Philips Healthcare is a world leader in medical imaging. Its products cover the full range of imaging modalities: X-Rays, MRI, Ultrasound, CT, etc. The company is internationally recognized for the excellence of its technology, developed within innovative research groups.
Philips Healthcare Medisys Research Lab is based in Suresnes (92) and is dedicated to medical image processing. The team, with about thirty researchers and engineers, is focused on delivering the most innovative solutions in the domain and is in close contact with famous universities and clinical sites in France and abroad.
Medical ultrasound is becoming today one of the most accessible diagnostic imaging modalities. A high image quality is the basis on which clinical interpretation can be made with sufficient confidence. However, medical ultrasound images suffer typically from speckle effect due to interference in the image formation.
In this internship, we propose to study deep learning approaches to perform ultrasound speckle reduction. We will explore several different methods including end-to-end learning and hybrid methods. We would also like to push the understanding and the interpretation of the network behavior through a deeper analysis of network structures and activation functions.
A first step consists of establishing an image base from existing tool of speckle synthesis. This allows us to attempt different existing methods on these synthetic data. The second step will consist in implementing and analyzing hybrid learning approaches to optimize de-speckling performance.
The programming language is Python in Tensorflow environment.
- Third year of engineer school / Master 2 Recherche, with specialty in machine learning, image processing or applied mathematics
- Solid knowledge of statistics, machine learning, deep learning, image processing
- Knowledge or experience on conventional denoising and filtering will highly appreciated
- Experience in Python and Matlab
- English speaking, reading and writing is mandatory
- Good communication skills and ability to work in a team
Duration: 6 months Preferred start date: from January 2020 or later
Localization: Suresnes (92)