A deep learning method for predicting knee osteoarthritis radiographic progression from MRI.

BACKGROUND: The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs. METHODS: Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months. RESULTS: Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction. CONCLUSIONS: This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.

Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients.

The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach.

The local properties of bold signal fluctuations at rest monitor inhibitory control training in adolescents.

Inhibitory control (IC) plays a critical role in cognitive and socio-emotional development. Short-term IC training improves IC abilities in children and adults. Surprisingly, few studies have investigated the IC training effect during adolescence, a developmental period characterized by high neuroplasticity and the protracted development of IC abilities. We investigated behavioural and functional brain changes induced by a 5-week computerized and adaptive IC training in adolescents. We focused on the IC training effects on the local properties of functional Magnetic Resonance Imaging (fMRI) signal fluctuations at rest (i.e., Regional Homogeneity [ReHo] and fractional Amplitude of Low Frequency Fluctuations [fALFF]). Sixty adolescents were randomly assigned to either an IC or an active control training group. In the pre- and post-training sessions, cognitive ('Cool') and emotional ('Hot') IC abilities were assessed using the Colour-Word and Emotional Stroop tasks. We found that ReHo and fALFF signals in IC areas (IFG, ACC, Striatum) were associated with IC efficiency at baseline. This association was different for Cool and Hot IC. Analyses also revealed that ReHo and fALFF signals were sensitive markers to detect and monitor changes after IC training, while behavioural data did not, suggesting that brain functional changes at rest precede behavioural changes following training.