Influence of clinical suspicion on CT accuracy of acute mesenteric ischemia: Retrospective study of 362 patients.

PURPOSE: Acute mesenteric ischemia (AMI) may be underdiagnosed when not clinically suspected before CT is performed. We assessed the influence of a clinical suspicion of AMI on the CT accuracy. METHOD: This retrospective single-centre study included patients who underwent CT in 2014-2019 and had clinically suspected AMI and/or confirmed AMI. CT protocols were adapted based on each patient's presentation and on findings from unenhanced images. The CT protocol was considered optimal for AMI when it included arterial and portal venous phases. CT protocols, accuracy of reports, and outcomes were compared between the groups with and without suspected AMI before CT. RESULTS: Of the 375 events, 337 (90 %) were suspected AMI and 66 (18 %) were AMI, including 28 (42 %) with and 38 without suspected AMI. These two groups did not differ significantly regarding the medical history, clinical presentation, or laboratory tests. The CT protocol was more often optimal for AMI in the group with suspected AMI (26/28 [93 %] vs. 28/38 [74 %], p = 0.046). Diagnostic accuracy was not different between groups with and without suspected AMI (26/28 [93 %] vs. 34/38 [90 %], p = 1.00). However, it was lower in the group without suspicion of AMI when the CT protocol was not optimal for AMI (27/28 [96 %] vs 7/10 [70 %], p = 0.048). CONCLUSIONS: The negative influence of not clinically suspecting AMI can be mitigated by using a tailored CT protocol.

Abdominal musculature segmentation and surface prediction from CT using deep learning for sarcopenia assessment.

PURPOSE: The purpose of this study was to build and train a deep convolutional neural networks (CNN) algorithm to segment muscular body mass (MBM) to predict muscular surface from a two-dimensional axial computed tomography (CT) slice through L3 vertebra. MATERIALS AND METHODS: An ensemble of 15 deep learning models with a two-dimensional U-net architecture with a 4-level depth and 18 initial filters were trained to segment MBM. The muscular surface values were computed from the predicted masks and corrected with the algorithm's estimated bias. Resulting mask prediction and surface prediction were assessed using Dice similarity coefficient (DSC) and root mean squared error (RMSE) scores respectively using ground truth masks as standards of reference. RESULTS: A total of 1025 individual CT slices were used for training and validation and 500 additional axial CT slices were used for testing. The obtained mean DSC and RMSE on the test set were 0.97 and 3.7 cm2 respectively. CONCLUSION: Deep learning methods using convolutional neural networks algorithm enable a robust and automated extraction of CT derived MBM for sarcopenia assessment, which could be implemented in a clinical workflow.

Three artificial intelligence data challenges based on CT and MRI.

PURPOSE: The second edition of the artificial intelligence (AI) data challenge was organized by the French Society of Radiology with the aim to: (i), work on relevant public health issues; (ii), build large, multicentre, high quality databases; and (iii), include three-dimensional (3D) information and prognostic questions. MATERIALS AND METHODS: Relevant clinical questions were proposed by French subspecialty colleges of radiology. Their feasibility was assessed by experts in the field of AI. A dedicated platform was set up for inclusion centers to safely upload their anonymized examinations in compliance with general data protection regulation. The quality of the database was checked by experts weekly with annotations performed by radiologists. Multidisciplinary teams competed between September 11th and October 13th 2019. RESULTS: Three questions were selected using different imaging and evaluation modalities, including: pulmonary nodule detection and classification from 3D computed tomography (CT), prediction of expanded disability status scale in multiple sclerosis using 3D magnetic resonance imaging (MRI) and segmentation of muscular surface for sarcopenia estimation from two-dimensional CT. A total of 4347 examinations were gathered of which only 6% were excluded. Three independent databases from 24 individual centers were created. A total of 143 participants were split into 20 multidisciplinary teams. CONCLUSION: Three data challenges with over 1200 general data protection regulation compliant CT or MRI examinations each were organized. Future challenges should be made with more complex situations combining histopathological or genetic information to resemble real life situations faced by radiologists in routine practice.

Volatile and semi-volatile organic compounds of respiratory health relevance in French dwellings.

Over the last decades, the prevalence of childhood respiratory conditions has dramatically increased worldwide. Considering the time spent in enclosed spaces, indoor air pollutants are of major interest to explain part of this increase. This study aimed to measure the concentrations of pollutants known or suspected to affect respiratory health that are present in dwellings in order to assess children's exposure. Measurements were taken in 150 homes with at least one child, in Brittany (western France), to assess the concentrations of 18 volatile organic compounds (among which four aldehydes and four trihalomethanes) and nine semi-volatile organic compounds (seven phthalates and two synthetic musks). In addition to descriptive statistics, a principal component analysis (PCA) was used to investigate grouping of contaminants. Formaldehyde was highly present and above 30 µg/m(3) in 40% of the homes. Diethyl phthalate, diisobutyl phthalate, and dimethylphthalate were quantified in all dwellings, as well as Galaxolide and Tonalide. For each chemical family, the groups appearing in the PCA could be interpreted in term of sources. The high prevalence and the levels of these compounds, with known or suspected respiratory toxicity, should question regulatory agencies to trigger prevention and mitigation actions.