ACCURATE AND EFFICIENT MEDICAL I MAGE CLASSIFICATION

  • Application deadline: November 30th, 2018
  • Beginning of the internship: February 4th, 2019
  • Duration: 6 months (longer duration possible condition to an agreement with the University/School)
  • Financial support: according to the competencies and the motivation
  • Locations of the internships: Lyon, France

more details in the pdf file

Keywords:

Image Classification, Medical Image Analysis, Machine Learning (ML), Deep Learning (DL),
Generative Adversarial Networks (GAN), Multiple Instance Learning (MIL), Convolutional Neural Networks
(CNN), U-net, TensorFlow, Keras.

Project - Accurate and Efficient Medical Image Classification

A set of medical images currently used in clinical routine need to be classified efficiently and
effectively in a number of classes, well-known by the orthodontists and dentists. The method needs
to be fast and effective. The study of traditional and deep learning technologies is envisaged, with
the strong constraint that the doctor ill need to use a simple (normal desktop or laptop to do it).
The accuracy of the classification will be measured and we are expecting a very high indicator,
enabling us to directly go to clinical use at the end of the project.

Context of the internship:

KITVIEW develops innovative solutions based on image analysis (medical and natural) to
continuously improving the ergonomics of its software, offering advanced features to its customers
and partners, as well as targeting new markets in France and abroad.


Competencies (selection) requested to reinforce our R&D projects:

- Image Classification, Pattern recognition, Machine Learning (SVM, Random Forest ...), Deep
Learning (CNN, U-net, GAN, MIL - Libraries: TensorFlow);
- Image and (in particular) Medical Image Analysis;
- Rapid prototyping of ergonomic, modern software interfaces.

Applicant profile:

- University Master or Engineering School student (last year of study) with computer science, image
analysis and/or applied mathematics profile;
- Interest, curiosity, learning capability and creativity are qualities we do appreciate;
- Positive spirit, communication skills and ability to work in a team, if necessary;
- Autonomy, dynamism and motivation to advance his/her own part of the project;
- Excellent methodological and hands-on computer programming skills. Programming languages:
Python, C ++ ; libraries: TensorFlow, Keras, Open CV, CUDA;
- Facility of understanding and manipulating mathematical models.