Radiomics-based decision support tool assists radiologists in small lung nodule classification and improves lung cancer early diagnosis.

BACKGROUND: Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis. METHODS: Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools. RESULTS: In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers. CONCLUSIONS: SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.

A Comparison of Long-Term Outcomes in Patients Managed With Venovenous Extracorporeal Membrane Oxygenation in the First and Second Waves of the COVID-19 Pandemic in the United Kingdom.

OBJECTIVES: Early studies of venovenous extracorporeal membrane oxygenation (ECMO) in COVID-19 have revealed similar outcomes to historical cohorts. Changes in the disease and treatments have led to differences in the patients supported on venovenous ECMO in the first and second waves. We aimed to compare these two groups in both the acute and follow-up phase. DESIGN: Retrospective single-center cohort study comparing mortality at censoring date (November 30, 2021) and decannulation, patient characteristics, complications and lung function and quality of life (QOL-by European Quality of Life 5 Dimensions 3 Level Version) at first follow-up in patients supported on venovenous ECMO between wave 1 and wave 2 of the COVID-19 pandemic. SETTING: Critical care department of a severe acute respiratory failure service. PATIENTS: Patients supported on ECMO for COVID-19 between wave 1 (March 17, 2020, to August 31, 2020) and wave 2 (January 9, 2020, to May 25, 2021). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: One hundred twenty-three patients were included in our analysis. Survival at censoring date (χ 2 , 6.35; p = 0.012) and decannulation (90.4% vs 70.0%; p < 0.001) was significantly lower in the second wave, while duration of ECMO run was longer (12.0 d [18.0-30.0 d] vs 29.5 d [15.5-58.3 d]; p = 0.005). Wave 2 patients had longer application of noninvasive ventilation (NIV) prior to ECMO and a higher frequency of barotrauma. Patient age and NIV use were independently associated with increased mortality (odds ratio 1.07 [1.01-1.14]; p = 0.025 and 3.37 [1.12-12.60]; p = 0.043, respectively). QOL and lung function apart from transfer coefficient of carbon monoxide corrected for hemoglobin was similar at follow-up across the waves. CONCLUSIONS: Most patients with COVID-19 supported on ECMO in both waves survived in the short and longer term. At follow-up patients had similar lung function and QOL across the two waves. This suggests that ECMO has an ongoing role in the management of a carefully selected group of patients with COVID-19.

Prevalence of Thrombotic Complications in ICU-Treated Patients With Coronavirus Disease 2019 Detected With Systematic CT Scanning.

OBJECTIVES: Severe coronavirus disease 2019 is associated with an extensive pneumonitis and frequent coagulopathy. We sought the true prevalence of thrombotic complications in critically ill patients with severe coronavirus disease 2019 on the ICU, with or without extracorporeal membrane oxygenation. DESIGN: We undertook a single-center, retrospective analysis of 72 critically ill patients with coronavirus disease 2019-associated acute respiratory distress syndrome admitted to ICU. CT angiography of the thorax, abdomen, and pelvis were performed at admission as per routine institution protocols, with further imaging as clinically indicated. The prevalence of thrombotic complications and the relationship with coagulation parameters, other biomarkers, and survival were evaluated. SETTING: Coronavirus disease 2019 ICUs at a specialist cardiorespiratory center. PATIENTS: Seventy-two consecutive patients with coronavirus disease 2019 admitted to ICU during the study period (March 19, 2020, to June 23, 2020). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: All but one patient received thromboprophylaxis or therapeutic anticoagulation. Among 72 patients (male:female = 74%; mean age: 52 ± 10; 35 on extracorporeal membrane oxygenation), there were 54 thrombotic complications in 42 patients (58%), comprising 34 pulmonary arterial (47%), 15 peripheral venous (21%), and five (7%) systemic arterial thromboses/end-organ embolic complications. In those with pulmonary arterial thromboses, 93% were identified incidentally on first screening CT with only 7% suspected clinically. Biomarkers of coagulation (e.g., d-dimer, fibrinogen level, and activated partial thromboplastin time) or inflammation (WBC count, C-reactive protein) did not discriminate between patients with or without thrombotic complications. Fifty-one patients (76%) survived to discharge; 17 (24%) patients died. Mortality was significantly greater in patients with detectable thrombus (33% vs 10%; p = 0.022). CONCLUSIONS: There is a high prevalence of thrombotic complications, mainly pulmonary, among coronavirus disease 2019 patients admitted to ICU, despite anticoagulation. Detection of thrombus was usually incidental, not predicted by coagulation or inflammatory biomarkers, and associated with increased risk of death. Systematic CT imaging at admission should be considered in all coronavirus disease 2019 patients requiring ICU.

Pulmonary Angiopathy in Severe COVID-19: Physiologic, Imaging, and Hematologic Observations.

Rationale: Clinical and epidemiologic data in coronavirus disease (COVID-19) have accrued rapidly since the outbreak, but few address the underlying pathophysiology.Objectives: To ascertain the physiologic, hematologic, and imaging basis of lung injury in severe COVID-19 pneumonia.Methods: Clinical, physiologic, and laboratory data were collated. Radiologic (computed tomography (CT) pulmonary angiography [n = 39] and dual-energy CT [DECT, n = 20]) studies were evaluated: observers quantified CT patterns (including the extent of abnormal lung and the presence and extent of dilated peripheral vessels) and perfusion defects on DECT. Coagulation status was assessed using thromboelastography.Measurements and Results: In 39 consecutive patients (male:female, 32:7; mean age, 53 ± 10 yr [range, 29-79 yr]; Black and minority ethnic, n = 25 [64%]), there was a significant vascular perfusion abnormality and increased physiologic dead space (dynamic compliance, 33.7 ± 14.7 ml/cm H2O; Murray lung injury score, 3.14 ± 0.53; mean ventilatory ratios, 2.6 ± 0.8) with evidence of hypercoagulability and fibrinolytic "shutdown". The mean CT extent (±SD) of normally aerated lung, ground-glass opacification, and dense parenchymal opacification were 23.5 ± 16.7%, 36.3 ± 24.7%, and 42.7 ± 27.1%, respectively. Dilated peripheral vessels were present in 21/33 (63.6%) patients with at least two assessable lobes (including 10/21 [47.6%] with no evidence of acute pulmonary emboli). Perfusion defects on DECT (assessable in 18/20 [90%]) were present in all patients (wedge-shaped, n = 3; mottled, n = 9; mixed pattern, n = 6).Conclusions: Physiologic, hematologic, and imaging data show not only the presence of a hypercoagulable phenotype in severe COVID-19 pneumonia but also markedly impaired pulmonary perfusion likely caused by pulmonary angiopathy and thrombosis.

Role of Quantitative Computed Tomographic Scan Analysis in Lung Volume Reduction for Emphysema.

Recent advances in bronchoscopic lung volume reduction (BLVR) offer new therapeutic alternatives for patients with emphysema and hyperinflation. Endobronchial valves and coils are 2 potential BLVR techniques which have been shown to improve pulmonary function and the quality of life in patients with emphysema. Current patient selection for LVR procedures relies on 3 main inclusion criteria: low attenuation area (in %), also known as emphysema score, heterogeneity score, and fissure integrity score. Volumetric analysis in combination with densitometric analysis of the affected lung lobe or segment with quantitative CT to determine emphysema severity play an important role in treatment planning and post-operative assessment. Due to the variations in lung anatomy, manual corrections are often required to ensure successful and accurate lobe segmentation for pathological and post-treatment CT scan analysis. The advanced development and utilisation of quantitative CT do not simply represent regional changes in pulmonary function but aids in analysis for better patient selection with severe emphysema who are most likely to benefit from BLVR.

Quantitative Evaluation of Lobar Pulmonary Function of Emphysema Patients with Endobronchial Coils.

BACKGROUND: Recent advances in bronchoscopic lung volume reduction offer new therapies for patients with emphysema and hyperinflation. Pulmonary lobe segmentation with quantification of lobar volumes and emphysema severity plays a pivotal role in treatment planning and post-interventional assessment. Computed tomography (CT)-derived lobar volumes could reflect more accurate regional changes in pulmonary function. OBJECTIVES: The aim of our study is to validate the reliability of an in-house CT Lung Segmentation software (LungSeg; the Hamlyn Centre, Imperial College London, UK) for lung lobar volume and emphysema quantification for chronic obstructive pulmonary disease (COPD) patients. METHODS: A total of 108 CT scans from subjects who participated in an endobronchial coil treatment trial were included. Lobar volume and emphysema quantification were performed using the LungSeg and Syngo CT Pulmo 3D package (Siemens Healthcare GmbH, Germany). The inter-user reliability of the LungSeg program was investigated. Correlation coefficients and Bland-Altman analyses were used to quantify the inter-software variability. The agreement between CT volume analysis and plethysmography analysis was also examined. RESULTS: The high intraclass correlation coefficients (mean ICC = 0.98) of the lobar volumes and emphysema indices measured by LungSeg suggest its excellent reproducibility. The LungSeg and Syngo program have good correlation (rho ≥0.94) and agreement for both lobar volume (median difference = 94 mL and LOAnp = 214.6 mL) and emphysema index (median difference ≤1.5% and LOAnp ≤2.03%) calculations. CT analysis provides a higher estimation of total lung capacity (TLCCT) than body plethysmography (TLCpleth), while there is a fair agreement on residual volume (RVCT) by LungSeg as compared with body plethysmography (RVpleth). CONCLUSIONS: CT-derived lobar volume and emphysema quantification using the LungSeg program is efficient and reliable in allowing lobar volume assessment. LungSeg has low inter-user variability and agrees better with plethysmography for COPD assessment in our study.

Differentiating between Subsolid and Solid Pulmonary Nodules at CT: Inter- and Intraobserver Agreement between Experienced Thoracic Radiologists.

PURPOSE: To quantify the reproducibility and accuracy of experienced thoracic radiologists in differentiating between subsolid and solid pulmonary nodules at CT. MATERIALS AND METHODS: The institutional review board of Beth Israel Deaconess Medical Center approved this multicenter study. Six thoracic radiologists, with a mean of 21 years of experience in thoracic radiology (range, 17-22 years), selected images of 10 solid and 10 subsolid nodules to create a database of 120 nodules; this selection served as the reference standard. Each radiologist then interpreted 120 randomly ordered nodules in two different sessions that were separated by a minimum of 3 weeks. The radiologists classified whether or not each nodule was subsolid. Inter- and intraobserver agreement was assessed with a κ statistic. The number of correct classifications was calculated and correlated with nodule size by using Bland-Altman plots. The relationship between disagreement and nodule morphologic characteristics was analyzed by calculating the intraclass correlation coefficient. RESULTS: Interobserver agreement (κ) was 0.619 (range, 0.469-0.745; 95% confidence interval (CI): 0.576, 0.663) and 0.670 (range, 0.440-0.839; 95% CI: 0.608, 0.733) for interpretation sessions 1 and 2, respectively. Intraobserver agreement (κ) was 0.792 (95% CI: 0.750, 0.833). Averaged for interpretation sessions, correct classification was achieved by all radiologists for 58% (70 of 120) of nodules. Radiologists agreed with their initial determination (the reference standard) in 77% of cases (range, 45%-100%). Nodule size weakly correlated with correct classification (long axis: Spearman rank correlation coefficient, rs = 0.161 and P = .049; short axis: rs = 0.128 and P = .163). CONCLUSION: The reproducibility and accuracy of thoracic radiologists in classifying whether or not a nodule is subsolid varied in the retrospective study. This inconsistency may affect surveillance recommendations and prognostic determinations.

Sclerosed hemangioma of the liver: concordance of MRI features with histologic characteristics.

PURPOSE: To correlate the MRI features of sclerosed hemangiomas with histologic appearance. MATERIALS AND METHODS: A medical record search identified patients with sclerosed hemangioma who underwent MRI and biopsy/resection from January 2000 to March 2012 for this retrospective institutional review board approved study. Two radiologists independently performed image analysis. A pathologist evaluated lesion histologic characteristics. RESULTS: Twelve patients (median age 65; range 41­78 years) were included; 7/12 patients had typical hemangiomas which were also analyzed. Sclerosed hemangiomas were less often moderately T2 hyperintense (5/11 45%; compared with 7/7, 100%; P = 0.0377) and demonstrated moderate arterial phase enhancement less frequently (4/12, 33% compared with 7/7, 100%; P = 0.0128) than typical hemangiomas. Markedly sclerosed hemangiomas (N = 7) exhibited the least "typical" findings, including mild T2 hyperintensity (5/7; 71%), absent arterial phase enhancement (4/7; 57%), mild portal venous phase enhancement (6/7; 86%), and absent centripetal fill-in (6/7; 86%). Arterial phase hyperenhancement occurred more often in mild/moderately sclerosed hemangiomas (3/5; 60%) compared with markedly sclerosed hemangiomas (1/7; 14%). CONCLUSION: Sclerosed hemangiomas exhibit MRI features that appear to correspond with the degree of sclerosis. These features coupled with the presence of other typical hemangiomas may aid in prospectively diagnosing sclerosed hemangioma.

Radiofrequency ablation of T1 lung carcinoma: comparison of outcomes for first primary, metachronous, and synchronous lung tumors.

PURPOSE: To report and compare outcomes after radiofrequency ablation for treatment-naïve first primary, metachronous, and synchronous T1 lung tumors. MATERIALS AND METHODS: This institutional review board-approved retrospective study reviewed 29 patients (12 men and 17 women; median age, 73 y; age range, 55-86 y) with treatment-naïve T1 lung tumors treated with radiofrequency ablation. Tumors in the 29 patients included 21 T1a and 8 T1b first primary (n = 11), metachronous (n = 14), or synchronous (n = 4) tumors (adenocarcinoma, n = 25; squamous cell carcinoma, n = 3; unspecified, n = 1). Median tumor diameter was 14 mm (range, 10-26 mm). Surveillance computed tomography or positron emission tomography-computed tomography was performed over a median period of 28 months (range, 12-83 mo). Technical success and effectiveness rates and overall and progression-free 1-year, 3-year, and 5-year survivals were calculated according to stage, first primary, metachronous, and synchronous tumor status. RESULTS: Technical success and effectiveness was 97%. Local control occurred in 17 of 21 T1a tumors (81%) and 5 of 8 T1b tumors (62.5%). The local progression rate of first primary tumors (5 of 11; 45%) was higher than that of metachronous (2 of 14; 14%; P = .07) and synchronous (0 of 4; P = .01) tumors. Estimated 1-year, 3-year, and 5-year local tumor progression-free survival was 79%, 75%, and 75%. Estimated 1-year, 3-year, and 5-year overall survival was 100%, 60%, and 14%. Survival outcomes were similar for patients with first primary, metachronous, or synchronous tumors. CONCLUSIONS: Radiofrequency ablation results in good local control and progression-free survival in patients with treatment-naïve T1 lung tumors, including patients with metachronous and synchronous tumors.

Incidentally detected lung nodules: clinical predictors of adherence to Fleischner Society surveillance guidelines.

OBJECTIVE: The objective of this study was to determine adherence to incidentally detected lung nodule computed tomographic (CT) surveillance recommendations and identify demographic and clinical factors that increase the likelihood of CT surveillance. MATERIALS AND METHODS: A total of 419 patients with incidentally detected lung nodules were included. Recorded data included patient demographic, radiologic, and clinical characteristics and outcomes at a 4-year follow-up. Multivariate logistic regression models determined the factors associated with likelihood of recommended CT surveillance. RESULTS: At least 1 recommended surveillance chest CT was performed on 48% of the patients (148/310). Computed tomographic result communication to the patient (odds ratio [OR], 2.2; P = 0.006; confidence interval [CI], 1.3-4.0) or to the referring physician (OR, 2.8; P = 0.001; CI, 1.7-4.5) and recommendation of a specific surveillance time interval (OR, 1.7; P = 0.023; CI, 1.08-2.72) increased the likelihood of surveillance. Other demographic, radiologic, and clinical factors did not influence surveillance. CONCLUSIONS: Documented physician and patient result communication as well as the recommendation of a specific surveillance time interval increased the likelihood of CT surveillance of incidentally detected lung nodules.

Discrepancy Between Achieved and Vendor-Predicted Ablation Zones in the Lung: Contributing Factors.

PURPOSE: Several factors are known to affect lung ablation zones. Questions remain as to why there are discrepancies between achieved and vendor-predicted ablation zones and what contributing factors can be modified to balance therapeutic effects with avoidance of complications. This retrospective study of lung tumour microwave ablation analyses day 1 post-treatment CT to assess the effects of lesion-specific and operator-dependent factors on ablation zones. METHODS AND MATERIALS: Consecutive patients treated at a tertiary centre from 2018 to 2021 were included. All ablations were performed using a single microwave ablation device under lung isolation. The lung tumours were categorised as primary or secondary, and their "resistance" to ablation was graded according to their locations. Intraprocedural pulmonary inflation was assessed as equal to or less than the contralateral non-isolated lung. Ablation energy was categorised as high, medium, or low. Ablation zone dimensions were measured on day 1 CT and compared to vendor reference charts. Ablations with multiple needle positions or indeterminate boundaries were excluded. RESULTS: A total of 47 lesions in 31 patients were analysed. Achieved long axes are longer than predicted by 5 mm or 14% (p < 0.01) without overall short axis discrepancy. Secondary tumours (p = 0.020), low-resistance location (p < 0.01), good lung inflation (p < 0.01), low (p = 0.003) and medium (p = 0.038) total energy produce lengthened long axes by 4-6 mm or 10-19%. High total energy results in shorter than predicated short axes by 6 mm or 18% (p = 0.010). CONCLUSION: We identified several factors affecting ablation zone dimensions which may have implications for ablation planning and the avoidance of complications.

Comparison of multiplanar reformatted CT lung tumor measurements to axial tumor measurement alone: impact on maximal tumor dimension and T stage.

OBJECTIVE: The purpose of this study was to compare measurements of lung tumor size between axial and multiplanar reformatted CT images, as well as to establish whether the difference between these measurements leads to a change in T stage. MATERIALS AND METHODS: Patients with lung tumors who underwent chest CT up to 31 days before lung resection between December 2010 and March 2012 were included. Axial, sagittal, and coronal CT images were evaluated by two independent readers (1 and 2) who were blinded to clinical data. In 89 patients, lung tumors categorized as T1a (54%), T1b (19%), T2a (24%), or T2b (3%) were analyzed. The longest tumor diameter using multiplanar reformatted CT was compared and correlated with axial CT alone and pathologic T stage. Statistical analysis included a Wilcoxon rank sum test to evaluate differences between measurements, intraclass correlation coefficient (ICC), and kappa statistic to assess agreement. RESULTS: Prediction of T stage using axial CT alone compared with multiplanar reformatted CT agreed in 82% of patients for reader 1 (κ = 0.660 [95% CI, 0.531-0.789]) and 80% of patients for reader 2 (κ = 0.695 [95% CI, 0.572-0.818]). Prediction of T stage using multiplanar reformatted CT resulted in upstaging in 18% and 20% of patients (for readers 1 and 2, respectively). Interobserver agreement (ICC [95% CI]) was 0.900 (0.803-0.954) for axial, 0.874 (0.772-0.946) for sagittal, and 0.754 (0.556-0.921) for coronal planes. CONCLUSION: Radiologic measurement of lung tumor T stage was higher using multiplanar reformatted CT as compared with axial CT alone. When available, multiplanar reformatted CT should be used to measure tumor dimension and thus assign an accurate lung cancer T stage.

Computed tomography angiography for suspected pulmonary embolism: comparison of 2 adaptive statistical iterative reconstruction blends to filtered back-projection alone.

OBJECTIVE: The objective of this study was to analyze pulmonary computed tomography angiography image quality and pulmonary embolism (PE) depiction comparing 2 blends of adaptive statistical iterative reconstruction (ASIR) to filtered back-projection alone. METHODS: Seventy-nine consecutive patients (49 women, 30 men; 52 ± 18 years) underwent pulmonary computed tomography angiography (120 kVp, 100-600 mA) reconstructed with filtered back-projection alone (ASIR0), 30% ASIR (ASIR30), and 50% ASIR (ASIR50) for this institutional review board-approved study. Two radiologists independently assessed PE depiction and vascular characterization, which was correlated with body mass index. RESULTS: Twelve patients (15%) had PE. No difference in PE depiction (P = 0.536), pulmonary arterial attenuation (P = 0.22-0.99), or subjective vascular characterization score (P = 0.58-.016) was observed for either blend. ASIR30 and ASIR50 achieved higher signal-to-noise ratio (P = 0.001-0.003). Body mass index inversely correlated with vascular characterization scores (P < 0.001). CONCLUSIONS: ASIR0, ASIR30, and ASIR50 accurately depict PE using the imaging parameters described. ASIR30 and ASIR50 improve objective image quality without altering subjective vascular characterization scores particularly when body mass index was less than 30 kg/m.

COVID-protected pathways for image-guided lung cancer intervention during the COVID-19 pandemic: A cohort study.

OBJECTIVES: To compare the experience of COVID-protected and mixed cohort pathways in COVID-19 transmission at a tertiary referral hospital for elective CT-guided lung biopsy and ablation during the COVID-19 pandemic. METHODS: From September 2020 to August 2021, patients admitted for elective thoracic intervention were treated at a tertiary hospital (Site 1). Site 1 received patients for extracorporeal membrane oxygenation (ECMO) and invasive ventilation in the treatment of COVID-19. Shared imaging, theater, and hallway facilities were used.From April 2020 to August 2020, patients admitted for elective thoracic intervention were treated at a COVID-protected hospital (Site 2). No patients with suspected or confirmed COVID-19 were treated at Site 2.Patients were surveyed for clinical and laboratory signs of COVID-19 infection up to 30 days post-procedure. RESULTS: At Sites 1 and 2, patients (2.4%) were tested positive for COVID-19 at 10 and 14 days post-procedure.At Site 2, there were no COVID-19 positive cases within 30 days of undergoing elective thoracic intervention. CONCLUSION: A mixed-site method for infection control could represent a pragmatic approach to the management of elective procedures during the COVID-19 pandemic or for similar illnesses. ADVANCES IN KNOWLEDGE: Mixed-cohort infection control is possible in the prevention of nosocomial COVID-19 infection.

Pulmonary hypertension: the hallmark of acute COVID-19 microvascular angiopathy?

In situ pulmonary arterial thrombosis in COVID-19 is not visible on CTPA. However, the presence of CT-measured right heart and pulmonary artery dilatation in COVID-19 is likely attributable to this process and may be a possible surrogate for its detection. https://bit.ly/3g7z5TV.