Revisiting foundation models for cell instance segmentation

Anwai Archit, Constantin Pape

Keywords: vision foundation models, segment anything, microscopy, instance segmentation

TL;DR: Automatic Cell Instance Segmentation using Vision Foundation Models

Abstract: Cell segmentation is a fundamental task in microscopy image analysis. Several foundation models for cell segmentation have been introduced, virtually all of them are extensions of Segment Anything Model (SAM), improving it for microscopy data. Recently, SAM2 and SAM3 have been published, further improving and extending the capabilities of general-purpose segmentation foundation models. Here, we comprehensively evaluate foundation models for cell segmentation (CellPose-SAM, CellSAM, $\mu$SAM) and for general-purpose segmentation (SAM, SAM2, SAM3) on a diverse set of (light) microscopy datasets, for tasks including cell, nucleus and organoid segmentation. Furthermore, we introduce a new segmentation strategy called automatic prompt generation (APG) that can be used to further improve the segmentation quality of SAM-based microscopy foundation models. APG achieves state-of-the-art results on several of the benchmarked datasets, providing practical benefits for microscopy image analysis. Moreover, our work provides important lessons for adaptation strategies of SAM-style models to microscopy and provides a strategy for creating even more powerful microscopy foundation models.

Primary Subject Area: Segmentation

Secondary Subject Area: Foundation Models

Registration Requirement: Yes

Reproducibility: https://github.com/computational-cell-analytics/micro-sam

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 324