Search

International audience; Purpose. Motion-mask segmentation from thoracic computed tomography (CT) images is the process of extracting the region that encompasses lungs and viscera, where large displacements occur during breathing. It has been shown to help image registration between different respiratory phases. This registration step is, for example, useful for radiotherapy planning or calculating local lung ventilation. Knowing the location of motion discontinuity, that is, sliding motion near the pleura, allows a better control of the registration preventing unrealistic estimates. Nevertheless, existing methods for motion-mask segmentation are not robust enough to be used in clinical routine. This article shows that it is feasible to overcome this lack of robustness by using a lightweight deep-learning approach usable on a standard computer, and this even without data augmentation or advanced model design.Methods. A convolutional neural-network architecture with three 2D U-nets for the three main orientations (sagittal, coronal, axial) was proposed. Predictions generated by the three U-nets were combined by majority voting to provide a single 3D segmentation of the motion mask. The networks were trained on a database of nonsmall cell lung cancer 4D CT images of 43 patients. Training and evaluation were done with a K-fold cross-validation strategy. Evaluation was based on a visual grading by two experts according to the appropriateness of the segmented motion mask for the registration task, and on a comparison with motion masks obtained by a baseline method using level sets. A second database (76 CT images of patients with early-stage COVID-19), unseen during training, was used to assess the generalizability of the trained neural network.Results. The proposed approach outperformed the baseline method in terms of quality and robustness: the success rate increased from urn:x-wiley:00942405:media:mp15347:mp15347-math-0001 to urn:x-wiley:00942405:media:mp15347:mp15347-math-0002 without producing any failure. It also achieved a speed-up factor of 60 with GPU, or 17 with CPU. The memory footprint was low: less than 5 GB GPU RAM for training and less than 1 GB GPU RAM for inference. When evaluated on a dataset with images differing by several characteristics (CT device, pathology, and field of view), the proposed method improved the success rate from urn:x-wiley:00942405:media:mp15347:mp15347-math-0003 to urn:x-wiley:00942405:media:mp15347:mp15347-math-0004.Conclusion. With 5-s processing time on a mid-range GPU and success rates around urn:x-wiley:00942405:media:mp15347:mp15347-math-0005, the proposed approach seems fast and robust enough to be routinely used in clinical practice. The success rate can be further improved by incorporating more diversity in training data via data augmentation and additional annotated images from different scanners and diseases. The code and trained model are publicly available.

International audience; Although neural networks have proven very successful in a number of medical image analysis applications, their use remains difficult when targeting subtle tasks such as the identification of barely visible brain lesions, especially given the lack of annotated datasets. Good candidate approaches are patch-based unsupervised pipelines which have both the advantage to increase the number of input data and to capture local and fine anomaly patterns distributed in the image, while potential inconveniences are the loss of global structural information. We illustrate this trade-off on Parkinson's disease (PD) anomaly detection comparing the performance of two anomaly detection models based on a spatial auto-encoder (AE) and an adaptation of a patch-fed siamese auto-encoder (SAE). On average, the SAE model performs better, showing that patches may indeed be advantageous.

An online survey among French-speaking Belgians (N=7711) investigated self-reported changes in alcohol consumption during the first COVID-19-related lockdown (March 17th - May 4th 2020). Population-weighted estimates indicated that 31.37% of the population increased consumption during lockdown, 30.32% decreased consumption and 38.31% reported unchanged consumption. The magnitude of change was higher for "decreasers" than "increasers", resulting in a slight reduction in overall consumption. A multiple regression analysis revealed that age, occupational status, number of cohabitants, perceived alcohol accessibility, drinking motivations and previous consumption predicted consumption changes. The lockdown was thus associated with consumption modifications among French-speaking Belgians, without a prevailing direction of change.

The global outbreak of coronavirus disease 2019 (COVID-19) and the resulting lockdown measures have raised concerns regarding their effect on alcohol consumption. We investigated alcohol use during lockdown in a population of college students, usually characterized by social and heavy drinking. We also tested the predictive role of pre-lockdown drinking motives on alcohol consumption during lockdown. We collected data from 1951 French-speaking Belgian students during the lockdown period (April 1st - May 3rd, 2020) through a cross-sectional online survey. Participants self-reported their daily alcohol consumption (1) during a typical week in normal circumstances (i.e., before lockdown), and (2) since lockdown onset. We also assessed drinking motives and severity of alcohol use before lockdown. Our findings showed that 68.2% of the sample reported a lower alcohol consumption during lockdown compared to before lockdown, 17.2% conversely reporting a higher consumption. Enhancement, social and coping motives were all associated with heavy drinking before lockdown. Enhancement and social motives predicted lower alcohol consumption during lockdown among heavy drinkers. Conversely, coping motives, as well as social motives among low drinkers, predicted higher consumption during lockdown. Conformity motives, as well as enhancement motives among low and moderate drinkers, did not predict alcohol consumption before or during lockdown. Overall, several pre-lockdown drinking motives reliably predicted alcohol consumption during lockdown and could thus be used to identify at-risk populations and to tailor intervention programs on alcohol misuse during sanitary crises.