%0 Journal Article
%A Hörst, Fabian
%A Rempe, Moritz
%A Becker, Helmut
%A Heine, Lukas
%A Keyl, Julius
%A Kleesiek, Jens
%T CellViT++: Energy-efficient and adaptive cell segmentation and classification using foundation models.
%J Computer methods and programs in biomedicine
%V 277
%@ 0169-2607
%C Amsterdam
%I Elsevier
%M DKFZ-2026-00196
%P 109206
%D 2026
%X Deep learning-based cell segmentation and classification methods in digital pathology are critical for diagnostics but are hampered by models that require extensive annotated datasets, are computationally expensive, and lack adaptability to new cell types. This creates a significant bottleneck in research and clinical workflows. This study introduces CellViT++, a data-efficient and lightweight framework for generalized cell segmentation that allows for rapid adaptation to novel cell taxonomies with minimal data.CellViT++ leverages a Vision Transformer with a frozen pretrained foundation model for segmentation. It simultaneously extracts deep cell embeddings from the transformer tokens during the forward pass at no extra computational cost. To adapt to new cell types, only a lightweight classifier is trained on these embeddings, bypassing the need to retrain the segmentation model. We also demonstrate an automated workflow to generate training data from registered H</td><td width="150">
%X E and immunofluorescence (IF) slides. The framework was validated on seven public datasets.The framework achieves remarkable zero-shot segmentation results and data efficiency. On the CoNSeP dataset for colon cancer, we achieved superior results with only 10
%K Artificial intelligence (Other)
%K Cells (Other)
%K Digital pathology (Other)
%K Foundation models (Other)
%K Segmentation (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:41576779
%R 10.1016/j.cmpb.2025.109206
%U https://inrepo02.dkfz.de/record/308663