Multicentric clinical evaluation of a computed tomography-based fully automated deep neural network for aortic maximum diameter and volumetric measurements.

OBJECTIVE: This study aims to evaluate a fully automatic deep learning-based method (augmented radiology for vascular aneurysm [ARVA]) for aortic segmentation and simultaneous diameter and volume measurements. METHODS: A clinical validation dataset was constructed from preoperative and postoperative aortic computed tomography angiography (CTA) scans for assessing these functions. The dataset totaled 350 computed tomography angiography scans from 216 patients treated at two different hospitals. ARVA's ability to segment the aorta into seven morphologically based aortic segments and measure maximum outer-to-outer wall transverse diameters and compute volumes for each was compared with the measurements of six experts (ground truth) and thirteen clinicians. RESULTS: Ground truth (experts') measurements of diameters and volumes were manually performed for all aortic segments. The median absolute diameter difference between ground truth and ARVA was 1.6 mm (95% confidence interval [CI], 1.5-1.7; and 1.6 mm [95% CI, 1.6-1.7]) between ground truth and clinicians. ARVA produced measurements within the clinical acceptable range with a proportion of 85.5% (95% CI, 83.5-86.3) compared with the clinicians' 86.0% (95% CI, 83.9-86.0). The median volume similarity error ranged from 0.93 to 0.95 in the main trunk and achieved 0.88 in the iliac arteries. CONCLUSIONS: This study demonstrates the reliability of a fully automated artificial intelligence-driven solution capable of quick aortic segmentation and analysis of both diameter and volume for each segment.

Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.

Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article.

CT, MRI and PET/CT features of abdominal manifestations of cutaneous melanoma: a review of current concepts in the era of tumor-specific therapies.

Abdominal manifestations in patients with cutaneous melanoma include involvement due to metastatic spread and immune checkpoint inhibitor induced adverse events. The purpose of this review is to provide a critical overview of abdominal manifestations in patients with cutaneous melanoma and highlight the current imaging challenges in the era of tumor-specific therapies. Immune checkpoint inhibitors represent a treatment with demonstrated efficacy in the treatment of advanced cutaneous melanoma but are associated with several abdominal adverse events that must be recognized. CT has a role in the identification of colitis, enteritis and pancreatitis, whereas MRI has an important role in the diagnosis of autoimmune pancreatitis. Current evidence demonstrates that MRI should be the preferred imaging technique for the detection and characterization of hepatic and splenic metastases from cutaneous melanoma. The role of 18F-FDG-PET/CT should be further evaluated but current literature suggests an efficacy in the detection of pancreatic metastases not seen on CT and MRI.

AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia.

Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.

COVID-19 pneumonia: Diagnostic and prognostic role of CT based on a retrospective analysis of 214 consecutive patients from Paris, France.

OBJECTIVES: To evaluate the diagnostic and prognostic performance of CT in patients referred for COVID19 suspicion to a French university hospital, depending on symptoms and date of onset. METHODS: From March 1st to March 28th, 214 patients having both chest CT scan and reverse transcriptase polymerase chain reaction (RT- PCT) within 24 h were retrospectively evaluated. Sensitivity, specificity, negative and positive predictive values of first and expert readings were calculated together with inter reader agreement, with results of RT-PCR as standard of reference and according to symptoms and onset date. Patient characteristics and disease extent on CT were correlated to short-term outcome (death or intubation at 3 weeks follow-up). RESULTS: Of the 214 patients (119 men, mean age 59 ±â€¯19 years), 129 had at least one positive RT-PCR result. Sensitivity, specificity, negative and positive predictive values were 79 % (95 % CI: 71-86 %), 84 %(74-91 %), 72 %(63-81 %) and 88 % (81-93 %) for initial CT reading and 81 %(74-88 %), 91 % (82-96 %), 76 % (67-84 %) and 93 % (87-97 %), for expert reading, with strong inter-reader agreement (kappa index: 0.89). Considering the 123 patients with symptoms for more than 5 days, the corresponding figures were 90 %, 78 %, 80 % and 89 % for initial reading and 93 %, 88 %, 86 % and 94 % for the expert. Disease extent exceeded 25 % for 68 % and 26 % of severe and non-severe patients, respectively (p < 0.001). CONCLUSION: CT sensitivity increased after 5 days of symptoms. A disease extent > 25 % was associated with poorer outcome.

Pre-test probability for SARS-Cov-2-related infection score: The PARIS score.

INTRODUCTION: In numerous countries, large population testing is impossible due to the limited availability of RT-PCR kits and CT-scans. This study aimed to determine a pre-test probability score for SARS-CoV-2 infection. METHODS: This multicenter retrospective study (4 University Hospitals) included patients with clinical suspicion of SARS-CoV-2 infection. Demographic characteristics, clinical symptoms, and results of blood tests (complete white blood cell count, serum electrolytes and CRP) were collected. A pre-test probability score was derived from univariate analyses of clinical and biological variables between patients and controls, followed by multivariate binary logistic analysis to determine the independent variables associated with SARS-CoV-2 infection. RESULTS: 605 patients were included between March 10th and April 30th, 2020 (200 patients for the training cohort, 405 consecutive patients for the validation cohort). In the multivariate analysis, lymphocyte (<1.3 G/L), eosinophil (<0.06 G/L), basophil (<0.04 G/L) and neutrophil counts (<5 G/L) were associated with high probability of SARS-CoV-2 infection but no clinical variable was statistically significant. The score had a good performance in the validation cohort (AUC = 0.918 (CI: [0.891-0.946]; STD = 0.014) with a Positive Predictive Value of high-probability score of 93% (95%CI: [0.89-0.96]). Furthermore, a low-probability score excluded SARS-CoV-2 infection with a Negative Predictive Value of 98% (95%CI: [0.93-0.99]). The performance of the score was stable even during the last period of the study (15-30th April) with more controls than infected patients. CONCLUSIONS: The PARIS score has a good performance to categorize the pre-test probability of SARS-CoV-2 infection based on complete white blood cell count. It could help clinicians adapt testing and for rapid triage of patients before test results.

Definitions, adjudication, and reporting of pulmonary embolism-related death in clinical studies: A systematic review.

BACKGROUND: Pulmonary embolism (PE)-related death is a component of the primary outcome in many venous thromboembolism (VTE) studies. The absence of a standardized definition for PE-related death hampers study outcome evaluation and between-study comparisons. OBJECTIVES: To summarize definitions for PE-related death used in recent VTE studies and to assess the PE-related death rate. PATIENTS/METHODS: A systematic literature search was conducted on 26 April 2018 from 1 January 2014 up to the search date in MEDLINE, Embase, and CENTRAL. Cohort studies and randomized trials in which PE-related death was included in the primary outcome were eligible. Screening of titles, abstracts, and full-text articles, and data extraction were independently performed in duplicate by two authors. Study outcomes included the definition for PE-related death, VTE case-fatality rate, and death due to PE rate. Descriptive statistics were used to analyze the data. RESULTS: Of the 6807 identified citations, 83 studies were included of which 27% were randomized trials, 31% were prospective, and 42% retrospective cohort studies. Thirty-five studies (42%) had a central adjudication committee. Thirty-eight (46%) reported a definition for PE-related death of which the most frequently used components were "autopsy-confirmed PE" (50%), "objectively confirmed PE before death" (55%), and "unexplained death" (58%). Median VTE case-fatality rate was 1.8% (interquartile range, 0.0-13). CONCLUSIONS: Only half of the included studies reported definitions for PE-related death, which were very heterogeneous. Case-fatality rate of VTE events varied widely across studies. Standardization of the definition and guidance on adjudication and reporting of PE-related death is needed.