AI Platform for Radiology (Internship)
In this role
The goal of this project is to develop an AI-based platform for the analysis of radiology images. This platform should be able to handle the different formats the images may have (chief among them is the DICOM format), as well as different resolutions and throughputs. Dimensionality of the images, whether 2D or 2D slices from a 3D stack, should also be integrated in the design. Then, analysis and machine learning tools should be made available through an interface. For example, feature selection algorithms, annotation tool, and classification models will be fully integrated. Finally, as it is destined to be used by radiologist, the platform should be easy to use, and the options offered should be self-explanatory. A use case that will be implemented is the classification of tumors at different stages and their segmentation in a given modality and for a given cancer type.
Challenges: The development of such a platform is challenging due to its generic nature. Implementing a single platform able to handle multimodal images (CTscans, MRI, Xrays) is complex. In addition, the variety of cases, patients and imaging systems make the image analysis and machine learning parts extremely challenging. Finally, these datasets suffer from an inconsistent ground truth, which leads to error in the learning phases and performance evaluation of the models.
Project applications: Computer-aided diagnosis, integration into hospital and pharma systems
What you will learn: You will be a junior data scientist and software engineer, developing your skills in machine learning as well as software engineering, implementing the complete lifecycle of an applied AI platform
Keywords: Machine learning, computer vision, software engineering, human-machine interface.
In this project, the goal is to:
- Develop a platform to enable and AI-based analysis of radiology images that is accurate, fast and easy to use.
What we offer
Join our team as intern and you will find a young, dynamic and culturally diverse working environment.
About your profile
- Required: machine learning, computer vision, deep learning, software development in Python
- Knowledge of UX development, Docker is a plus.
With 50+ year of history and over 1300 specialists, we offer a unique spectrum of experience, skills and technical innovations.
You want to leverage your educational background, apply your infinite curiosity and your out-of-the-box thinking.
Your initiative is a chance ! We're constantly looking for talented individuals. Check our latest job opportunities !