Lab · Informatics / Mathematics & Natural Sciences · SS 2026

Computational Medical Imaging (Lab)

The Computational Imaging Research (CoMI) Lab at the University of Bonn is a project-based lab where students carry out a semester-long research project in computational medical imaging, implementing and evaluating state-of-the-art algorithms on real medical data.

Image created with assistance from DALL·E for the CoMI Lab at the University of Bonn.

About this course

The course description, objectives, audience, prerequisites, materials and evaluation are the same every semester and live on the course page.

🗓 Project (Summer 2026)

Segmentation-Aware Benchmarking of Clinical, Radiomic, Deep-Learning and Foundation-Model Biomarkers for NSCLC Survival Prediction on Pretreatment CT

Can AI support reproducible imaging-biomarker discovery for non-small cell lung cancer (NSCLC)? Students benchmark zero-shot and promptable tumour-segmentation models, clinical risk models, handcrafted radiomics and pretrained CT foundation-model representations for prognosis and phenotype discovery. The central question: do prognostic conclusions change when the tumour contour comes from an automated model instead of an expert?

  • Dataset: TCIA NSCLC-Radiomics / LUNG1 — pretreatment thoracic CT of 422 patients with manual 3D gross-tumour-volume contours and survival data (doi:10.7937/K9/TCIA.2015.PF0M9REI), the cohort of the landmark radiomics study by Aerts et al.
  • Team: 4 students; all share data handling and phenotyping, each leads one experimental work package.
  • Software: all experiments run on the lab’s open CoMI library for consistent pre-processing, metrics and figures.
WPTopicLead
1Data handling, normalisation, harmonisation and quality controlall
2Zero-shot / promptable segmentation benchmark (MedSAM, SAM-Med3D, FastSAM3D)S1
3Clinical survival model (Cox, random survival forest, calibration)S2
4Radiomics (PyRadiomics), feature selection and stability under automated contoursS3
5Foundation-model benchmarking (CT-CLIP, DINOv2, MedicalNet)S4
6Correlation analysis, phenotyping and survival curvesall

Schedule

Lab meetings every four weeks on Fridays, 15:00–17:00, in room 3.110 at B-IT (BASIS no. 614022300). Between meetings, groups work on their projects independently.

DateSession
17 Apr 2026
15 May 2026
12 Jun 2026
10 Jul 2026

Other semesters