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.

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.
| WP | Topic | Lead |
|---|---|---|
| 1 | Data handling, normalisation, harmonisation and quality control | all |
| 2 | Zero-shot / promptable segmentation benchmark (MedSAM, SAM-Med3D, FastSAM3D) | S1 |
| 3 | Clinical survival model (Cox, random survival forest, calibration) | S2 |
| 4 | Radiomics (PyRadiomics), feature selection and stability under automated contours | S3 |
| 5 | Foundation-model benchmarking (CT-CLIP, DINOv2, MedicalNet) | S4 |
| 6 | Correlation analysis, phenotyping and survival curves | all |
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.
| Date | Session |
|---|---|
| 17 Apr 2026 | |
| 15 May 2026 | |
| 12 Jun 2026 | |
| 10 Jul 2026 |