Trainee Project
Characterization of the SpectroLive clinical database and development of artificial intelligence methods for the classification of healthy states of human skin (phototypes, apparent skin age in particular).
2023/02/13 - 2023/08/13
As part of the SpectroLive clinical trial (carried out at CHR Metz-Thionville), optical spectra were acquired on 140
patients. The experimental data were grouped together in a database made up of more than 2,000 optical
spectra, each corresponding to a skin site (healthy, cancerous or precancerous). The objective of the proposed
internship will be to use the database to characterize it, make the necessary corrections and develop methods for
classifying biological parameters characteristic of healthy skin (apparent skin age, phototype).

Internship tasks
The intern will have to characterize the database statistically and make the necessary adjustments to it when
identifying malfunctions. The trainee will have to carry out a state of the art in order to define the classification
methods (supervised or not) best suited to the database and the objectives set (SVM, k-NN, etc.). He/she will have
to implement the method(s) selected to characterize the relationship between one or more optical parameters
(e.g. intensity on a given spectral band) and biological parameters: apparent skin age, civil age and phototype,
The results obtained may be valued in the context of a scientific publication.
database, classification, machine learning, optical spectroscopy, human skin
Duration: 02/13/2023 - 08/13/2023
Employer: University of Lorraine
Location: CRAN, Faculty of Medicine of Nancy
Remuneration: no funding available
Expected profile: database specialist, Python, SQL, Matlab programming skills, use of Gitlab, autonomy, sense of
responsibility, strength of proposal
Biology, Signals and Systems in Cancer and Neuroscience