Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Pneumothorax Incidence with Normal Saline Instillation for Sealing the Needle Track After Computed Tomography-Guided Percutaneous Lung Biopsy.

PURPOSE: To determine whether instillation of normal saline solution for sealing the needle track reduces incidence of pneumothorax and chest tube placement after computed tomography-guided percutaneous lung biopsy. MATERIALS AND METHODS: A total of 242 computed tomography-guided percutaneous lung biopsies performed at a single institution were retrospectively reviewed, including 93 biopsies in which the needle track was sealed by instillation of 3-5 ml of normal saline solution during needle withdrawal (water seal group) and 149 biopsies without sealing (control group). Patient and lesion characteristics, procedure-specific variables, pneumothorax and chest tube placement rates were recorded. RESULTS: Baseline characteristics were comparable in both groups. There was a statistically significant decrease in the pneumothorax rate (19.4% [18/93] vs. 40.9% [61/149]; p < 0.001) and a numerically lower chest tube placement rate without significant reduction (4.3% [4/93] vs. 10.7% [16/149]; p = 0.126) with using normal saline instillation for sealing the needle track versus not using sealant material. Using a multiple logistic regression analysis, using normal saline instillation to seal the needle track, having a senior radiologist as operator of the procedure and putting patients in prone position were significantly associated with a decreased risk of pneumothorax. The presence of emphysema along the needle track was significantly associated with an increased risk of pneumothorax. No complication was observed due to normal saline injection. CONCLUSION: Normal saline solution instillation for sealing the needle track after computed tomography-guided percutaneous lung biopsy is a simple, low-cost and safe technique resulted in significantly decreased pneumothorax occurrence and a numerically lower chest tube placement rate, and might help to reduce both hospitalization risks and costs for the healthcare system. Level of evidence 3 Non-controlled retrospective cohort study.

Generating High-Resolution Synthetic CT from Lung MRI with Ultrashort Echo Times: Initial Evaluation in Cystic Fibrosis.

Background Lung MRI with ultrashort echo times (UTEs) enables high-resolution and radiation-free morphologic imaging; however, its image quality is still lower than that of CT. Purpose To assess the image quality and clinical applicability of synthetic CT images generated from UTE MRI by a generative adversarial network (GAN). Materials and Methods This retrospective study included patients with cystic fibrosis (CF) who underwent both UTE MRI and CT on the same day at one of six institutions between January 2018 and December 2022. The two-dimensional GAN algorithm was trained using paired MRI and CT sections and tested, along with an external data set. Image quality was assessed quantitatively by measuring apparent contrast-to-noise ratio, apparent signal-to-noise ratio, and overall noise and qualitatively by using visual scores for features including artifacts. Two readers evaluated CF-related structural abnormalities and used them to determine clinical Bhalla scores. Results The training, test, and external data sets comprised 82 patients with CF (mean age, 21 years ± 11 [SD]; 42 male), 28 patients (mean age, 18 years ± 11; 16 male), and 46 patients (mean age, 20 years ± 11; 24 male), respectively. In the test data set, the contrast-to-noise ratio of synthetic CT images (median, 303 [IQR, 221-382]) was higher than that of UTE MRI scans (median, 9.3 [IQR, 6.6-35]; P < .001). The median signal-to-noise ratio was similar between synthetic and real CT (88 [IQR, 84-92] vs 88 [IQR, 86-91]; P = .96). Synthetic CT had a lower noise level than real CT (median score, 26 [IQR, 22-30] vs 42 [IQR, 32-50]; P < .001) and the lowest level of artifacts (median score, 0 [IQR, 0-0]; P < .001). The concordance between Bhalla scores for synthetic and real CT images was almost perfect (intraclass correlation coefficient, ≥0.92). Conclusion Synthetic CT images showed almost perfect concordance with real CT images for the depiction of CF-related pulmonary alterations and had better image quality than UTE MRI. Clinical trial registration no. NCT03357562 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Schiebler and Glide-Hurst in this issue.

Detection and quantification of pulmonary embolism with artificial intelligence: The SFR 2022 artificial intelligence data challenge.

PURPOSE: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence. MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks. RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784. CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.

Safety of High-Frequency Jet Ventilation During Image-Guided Thermal Ablation Procedures.

RATIONALE AND OBJECTIVE: Percutaneous thermal ablative technique is a common radiological procedure for malignant lesions treatment. Controlled assisted ventilation during general anesthesia is the usual mode of ventilation, but high-frequency jet ventilation (HFJV) can be a helpful alternative for the operator. The objective was to evaluate the safety of HFJV during thermal ablation procedures. MATERIALS AND METHODS: This monocentric prospective analysis included adult patients undergoing percutaneous thermal ablation procedures for abdominal tumor performed under HFJV. Procedures with a transpulmonary path were excluded. The primary outcome was the incidence of respiratory complications. Secondary outcomes included gas exchange modifications (hypercapnia, hypoxemia, pulmonary atelectasis) and the incidence of barotrauma. RESULTS: Sixty patients were included during the study period. The mean duration time was 88 min. All procedures went according to the protocol and there was no respiratory complication. There was no barotrauma event. Three patients had an exhaled capnia above 45 mmHg at the end of the procedure which normalized within 10 min of conventional ventilation. CONCLUSION: HFJV during thermal ablation procedures is safe regarding gas exchange and barotrauma. This technique could be an interesting alternative to conventional ventilation during image-guided thermal ablation procedures. Clinical Trials database This study was registered in Clinical Trials database (NCT04209608).

Immune alveolitis in interstitial lung disease: an attractive cytological profile in immunocompromised patients.

BACKGROUND: Bronchoalveolar lavage (BAL) is a major diagnostic tool in interstitial lung disease (ILD). Its use remains largely quantitative, usually focused on cell differential ratio. However, cellular morphological features provide additional valuable information. The significance of the "immune alveolitis" cytological profile, characterized by lymphocytic alveolitis with activated lymphocytes and macrophages in epithelioid transformation or foamy macrophages desquamating in cohesive clusters with lymphocytes, remains unknown in ILD. Our objective was to describe patients' characteristics and diagnoses associated with an immune alveolitis profile in undiagnosed ILD. METHODS: We performed a monocentric retrospective observational study. Eligible patients were adults undergoing diagnostic exploration for ILD and whose BAL fluid displayed an immune alveolitis profile. For each patient, we collected clinical, radiological and biological findings as well as the final etiology of ILD. RESULTS: Between January 2012 and December 2018, 249 patients were included. Mean age was 57 ± 16 years, 140 patients (56%) were men, and 65% of patients were immunocompromised. The main etiological diagnosis was Pneumocystis pneumonia (PCP) (24%), followed by drug-induced lung disease (DILD) (20%), viral pneumonia (14%) and hypersensitivity pneumonitis (HP) (10%). All PCP were diagnosed in immunocompromised patients while HP was found in only 8% of this subgroup. DILD and viral pneumonia were also commonly diagnosed in immunocompromised patients (94% and 80%, respectively). CONCLUSION: Our study highlights the additional value of BAL qualitative description in ILD. We suggest incorporating the immune alveolitis profile for the diagnosis and management of ILD, especially in immunocompromised patients, since it guides towards specific diagnoses.

Evaluation of the Post-COVID-19 Functional Status (PCFS) Scale in a cohort of patients recovering from hypoxemic SARS-CoV-2 pneumonia.

INTRODUCTION: COVID-19 sequelae are numerous and multisystemic, and how to evaluate those symptomatic patients is a timely issue. Klok et al proposed the Post-COVID-19 Functional Status (PCFS) Scale as an easy tool to evaluate limitations related to persistent symptoms. Our aim was to analyse PCFS Scale ability to detect functional limitations and its correlation with quality of life in a cohort of patients, 2-9 months after hospitalisation for COVID-19 hypoxemic pneumonia. METHODS: PCFS Scale was evaluated in 121 patients together with quality of life and dyspnoea questionnaires, pulmonary function tests and CT scans. RESULTS: We observed a high correlation with multiple questionnaires (Short Form-36, Hospital Anxiety and Depression Scale, modified Medical Research Council, end Borg Six-Minute Walk Test), making the PCFS Scale a quick and global tool to evaluate functional limitations related to various persistent symptoms following COVID-19 pneumonia. DISCUSSION: The PCFS Scale seems to be a suitable instrument to screen for patients who will require careful follow-up after COVID-19 hypoxemic pneumonia even in the absence of pulmonary sequelae.

Percutaneous thermal ablation of lung metastases from thyroid carcinomas. A retrospective multicenter study of 107 nodules. On behalf of the TUTHYREF network.

PURPOSE: To determine efficacy and safety of thermal ablation (TA) for the local treatment of lung metastases of thyroid cancer. METHODS: We retrospectively studied 47 patients from 10 centers treated by TA (radiofrequency, microwaves, and cryoablation) over 10 years. The endpoints were overall survival (OS), local efficacy, complications (CTCAE classification), and factors associated with survival. OS curves after first TA were built using the Kaplan-Meier method and compared with the log-rank test. RESULTS: A total of 107 lung metastases during 75 sessions were treated by radiofrequency (n = 56), microwaves (n = 9), and cryoablation (n = 10). Median follow-up time after TA was 5.2 years (0.2-13.3). OS was 93% at 2 years (95% confidence interval (CI): 86-94) and 79% at 3 years (95% CI: 66-91). On univariate and multivariate analysis with a Cox model, histology was the only significant factor for OS. OS at 3 years was 94% for follicular, oncocytic, or papillary follicular variant carcinomas, compared to 59% for papillary, medullary, insular or anaplastic carcinomas (P = 0.0001). The local control rate was 98.1% at 1 year and 94.8% at 2, 3, 4, and 5 years. Morbidity was low with no major complications (grade 4 and 5 CTCAE) and no complications in 29 of 75 sessions (38.7%). CONCLUSIONS: TA is a useful, safe and effective option for local treatment of lung metastases from thyroid carcinoma. Prolonged OS was obtained, especially for lung metastases from follicular, oncocytic, or papillary follicular variant carcinomas. Achieving disease control with TA delays the need for systemic treatment.

Incidental findings suggestive of COVID-19 in asymptomatic cancer patients undergoing 18F-FDG PET/CT in a low prevalence region.

PURPOSE: To assess the rate and pattern of incidental interstitial lung abnormalities suggestive of COVID-19 on 18F-FDG PET/CT in asymptomatic cancer patients during the period of active COVID-19 circulation between March and April 2020 in a geographic area of low prevalence of the virus. METHODS: 1396 18F-FDG PET/CT performed between January 1, 2020, and February 21, 2020, and between March 16, 2020, and April 17, 2020 for routine oncological indication were retrospectively analyzed. No patients had symptoms suggestive of COVID-19 at the time of the 18F-FDG PET/CT. Incidental interstitial pneumonias suggestive of COVID-19 were identified, and the 18F-FDG PET/CT patterns were described. We compared the incidence of these lesions in the pre-COVID and pandemic phases. RESULTS: We observed a 1.6% increase in interstitial lung abnormalities during the period of COVID-19 circulation. All had < 50% lung involvement. We describe a case series with typical and atypical interstitial pneumonias suggestive of COVID-19 as unilateral or bilateral with ground-glass opacity, consolidation, or crazy-paving patterns. CONCLUSION: The relatively low increase in incidental findings suggestive of COVID-19 infection on 18F-FDG PET/CT in asymptomatic cancer patients was in accordance with the low COVID-19 transmission in our geographic region. Nevertheless, nuclear medicine physicians should familiarize themselves with typical and atypical 18F-FDG PET/CT patterns suggestive of COVID-19 pneumonia and initiate appropriate intervention where necessary.

Pneumocystis pneumonia after lung transplantation: A retrospective multicenter study.

BACKGROUND: Lung transplantation (LT) is an identified risk factor for Pneumocystis pneumonia (PCP). However, PCP management and outcomes remain poorly described in LT recipients and PCP incidence is rarely documented in this population. METHODS: PCP episodes that occurred in 9 French LT centers between January 2010 and October 2017 were included in this analysis. PCP was defined as compatible clinical and radiologic findings associated with fungal identification. RESULTS: Forty-seven PCP were included. The annual incidence rate of PCP was 2.7/1000 patients/year. Patients had a mean age of 53 ± 14 years. Median time from LT was 2.4 ± 3.0 years. Sixty-five percent of patients were not on prophylaxis at the time of PCP while all patients were receiving steroids at the time of PCP. Diagnosis was obtained by bronchoalveolar lavage in 91% (direct examination: 47%, PCR: 62%). The majority of patients were treated with trimethoprim-sulfamethoxazole (78%). Fifty-five percent of patients were hospitalized in ICU for organ failure (for which non-invasive ventilation was used for 21% and mechanical ventilation for 23%). Mortality rate was 15% at day 28 and reached 23% at day 90. Mortality was associated with decreased FEV1, everolimus treatment, Pseudomonas aeruginosa coinfection, fungal coinfection (especially Aspergillus sp.), mechanical ventilation and vasopressors. PCP primary prophylaxis, steroid modification during PCP and the number of immunosuppressive molecules were not associated with mortality. CONCLUSION: PCP is associated with a high mortality in LT. Our data suggest the need for a lifetime PCP prophylaxis in LT recipients. The benefit of adjuvant steroids remains unclear.

Bronchiectasis is highly prevalent in anti-MPO ANCA-associated vasculitis and is associated with a distinct disease presentation.

OBJECTIVES: To assess the prevalence of bronchiectasis in a Western cohort with ANCA-positive granulomatosis with polyangiitis (GPA) or microscopic polyangiitis (MPA) and its correlations with disease presentation and outcome. METHODS: Retrospective study of ANCA-associated vasculitis (AAV) patients followed at Nantes University Hospital (2005-2015). Clinical, biological, and follow-up data were collected through chart review. Two experienced radiologists blinded to the clinical data interpreted chest high-resolution CTs according to the Feischner Society criteria. RESULTS: Fifty-eight patients were included: 30 had MPA (51.7%) and 28 had GPA (48.3%). The median age at AAV diagnosis was 65.5 years. Anti-MPO-ANCA and anti-PR3-ANCA were present in 39 (67.2%) and 19 (32.8%) patients, respectively. Overall, bronchiectasis was found in 22 patients (37.9%), all of whom had anti-MPO ANCA. In multivariate analysis, bronchiectasis was independently associated with anti-MPO-ANCA, female gender and age at AAV diagnosis. Furthermore, anti-MPO ANCA patients with bronchiectasis had more frequent peripheral nerve involvement (54.5 vs. 17.6%, p = 0.019) and less frequent renal involvement than those without bronchiectasis (40.9% vs. 82.3%, p = 0.009). Disease course, survival and risk of severe pulmonary infection were similar in patients with and without bronchiectasis on chest CT. CONCLUSIONS: This study shows that bronchiectasis is a highly prevalent pre-existing respiratory condition in Caucasian patients with anti-MPO AAV. This subset of patients exhibits a distinct presentation. Further studies are needed to confirm these findings and clarify the clinical implications of this association. Whether the respiratory tract could be the site of initiation of anti-MPO auto-immunity remains to be investigated.

Pulmonary nodules and masses in lung transplant recipients: clinical and CT findings.

OBJECTIVES: The purpose of this study was to review the clinical and CT findings of pulmonary nodules and masses in lung transplant recipients and to determine distinguishing features among the various aetiologies. METHODS: This retrospective study included 106 lung transplant recipients who had a chest CT performed over a 7-year period in a single institution. RESULTS: Twenty-four cases of pulmonary nodules and masses were observed on CT. Among the single lesions, three (50%) were due to infections, one (17%) to organizing pneumonia, and two (33%) remained of undetermined origin. Among the multiple lesions, 14 (78%) were due to infection, three to post-transplant lymphoproliferative disorder (17%), and one to bronchogenic carcinoma (5%). The two main microorganisms were P. aeruginosa and Aspergillus spp. Among 12 solid nodules > 1 cm, four (33%) were due to malignancy: three post-transplant lymphoproliferative disorders (25%), and one bronchogenic carcinoma (8%). Among five cavitary nodules four (80%) were due to aspergillosis. CONCLUSION: Infection is the most frequent aetiology of pulmonary nodules and masses in lung transplant recipients, but other causes such as post-transplant lymphoproliferative disorder, bronchogenic carcinoma, or organizing pneumonia should be considered. KEY POINTS: Pulmonary nodules and masses are frequent in lung transplant recipients. Infection is the most frequent aetiology of solitary and multiple pulmonary nodules. Differential diagnosis includes post-transplant lymphoproliferative disorder, bronchogenic carcinoma, and organizing pneumonia. Clinical and CT findings are often non-specific. CT findings may be suggestive of some aetiologies that justify a biopsy.

Polytetrafluoroethylene-covered nitinol stent graft for treatment of carotid artery blowout syndrome in head and neck cancer patients.

OBJECTIVES/HYPOTHESIS: To evaluate the efficacy, tolerance, and outcomes of covered stents in the treatment of carotid blowout syndrome (CBS) in head and neck cancer patients. STUDY DESIGN: Individual retrospective cohort study. METHODS: We retrospectively reviewed the medical and image files of all 20 consecutive head and neck cancer patients treated with covered stent grafts for CBS. Six acute, 12 impending, and two threatened cases of CBS were treated in patients who all had previously received radiation therapy. We evaluated the feasibility, hemostatic efficacy, survival without bleeding, and complications. RESULTS: The etiologies of CBS were as follows: group 1, 13 carotid axis (common or internal carotid artery) pseudoaneurysms and one rupture; group 2, six patients with no identifiable source of bleeding on angiography but with a threatened carotid axis on computed tomography (CT). In all patients, a polytetrafluoroethylene-covered nitinol stent graft (Fluency; Bard/Angiomed GmbH & Co, Karlsruhe, Germany) was successfully placed. All of the stents were patent at the end of the procedure. Immediate hemostasis was achieved in the six hemorrhagic cases. Immediate transient ischemic attacks were observed in two patients, and carotid sinus syndrome was observed in one patient. Post-treatment bleeding was observed in five patients in group 2 and no patients in group 1. Survival without bleeding was 251 days in group 1 and 35 days in group 2. During follow-up, three asymptomatic stent thromboses occurred at a mean of 58 days. CONCLUSIONS: Covered stent placement is highly feasible and proved effective without major complications in CBS due to carotid axis bleeding.