Organisation/Company: CNRS
Department: Institut Fresnel
Research Field: Engineering, Computer Science, Mathematics
Researcher Profile: Recognised Researcher (R2)
Country: France
Application Deadline: 5 Dec 2024 - 23:59 (UTC)
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 35
Offer Starting Date: 6 Jan 2025
Is the job funded through the EU Research Framework Programme? Not funded by a EU programme
Is the Job related to staff position within a Research Infrastructure? No
Offer Description It has been shown that the patterns and color of dried blood droplets are characteristic of a number of physiological and chemical blood parameters. For example, cholesterol levels (HDL or LDL) strongly influence the cracking patterns of dried blood droplets.
The recruitment is part of the ANR BloodDrop project, in collaboration with Institut Fresnel (Marseille), C2VN (Marseille), and IUSTI (Marseille). One of the aims of this project is to study these drying patterns in greater detail, and to establish predictions of various physiological and chemical parameters of blood based on the reading of images of dried droplets. The main parameters studied will be: cholesterol levels (HDL, LDL), anemia, and malaria. A database of blood samples is being set up at C2VN: precise measurements of physiological and chemical parameters are recorded in addition to the image of the dried droplet (under controlled temperature and lighting conditions).
Developments in image processing (texture analysis, pattern recognition, etc.) and learning (supervised classification, SVM, random forest, neural networks, etc.) will be required to match dried blood drop patterns to physiological or chemical blood parameters. Preliminary results analyzing the repetition frequencies of cracks observable in images of dried blood droplets have shown a good ability to predict HDL and LDL measurements. These results will need to be consolidated and improved during the postdoctoral contract. Other methods will need to be investigated for the prediction of other parameters (malaria or anemia), and a fine analysis of the color and its calibration will probably prove relevant.
The post-doctorate will take place at the Institut Fresnel in Marseille and will be supervised by Mouloud Adel (University Professor) and Julien Wojak (Research Engineer). Close collaboration with the project partners, C2VN and IUSTI, will be necessary to validate the developments made.
Required Skills Image processing
Machine learning
Python and machine learning libraries
Good interpersonal and communication skills
#J-18808-Ljbffr