Centroid-Aware Gaussian Prompt Learning with Erosion-Guided Accumulator for Robust Semantic Cell Segmentation

Nur Suriza Syazwany, Su Jung Kim, Ju-Hyeon Nam, Sang-Chul Lee
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 316:160-170, 2026.

Abstract

Accurately segmenting cell images remains challenging due to variations in cell size, shape, and overlapping structures. Existing approaches often struggle with densely packed and overlapping cell regions, leading to inconsistent performance. While recent methods, such as the Segment Anything Model (SAM), have shown promise, they rely heavily on manual prompting, which can be time-consuming and inconsistent for densely packed nuclei datasets. To address these limitations, we propose a novel centroid-guided Gaussian mapbased accumulator prompting approach for robust nuclei segmentation. Our method constructs Gaussian maps by accumulating centroids across multiple erosion iterations, capturing the frequency and spatial distribution of nuclei centroids. These maps serve as informative priors to guide the segmentation model, enhancing its ability to localize cell structures while maintaining adaptability to varying cell sizes. By integrating these Gaussian-based prompts into a transformer-based segmentation model, our approach enables refined predictions with improved spatial awareness. We validate our method on two challenging, densely packed datasets, DSB18 and ConSeP, demonstrating robust and superior segmentation performance over state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v316-syazwany26a, title = {Centroid-Aware Gaussian Prompt Learning with Erosion-Guided Accumulator for Robust Semantic Cell Segmentation}, author = {Syazwany, Nur Suriza and Kim, Su Jung and Nam, Ju-Hyeon and Lee, Sang-Chul}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {160--170}, 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/syazwany26a/syazwany26a.pdf}, url = {https://proceedings.mlr.press/v316/syazwany26a.html}, abstract = {Accurately segmenting cell images remains challenging due to variations in cell size, shape, and overlapping structures. Existing approaches often struggle with densely packed and overlapping cell regions, leading to inconsistent performance. While recent methods, such as the Segment Anything Model (SAM), have shown promise, they rely heavily on manual prompting, which can be time-consuming and inconsistent for densely packed nuclei datasets. To address these limitations, we propose a novel centroid-guided Gaussian mapbased accumulator prompting approach for robust nuclei segmentation. Our method constructs Gaussian maps by accumulating centroids across multiple erosion iterations, capturing the frequency and spatial distribution of nuclei centroids. These maps serve as informative priors to guide the segmentation model, enhancing its ability to localize cell structures while maintaining adaptability to varying cell sizes. By integrating these Gaussian-based prompts into a transformer-based segmentation model, our approach enables refined predictions with improved spatial awareness. We validate our method on two challenging, densely packed datasets, DSB18 and ConSeP, demonstrating robust and superior segmentation performance over state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Centroid-Aware Gaussian Prompt Learning with Erosion-Guided Accumulator for Robust Semantic Cell Segmentation %A Nur Suriza Syazwany %A Su Jung Kim %A Ju-Hyeon Nam %A Sang-Chul Lee %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-syazwany26a %I PMLR %P 160--170 %U https://proceedings.mlr.press/v316/syazwany26a.html %V 316 %X Accurately segmenting cell images remains challenging due to variations in cell size, shape, and overlapping structures. Existing approaches often struggle with densely packed and overlapping cell regions, leading to inconsistent performance. While recent methods, such as the Segment Anything Model (SAM), have shown promise, they rely heavily on manual prompting, which can be time-consuming and inconsistent for densely packed nuclei datasets. To address these limitations, we propose a novel centroid-guided Gaussian mapbased accumulator prompting approach for robust nuclei segmentation. Our method constructs Gaussian maps by accumulating centroids across multiple erosion iterations, capturing the frequency and spatial distribution of nuclei centroids. These maps serve as informative priors to guide the segmentation model, enhancing its ability to localize cell structures while maintaining adaptability to varying cell sizes. By integrating these Gaussian-based prompts into a transformer-based segmentation model, our approach enables refined predictions with improved spatial awareness. We validate our method on two challenging, densely packed datasets, DSB18 and ConSeP, demonstrating robust and superior segmentation performance over state-of-the-art methods.
APA
Syazwany, N.S., Kim, S.J., Nam, J. & Lee, S.. (2026). Centroid-Aware Gaussian Prompt Learning with Erosion-Guided Accumulator for Robust Semantic Cell Segmentation. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 316:160-170 Available from https://proceedings.mlr.press/v316/syazwany26a.html.

Related Material