Automatic Segmentation of Facial Regions of Interest and Stress Detection Using Machine Learning.

Stress is a factor that affects many people today and is responsible for many of the causes of poor quality of life. For this reason, it is necessary to be able to determine whether a person is stressed or not. Therefore, it is necessary to develop tools that are non-invasive, innocuous, and easy to use. This paper describes a methodology for classifying stress in humans by automatically detecting facial regions of interest in thermal images using machine learning during a short Trier Social Stress Test. Five regions of interest, namely the nose, right cheek, left cheek, forehead, and chin, are automatically detected. The temperature of each of these regions is then extracted and used as input to a classifier, specifically a Support Vector Machine, which outputs three states: baseline, stressed, and relaxed. The proposal was developed and tested on thermal images of 25 participants who were subjected to a stress-inducing protocol followed by relaxation techniques. After testing the developed methodology, an accuracy of 95.4% and an error rate of 4.5% were obtained. The methodology proposed in this study allows the automatic classification of a person's stress state based on a thermal image of the face. This represents an innovative tool applicable to specialists. Furthermore, due to its robustness, it is also suitable for online applications.

Cell Enumeration of Leptospira by Flow Cytometry.

Rapid and reliable enumeration of Leptospira spp., the causative agent of leptospirosis, represents a technical challenge because leptospires are thin, highly motile, and slow-growing bacteria. The current gold standard for cell enumeration is the use of a Petroff-Hausser counting chamber and a dark-field microscope, but this method remains time-consuming and lacks reproducibility. New alternative techniques are then of great interest. Here we describe the protocol for counting leptospires by flow cytometry. This method is rapid, reproducible, sensitive, and hence suitable to become a new standard to enumerate Leptospira spp.

Use of flow cytometry for rapid and accurate enumeration of live pathogenic Leptospira strains.

Enumeration of Leptospira, the causative agent of leptospirosis, is arduous mainly because of its slow growth rate. Rapid and reliable tools for numbering leptospires are still lacking. The current standard for Leptospira cultures is the count on Petroff-Hausser chamber under dark-field microscopy, but this method remains time-consuming, requires well-trained operators and lacks reproducibility. Here we present the development of a flow-cytometry technique for counting leptospires. We showed that upon addition of fluorescent dyes, necessary to discriminate the bacterial population from debris, several live Leptospira strains could be enumerated at different physiologic states. Flow cytometry titers were highly correlated to counts with Petroff-Hausser chambers (R2>0.99). Advantages of flow cytometry lie in its rapidity, its reproducibility significantly higher than Petroff-Hausser method and its wide linearity range, from 104 to 108leptospires/ml. Therefore, flow cytometry is a fast, reproducible and sensitive tool representing a promising technology to replace current enumeration techniques of Leptospira in culture. We were also able to enumerate Leptospira in artificially infected urine and blood with a sensitivity limit of 105leptospires/ml and 106leptospires/ml, respectively, demonstrating the feasibility to use flow cytometry as first-line tool for diagnosis or bacterial dissemination studies.