The CT revolution: the role of PIOPED II in establishing CT pulmonary angiography as the reference standard for pulmonary embolism diagnosis.

The PIOPED II study provided a robust estimate of the diagnostic accuracy of multidetector CTPA in suspected pulmonary embolism and played a pivotal role in establishing CTPA as the current diagnostic gold standard https://bit.ly/3HEyVxy.

Strategies to safely rule out pulmonary embolism in COVID-19 outpatients: a multicenter retrospective study.

OBJECTIVES: The objective was to define a safe strategy to exclude pulmonary embolism (PE) in COVID-19 outpatients, without performing CT pulmonary angiogram (CTPA). METHODS: COVID-19 outpatients from 15 university hospitals who underwent a CTPA were retrospectively evaluated. D-Dimers, variables of the revised Geneva and Wells scores, as well as laboratory findings and clinical characteristics related to COVID-19 pneumonia, were collected. CTPA reports were reviewed for the presence of PE and the extent of COVID-19 disease. PE rule-out strategies were based solely on D-Dimer tests using different thresholds, the revised Geneva and Wells scores, and a COVID-19 PE prediction model built on our dataset were compared. The area under the receiver operating characteristics curve (AUC), failure rate, and efficiency were calculated. RESULTS: In total, 1369 patients were included of whom 124 were PE positive (9.1%). Failure rate and efficiency of D-Dimer > 500 µg/l were 0.9% (95%CI, 0.2-4.8%) and 10.1% (8.5-11.9%), respectively, increasing to 1.0% (0.2-5.3%) and 16.4% (14.4-18.7%), respectively, for an age-adjusted D-Dimer level. D-dimer > 1000 µg/l led to an unacceptable failure rate to 8.1% (4.4-14.5%). The best performances of the revised Geneva and Wells scores were obtained using the age-adjusted D-Dimer level. They had the same failure rate of 1.0% (0.2-5.3%) for efficiency of 16.8% (14.7-19.1%), and 16.9% (14.8-19.2%) respectively. The developed COVID-19 PE prediction model had an AUC of 0.609 (0.594-0.623) with an efficiency of 20.5% (18.4-22.8%) when its failure was set to 0.8%. CONCLUSIONS: The strategy to safely exclude PE in COVID-19 outpatients should not differ from that used in non-COVID-19 patients. The added value of the COVID-19 PE prediction model is minor. KEY POINTS: • D-dimer level remains the most important predictor of pulmonary embolism in COVID-19 patients. • The AUCs of the revised Geneva and Wells scores using an age-adjusted D-dimer threshold were 0.587 (95%CI, 0.572 to 0.603) and 0.588 (95%CI, 0.572 to 0.603). • The AUC of COVID-19-specific strategy to rule out pulmonary embolism ranged from 0.513 (95%CI: 0.503 to 0.522) to 0.609 (95%CI: 0.594 to 0.623).

Artificial intelligence: A critical review of applications for lung nodule and lung cancer.

Artificial intelligence (AI) is a broad concept that usually refers to computer programs that can learn from data and perform certain specific tasks. In the recent years, the growth of deep learning, a successful technique for computer vision tasks that does not require explicit programming, coupled with the availability of large imaging databases fostered the development of multiple applications in the medical imaging field, especially for lung nodules and lung cancer, mostly through convolutional neural networks (CNN). Some of the first applications of AI is this field were dedicated to automated detection of lung nodules on X-ray and computed tomography (CT) examinations, with performances now reaching or exceeding those of radiologists. For lung nodule segmentation, CNN-based algorithms applied to CT images show excellent spatial overlap index with manual segmentation, even for irregular and ground glass nodules. A third application of AI is the classification of lung nodules between malignant and benign, which could limit the number of follow-up CT examinations for less suspicious lesions. Several algorithms have demonstrated excellent capabilities for the prediction of the malignancy risk when a nodule is discovered. These different applications of AI for lung nodules are particularly appealing in the context of lung cancer screening. In the field of lung cancer, AI tools applied to lung imaging have been investigated for distinct aims. First, they could play a role for the non-invasive characterization of tumors, especially for histological subtype and somatic mutation predictions, with a potential therapeutic impact. Additionally, they could help predict the patient prognosis, in combination to clinical data. Despite these encouraging perspectives, clinical implementation of AI tools is only beginning because of the lack of generalizability of published studies, of an inner obscure working and because of limited data about the impact of such tools on the radiologists' decision and on the patient outcome. Radiologists must be active participants in the process of evaluating AI tools, as such tools could support their daily work and offer them more time for high added value tasks.

Interstitial lung diseases after hematopoietic stem cell transplantation: New pattern of lung chronic graft-versus-host disease?

Bronchiolitis obliterans syndrome (BOS) after allogeneic HSCT is the only formally recognized manifestation of lung chronic graft-versus-host disease (GVHD). Other lung complications were reported, including interstitial lung diseases (ILDs). Whether ILDs belong to the spectrum of lung cGVHD remains unknown. We compared characteristics and specific risk factors for both ILD and BOS. Data collected from consecutive patients diagnosed with ILD or BOS from 1981-2019 were analyzed. The strength of the association between patient characteristics and ILD occurrence was measured via odds ratios estimated from univariable logistic models. Multivariable models allowed us to handle potential confounding variables. Overall survival (OS) was estimated using the Kaplan-Meier method. 238 patients were included: 79 with ILD and 159 with BOS. At diagnosis, FEV1 was lower in patients with BOS compared to patients with ILD, while DLCO was lower in ILD. 84% of ILD patients received systemic corticosteroids, leading to improved CT scans and pulmonary function, whereas most BOS patients were treated by inhaled corticosteroids, with lung-function stabilization. In the multivariable analysis, prior thoracic irradiation and absence of prior treatment with prednisone were associated with ILD. OS was similar, even if hematological relapse was more frequent in the ILD group. Both complications occurred mainly in patients with GVHD history.

Artificial intelligence in lung cancer: current applications and perspectives.

Artificial intelligence (AI) has been a very active research topic over the last years and thoracic imaging has particularly benefited from the development of AI and in particular deep learning. We have now entered a phase of adopting AI into clinical practice. The objective of this article was to review the current applications and perspectives of AI in thoracic oncology. For pulmonary nodule detection, computer-aided detection (CADe) tools have been commercially available since the early 2000s. The more recent rise of deep learning and the availability of large annotated lung nodule datasets have allowed the development of new CADe tools with fewer false-positive results per examination. Classical machine learning and deep-learning methods were also used for pulmonary nodule segmentation allowing nodule volumetry and pulmonary nodule characterization. For pulmonary nodule characterization, radiomics and deep-learning approaches were used. Data from the National Lung Cancer Screening Trial (NLST) allowed the development of several computer-aided diagnostic (CADx) tools for diagnosing lung cancer on chest computed tomography. Finally, AI has been used as a means to perform virtual biopsies and to predict response to treatment or survival. Thus, many detection, characterization and stratification tools have been proposed, some of which are commercially available.

Safety Profile of Ambulatory Prostatic Artery Embolization after a Significant Learning Curve: Update on Adverse Events.

BACKGROUND: to report the safety of outpatient prostatic artery embolization (PAE) after a significant learning curve. METHODS: a retrospective bi-institutional study was conducted between June 2018 and April 2022 on 311 consecutive patients, with a mean age of 69 years ± 9.8 (47-102), treated by outpatient PAE. Indications included lower urinary tract symptoms, acute urinary retention, and hematuria. When needed, 3D-imaging and/or coil protection of extra-prostatic supplies were performed to avoid non-target embolization. Adverse events were monitored at 1-, 6-, and 12-month follow-ups. RESULTS: bilateral PAE was achieved in 305/311 (98.1%). Mean dose area product/fluoroscopy times were 16,408.3 ± 12,078.9 (2959-81,608) µGy.m2/36.3 ± 1.7 (11-97) minutes. Coil protection was performed on 67/311 (21.5%) patients in 78 vesical, penile, or rectal supplies. Embolization-related adverse events varied between 0 and 2.6%, access-site adverse events between 0 and 18%, and were all minor. There was no major event. CONCLUSION: outpatient PAE performed after achieving a significant learning curve may lead to a decreased and low rate of adverse events. Experience in arterial anatomy and coil protection may play a role in safety, but the necessity of the latter in some patterns may need confirmation by additional studies in randomized designs.

Feasibility of Outpatient Transradial Prostatic Artery Embolization and Safety of a Shortened Deflation Protocol for Hemostasis.

BACKGROUND: to evaluate the safety and feasibility of a shorter time to hemostasis applied to outpatient transradial (TR) Prostatic Artery Embolization (PAE). METHODS: a retrospective bi-institutional study was conducted between July 2018 and April 2022 on 300 patients treated by outpatient TR PAE. Indications included lower urinary tract symptoms, acute urinary retention, and hematuria. Mean patient height was 176 ± 6.3 (158-192) cm. The primary endpoint was safety of a 45 min deflation protocol for hemostasis. The secondary endpoint was the feasibility of PAE using TR access. RESULTS: technical success was 98.7% (296/300). There was one failure due to patient height. Mean DAP/fluoroscopy times were 16,225 ± 12,126.3 (2959-81,608) µGy·m2/35 ± 14.7 (11-97) min, and mean time to discharge was 80 ± 6 (75-90) min. All access site and embolization-related adverse events were minor. Mild hematoma occurred in 10% (30/300), radial artery occlusion (RAO) in 10/300 (3.3%) cases, and history of smoking was a predictor for RAO. There was no major event. CONCLUSION: the safety of TR PAE using a 45 min time to hemostasis was confirmed, and TR PAE is feasible in most cases. Radial artery occlusion was still observed and may be favored by smoking.

Deep Learning for the Detection, Localization, and Characterization of Focal Liver Lesions on Abdominal US Images.

Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and Methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters. Results: DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks. Conclusion: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article. RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN).

Long-term outcomes of adult pulmonary Langerhans cell histiocytosis: a prospective cohort.

BACKGROUND: The long-term outcomes of adult pulmonary Langerhans cell histiocytosis (PLCH), particularly survival, are largely unknown. Two earlier retrospective studies reported a high rate of mortality, which contrasts with our clinical experience. METHODS: To address this issue, all patients with newly diagnosed PLCH referred to the French national reference centre for histiocytoses between 2004 and 2018 were eligible for inclusion. The primary outcome was survival, which was defined as the time from inclusion to lung transplantation or death from any cause. Secondary outcomes included the cumulative incidences of chronic respiratory failure (CRF), pulmonary hypertension (PH), malignant diseases and extrapulmonary involvement in initially isolated PLCH. Survival was estimated using the Kaplan-Meier method. RESULTS: 206 patients (mean age 39±13 years, 60% female, 95% current smokers) were prospectively followed for a median duration of 5.1 years (IQR 3.2-7.6 years). Of these, 12 patients (6%) died. The estimated rate of survival at 10 years was 93% (95% CI 89-97%). The cumulative incidences of CRF and/or PH were <5% at both 5 and 10 years, and 58% of these patients died. 27 malignancies were observed in 23 patients. The estimated standardised incidence ratio of lung carcinoma was 17.0 (95% CI 7.45-38.7) compared to an age- and sex-matched French population. Eight (5.1%) of the 157 patients with isolated PLCH developed extrapulmonary involvement. CONCLUSION: The long-term prognosis of PLCH is significantly more favourable than has previously been reported. Patients must be closely monitored after diagnosis to detect severe complications early.

Study of Thoracic CT in COVID-19: The STOIC Project.

Background There are conflicting data regarding the diagnostic performance of chest CT for COVID-19 pneumonia. Disease extent at CT has been reported to influence prognosis. Purpose To create a large publicly available data set and assess the diagnostic and prognostic value of CT in COVID-19 pneumonia. Materials and Methods This multicenter, observational, retrospective cohort study involved 20 French university hospitals. Eligible patients presented at the emergency departments of the hospitals involved between March 1 and April 30th, 2020, and underwent both thoracic CT and reverse transcription-polymerase chain reaction (RT-PCR) testing for suspected COVID-19 pneumonia. CT images were read blinded to initial reports, RT-PCR, demographic characteristics, clinical symptoms, and outcome. Readers classified CT scans as either positive or negative for COVID-19 based on criteria published by the French Society of Radiology. Multivariable logistic regression was used to develop a model predicting severe outcome (intubation or death) at 1-month follow-up in patients positive for both RT-PCR and CT, using clinical and radiologic features. Results Among 10 930 patients screened for eligibility, 10 735 (median age, 65 years; interquartile range, 51-77 years; 6147 men) were included and 6448 (60%) had a positive RT-PCR result. With RT-PCR as reference, the sensitivity and specificity of CT were 80.2% (95% CI: 79.3, 81.2) and 79.7% (95% CI: 78.5, 80.9), respectively, with strong agreement between junior and senior radiologists (Gwet AC1 coefficient, 0.79). Of all the variables analyzed, the extent of pneumonia at CT (odds ratio, 3.25; 95% CI: 2.71, 3.89) was the best predictor of severe outcome at 1 month. A score based solely on clinical variables predicted a severe outcome with an area under the curve of 0.64 (95% CI: 0.62, 0.66), improving to 0.69 (95% CI: 0.6, 0.71) when it also included the extent of pneumonia and coronary calcium score at CT. Conclusion Using predefined criteria, CT reading is not influenced by reader's experience and helps predict the outcome at 1 month. ClinicalTrials.gov identifier: NCT04355507 Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Rubin in this issue.

Nonpalpable breast lesions: impact of a second-opinion review at a breast unit on BI-RADS classification.

OBJECTIVE: To compare BI-RADS classification, management, and outcome of nonpalpable breast lesions assessed both by community practices and by a multidisciplinary tumor board (MTB) at a breast unit. METHODS: All nonpalpable lesions that were first assigned a BI-RADS score by community practices and then reassessed by an MTB at a single breast unit from 2009 to 2017 were retrospectively reviewed. Inter-review agreement was assessed with Cohen's kappa statistic. Changes in biopsy recommendation were calculated. The percentage of additional tumor lesions detected by the MTB was obtained. The sensitivity, AUC, and cancer rates for BI-RADS category 3, 4, and 5 lesions were computed for both reviews. RESULTS: A total of 1909 nonpalpable lesions in 1732 patients were included. For BI-RADS scores in the whole cohort, a fair agreement was found (κ = 0.40 [0.36-0.45]) between the two reviews. Agreement was higher when considering only mammography combined with ultrasound (κ = 0.53 [0.44-0.62]), masses (κ = 0.50 [0.44-0.56]), and architectural distortion (κ = 0.44 [0.11-0.78]). Changes in biopsy recommendation occurred in 589 cases (31%). Ninety of 345 additional biopsies revealed high-risk or malignant lesions. Overall, the MTB identified 27% additional high-risk and malignant lesions compared to community practices. The BI-RADS classification AUCs for detecting malignant lesions were 0.66 (0.63-0.69) for community practices and 0.76 (0.75-0.78) for the MTB (p < 0.001). CONCLUSION: Agreement between community practices and MTB reviews for BI-RADS classification in nonpalpable lesions is only fair. MTB review improves diagnostic performances of breast imaging and patient management. KEY POINTS: • The inter-review agreement for BI-RADS classification between community practices and the multidisciplinary board was only fair (κ = 0.40). • Disagreements resulted in changes of biopsy recommendation in 31% of the lesions. • The multidisciplinary board identified 27% additional high-risk and malignant lesions compared to community practices.

Efficacy of Chest CT for COVID-19 Pneumonia Diagnosis in France.

Background The role and performance of chest CT in the diagnosis of the coronavirus disease 2019 (COVID-19) pandemic remains under active investigation. Purpose To evaluate the French national experience using chest CT for COVID-19, results of chest CT and reverse transcription polymerase chain reaction (RT-PCR) assays were compared together and with the final discharge diagnosis used as the reference standard. Materials and Methods A structured CT scan survey (NCT04339686) was sent to 26 hospital radiology departments in France between March 2, 2020, and April 24, 2020. These dates correspond to the peak of the national COVID-19 epidemic. Radiology departments were selected to reflect the estimated geographic prevalence heterogeneities of the epidemic. All symptomatic patients suspected of having COVID-19 pneumonia who underwent both initial chest CT and at least one RT-PCR test within 48 hours were included. The final discharge diagnosis, based on multiparametric items, was recorded. Data for each center were prospectively collected and gathered each week. Test efficacy was determined by using the Mann-Whitney test, Student t test, χ2 test, and Pearson correlation coefficient. P < .05 indicated a significant difference. Results Twenty-six of 26 hospital radiology departments responded to the survey, with 7500 patients entered; 2652 did not have RT-PCR test results or had unknown or excess delay between the RT-PCR test and CT. After exclusions, 4824 patients (mean age, 64 years ± 19 [standard deviation], 2669 male) were included. With final diagnosis as the reference, 2564 of the 4824 patients had COVID-19 (53%). Sensitivity, specificity, negative predictive value, and positive predictive value of chest CT in the diagnosis of COVID-19 were 2319 of 2564 (90%; 95% CI: 89, 91), 2056 of 2260 (91%; 95% CI: 91, 92), 2056 of 2300 (89%; 95% CI: 87, 90), and 2319 of 2524 (92%; 95% CI: 91, 93), respectively. There was no significant difference for chest CT efficacy among the 26 geographically separate sites, each with varying amounts of disease prevalence. Conclusion Use of chest CT for the initial diagnosis and triage of patients suspected of having coronavirus disease 2019 was successful. © RSNA, 2021 Online supplemental material is available for this article.

Impact of New Systemic Treatment and Radiotherapy in Melanoma Patients with Leptomeningeal Metastases.

IMPORTANCE: Few data are available on patients with leptomeningeal disease (LM) from melanoma treated with new systemic therapies. OBJECTIVE: To gain a better understanding of patients, disease characteristics, and therapeutic interventions in melanoma patients with LM in the era of new systemic treatment. DESIGN: Clinical characteristics, treatments, and survival of melanoma patients diagnosed with LM, isolated or associated with brain metastases, were collected. The Cox regression model assessed the influence of patient and melanoma characteristics on survival. SETTING: Monocentric, retrospective, real-life cohort of patients with LM from melanoma. PARTICIPANTS: All patients followed up at Saint-Louis University Hospital and diagnosed with LM between December 2013 and February 2020 were included. For each patient identified, a central review by dermato-oncologist and neuro-oncologist experts was performed to confirm the diagnosis of LM. EXPOSURE: Impact of new systemic therapies and radiotherapy. RESULTS: Among the 452 advanced melanoma patients followed at St Louis Hospital between 2013 and 2020, 41 patients with LM from melanoma were identified. Among them, 29 patients with a diagnosis of LM "confirmed" or "probable" after central neuro-oncologists reviewing were included. Nineteen patients had known melanoma brain metastases at LM diagnosis. Among the 27 patients treated with systemic therapy, 17 patients were treated with immunotherapy, 5 patients received targeted therapy, 1 was treated with chemotherapy, and 4 patients were treated with anti-PD-1 in combination with BRAF inhibitor. The median overall survival (OS) from LM diagnosis was 5.1 months. Median OS was 7.1 months for the 9 patients receiving systemic therapy combined with radiotherapy, and 3.2 months for the 20 patients not receiving combined radiotherapy. Elevated serum lactate dehydrogenase (LDH) (HR 1.44, 95% CI 1.09-1.90, p < 0.01) and presence of neurological symptoms at LM diagnosis (HR 2.96, 95% CI 1.25-6.99, p = 0.01) were associated with poor survival. At the time of data analysis, five patients were still alive with a median follow-up of 47.4 months and had persistent complete response. CONCLUSION: Targeted therapy and immunotherapy are promising new treatment options in LM from melanoma that can increase overall survival, and may induce long lasting remission in some patients.

Assessing invasiveness of subsolid lung adenocarcinomas with combined attenuation and geometric feature models.

The aim of this study was to develop and test multiclass predictive models for assessing the invasiveness of individual lung adenocarcinomas presenting as subsolid nodules on computed tomography (CT). 227 lung adenocarcinomas were included: 31 atypical adenomatous hyperplasia and adenocarcinomas in situ (class H1), 64 minimally invasive adenocarcinomas (class H2) and 132 invasive adenocarcinomas (class H3). Nodules were segmented, and geometric and CT attenuation features including functional principal component analysis features (FPC1 and FPC2) were extracted. After a feature selection step, two predictive models were built with ordinal regression: Model 1 based on volume (log) (logarithm of the nodule volume) and FPC1, and Model 2 based on volume (log) and Q.875 (CT attenuation value at the 87.5% percentile). Using the 200-repeats Monte-Carlo cross-validation method, these models provided a multiclass classification of invasiveness with discriminative power AUCs of 0.83 to 0.87 and predicted the class probabilities with less than a 10% average error. The predictive modelling approach adopted in this paper provides a detailed insight on how the value of the main predictors contribute to the probability of nodule invasiveness and underlines the role of nodule CT attenuation features in the nodule invasiveness classification.

The Growth Rate of Subsolid Lung Adenocarcinoma Nodules at Chest CT.

Background Confirming that subsolid adenocarcinomas show exponential growth is important because it would justify using volume doubling time to assess their growth. Purpose To test whether the growth of lung adenocarcinomas manifesting as subsolid nodules at chest CT is accurately represented by an exponential model. Materials and Methods Patients with lung adenocarcinomas manifesting as subsolid nodules surgically resected between January 2005 and May 2018, with three or more longitudinal CT examinations before resection, were retrospectively included. Overall volume (for all nodules) and solid component volume (for part-solid nodules) were measured over time. A linear mixed-effects model was used to identify the growth pattern (linear, exponential, quadratic, or power law) that best represented growth. The interactions between nodule growth and clinical, CT morphologic, and pathologic parameters were studied. Results Sixty-nine patients (mean age, 70 years ± 9 [standard deviation]; 48 women) with 74 lung adenocarcinomas were evaluated. Overall growth and solid component growth were better represented by an exponential model (adjusted R2 = 0.89 and 0.95, respectively) than by a quadratic model (r2 = 0.88 and 0.93, respectively), a linear model (r2 = 0.87 and 0.92, respectively), or a power law model (r2 = 0.82 and 0.93, respectively). Faster overall volume growth was associated with a history of lung cancer (P < .001), a baseline nodule volume less than 500 mm3 (P = .03), and histologic findings of invasive adenocarcinoma (P < .001). The median volume doubling time of noninvasive adenocarcinoma was significantly longer than that of invasive adenocarcinoma (939 days [interquartile range, 588-1563 days] vs 678 days [interquartile range, 392-916 days], respectively; P = .01). Conclusion The overall volume growth of adenocarcinomas manifesting as subsolid nodules at chest CT was best represented by an exponential model compared with the other tested models. This justifies the use of volume doubling time for the growth assessment of these nodules. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuriyama and Yanagawa in this issue.