Evaluation of computed tomography in the diagnosis of ultrasound-proven diaphragm dysfunction.

INTRODUCTION: Computed tomography (CT) is routinely employed on the evaluation of dyspnea, yet limited data exist on its assessment of diaphragmatic muscle. This study aimed to determine the capability of CT in identifying structural changes in the diaphragm among patients with ultrasound-confirmed diaphragmatic dysfunction. METHODS: Diaphragmatic ultrasounds conducted between 2018 and 2021 at our center in Marseille, France, were retrospectively collected. Diaphragmatic pillars were measured on CT scans at the L1 level and the celiac artery. Additionally, the difference in height between the two diaphragmatic domes in both diaphragmatic dysfunction cases and controls was measured and compared. RESULTS: A total of 65 patients were included, comprising 24 with diaphragmatic paralysis, 13 with diaphragmatic weakness, and 28 controls. In the case group (paralysis and weakness) with left dysfunctions (n = 24), the CT thickness of the pillars at the level of L1 and the celiac artery was significantly thinner compared with controls (2.0 mm vs. 7.4 mm and 1.8 mm vs. 3.1 mm, p < 0.001 respectively). Significantly different values were observed for paralysis (but not weakness) in the right dysfunction subgroup (n = 15) (2.6 mm vs. 7.4 mm and 2.2 mm vs. 3.8 mm, p < 0.001 respectively, for paralysis vs. controls). Regardless of the side of dysfunction, a significant difference in diaphragmatic height was observed between cases and controls (7.70 cm vs. 1.16 cm and 5.51 cm vs. 1.16 cm, p < 0.001 for right and left dysfunctions, respectively). Threshold values determined through ROC curve analyses for height differences between the two diaphragmatic domes, indicative of paralysis or weakness in the right dysfunctions, were 4.44 cm and 3.51 cm, respectively. Similarly for left dysfunctions, the thresholds were 2.70 cm and 2.48 cm, respectively, demonstrating good performance (aera under the curve of 1.00, 1.00, 0.98, and 0.79, respectively). CONCLUSION: In cases of left diaphragmatic dysfunction, as well as in paralysis associated with right diaphragmatic dysfunction, CT revealed thinner pillars. Additionally, a notable increase in the difference in diaphragmatic height demonstrated a strong potential to identify diaphragmatic dysfunction, with specific threshold values.

Artificial intelligence-driven volumetric CT outcome score in cystic fibrosis: longitudinal and multicenter validation with/without modulators treatment.

OBJECTIVES: Holistic segmentation of CT structural alterations with 3D deep learning has recently been described in cystic fibrosis (CF), allowing the measurement of normalized volumes of airway abnormalities (NOVAA-CT) as an automated quantitative outcome. Clinical validations are needed, including longitudinal and multicenter evaluations. MATERIALS AND METHODS: The validation study was retrospective between 2010 and 2023. CF patients undergoing Elexacaftor/Tezacaftor/Ivacaftor (ETI) or corticosteroids for allergic broncho-pulmonary aspergillosis (ABPA) composed the monocenter ETI and ABPA groups, respectively. Patients from six geographically distinct institutions composed a multicenter external group. All patients had completed CT and pulmonary function test (PFT), with a second assessment at 1 year in case of ETI or ABPA treatment. NOVAA-CT quantified bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus, collapse/consolidation, and their overall total abnormal volume (TAV). Two observers evaluated the visual Bhalla score. RESULTS: A total of 139 CF patients (median age, 15 years [interquartile range: 13-25]) were evaluated. All correlations between NOVAA-CT to both PFT and Bhalla score were significant in the ETI (n = 60), ABPA (n = 20), and External groups (n = 59), such as the normalized TAV (ρ ≥ 0.76; p < 0.001). In both ETI and ABPA groups, there were significant longitudinal improvements in peribronchial thickening, bronchial mucus, bronchiolar mucus and collapse/consolidation (p ≤ 0.001). An additional reversibility in bronchiectasis volume was quantified with ETI (p < 0.001). Intraclass correlation coefficient of reproducibility was > 0.99. CONCLUSION: NOVAA-CT automated scoring demonstrates validity, reliability and responsiveness for monitoring CF severity over an entire lung and quantifies therapeutic effects on lung structure at CT, such as the volumetric reversibility of airway abnormalities with ETI. CLINICAL RELEVANCE STATEMENT: Normalized volume of airway abnormalities at CT automated 3D outcome enables objective, reproducible, and holistic monitoring of cystic fibrosis severity over an entire lung for management and endpoints during therapeutic trials. KEY POINTS: Visual scoring methods lack sensitivity and reproducibility to assess longitudinal bronchial changes in cystic fibrosis (CF). AI-driven volumetric CT scoring correlates longitudinally to disease severity and reliably improves with Elexacaftor/Tezacaftor/Ivacaftor or corticosteroid treatments. AI-driven volumetric CT scoring enables reproducible monitoring of lung disease severity in CF and quantifies longitudinal structural therapeutic effects.

Ultrasound evaluation of diaphragmatic function in patients with idiopathic pulmonary fibrosis: a retrospective observational study.

INTRODUCTION: The diaphragm function assessed by ultrasound has been well-studied in COPD, asthma, and intensive care. However, there are only a few studies on diffuse interstitial lung disease, while dyspnea and quality of life are major issues in the management that may depend on the diaphragm. METHODS: We retrospectively included idiopathic pulmonary fibrosis (IPF) patients followed in our center (Marseille, France) between January 2020 and February 2023 who underwent diaphragmatic ultrasound. Our objectives were to describe the diaphragmatic function of IPFs compared to healthy controls and to correlate with clinical, functional, and lung density on CT-scan. RESULTS: 24 IPF patients and 157 controls were included. The diaphragmatic amplitude in IPF was increased at rest (median of 2.20 cm vs 1.88 cm on the right, p < 0.007, and 2.30 cm vs 1.91 cm on the left, p < 0.03, in IPF and controls respectively) and decreased in deep breathing (median of 4.85 cm vs 5.45 cm on the right, p < 0.009, and 5.10 cm vs 5.65 cm on the left, p < 0.046, in IPF and controls respectively). Diaphragmatic thickness was significantly reduced at rest on the right side (median of 1.75 mm vs 2.00 mm, p < 0.02, in IPF and controls respectively) and in deep breathing on both sides compared to controls (mean of 3.82 mm vs 4.15 mm on the right, p < 0.02, and 3.53 mm vs 3.94 mm, on the left, p < 0.009, in IPF and controls respectively). Diaphragmatic amplitude in deep breathing was moderate to strongly correlated with FVC, DLCO, and 6MWT and negatively correlated with the dyspnea and lung density on CT scan. CONCLUSION: The diaphragmatic amplitude and thickness were impaired in IPF compared to controls. Diaphragmatic amplitude is the parameter best correlated with clinical, functional, and lung density criteria. Further studies are needed to determine if diaphragmatic amplitude can be a prognostic factor in IPF.

Thoracic manifestations of IgG4-related disease.

Immunoglobulin G4-related disease (IgG4-RD) is a recently described rare systemic fibroinflammatory disease with an estimated incidence of less than 1 in 100,000 persons per year. The disease can affect virtually any organ and is characterized by unifying histopathological findings. Recently, four subgroups of patients have been characterized: hepatobiliary, head and neck, Mikulicz syndrome and retroperitoneal fibrosis, who illustrate the mainly abdominal and ENT tropism of the disease. Yet, thoracic involvement is not uncommon. It can be detected in up to 30% of patients with systemic IgG4-RD and is the exclusive manifestation of the disease in about 10% of cases. Clinical symptoms are nonspecific and may include dyspnoea, cough or chest pain. Chest CT findings are heterogeneous and primarily include peribronchovascular thickening, nodules, ground-glass opacities and lymphadenopathy. There is no specific diagnostic test for IgG4-RD thoracic involvement, which may mimic malignancy or vasculitis. Therefore, a cautious approach is needed to make an accurate diagnosis: a search for extra-thoracic manifestations, elevated serum IgG4 levels, circulating levels of plasmablasts and pathologic evidence of disease is warranted. Although very suggestive, neither the presence of a polyclonal IgG4 lymphoplasmacytic infiltrate, storiform fibrosis or obliterative phlebitis are sufficient to confirm the histological diagnosis. Steroids are recommended as first-line therapy. Rituximab or disease-modifying antirheumatic drugs may be used in relapsed or rare cases of steroid-refractory disease. In this review, we summarize current knowledge regarding the pathophysiology, epidemiology, diagnostic modalities (clinical-biological-imaging-histopathology) and treatment of IgG4-RD thoracic involvement.

Cardiac MRI Features and Prognostic Value in Immune Checkpoint Inhibitor-induced Myocarditis.

Background Cardiac MRI features are not well-defined in immune checkpoint inhibitor (ICI)-induced myocarditis (ICI-M), a severe complication of ICI therapy in patients with cancer. Purpose To analyze the cardiac MRI features of ICI-M and to explore their prognostic value in major adverse cardiovascular events (MACE). Materials and Methods In this retrospective study from May 2017 to January 2020, cardiac MRI findings (including late gadolinium enhancement [LGE], T1 and T2 mapping, and extracellular volume fraction [ECV] z scores) of patients with ICI-M were compared with those of patients with cancer scheduled to receive ICI therapy (pre-ICI group) and patients with viral myocarditis. As a secondary objective, the potential value of cardiac MRI for predicting MACE in patients with ICI-M by using Cox proportional hazards models was explored. Results Thirty-three patients with ICI-M (mean age ± standard deviation, 68 years ± 14; 23 men) were compared with 21 patients scheduled to receive to ICI therapy (mean age, 65 years ± 14; 14 men) and 85 patients with viral myocarditis (mean age, 32 years ± 13; 67 men). Compared with the pre-ICI group, patients with ICI-M showed higher global native T1, ECV, and T2 z scores (0.03 ± 0.85 vs 1.79 ± 1.93 [P < .001]; 1.34 ± 0.57 vs 2.59 ± 1.97 [P = .03]; and -0.76 ± 1.41 vs 0.88 ± 1.96 [P = .002], respectively), and LGE was more frequently observed (27 of 33 patients [82%] vs two of 21 [10%]; P < .001). LGE was less frequent in patients with ICI-M than those with viral myocarditis (27 of 33 patients [82%] vs 85 of 85 [100%]; P < .001) but was more likely to involve the septal segments (16 of 33 patients [48%] vs 25 of 85 [29%]; P < .001) and midwall layer (11 of 33 patients [33%] vs two of 85 [2%]; P < .001). Septal LGE was the only cardiac MRI predictor of MACE at 1 year even after adjustment for peak troponin (adjusted hazard ratio, 2.7 [95% CI: 1.1, 6.7]; P = .03). Conclusion Cardiac MRI features of immune checkpoint inhibitor (ICI)-induced myocarditis (ICI-M) seem to differ from those in patients scheduled to receive ICIs and patients with viral myocarditis. Septal late gadolinium enhancement might be a predictor of major cardiovascular events in patients with ICI-M. Clinical trial registration no. NCT03313544 © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Edelman and Pursnani in this issue.

Rectal Artery Embolization for Hemorrhoidal Disease: Anatomy, Evaluation, and Treatment Techniques.

Chronic hemorrhoidal disease is a common anorectal condition that leads to hemorrhoidal hyperplasia, which affects millions of people worldwide and is a significant medical and socioeconomic issue. Rectal bleeding is one of the main chronic symptoms. Recurrent rectal bleeding can alter an individual's quality of life and, more rarely, cause anemia. Pain is less common, occurring only in the event of complications such as congestive exacerbation, external hemorrhoidal thrombosis, or fissures. The most standard treatment involves dietary and hygiene measures, use of phlebotonic drugs, and nonsurgical treatment such as infrared photocoagulation or elastic band ligation. Excisional treatments such as hemorrhoidectomy and hemorrhoidopexy are the reference standards for treatment of hemorrhoidal disease. Embolization of the rectal arteries (ie, emborrhoid) has recently emerged as an effective treatment option, with few reported adverse effects, minimal blood loss, and a same-day hospital procedure. Hemorrhoid embolization is performed by using femoral or radial access. The inferior mesenteric artery and then the superior rectal arteries are catheterized with a microcatheter. Embolization can be performed by using different agents. Studies have shown improvement in symptoms and high technical success rates after treatment. The basic principles of hemorrhoid embolization that must be understood to achieve effective treatment, including those related to patient evaluation, the arterial anatomy, basic embolization, and published results, are reviewed. An invited commentary by Thompson and Kelley is available online. ©RSNA, 2022.

Early combination therapy with hydroxychloroquine and azithromycin reduces mortality in 10,429 COVID-19 outpatients.

We evaluated the age-specific mortality of unselected adult outpatients infected with SARS-CoV-2 treated early in a dedicated COVID-19 day hospital and we assessed whether the use of hydroxychloroquine (HCQ) + azithromycin (AZ) was associated with improved survival in this cohort. A retrospective monocentric cohort study was conducted in the day hospital of our center from March to December 2020 in adults with PCR-proven infection who were treated as outpatients with a standardized protocol. The primary endpoint was 6-week mortality, and secondary endpoints were transfer to the intensive care unit and hospitalization rate. Among 10,429 patients (median age, 45 [IQR 32-57] years; 5597 [53.7%] women), 16 died (0.15%). The infection fatality rate was 0.06% among the 8315 patients treated with HCQ+AZ. No deaths occurred among the 8414 patients younger than 60 years. Older age and male sex were associated with a higher risk of death, ICU transfer, and hospitalization. Treatment with HCQ+AZ (0.17 [0.06-0.48]) was associated with a lower risk of death, independently of age, sex and epidemic period. Meta-analysis evidenced consistency with 4 previous outpatient studies (32,124 patients-Odds ratio 0.31 [0.20-0.47], I2 = 0%). Early ambulatory treatment of COVID-19 with HCQ+AZ as a standard of care is associated with very low mortality, and HCQ+AZ improve COVID-19 survival compared to other regimens.

Description of morphological evolution of lung tumors treated by percutaneous radiofrequency ablation: long term follow-up of 100 lesions with chest CT.

PURPOSE: Radiofrequency ablation (RFA) is a safe and effective minimally invasive treatment for pulmonary tumors. Patterns on chest computed tomography (CT) after RFA are classified into five types; however, the follow-up has not been fully described. The objectives of this study were to describe (1) the CT pattern 3 years after RFA and (2) its evolution over 7 years. MATERIALS AND METHODS: Lesions treated with RFA between 2009 and 2017 and with ≥3 years of follow-up CT data were included. Lesions with local recurrences were excluded from the study. The morphology of the ablation zone was classified as nodular, fibrotic, atelectatic, cavitary, and disappeared. Other initial anatomical parameters were recorded. Kruskal-Wallis or Chi-square tests were used to compare the groups. RESULTS: One hundred lung RFA scars were included, and a retrospective longitudinal study was performed. Three years after RFA, nodular, fibrotic, atelectatic, and cavitary scars, and disappearance were observed in 49%, 36%, 5%, 3%, and 6% of the scars, respectively. Evolution over 7 years showed that the fibrosis, atelectasis, and disappearance remained stable over time, whereas 28% of nodular scars evolved into fibrotic scars. Additionally, 45% of cavitary scars evolved into nodular scars. Pleural contact was associated with disappearance, and the use of a 20-mm needle was associated with atelectasis. CONCLUSION: Follow-up after RFA showed that fibrosis, disappearance, and atelectasis remained stable over time. Nodular scars could evolve into fibrotic scars, and cavitary scars could evolve into nodular scars.

Percutaneous lung and liver CT-guided ablation on swine model using microwave ablation to determine ablation size for clinical practice.

PURPOSE: Microwave ablation (MWA) provides an effective treatment of lung and liver tumors but suffers from a lack of reproducibility of ablation size among currently available technologies. In-vitro evaluations are far removed from clinical practices because of uninfused tissue. This study is in-vivo preclinical testing of a new MWA system on swine lungs and liver. MATERIALS AND METHODS: All ablations were performed under CT guidance and multiple algorithms were tested with a power of 50, 75, and 100 W for durations of 3, 5, 8, 10, and 15 min. A 3 D-evaluation of the ablation zone was carried out using enhanced-CT. The sphericity index, coefficients of variation, and energy efficiency (which corresponds to the volume yield according to the power supplied) were calculated. RESULTS: Fifty liver and 48 lung ablations were performed in 17 swine. The sphericity index varies from 0.50 to 0.80 for liver ablations and from 0.40 to 0.69 for lung ablations. The coefficient of variation was below 15% for 4/5 and 4/8 protocols for lung and liver ablations, respectively. The energy efficiency seems to decrease with the duration of the ablation from 0.60 × 10-3 cm3/J (75 W, 3 min) to 0.26 × 10-3 cm3/J (100 W, 15 min) in the liver and from 0.57 × 10-3 cm3/J (50 W, 10 min) to 0.42 × 10-3 cm3/J (100 W, 12 min) in the lungs. CONCLUSION: A shorter treatment time provides the best energy efficiency, and the best reproducibility is obtained for a 10 min treatment duration. The system tested provides an interesting reproducibility in both lung and liver measurements. Our results may help interventional radiologists in the optimal selection of treatment parameters.

Can the use of whole-body CT be reduced in cases of kinetic-based polytrauma patients without a clinical severity criterion? A bi-center retrospective study.

OBJECTIVE: To identify clinical and biological criteria predictive of significant traumatic injury in only kinetic-based polytrauma patients without clinical severity criteria. To propose a decisional algorithm to assist the emergency doctor in deciding whether or not to perform a WBCT in the above population. METHODS: Retrospective bi-center study. 1270 patients with high velocity trauma without clinical severity criteria, for whom a WBCT was performed in 2017, were included. Patients with hemodynamic, respiratory or neurological severity criterion or those requiring pre-hospital resuscitation measures were excluded. Our primary endpoint was the identification of a significant lesion, i.e. any lesion that led to hospitalization > 24 h for monitoring or medico-surgical treatment. Data collected were age, sex, mechanism of injury, Glasgow Coma Scale score, number of symptomatic body regions, blood alcohol level, and neutrophil count. RESULTS: Multivariate analysis found independent predictors of significant injury: fall > 5 m (OR: 14.36; CI: 2.3-283.4; p = 0.017), Glasgow score = 13 or 14 (OR: 4.40; CI:1.30-18.52; p = 0.027), presence of 2 symptomatic body regions (OR: 10.21; CI: 4.66-23.72; p = 0.05), positive blood alcohol level (OR: 2.81; CI: 1.13-7.33; p = 0.029) and neutrophilic leukocytosis (OR: 8.76; CI: 3.94-21.27; p = 0.01). A composite clinico-biological endpoint predictive of the absence of significant lesion was identified using a Classification and Regression Tree: number of symptomatic regions < 2, absence of Neutrophilic leukocytosis and negative blood alcohol concentration. CONCLUSION: A simple triage algorithm was created with the objective of identifying, in high velocity trauma without clinical severity criteria, those without significant traumatic injury.

Impact of preexisting interstitial lung disease on outcomes of lung cancer surgery: A monocentric retrospective study.

INTRODUCTION: Interstitial lung disease (ILD) is a known risk factor for lung cancer (LC). However, the surgical risk of LC in patients with ILD remains unclear. Therefore, we conducted a single-center retrospective study to assess clinical features and outcomes of LC population who underwent surgery with or without ILD. METHODS: Patients who underwent surgery for LC between January 2006 and June 2023 in our center were assessed using data extracted from the nationwide EPITHOR thoracic surgery database. Suspicion of ILD was based on patients' records. Confirmation of ILD was then made on the patient's medical and radiological history. Patients were classified according to the pattern of ILD. The study aimed to describe the outcomes after lung cancer resection in patients with confirmed LC-ILD group compared to those without ILD (LC-non-ILD): post-operative complications, disease-free survival (DFS) and overall survival (OS). A subgroup analysis was also performed on patients with idiopathic pulmonary fibrosis and lung cancer (LC-IPF). RESULTS: 4073 patients underwent surgery for LC at Assistance Publique des Hôpitaux de Marseille between January 2006 and June 2023. Of these, 4030 were in the LC-non-ILD group and 30 were LC-ILD patients. In the LC-ILD group, the predominant CT scan pattern was probable UIP (50 %). OS was not significantly lower in the LC-ILD group (45 months versus 84 months, p = 0.068). Dyspnea and tumor size were identified as potential univariate predictors of OS. No significant differences were observed on post-operative complications or their severity. The most common post-operative complications in the LC-ILD group were prolonged air leak, respiratory failure, or pneumonia. 13 patients had cancer recurrence in the LC-ILD group. CONCLUSION: Our study provides a comprehensive analysis of a LC-ILD population features and outcome when undergoing surgery for LC. Patients with LC-ILD appeared to have a reduced OS compared with LC-non-ILD. Further investigations with larger prospective studies could be useful to confirm and develop these preliminary findings.

Pulmonary Hypertension Induced by Right Pulmonary Artery Occlusion: Hemodynamic Consequences of Bmpr2 Mutation.

BACKGROUND: The primary genetic risk factor for heritable pulmonary arterial hypertension is the presence of monoallelic mutations in the BMPR2 gene. The incomplete penetrance of BMPR2 mutations implies that additional triggers are necessary for pulmonary arterial hypertension occurrence. Pulmonary artery stenosis directly raises pulmonary artery pressure, and the redirection of blood flow to unobstructed arteries leads to endothelial dysfunction and vascular remodeling. We hypothesized that right pulmonary artery occlusion (RPAO) triggers pulmonary hypertension (PH) in rats with Bmpr2 mutations. METHODS AND RESULTS: Male and female rats with a 71 bp monoallelic deletion in exon 1 of Bmpr2 and their wild-type siblings underwent acute and chronic RPAO. They were subjected to full high-fidelity hemodynamic characterization. We also examined how chronic RPAO can mimic the pulmonary gene expression pattern associated with installed PH in unobstructed territories. RPAO induced precapillary PH in male and female rats, both acutely and chronically. Bmpr2 mutant and male rats manifested more severe PH compared with their counterparts. Although wild-type rats adapted to RPAO, Bmpr2 mutant rats experienced heightened mortality. RPAO induced a decline in cardiac contractility index, particularly pronounced in male Bmpr2 rats. Chronic RPAO resulted in elevated pulmonary IL-6 (interleukin-6) expression and decreased Gdf2 expression (corrected P value<0.05 and log2 fold change>1). In this context, male rats expressed higher pulmonary levels of endothelin-1 and IL-6 than females. CONCLUSIONS: Our novel 2-hit rat model presents a promising avenue to explore the adaptation of the right ventricle and pulmonary vasculature to PH, shedding light on pertinent sex- and gene-related effects.

Change in diaphragmatic morphology in single-lung transplant recipients: a computed tomographic study.

Introduction: The influence of lung disease on the diaphragm has been poorly studied. The study aimed to evaluate the diaphragm morphology (height and thickness) in single-lung transplantation (SLTx), using computed tomography (CT), by assessing the evolution of the hemidiaphragm of the transplanted and the native side. Methods: Patients who underwent single lung transplantation in our center (Marseille, France) between January 2009 and January 2022 were retrospectively included. Thoracic or abdominal CT scans performed before and the closest to and at least 3 months after the surgery were used to measure the diaphragm crus thickness and the diaphragm dome height. Results: 31 patients mainly transplanted for emphysema or pulmonary fibrosis were included. We demonstrated a significant increase in diaphragm crus thickness on the side of the transplanted lung, with an estimated difference of + 1.25 mm, p = <0.001, at the level of the celiac artery, and + 0.90 mm, p < 0.001, at the level of the L1 vertebra while no significant difference was observed on the side of the native lung. We showed a significant reduction in the diaphragm height after SLTx on the transplanted side (-1.20 cm, p = 0.05), while no change on the native side (+0.02 cm, p = 0.88). Conclusion: After a SLTx, diaphragmatic morphology significantly changed on the transplanted lung, while remaining altered on the native lung. These results highlights that an impaired lung may have a negative impact on its diaphragm. Replacement with a healthy lung can promote the recovery of the diaphragm to its anatomical morphology, reinforcing the close relationship between these two organs.

Comparative performances of machine learning algorithms in radiomics and impacting factors.

There are no current recommendations on which machine learning (ML) algorithms should be used in radiomics. The objective was to compare performances of ML algorithms in radiomics when applied to different clinical questions to determine whether some strategies could give the best and most stable performances regardless of datasets. This study compares the performances of nine feature selection algorithms combined with fourteen binary classification algorithms on ten datasets. These datasets included radiomics features and clinical diagnosis for binary clinical classifications including COVID-19 pneumonia or sarcopenia on CT, head and neck, orbital or uterine lesions on MRI. For each dataset, a train-test split was created. Each of the 126 (9 × 14) combinations of feature selection algorithms and classification algorithms was trained and tuned using a ten-fold cross validation, then AUC was computed. This procedure was repeated three times per dataset. Best overall performances were obtained with JMI and JMIM as feature selection algorithms and random forest and linear regression models as classification algorithms. The choice of the classification algorithm was the factor explaining most of the performance variation (10% of total variance). The choice of the feature selection algorithm explained only 2% of variation, while the train-test split explained 9%.

Radiomics model to classify mammary masses using breast DCE-MRI compared to the BI-RADS classification performance.

BACKGROUND: Recent advanced in radiomics analysis could help to identify breast cancer among benign mammary masses. The aim was to create a radiomics signature using breast DCE-MRI extracted features to classify tumors and to compare the performances with the BI-RADS classification. MATERIAL AND METHODS: From September 2017 to December 2019 images, exams and records from consecutive patients with mammary masses on breast DCE-MRI and available histology from one center were retrospectively reviewed (79 patients, 97 masses). Exclusion criterion was malignant uncertainty. The tumors were split in a train-set (70%) and a test-set (30%). From 14 kinetics maps, 89 radiomics features were extracted, for a total of 1246 features per tumor. Feature selection was made using Boruta algorithm, to train a random forest algorithm on the train-set. BI-RADS classification was recorded from two radiologists. RESULTS: Seventy-seven patients were analyzed with 94 tumors, (71 malignant, 23 benign). Over 1246 features, 17 were selected from eight kinetic maps. On the test-set, the model reaches an AUC = 0.94 95 CI [0.85-1.00] and a specificity of 33% 95 CI [10-70]. There were 43/94 (46%) lesions BI-RADS4 (4a = 12/94 (13%); 4b = 9/94 (10%); and 4c = 22/94 (23%)). The BI-RADS score reached an AUC = 0.84 95 CI [0.73-0.95] and a specificity of 17% 95 CI [3-56]. There was no significant difference between the ROC curves for the model or the BI-RADS score (p = 0.19). CONCLUSION: A radiomics signature from features extracted using breast DCE-MRI can reach an AUC of 0.94 on a test-set and could provide as good results as BI-RADS to classify mammary masses.

FairEmbo Concept for Postpartum Hemorrhage: Evaluation of the Efficacy of Suture Fragment Compared with Gelatin Sponge Torpedo Embolization in a Post-Gravid Swine Model.

BACKGROUND: Postpartum hemorrhage is the leading cause of maternal mortality in emerging countries. This study aims to evaluate the effectiveness and safety of uterine artery embolization (UAE) using suture fragment (FairEmbo concept) in a swine model. METHODS: Seven female swine uteri were embolized. The left uterine artery was embolized with 1 cm fragments of absorbable suture (Optime® 0), and with gelatin sponge torpedoes for the contralateral side for comparison. The embolization effectiveness and the time for arterial recanalization with digital subtraction angiography (DSA) controls at D0, D7, and M1, were evaluated. Follow-up protocol also included clinical monitoring and macroscopical analyses at M1. A Mann-Whitney test (significance at P 0.05) was used for statistics. RESULTS: A technical success was obtained for the seven arteries on each side, with no off-target embolization. The procedure time (10 min versus 3.7 min) and number of fragments (13.8 versus 5.7) required for complete occlusion were significantly greater in the FairEmbo group. All arteries were repermeabilized at M1. No necrosis was macroscopically visible at harvest at M1. CONCLUSION: This experimental study suggests that UAE with SBM FairEmbo method is feasible, safe, and effective in comparison with gelatin sponge procedure.

Early chest CT abnormalities to predict the subsequent occurrence of chronic lung allograft dysfunction.

INTRODUCTION: Chronic lung allograft dysfunction (CLAD) can take two forms: bronchiolitis obliterans syndrome (BOS) or restrictive allograft syndrome (RAS). The aim was to determine if chest-CT abnormalities after lung transplantation (LTx) could predict CLAD before respiratory functional deterioration. MATERIALS AND METHODS: This monocentric retrospective study analyzed consecutive patients who underwent LTx from January 2015 to December 2018. Initial CT post-LTx (CTi) and a follow-up CT at least 9 months post-LTx (CTf) were reviewed. CLAD was defined as a persistent respiratory functional decline (> 20% of basal FEV1) outside acute episode. A Cox regression was performed in univariate, then in multivariate analysis (including features with p < 0.01 in univariate or of clinical importance) to determine risk factors for CLAD. Subgroup analyses were made for BOS, RAS, and death. RESULTS: Among 118 LTx patients (median (min-max) 47 (18-68) years), 25 developed CLAD during follow-up (19 BOS). The median time to CLAD since LTx was 570 days [150-1770]. Moderate pulmonary artery stenosis (30-50%) was associated with the occurrence of CLAD on CTi (hazard ratio HR = 4.6, CI [1.6-13.2]) and consolidations and pleural effusion on CTf (HR = 2.6, CI [1.3-4.9] and HR = 4.5, CI [1.5-13.6] respectively). The presence of mosaic attenuation (HR = 4.1, CI [1.4-12.5]), consolidations (HR = 2.6, CI [1.3-5.4]), and pleural effusions (p = 0.01, HR = 5.7, CI [1.4-22.3]) were risk factors for BOS on CTf. The consolidations (p = 0.029) and pleural effusions (p = 0.001) were risk factors for death on CTf. CONCLUSIONS: CTi and CTf in the monitoring of LTx patients could predict CLAD. Moderate pulmonary artery stenosis, mosaic pattern, parenchyma condensations, and pleural effusions were risk factors for CLAD. CRITICAL RELEVANCE STATEMENT: There is a potential predictive role of chest CT in the follow-up of LTx patients for chronic lung allograft dysfunction (CLAD). Early chest CT should focus on pulmonary artery stenosis (risk factor for CLAD in this study). During the follow-up (at least 9 months post-LTx), parenchymal consolidations and pleural effusions were shown to be risk factors for CLAD, and death in subgroup analyses. KEY POINTS: • Pulmonary artery stenosis (30-50%) on initial chest-CT following lung transplantation predicts CLAD HR = 4.5; CI [1.6-13.2]. • Pleural effusion and consolidations 1 year after lung transplantation predict CLAD and death. • Early evaluation of lung transplanted patients should evaluate pulmonary artery anastomosis.