NeXtMarker: Contrastive Learning for Marker-Level Interpretability in Single-Cell Multiplex Imaging

Simon Gutwein, Daria Lazic, Thomas Walter, Sabine Taschner-Mandl, Roxane Licandro
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 316:328-337, 2026.

Abstract

Understanding cell phenotypes and their spatial organization is crucial in multiplex imaging for spatial biology. Conventional analysis pipelines rely on extensive preprocessing, including background correction and segmentation, introducing biases and information loss. We present NeXtMarker, an interpretable deep learning framework for end-to-end single-cell analysis of multiplex images, eliminating the need for manual preprocessing or segmentation. NeXtMarker employs learned marker-specific normalization and interpretable feature extraction to generate biologically meaningful embeddings in a fully self-supervised manner. It directly processes raw images of cells while preserving spatial and morphological information. We demonstrate NeXtMarker’s ability to (i) resolve intercellular expression patterns and cell morphology, (ii) enable accurate cell phenotyping in a large neuroblastoma tumor dataset, and (iii) generalize to independent osteosarcoma images. NeXtMarker maintains high agreement with conventional pipelines while eliminating the need for preprocessing and segmentation and enhancing interpretability. By enabling unbiased, scalable singlecell analysis, NeXtMarker establishes a foundation for improved phenotyping in multiplex imaging. Code and pretrained models available at: [code_released_upon_acceptance].

Cite this Paper

BibTeX
@InProceedings{pmlr-v316-gutwein26a, title = {NeXtMarker: Contrastive Learning for Marker-Level Interpretability in Single-Cell Multiplex Imaging}, author = {Gutwein, Simon and Lazic, Daria and Walter, Thomas and Taschner-Mandl, Sabine and Licandro, Roxane}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {328--337}, year = {2026}, editor = {Studer, Linda and Ciompi, Francesco and Khalili, Nadieh and Faryna, Khrystyna and Faryna, Khrystyna and Yeong, Joe and Lau, Mai Chan and Chen, Hao and Liu, Ziyi and Brattoli, Biagio}, volume = {316}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v316/main/assets/gutwein26a/gutwein26a.pdf}, url = {https://proceedings.mlr.press/v316/gutwein26a.html}, abstract = {Understanding cell phenotypes and their spatial organization is crucial in multiplex imaging for spatial biology. Conventional analysis pipelines rely on extensive preprocessing, including background correction and segmentation, introducing biases and information loss. We present NeXtMarker, an interpretable deep learning framework for end-to-end single-cell analysis of multiplex images, eliminating the need for manual preprocessing or segmentation. NeXtMarker employs learned marker-specific normalization and interpretable feature extraction to generate biologically meaningful embeddings in a fully self-supervised manner. It directly processes raw images of cells while preserving spatial and morphological information. We demonstrate NeXtMarker’s ability to (i) resolve intercellular expression patterns and cell morphology, (ii) enable accurate cell phenotyping in a large neuroblastoma tumor dataset, and (iii) generalize to independent osteosarcoma images. NeXtMarker maintains high agreement with conventional pipelines while eliminating the need for preprocessing and segmentation and enhancing interpretability. By enabling unbiased, scalable singlecell analysis, NeXtMarker establishes a foundation for improved phenotyping in multiplex imaging. Code and pretrained models available at: [code_released_upon_acceptance].} }
Endnote
%0 Conference Paper %T NeXtMarker: Contrastive Learning for Marker-Level Interpretability in Single-Cell Multiplex Imaging %A Simon Gutwein %A Daria Lazic %A Thomas Walter %A Sabine Taschner-Mandl %A Roxane Licandro %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2026 %E Linda Studer %E Francesco Ciompi %E Nadieh Khalili %E Khrystyna Faryna %E Khrystyna Faryna %E Joe Yeong %E Mai Chan Lau %E Hao Chen %E Ziyi Liu %E Biagio Brattoli %F pmlr-v316-gutwein26a %I PMLR %P 328--337 %U https://proceedings.mlr.press/v316/gutwein26a.html %V 316 %X Understanding cell phenotypes and their spatial organization is crucial in multiplex imaging for spatial biology. Conventional analysis pipelines rely on extensive preprocessing, including background correction and segmentation, introducing biases and information loss. We present NeXtMarker, an interpretable deep learning framework for end-to-end single-cell analysis of multiplex images, eliminating the need for manual preprocessing or segmentation. NeXtMarker employs learned marker-specific normalization and interpretable feature extraction to generate biologically meaningful embeddings in a fully self-supervised manner. It directly processes raw images of cells while preserving spatial and morphological information. We demonstrate NeXtMarker’s ability to (i) resolve intercellular expression patterns and cell morphology, (ii) enable accurate cell phenotyping in a large neuroblastoma tumor dataset, and (iii) generalize to independent osteosarcoma images. NeXtMarker maintains high agreement with conventional pipelines while eliminating the need for preprocessing and segmentation and enhancing interpretability. By enabling unbiased, scalable singlecell analysis, NeXtMarker establishes a foundation for improved phenotyping in multiplex imaging. Code and pretrained models available at: [code_released_upon_acceptance].
APA
Gutwein, S., Lazic, D., Walter, T., Taschner-Mandl, S. & Licandro, R.. (2026). NeXtMarker: Contrastive Learning for Marker-Level Interpretability in Single-Cell Multiplex Imaging. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 316:328-337 Available from https://proceedings.mlr.press/v316/gutwein26a.html.

Related Material