All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning

TL;DR

This paper introduces all-in-SAM, a pipeline that leverages the Segment Anything Model for biomedical nuclei segmentation by generating pixel-level annotations from weak prompts and finetuning, eliminating the need for manual prompts during inference.

Contribution

The paper presents a novel workflow that uses SAM for annotation and finetuning, outperforming state-of-the-art methods with weak annotations in biomedical segmentation.

Findings

Outperforms SOTA in nuclei segmentation on Monuseg dataset.

Weak and few annotations enable competitive performance after finetuning.

Eliminates manual prompts during inference for SAM-based segmentation.

Abstract

The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various segmentation tasks. However, the current pipeline requires manual prompts during the inference stage, which is still resource intensive for biomedical image segmentation. In this paper, instead of using prompts during the inference stage, we introduce a pipeline that utilizes the SAM, called all-in-SAM, through the entire AI development workflow (from annotation generation to model finetuning) without requiring manual prompts during the inference stage. Specifically, SAM is first employed to generate pixel-level annotations from weak prompts (e.g., points, bounding box). Then, the pixel-level annotations are used to finetune the SAM segmentation model rather than training from scratch. Our experimental results reveal two key findings: 1) the proposed pipeline surpasses the state-of-the-art (SOTA) methods in a nuclei segmentation task on the public Monuseg dataset, and 2) the utilization of weak and few annotations for SAM finetuning achieves competitive performance compared to using strong pixel-wise annotated data.