there is a high probability that an individual will be adequately classified by the software. It has also been documented that the presence of Port-a-cath is the cause of 8 of the 50 of false positives by the software. ConclusionsThe software has detected 100% of cases of pneumothorax in the postbiopsy chest radiographs. A potential use of this software could be as a prioritization tool, allowing radiologists not to read immediately (or even not to read) chest radiographs classified as non-pathological by the software, with the confidence that there are no pathological cases.

Lung CAncer SCreening in French women using low-dose CT and Artificial intelligence for DEtection: the CASCADE study protocol

IntroductionLung cancer screening (LCS) using low-dose CT has been demonstrated to reduce lung cancer-related mortality in large randomised controlled trials. Moving from trials to practice requires answering practical questions about...

Diagnostic performance of the RSNA-proposed classification for COVID-19 pneumonia versus pre-pandemic controls

ObjectiveTo evaluate the diagnostic accuracy of the Radiological Society of North America (RSNA) classification system for coronavirus disease 2019 (COVID-19) pneumonia compared to pre-pandemic chest computed tomography (CT) scan images to mitigate the risk of bias regarding the reference standard. Materials and methodsThis was a retrospective, cross-sectional, diagnostic test accuracy study. Chest CT scans, carried out from May 1 to June 30, 2020, and from May 1 to July 17, 2017, were consecutively selected for the COVID-19 (positive reverse transcription-polymerase chain reaction [RT-PCR] for severe acute respiratory syndrome coronavirus 2 result) and control (pre-pandemic) groups, respectively. Four expert thoracic radiologists blindly interpreted each CT scan image. Sensitivity and specificity were calculated. ResultsA total of 160 chest CT scan images were included: 79 in the COVID-19 group (56 [43.5–67] years old, 41 men) and 81 in the control group (62 [52–72] years old, 44 men). Typically, an estimated specificity of 98.5% (95% confidence interval [CI] 98.1%–98.4%) was obtained. For the indeterminate classification as a diagnostic threshold, an estimated sensitivity of 88.3% (95% CI 84.7%–91.7%) and a specificity of 79.0% (95% CI 74.5%–83.4%), with an area under the curve of 0.865 (95% CI 0.838–0.895), were obtained. ConclusionThe RSNA classification system shows strong diagnostic accuracy for COVID-19 pneumonia, even against pre-pandemic controls. It can be an important aid in clinical decision-making, especially when a typical or indeterminate pattern is found, possibly advising retesting following an initial negative RT-PCR result and streamlining early management and isolation.

Establishing diagnostic criteria and treatment of subsegmental pulmonary embolism: A Delphi analysis of experts

BackgroundImproved imaging techniques have increased the incidence of subsegmental pulmonary embolism (ssPE). Indirect evidence is suggesting that ssPE may represent a more benign presentation of venous thromboembolism not necessarily requiring anticoagulant treatment. However, correctly diagnosing ssPE is challenging with reported low interobserver agreement, partly due to the lack of widely accepted diagnostic criteria. ObjectivesWe sought to derive uniform diagnostic criteria for ssPE, guided by expert consensus. MethodsBased on an extensive literature review and expert opinion of a Delphi steering committee, two surveys including statements regarding diagnostic criteria and management options for ssPE were established. These surveys were conducted electronically among two panels, respectively: expert thoracic radiologists and clinical venous thromboembolism specialists. The Delphi method was used to achieve consensus after multiple survey rounds. Consensus was defined as a level of agreement >70%. ResultsTwenty‐nine of 40 invited radiologists (73%) and 40 of 51 clinicians (78%) participated. Following two survey rounds by the expert radiologists, consensus was achieved on 15 of 16 statements, including on the established diagnostic criteria for ssPE (96% agreement): a contrast defect in a subsegmental artery, that is, the first arterial branch division of any segmental artery independent of artery diameter, visible in at least two subsequent axial slices, using a computed tomography scanner with a desired maximum collimator width of ≤1 mm. These criteria were approved by 83% of the clinical venous thromboembolism (VTE) specialists. The clinical expert panel favored anticoagulant treatment in case of prior VTE, antiphospholipid syndrome, pregnancy, cancer, and proximal deep vein thrombosis. ConclusionThe results of this analysis provide standard radiological criteria for ssPE that may be applicable in both clinical trials and practice.

Short-term Reproducibility of Pulmonary Nodule and Mass Detection in Chest Radiographs: Comparison among Radiologists and Four Different Computer-Aided Detections with Convolutional Neural Net

To investigate the reproducibility of computer-aided detection (CAD) for detection of pulmonary nodules and masses for consecutive chest radiographies (CXRs) of the same patient within a short-term period. A total of 944 CXRs (Chest PA) with nodules and masses, recorded between January 2010 and November 2016 at the Asan Medical Center, were obtained. In all, 1092 regions of interest for the nodules and mass were delineated using an in-house software. All CXRs were randomly split into 6:2:2 sets for training, development, and validation. Furthermore, paired follow-up CXRs (n = 121) acquired within one week in the validation set, in which expert thoracic radiologists confirmed no changes, were used to evaluate the reproducibility of CAD by two radiologists (R1 and R2). The reproducibility comparison of four different convolutional neural net algorithms and two chest radiologists (with 13- and 14-years’ experience) was conducted. Model performances were evaluated by figure-of-merit (FOM) analysis of the jackknife free-response receiver operating curve and reproducibility rates were evaluated in terms of percent positive agreement (PPA) and Chamberlain’s percent positive agreement (CPPA). Reproducibility analysis of the four CADs and R1 and R2 showed variations in the PPA and CPPA. Model performance of YOLO (You Only Look Once) v2 based eDenseYOLO showed a higher FOM (0.89; 0.85–0.93) than RetinaNet (0.89; 0.85–0.93) and atrous spatial pyramid pooling U-Net (0.85; 0.80–0.89). eDenseYOLO showed higher PPAs (97.87%) and CPPAs (95.80%) than Mask R-CNN, RetinaNet, ASSP U-Net, R1, and R2 (PPA: 96.52%, 94.23%, 95.04%, 96.55%, and 94.98%; CPPA: 93.18%, 89.09%, 90.57%, 93.33%, and 90.43%). There were moderate variations in the reproducibility of CAD with different algorithms, which likely indicates that measurement of reproducibility is necessary for evaluating CAD performance in actual clinical environments.

High-Resolution CT Change over Time in Patients with Idiopathic Pulmonary Fibrosis on Antifibrotic Treatment.

Antifibrotic treatment slows down functional decline and disease progression in idiopathic pulmonary fibrosis (IPF). High-resolution computed tomography (HRCT) is useful to diagnose IPF; however, little is known about whether and to what extent HRCT changes reflect functional changes during antifibrotic therapy. The aim of this study was, therefore, to assess HRCT change over time after 1 year of treatment and to evaluate whether these changes correlate with functional decline over the same period of time. Sixty-eight IPF patients on antifibrotic treatment (i.e., pirfenidone or nintedanib) were functionally categorized as stable or progressors based on whether (or not) they had a decline in forced vital capacity (FVC) >5% predicted/year, and their HRCT were scored blindly and independently by two expert thoracic radiologists at treatment initiation (HRCT1) and after 1 year of treatment (HRCT2). Ground glass opacities (Alveolar Score, AS), reticulations (Interstitial Score, IS) and honeycombing (HC) were quantified and correlated with FVC decline between HRCT1 and HRCT2. At treatment initiation, HRCT scores were similar in both stable patients and progressors. After one year of treatment, in the entire population, AS and HC increased significantly, while IS did not. However, when stratified by the rate of functional decline, in stable patients, HC increased significantly while AS and IS did not. On the other hand, among progressors AS and HC increased significantly whereas IS did not. In the entire population, the combined score of fibrosis (IS + HC) correlated significantly with FVC decline. In conclusion, IPF patients on antifibrotic treatment exhibit different patterns of HRCT change over time based on their rate of functional decline. HRCT data should be integrated to lung function data when assessing response to antifibrotic treatment in patients with IPF.

Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks.

A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1-2-mm slices, 5-10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18mm, and 25.47 ± 13.63mm, respectively. Our deep-learning method showed significantly better segmentation performance (p < 0.001), and its segmentation accuracies for volumetric CT were similar to those for HRCT. We have developed an accurate and robust U-Net-based DILD lung segmentation method that can be used for patients scanned with different clinical protocols, including HRCT and volumetric CT.

A Prospective Study of Magnetic Resonance Imaging Assessment of Post-radiation Changes Following Stereotactic Body Radiation Therapy for Non-small Cell Lung Cancer

AimsFollow-up computed tomography scans after lung stereotactic body radiation therapy (SBRT) are difficult to interpret due to the presence of benign fibrosis, which can make the detection of local recurrence difficult. The objective of this study was to determine the feasibility of a novel thoracic magnetic resonance imaging (MRI) protocol incorporating diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) imaging for the assessment of the treated lung parenchyma after SBRT. Materials and methodsOn a prospective trial, post-treatment MR images were acquired in 30 patients treated with SBRT (divided into three different cohorts according to the likelihood of local recurrence as per an expert panel). These images were assessed by an expert thoracic radiologist blind to clinical data, who indicated local recurrence in a dichotomous manner. Local recurrence was confirmed by biopsy or subsequent growth on follow-up computed tomography scans. ResultsThirty patients underwent MRI as part of this study; 27/30 patients were analysable for local recurrence. MRI was conducted at a median of 27.3 months (range 6.5–71 months) from SBRT. No side-effects resulted from either MRI or contrast administration. At a median follow-up time of 45 months after treatment, three local recurrence episodes have occurred. MRI assessment diagnosed seven patients as having a local recurrence, which was later confirmed in three and did not miss any of the true local recurrences. When comparing apparent diffusion coefficient (ADC) values according to local recurrence, the mean ADC value for the local recurrence-free group was 1770 × 10−3 mm/s2 (range 1038–3105 × 10−3 mm/s2) versus 981 × 10−3 mm/s2 (range 926.6–1065 × 10−3 mm/s2) for the local recurrence group (P = 0.0014). ConclusionsA novel 3.0 T MRI protocol incorporating DWI and DCE was feasible and confirmed the suspicion of local recurrence in patients with highly suspicious computed tomography scans. This imaging tool could potentially aid in selecting patients for salvage treatment after local SBRT failure. Future work should be pursued to validate these findings.

Fully Automated Lung Lobe Segmentation in Volumetric Chest CT with 3D U-Net: Validation with Intra- and Extra-Datasets.

Lung lobe segmentation in chest CT has been used for the analysis of lung functions and surgical planning. However, accurate lobe segmentation is difficult as 80% of patients have incomplete and/or fake fissures. Furthermore, lung diseases such as chronic obstructive pulmonary disease (COPD) can increase the difficulty of differentiating the lobar fissures. Lobar fissures have similar intensities to those of the vessels and airway wall, which could lead to segmentation error in automated segmentation. In this study, a fully automated lung lobe segmentation method with 3D U-Net was developed and validated with internal and external datasets. The volumetric chest CT scans of 196 normal and mild-to-moderate COPD patients from three centers were obtained. Each scan was segmented using a conventional image processing method and manually corrected by an expert thoracic radiologist to create gold standards. The lobe regions in the CT images were then segmented using a 3D U-Net architecture with a deep convolutional neural network (CNN) using separate training, validation, and test datasets. In addition, 40 independent external CT images were used to evaluate the model. The segmentation results for both the conventional and deep learning methods were compared quantitatively to the gold standards using four accuracy metrics including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). In internal validation, the segmentation method achieved high accuracy for the DSC, JSC, MSD, and HSD (0.97±0.02, 0.94±0.03, 0.69±0.36, and 17.12±11.07, respectively). In external validation, high accuracy was also obtained for the DSC, JSC, MSD, and HSD (0.96±0.02, 0.92±0.04, 1.31±0.56, and 27.89±7.50, respectively). This method took 6.49±1.19s and 8.61±1.08s for lobe segmentation of the left and right lungs, respectively. Although various automatic lung lobe segmentation methods have been developed, it is difficult to develop a robust segmentation method. However, the deep learning-based 3D U-Net method showed reasonable segmentation accuracy and computational time. In addition, this method could be adapted and applied to severe lung diseases in a clinical workflow.

MOLECULAR DIAGNOSIS OF USUAL INTERSTITIAL PNEUMONIA (UIP) FROM TRANSBRONCHIAL BIOPSY IS ACCURATE IN SUBJECTS WITHOUT DEFINITE OR PROBABLE UIP ON CT

SESSION TITLE: Diagnosis and Treatment of Idiopathic Pulmonary Fibrosis SESSION TYPE: Original Investigations PRESENTED ON: 10/08/2018 07:30 am - 08:30 am PURPOSE: Under the diagnostic criteria for idiopathic pulmonary fibrosis (IPF) recently proposed by the Fleischner Society, histologic confirmation of UIP by tissue biopsy is necessary for a confident diagnosis of IPF if high-resolution computed tomography (HRCT) does not show either definite or probable usual interstitial pneumonia (UIP), in the clinical context of an idiopathic interstitial pneumonia. If histopathology is not available or not definitive, a working IPF diagnosis may be appropriate. The Envisia Genomic Classifier (Envisia) detects UIP at the molecular level (‘molecular UIP’) in transbronchial biopsy samples, using a locked machine learning algorithm applied to the expression of 190 genes. In a prospective, multi-center validation study of 49 subjects undergoing clinical evaluation for new-onset interstitial lung disease (BRonchial sAmple collection for a noVel gEnomic test, BRAVE), Envisia shows 88% specificity and 70% sensitivity for histopathology-proven UIP. We report Envisia performance in validation cohort subjects who had HRCT patterns other than definite or probable UIP, determined by local radiology diagnoses and by central radiology review. METHODS: HRCT scans and diagnoses were obtained from BRAVE sites. Available scans were reviewed by an expert thoracic radiologist and diagnosed as definite UIP, probable UIP, possible UIP, non-UIP or ‘other’. For categorical comparison (Cohen’s kappa), specific non-UIP and ‘other’ diagnoses were defined as ‘inconsistent with UIP’. RESULTS: 46 of 49 validation subjects had available HRCT scans. Diagnostic agreement between local and central radiology was low (kappa= 0.28), but improved when confident UIP (definite or probable UIP) was compared to those with either possible UIP or a pattern inconsistent with UIP (kappa =0.49). We excluded 4 subjects with definite or probable UIP patterns by both local and central radiology, as these subjects would be considered already to have a confident diagnosis. Among 42 subjects without definite or probable UIP on HRCT (40% UIP prevalence by histopathology), Envisia showed specificity of 88% [CI:69%-97%], sensitivity of 76% [CI:50%-93%], positive predictive value of 81% [54%-96%] and negative predictive value of 85% [CI:65%-96%]. CONCLUSIONS: In a retrospective analysis of subjects with HRCT patterns other than definite or probable UIP, Envisia molecular UIP had >80% predictive value for histologically-proven UIP. CLINICAL IMPLICATIONS: Molecular UIP results may be useful in the multidisciplinary evaluation of subjects without high-confidence HRCT patterns, who are being considered for surgical biopsy. In the appropriate clinical context, the high predictive value of molecular UIP may support confident IPF diagnosis without surgery. DISCLOSURES: Consultant relationship with Veracyte Please note: $1001 - $5000 Added 03/03/2018 by Kevin Brown, source=Web Response, value=Consulting fee No relevant relationships by Yoonha Choi, source=Web Response No relevant relationships by Thomas Colby, source=Web Response Consultant relationship with Veracyte Please note: $5001 - $20000 Added 03/15/2018 by Steve Groshong, source=Web Response, value=Consulting fee Employee relationship with Veracyte Inc Please note: >$100000 Added 03/04/2018 by Jing Huang, source=Web Response, value=Salary Employee relationship with Veracyte Please note: >$100000 Added 03/27/2018 by Giulia Kennedy, source=Admin input, value=Salary Employee relationship with Veracyte Please note: >$100000 Added 03/03/2018 by Lori Lofaro, source=Web Response, value=Salary Consultant relationship with Boehringer Ingelheim Please note: $1-$1000 Added 03/02/2018 by David Lynch, source=Web Response, value=Honoraria Scientific Medical Advisor relationship with Siemens Please note: $5001 - $20000 Added 03/02/2018 by David Lynch, source=Web Response, value=Grant/Research Support Scientific Medical Advisor relationship with Veracyte Please note: $5001 - $20000 Added 03/02/2018 by David Lynch, source=Web Response, value=Grant/Research Support Scientific Medical Advisor relationship with Acceleron Please note: $1001 - $5000 Added 03/02/2018 by David Lynch, source=Web Response, value=Consulting fee Consultant relationship with Parexel Please note: $5001 - $20000 Added 03/02/2018 by David Lynch, source=Web Response, value=Grant/Research Support No relevant relationships by Jeffrey Myers, source=Web Response Employee relationship with Veracyte, Inc Please note: $20001 - $100000 Added 03/04/2018 by Hannah Neville, source=Web Response, value=Salary Employee relationship with Veracyte Please note: >$100000 Added 03/05/2018 by Daniel Pankratz, source=Web Response, value=Salary Consultant relationship with BI, FIbrogen, Gilead,Promedior,Patara,Sanofi ,Veracyte Please note: $5001 - $20000 Added 03/03/2018 by Ganesh Raghu, source=Web Response, value=Travel no disclosure on file for Mark Steele; No relevant relationships by Patric Walsh, source=Web Response

Agreement between expert thoracic radiologists and the chest radiograph reports provided by consultant radiologists and reporting radiographers in clinical practice: Review of a single clinical site

IntroductionTo compare the clinical chest radiograph (CXR) reports provided by consultant radiologists and reporting radiographers with expert thoracic radiologists. MethodsAdult CXRs (n = 193) from a single site were included; 83% randomly selected from CXRs performed over one year, and 17% selected from the discrepancy meeting. Chest radiographs were independently interpreted by two expert thoracic radiologists (CTR1/2).Clinical history, previous and follow-up imaging was available, but not the original clinical report. Two arbiters compared expert and clinical reports independently. Kappa (Ƙ), Chi Square (χ2) and McNemar tests were performed to determine inter-observer agreement. ResultsCTR1 interpreted 187 (97%) and CTR2 186 (96%) CXRs, with 180 CXRs interpreted by both experts. Radiologists and radiographers provided 93 and 87 of the original clinical reports respectively. Consensus between both expert thoracic radiologists and the radiographer clinical report was 70 (CTR1; Ƙ = 0.59) and 70 (CTR2; Ƙ = 0.62), and comparable to agreement between expert thoracic radiologists and the radiologist clinical report (CTR1 = 76, Ƙ = 0.60; CTR2 = 75, Ƙ = 0.62). Expert thoracic radiologists agreed in 131 cases (Ƙ = 0.48). There was no difference in agreement between either expert thoracic radiologist, when the clinical report was provided by radiographers or radiologists (CTR1 χ = 0.056, p = 0.813; CTR2 χ = 0.014, p = 0.906), or when stratified by inter-expert agreement; radiographer McNemar p = 0.629 and radiologist p = 0.701. ConclusionEven when weighted with chest radiographs reviewed at discrepancy meetings, content of CXR reports from trained radiographers were indistinguishable from content of reports issued by radiologists and expert thoracic radiologists.

A fast and robust level set motion-assisted deformable registration method for volumetric CT guided lung intervention

This paper describes the accurate deformable registration method for image-guided lung interventions, including lung nodule biopsy and radiofrequency ablation of lung tumours. A level set motion assisted deformable registration method for computed tomography (CT) images was proposed and its accuracy and speed were compared with those of other conventional methods. Fifteen 3D CT images obtained from lung biopsy patients were scanned. Each scan consisted of diagnostic and preoperative CT images. Each deformable registration method was initially evaluated with a landmark-based affine registration algorithm. Various deformable registration methods such as level set motion, demons, diffeomorphic demons, and b-spline were compared. Visual assessment by two expert thoracic radiologists using five scales showed an average visual score of 3.2 for level set motion deformable registration, whereas scores were below 3 for other deformable registration methods. In the qualitative assessment, the level set motion algorithm showed better results than those obtained with other deformable registration methods. A level set motion based deformable registration algorithm was effective for registering diagnostic and preoperative volumetric CT images for image-guided lung intervention.

Structured reporting for fibrosing lung disease: a model shared by radiologist and pulmonologist

ObjectivesTo apply the Delphi exercise with iterative involvement of radiologists and pulmonologists with the aim of defining a structured reporting template for high-resolution computed tomography (HRCT) of patients with fibrosing lung disease (FLD).MethodsThe writing committee selected the HRCT criteria—the Delphi items—for rating from both radiology panelists (RP) and pulmonology panelists (PP). The Delphi items were first rated by RPs as “essential”, “optional”, or “not relevant”. The items rated “essential” by < 80% of the RP were selected for the PP rating. The format of reporting was rated by both RP and PP.ResultsA total of 42 RPs and 12 PPs participated to the survey. In both Delphi round 1 and 2, 10/27 (37.7%) items were rated “essential” by more than 80% of RP. The remaining 17/27 (63.3%) items were rated by the PP in round 3, with 2/17 items (11.7%) rated “essential” by the PP. PP proposed additional items for conclusion domain, which were rated by RPs in the fourth round. Poor consensus was observed for the format of reporting.ConclusionsThis study provides a template for structured report of FLD that features essential items as agreed by expert thoracic radiologists and pulmonologists.

High resolution computed tomography pattern of usual interstitial pneumonia in rheumatoid arthritis-associated interstitial lung disease: Relationship to survival

PurposeInterstitial lung disease is a common extra-articular manifestation of rheumatoid arthritis (RA-ILD) and is associated with significant morbidity and mortality. However, limited data exist regarding predictors of mortality. We sought to examine the prognostic value of the high-resolution computed tomography (HRCT) patterns in patients with RA-ILD. Materials and methodsRA-ILD patients with HRCT patterns of usual interstitial pneumonia (UIP) or nonspecific interstitial pneumonia (NSIP) were identified among a longitudinal cohort of individuals evaluated at National Jewish Health. A total of 158 subjects were included in the study. For each subject, the earliest available HRCT was reviewed independently by two expert thoracic radiologists blinded to clinical data. HRCT patterns were classified as demonstrating definite UIP, possible UIP, or NSIP. Kaplan-Meier curves were generated and survival was compared among the three patterns using a log rank test for trend. ResultsOne hundred subjects (63%) had HRCT findings classified as definite UIP, 23 (15%) as possible UIP and 35 (22%) as NSIP. No difference in survival was seen between subjects with definite UIP versus those with possible UIP. The combined group of subjects with either definite- or possible UIP had significantly worse survival than those with NSIP (log-rank p = 0.03). ConclusionsIn patients with RA-ILD, patients with either definite UIP or possible UIP have equally poor survival when compared to those with an NSIP pattern.

Incidental pulmonary embolism in cancer patients: Interobserver agreement on the diagnosis and extent with a focus on distal clots

BackgroundThe incidence of incidental pulmonary embolism (IPE) in cancer patients is increasing. There is scant information on the interobserver agreement among radiologists about the diagnosis of distal incidental clots and the actual radiologic extension of IPE. MethodsA total of 88 contrast-enhanced computed tomography (CT) scans of cancer patients with IPE were reassessed blindly by two expert thoracic radiologists. First, 62 scans were reassessed and the interobserver agreement on most proximal extent of IPE was calculated between the two expert radiologists as well as between the initial and expert reading, using the kappa statistic. The sample was enriched with 26 additional scans for a total of 30 segmental and 29 subsegmental IPE to determine the interobserver agreement on distal clots. ResultsThe level of agreement regarding the most proximal extent of IPE between the expert radiologists was very good (kappa 0.84; 95% CI, 0.73–0.95) and poor between the original radiologist and expert radiologists (kappa 0.39; 95% CI, 0.22–0.56). In the patients with segmental or subsegmental IPE on initial reading, the expert radiologists agreed with the segmental location in 12 out of 30 patients (40%) and with the subsegmental location in 17 out of 29 patients (59%). The interobserver agreement between the expert radiologists was good (kappa 0.68; 95% CI, 0.46–0.90) and moderate (kappa 0.48; 95% CI, 0.25–0.71), respectively. ConclusionsWhile the interobserver agreement between radiologists on the most proximal location of IPE in cancer patients appears to be fairly good, it decreases significantly for more distally located incidental clots.