Spotting L3 slice in CT scans using deep convolutional network and transfer learning.

In this article, we present a complete automated system for spotting a particular slice in a complete 3D Computed Tomography exam (CT scan). Our approach does not require any assumptions on which part of the patient's body is covered by the scan. It relies on an original machine learning regression approach. Our models are learned using the transfer learning trick by exploiting deep architectures that have been pre-trained on imageNet database, and therefore it requires very little annotation for its training. The whole pipeline consists of three steps: i) conversion of the CT scans into Maximum Intensity Projection (MIP) images, ii) prediction from a Convolutional Neural Network (CNN) applied in a sliding window fashion over the MIP image, and iii) robust analysis of the prediction sequence to predict the height of the desired slice within the whole CT scan. Our approach is applied to the detection of the third lumbar vertebra (L3) slice that has been found to be representative to the whole body composition. Our system is evaluated on a database collected in our clinical center, containing 642 CT scans from different patients. We obtained an average localization error of 1.91±2.69 slices (less than 5 mm) in an average time of less than 2.5 s/CT scan, allowing integration of the proposed system into daily clinical routines.

Daytime cortisol and stress reactivity in the offspring of parents with bipolar disorder.

The hypothalamic-pituitary-adrenal (HPA) axis is compromised in major depression and bipolar disorder (BD). It is not known however whether HPA abnormalities predate the onset of these disorders. Preliminary data indicated that the adolescent offspring of parents with BD (high-risk), as compared to adolescents of parents with no mental disorder (low-risk), had higher levels of daytime salivary cortisol. The present study re-examined the cortisol increase after awakening and basal cortisol levels in a larger sample, and tested the hypothesis that high-risk offspring are more reactive to psychosocial stress than low-risk offspring. Saliva samples were collected from 58 adolescents, 29 high-risk (14 male/15 female, 16.8 years) and 29 (14 male/15 female, 16.6 years) low-risk, in their natural environment during at least two days. Twenty-five high-risk (13 male/12 female) and 25 low-risk (13 male/12 female) youth completed a child adaptation (15 years) or the standard version of the "Trier Social Stress Test". Consistent with our previous finding, high-risk offspring had higher daytime levels of cortisol in their natural environment than low-risk offspring, and the difference was unrelated to clinical symptoms or other known confounds. Irrespective of risk status, female participants had higher daytime levels of cortisol than male participants. In contrast, there were no group differences in the cortisol response to the laboratory psychosocial stressor. The offspring of parents with BD show evidence of increased daytime basal HPA functioning with normal reactivity to psychosocial stress.