Postdoc: AI Vision for 3D Segmentation & Quantification

DTU - Technical University of Denmark; Kongens Lyngby; On-site; DKK 448,000 - 523,000; Full time

Job summary

DTU Compute seeks a postdoctoral researcher to advance segmentation and quantitative analysis of micro‑CT data for natural heritage specimens. You will design scalable methods, validate automatic and human‑in‑the‑loop segmentation, and contribute to open‑source tools within the Core Imaging Library and qim3D, collaborating with physics and biology groups.

The role focuses on 3D volumetric imaging, methodological development, and dissemination through publications and code in an international DTU

Qualifications

• PhD in computer vision, ideally segmentation and/or quantification of micro‑CT data.
• Experience developing deep learning‑based image analysis 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 segmentation methods for large‑scale analysis of micro‑CT data.
• Develop and validate methods for efficient human‑in‑the‑loop segmentation of CT images.
• Explore self‑supervised foundation models for segmentation with limited labels.
• Establish reference benchmark datasets for natural heritage.
• Collaborate with domain experts in natural heritage and evolutionary biology.
• Contribute to and be part of open‑source scientific software communities around the Core Imaging Library and qim3D packages.
• Publish scientific articles within computer vision, data, and applications in collaboration with colleagues in physics and natural history.

Skills

Deep learning

Python programming

English communication

Collaboration skills

Education

PhD in computer vision

Tools

Python

Job description

DTU Compute seeks a postdoctoral researcher to advance segmentation and quantitative analysis of micro‑CT data for natural heritage specimens. You will design scalable methods, validate automatic and human‑in‑the‑loop segmentation, and contribute to open‑source tools within the Core Imaging Library and qim3D, collaborating with physics and biology groups.

The role focuses on 3D volumetric imaging, methodological development, and dissemination through publications and code in an international DTU