What does this research mean for the field?

The NucVerse3D deep-learning framework enables accurate, modality-agnostic 3D nuclear instance segmentation and reveals that the tightly regulated scaling relationship between nuclear DNA content and volume is progressively disrupted in hepatocellular carcinoma. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to develop NucVerse3D, a framework for accurate 3D nuclear instance segmentation across diverse microscopy modalities.

May 18, 2026Scientific ReportsOpen Access

NucVerse3D: generalizable 3D nuclear instance segmentation across heterogeneous microscopy modalities

View Full Paper

Ask AI

Bookmark

Authors

JVJorge Vergara CPCristian Pérez-Gallardo RVRicardo Velasco

Discussion

Member takes

Overview

Randomized trial demonstrates effective 3D nuclear segmentation in various tissues, suggesting new biomarker applications.

Key Points

This research aims to develop NucVerse3D, a framework for accurate 3D nuclear instance segmentation across diverse microscopy modalities.
Developed a residual attention 3D U-Net architecture for segmentation.
Trained on pooled data from seven volumetric datasets with over forty thousand annotated nuclei.
Utilized preprocessing and isotropic scale normalization to enhance performance.
NucVerse3D achieved high precision and competitive recall with strong F1-scores and average precision across imaging conditions.
The generalized model outperformed dataset-specific models in segmentation tasks.
Demonstrated a Nuclear Decoupling Score (NDS) revealing increased nuclear instability in tumor regions, suggesting NDS as a potential biomarker.

Cite This Study

Vergara et al. (2026) studied this question.

synapsesocial.com/papers/6a0aabf55ba8ef6d83b6f92e https://doi.org/10.1038/s41598-026-51994-x

View Full Paper

Ask AI

Bookmark

May 18, 2026Scientific ReportsOpen Access

NucVerse3D: generalizable 3D nuclear instance segmentation across heterogeneous microscopy modalities

View Full Paper

Ask AI

Bookmark

Authors

JVJorge Vergara CPCristian Pérez-Gallardo RVRicardo Velasco

Discussion

Member takes

Overview

Randomized trial demonstrates effective 3D nuclear segmentation in various tissues, suggesting new biomarker applications.

Key Points

This research aims to develop NucVerse3D, a framework for accurate 3D nuclear instance segmentation across diverse microscopy modalities.
Developed a residual attention 3D U-Net architecture for segmentation.
Trained on pooled data from seven volumetric datasets with over forty thousand annotated nuclei.
Utilized preprocessing and isotropic scale normalization to enhance performance.
NucVerse3D achieved high precision and competitive recall with strong F1-scores and average precision across imaging conditions.
The generalized model outperformed dataset-specific models in segmentation tasks.
Demonstrated a Nuclear Decoupling Score (NDS) revealing increased nuclear instability in tumor regions, suggesting NDS as a potential biomarker.

Cite This Study

Vergara et al. (2026) studied this question.

synapsesocial.com/papers/6a0aabf55ba8ef6d83b6f92e https://doi.org/10.1038/s41598-026-51994-x

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark