Master Thesis - Machine Learning (Planning)

RaySearch develops innovative software solutions to improve cancer care. About 1000 clinics in more than 40 countries use RaySearch software to improve treatments and quality of life for patients. RaySearch was founded in 2000 and is listed on Nasdaq Stockholm. The headquarters is located in Stockholm, with subsidiaries in the US, Europe, Asia and Australia & New Zealand. Today we are more than 380 employees with a common vision of improving cancer care with innovative software. Our great staff is crucial for our success and we offer a fantastic working environment in modern offices, flexibility and good opportunities for development. We believe in equal opportunities, value diversity and work actively to prevent discrimination.

Are you in the end of your studies in computer science, machine learning or some other similar field and want to make an impact with technology in cancer treatment? RaySearch now offers master thesis positions within the machine learning team starting January 2025.

“Working at RaySearch allows me to deepen my interest in different machine learning techniques while also learning about the human body and having a real impact on people’s lives."

Frida S, Machine Learning Engineer

We offer the following Master Thesis project:

Developing a General Dose Prediction Model for Radiotherapy

In radiotherapy, machine learning models that predict optimal dose distributions are a crucial part of automating the clinical workflow. Current methods often rely on a 'one clinical protocol - one model' approach where a deep learning model predicts dose distributions only for one clinical protocol. This approach has proven to be limited in scalability and adaptability. This project aims to improve this process by developing a general dose prediction model capable of handling multiple protocols and even unseen protocols.

Project Objectives

The main goal of this project is to design and implement a deep learning model that can:

1. Predict dose distributions for multiple radiotherapy protocols
2. Adapt to variations in protocols across different clinics
3. Potentially predict doses for unseen protocols

Your role

As a master's student, you will develop a computer vision, deep learning model for multi-protocol dose prediction, evaluate the model's performance across various tumor sites and treatment protocols, validate the effectiveness and statistical significance of the model's predictions and explore the model's adaptability to unseen protocols.

This project is fundamentally a computer vision problem, specifically involving image-to-image translation. You will be working with 3D medical imaging data and applying advanced computer vision techniques to predict dose distributions. Experience in computer vision is a significant plus for this project.

Impact

This project has the potential to:

• Significantly reduce the number of models that need to be maintained
• Improve the scalability of dose prediction in radiotherapy
• Enable clinics to use AI-assisted planning for a wider range of protocols, including their own variations
• Streamline the treatment planning workflow, potentially leading to faster, more accurate, and more efficient treatment plans

Starting your career at RaySearch

Joining RaySearch as a Master Thesis Student, you will:

• … get a solid introduction to our company, products and ways of working.
• …become part of a rapidly growing, global Swedish company with head office and R&D department in Stockholm with a chance of full-time employment after graduation.
• … join 200 well-educated and dedicated engineers who enjoy knowledge sharing, problem-solving and working in teams.
• … work with cutting-edge technology for cancer treatment. Your daily work will contribute to improve cancer treatments for patients all over the world.

Our office

Our office is located in Hagastaden, Stockholm's Life Science Hub, with a modern and creative work environment. We offer a private gym, yoga, and social activities such as table tennis, foosball, and regular after-work events. Our bistro serves a fantastic lunch buffet, and every day we provide morning fika , as well as afternoon snacks. Our rooftop terrace offers a stunning view of Stockholm.

Who can apply?

Master students with a big interest in machine learning and computer vision. The start of the thesis project is planned for January 2025.

You are a master student, within machine learning, computer science, mathematics, statistics or similar. You have a great interest in software development and contributing to our mission. Programming skills, relevant hobby projects and summer/part time jobs within development and/or machine learning are highly valued. In order to be able to contribute to this project, you are a self-motivated and structured person.

Qualifications:

• Knowledge in Python development
• Strong background in machine learning, particularly deep learning and computer vision
• Experience in machine learning, computer vision and technical report writing
• Ability to work with complex medical image data
• Hands-on experience with deep learning frameworks such as TensorFlow and/or PyTorch
• Interest in medical physics and radiotherapy

Application

Please apply to the position through the application form below. Selection and interviews will be ongoing. We do not accept applications by e-mail.