Machine Learning Based Treatment Prediction New machine and deep learning methods for treatment prediction in breast cancer – PhD student

We offer an exciting PhD student position at the Universitat de Barcelona (as part of the PhD Program in Mathematics and Computer Science), to develop new algorithms and tools for predictive modelling of breast cancer treatment. During the three years of this PhD, the selected candidate will work on developing new deep learning / machine learning based methods aimed at Neoadjuvant treatment prediction in breast cancer. Namely, using MRI images and non-imaging data to predict response treatment. Moreover, the student will participate in the technical evaluations of the prediction tool, in particular that of robustness and fairness, and will leverage its federated analytics capabilities to perform remote privacy-preserving evaluations in all clinical sites. The student will work on a large database collected from clinical centres across the world. We are thus seeking candidates with a Msc degree (or equivalent) in an area pertinent to the project, such as applied mathematics, statistics, machine learning, data science, software engineering, computer vision or any other related field. The ideal candidate should have experience working with radiomics, medical imaging, programming using C++/Python, Putorch, Tensorflow, Keras. We are looking for highly motivated candidates with strong interests in mathematical and computational applications in biomedicine. Candidates must have excellent teamwork and communication skills and be enthusiastic about their research. Due to multiple collaborations within the RadioVal project with consortium partners across Europe and Africa & South America, advanced oral and writing English knowledge are required. Female applicants are explicitly encouraged to apply. The Project: RadioVal is the first multi-centre, multi-continental and multi-faceted clinical validation of radiomics-driven estimation of NAC response in breast cancer. The project builds on the repositories, tools and results of five EU-funded projects from the AI for Health Imaging (AI4HI) Network, including a large multi-centre cancer imaging dataset on NAC treatment in breast cancer. Additionally, this new EU-funded project will develop a comprehensive and standardised methodological framework for multi-faceted radiomics evaluation based on the FUTURE-AI Guidelines, to assess Fairness, Universality, Traceability, Usability, Robustness and Explainability. Furthermore, the project will introduce new tools to enable transparent and continuous evaluation and monitoring of the radiomics tools over time. The Institution: 2 The University of Barcelona (UB), founded in 1450, is one of the oldest universities in Spain. It comprises a student body of 84,370 and 4,548 research staff members. With 73 undergraduate programs, 273 graduate programs and 48 doctorate programs, UB is the largest university in Barcelona and Catalonia. The UB is ranked the first Spanish university according to several rankings (QS World University Rankings 2018, ARWU/Shanghai Ranking 2018). It is particularly interested in fostering international relations and, for many years, has managed an average of 150 European projects per year. Since January 2010, Universitat de Barcelona is part of the prestigious League of European Universities Research (LERU). The candidate will join the Artificial Intelligence in Medicine Lab (www.bcn-aim.org), which is an integral part of the University of Barcelona’s Faculty of Mathematics and Computer Science. It is a young and dynamic research lab, highly active in international projects, and composed of 20 enthusiastic academics, researchers, students and research managers, with expertise in data science, machine/deep learning, biomedical informatics, biomedical ethics, and healthrelated applications.

Gross salary per year €24,500

How to apply; https://seu.ub.edu/ajutsPublic/showPublicacion/376409