Seleziona la tua lingua

Thesis Project Form

Title (tentative): Preterm infants motion analysis

Thesis advisor(s): Casadio Maura, Matteo Moro, Francesca Odone (DIBRIS) E-mail:
Address: Via Opera Pia 13, 16145 Genova (ITALY) Phone: (+39) 010 33 52749
Description

Motivation and application domain
Preterm infants neurological evaluation includes two methods of analysis: traditional neurological examination based on the observation of involuntary movements and the one based on the observation of spontaneous motor behavior, often called General Movements (GM).
GM are able to give qualitative and quantitative information about the incidence of future neurological diseases. In this work, in particular, the focus is on the fidgety movements: small amplitude and moderate speed movements, with variable acceleration of neck, trunk, and limbs in all directions in the awake infant. There are many studies in the literature that analyze GM using expensive and obtrusive markers and accelerometers.
Here we want to use only RGB videos and computer vision techniques (for example Optical Flow could be very powerful) and try to characterize movements of infants with normal and abnormal motion patterns.
To this purpose we will set up an approach based on first automatically detecting hands and feet and then performing a dense motion analysis in these areas to extract quantitative information that could describe motion patterns.

General objectives and main activities
) Study and test available computer vision / deep learning approaches to markerless motion analysis;
2) State of the art analysis of optical flow approaches to human motion analysis;
3) Identification of new parameters that better describe infants' movements (focus on hands’ fine motion), based on optical flow computed in the hands area;
4) Use the parameters to characterize normal and abnormal motion patterns and highlight differences among the two classes and among different acquisition sessions;

1] Moro, M., Pastore, V. P., Tacchino, C., Durand, P., Blanchi, I., Moretti, P., ... & Casadio, M. (2022). A markerless pipeline to analyze spontaneous movements of preterm infants. Computer Methods and Programs in Biomedicine, 226, 107119.
[2] Sun D, Roth S, Black MJ. Secrets of optical flow estimation and their principles. In 2010 IEEE computer society conference on computer vision and pattern recognition 2010.
[3] Prechtl, H.F. Qualitative changes of spontaneous movements in fetus and preterm infant are a marker of neurological dysfunction, Early human development 1990.

Training Objectives (technical/analytical tools, experimental methodologies)
Acquire knowledge related to

- kinematics data analysis
- computer vision techniques as optical flow
- spontaneous movement in infants
- motor assessment in clinical environement


Place(s) where the thesis work will be carried out: Neurolab, MaLGa Center

Additional information

Maximum number of students: 1