Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning

TL;DR

This paper introduces a zero-shot segmentation approach using the Segment Anything Model (SAM) to convert weak box annotations into pixel-level labels, reducing expert effort in pathological image annotation without sacrificing accuracy.

Contribution

It proposes a novel SAM-assisted molecular-empowered learning method that enables non-expert annotators to generate high-quality segmentation labels from weak annotations, bypassing manual delineation.

Findings

SAM can produce accurate pixel-level labels from box annotations.

The method reduces annotation effort without loss of segmentation performance.

It democratizes pathological image annotation by enabling non-experts to contribute effectively.

Abstract

Precise identification of multiple cell classes in high-resolution Giga-pixel whole slide imaging (WSI) is critical for various clinical scenarios. Building an AI model for this purpose typically requires pixel-level annotations, which are often unscalable and must be done by skilled domain experts (e.g., pathologists). However, these annotations can be prone to errors, especially when distinguishing between intricate cell types (e.g., podocytes and mesangial cells) using only visual inspection. Interestingly, a recent study showed that lay annotators, when using extra immunofluorescence (IF) images for reference (referred to as molecular-empowered learning), can sometimes outperform domain experts in labeling. Despite this, the resource-intensive task of manual delineation remains a necessity during the annotation process. In this paper, we explore the potential of bypassing pixel-level delineation by employing the recent segment anything model (SAM) on weak box annotation in a zero-shot learning approach. Specifically, we harness SAM's ability to produce pixel-level annotations from box annotations and utilize these SAM-generated labels to train a segmentation model. Our findings show that the proposed SAM-assisted molecular-empowered learning (SAM-L) can diminish the labeling efforts for lay annotators by only requiring weak box annotations. This is achieved without compromising annotation accuracy or the performance of the deep learning-based segmentation. This research represents a significant advancement in democratizing the annotation process for training pathological image segmentation, relying solely on non-expert annotators.