Article

Cellpose-SAM: superhuman generalization for cellular segmentation

2025-05-01

Abstract excerpt

Modern algorithms for biological segmentation can match inter-human agreement in annotation quality. This however is not a performance bound: a hypothetical human-consensus segmentation could reduce error rates in half. To obtain a model that generalizes better we adapted the pretrained transformer backbone of a foundation model (SAM) to the Cellpose framework. The resulting Cellpose-SAM model substantially outper...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8f9eceaa-3544-5847-910a-2da61caa66f2
DOI: 10.1101/2025.04.28.651001

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Cellpose-SAM: superhuman generalization for cellular segmentationDOI 10.1101/2025.04.28.651001Read

Cellpose 2.0: how to train your own modelSemantic proximity Read

CellSAM: A Foundation Model for Cell SegmentationSemantic proximity Read

A Decade of Deep Learning-based Biomedical Image SegmentationSemantic proximity Read

OrganSegBench: A Comprehensive Multi-Organ Benchmark for Segmentation Foundation Models with a Practical Synergy Pathway to Clinical ApplicationSemantic proximity Read

OrganSegBench: Bridging the Translational Gap for Medical Segmentation Foundation Models Through Principled Model SynergySemantic proximity Read

OrganoLabeling: Quick and accurate annotation tool for organoid imagesSemantic proximity Read

Penumbria: Advanced 3D cell segmentation for biomedical imagingSemantic proximity Read

Segmenting functional tissue units across human organs using community-driven development of generalizable machine learning algorithmsSemantic proximity Read

UltimateSynth: MRI Physics for Pan-Contrast AISemantic proximity Read

Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learningSemantic proximity Read

Unifying the Electron Microscopy Multiverse through a Large-scale Foundation ModelSemantic proximity Read

Foundation versus Domain-Specific Models for Left Ventricular Segmentation on Cardiac UltrasoundSemantic proximity Read