Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
BP: Fachverband Biologische Physik
BP 33: Bioimaging
BP 33.5: Vortrag
Donnerstag, 12. März 2026, 16:15–16:30, BAR/0205
Image segmentation of treated and untreated tumor spheroids by fully convolutional networks — Matthias Streller1, Soňa Michlíková2, Katharina Lönnecke1, Leoni A. Kunz-Schughart2, Anja Voss-Böhme1, and •Steffen Lange1,2 — 1HTW Dresden — 2OncoRay, TU Dresden, HZDR, Germany
Multicellular 3D tumor spheroids (MCTS) are advanced preclinical cell culture systems for assessing the impact of combinatorial radio(chemo)therapy as they exhibit therapeutically relevant in vivo-like characteristics. State-of-the-art assays quantify long-term curative endpoints based on collected brightfield image time series from large treated spheroid populations, which requires laborious spheroid segmentation of up to 100,000 images per treatment arm. While several image analysis algorithms are available for spheroid segmentation, they all focus on compact MCTS with a clearly distinguishable outer rim throughout growth and often fail for the common case of treated MCTS, which may partly be detached and destroyed and are usually obscured by dead cell debris. To address these issues, we successfully train 2 fully convolutional networks, UNet and HRNet, and optimize their hyperparameters to develop an automatic segmentation for both untreated and treated MCTS[1]. We extensively test the automatic segmentation on larger, independent datasets and observe high accuracy for most images with Jaccard indices around 90%, with deviations consistent to inter-observer variability. We also successfully test against previously published datasets and spheroid segmentations.
[1] Streller et.al, GigaScience 2025, doi.org/10.1093/gigascience/giaf027
Keywords: tumor spheroids; image segmentation; deep learning; 3D cancer models; high-content screening