Antoine de Reviers

Mr. Antoine de Reviers

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2022 in Insights into Imaging
Verified
Journal Article
Open access
PDF file
QVQuentin Vanderbecq
Quentin Vanderbecq
RARoberto Ardon
Roberto Ardon
ARAntoine de Reviers
Antoine de Reviers
CRCamille Ruppli
Camille Ruppli
ADAxel Dallongeville
Axel Dallongeville
MZMarc Zins
Marc Zins
Background: To train a machine-learning model to locate the transition zone (TZ) of adhesion-related small bowel obstruction (SBO) on CT scans. Materials and methods: We used 562 CTs performed in 2005–2018 in 404 patients with adhesion-related SBO. Annotation of the TZs was performed by experienced radiologists and trained residents using bounding boxes. Preprocessing involved using a pretrained model to extract the abdominopelvic region. We modeled TZ localization as a binary classification problem by splitting the abdominopelvic region into 125 patches. We then trained a neural network model to classify each patch as containing or not containing a TZ. We coupled this with a trained probabilistic estimation of presence of a TZ in each patch. The models were first evaluated by computing the area under the receiver operating characteristics curve (AUROC). Then, to assess the clinical benefit, we measured the proportion of total abdominopelvic volume classified as containing a TZ for several different false-negative rates. Results: The probability of containing a TZ was highest for the hypogastric region (56.9%). The coupled classification network and probability mapping produced an AUROC of 0.93. For a 15% proportion of volume classified as containing TZs, the probability of highlighted patches containing a TZ was 92%. Conclusion: Modeling TZ localization by coupling convolutional neural network classification and probabilistic localization estimation shows the way to a possible automatic TZ detection, a complex radiological task with a major clinical impact.

1 July 2021 in Clinical Nutrition
Verified
Journal Article
Closed access
CBC. Breuillard
C. Breuillard
CMChristophe Moinard
Christophe Moinard
AGA. Goron
A. Goron
NNN. Neveux
N. Neveux
ARAntoine de Reviers
Antoine de Reviers
Vickie Elaine BaracosVickie Elaine Baracos
Vickie Elaine Baracos

4 November 2023 in Nutrients
Verified
Journal Article
Open access
PDF file
ARAntoine de Reviers
Antoine de Reviers
AHAgnes Helme-Guizon
Agnes Helme-Guizon
CMChristophe Moinard
Christophe Moinard
Catherine FéartCatherine Féart
Catherine Féart
Background: The COVID-19 pandemic has imposed local lockdowns resulting in strong disruptions in our lifestyles and dietary behaviors. This study aimed to determine how the lockdown in France affected these behaviors and weight during the lockdown and in a one month follow up period of time after the end of the lockdown. Methods: The study design was a longitudinal cohort, among French adults. A total of 593 participants (68.6% female), with a mean age of 42.2 years (SD = 15.2) completed a self-reported questionnaire on four occasions spaced one month apart, from the beginning of the lockdown starting 17 March 2020, until one month after its end (mid-June 2020). Clusters of participants were formed using the non-supervised k-means algorithm. Results: The mean weight gain after one month of lockdown was 0.56 kg (SD = 0.6). The cluster analysis exposed three different patterns of behavioral changes, despite no significant differences in age or BMI between clusters. These three groups have experienced different weight change dynamics over the follow-up duration. The first cluster (n = 210) reported fewer changes in sleep quality and quantity and less change in snacking frequency (p ≤ 0.001). The second cluster (n = 200) reported significantly lower levels of stress than the other clusters (p ≤ 0.001). The third cluster (n = 183) differed from the others, with a more degraded quality of sleep reported throughout the lockdown (p ≤ 0.01). However, changes in eating behaviors and body weight were not significant. Conclusions: During the lockdown, behavioral changes occurred, both health-favorable and non-health-favorable, yet they had a minor impact on eating behaviors and reported body weight once the restrictive measures were lifted. The identification of three patterns suggests that, in such constraining situations, personalized recommendations should be provided.