Postdoc: AI CT Reconstruction for High-Throughput Specimens

DTU Wind; Kongens Lyngby; On-site; DKK 420,000 - 540,000; Full time

Job summary

DTU Compute in Denmark invites applications for a postdoc to develop advanced image reconstruction algorithms for a robotic CT system that digitizes natural history collections. You will work on fast reconstruction from sparse-view/noisy data and validate methods on simulated and real CT data.

Join an interdisciplinary team across DTU Compute, DTU Physics, Copenhagen University, and the Natural History Museum to push computational imaging, AI, and open-source software, publish your work, and

Qualifications

• A PhD degree in computational imaging, ideally X-ray CT reconstruction.
• Experience developing deep learning and/or regularization-based image reconstruction methods.
• Experience with scientific Python programming.
• Experience handling both simulations and large real data.
• Strong spoken and written communication skills in English.
• Strong collaboration skills as well as being self-driven.

Responsibilities

• Develop new mathematical methods for fast reconstruction of CT data from fast (e.g. sparse-view and/or high-noise) data.
• Develop and validate numerical implementations on simulated and real CT data.
• Explore and compare supervised and self-supervised machine learning/AI-based reconstruction methods with optimization/regularization-based as well as filtered back-projection reconstruction methods.
• Contribute to the development and validation of practical computational reconstruction pipelines for a new fast robotic computed tomography system in the DTU 3D Imaging Centre in collaboration with scientific software developers.
• Contribute to and be part of open-source scientific software communities around the Core Imaging Library and qim3D packages.
• Publish scientific articles within computational methods, data, and applications in collaboration with colleagues in physics and natural history.

Skills

Computational imaging

Deep learning

Python programming

English communication

Education

PhD in computational imaging

Tools

Python

PyTorch

Job description

DTU Compute in Denmark invites applications for a postdoc to develop advanced image reconstruction algorithms for a robotic CT system that digitizes natural history collections. You will work on fast reconstruction from sparse-view/noisy data and validate methods on simulated and real CT data.

Join an interdisciplinary team across DTU Compute, DTU Physics, Copenhagen University, and the Natural History Museum to push computational imaging, AI, and open-source software, publish your work, and