arXiv 2308.057852023-08-10eess.IVcs.CV

利用零样本分割一切模型将弱标注提升为像素级标注以实现分子赋能学习

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

Data Science Institute, Vanderbilt University（范德堡大学数据科学研究所）；Department of Computer Science, Vanderbilt University（范德堡大学计算机科学系）；NVIDIA Corporation（英伟达公司）；Department of Electrical and Computer Engineering, Vanderbilt University Medical Center（范德堡大学医学中心电气与计算机工程系）；Department of Pathology, Microbiology and Immunology, Vanderbilt University Medical Center（范德堡大学医学中心病理学、微生物学与免疫学系）

Xueyuan Li, Ruining Deng, Yucheng Tang, Shunxing Bao, Haichun Yang, Yuankai Huo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出SAM-L方法，利用零样本分割一切模型将弱框标注自动转换为像素级标注，用于分子赋能学习，在保持分割性能的同时显著降低非专业标注者的标注负担。

摘要：

在高分辨率千兆像素全切片成像（WSI）中精确识别多个细胞类别对于多种临床场景至关重要。构建用于此目的的人工智能模型通常需要像素级标注，而这类标注往往难以大规模扩展，且必须由熟练的领域专家（如病理学家）完成。然而，这些标注容易出错，尤其是在仅凭视觉检查区分复杂细胞类型（如足细胞和系膜细胞）时。有趣的是，最近一项研究表明，非专业标注者在借助额外的免疫荧光（IF）图像作为参考（称为分子赋能学习）时，有时在标注上能够优于领域专家。尽管如此，在标注过程中仍然需要耗费大量资源的人工勾画。在本文中，我们探索了通过在零样本学习方法中对弱框标注使用最近的分割一切模型（SAM）来绕过像素级勾画的可能性。具体而言，我们利用SAM从框标注生成像素级标注的能力，并使用这些由SAM生成的标签来训练分割模型。我们的研究结果表明，所提出的SAM辅助分子赋能学习（SAM-L）可以通过仅要求弱框标注来减少非专业标注者的标注工作量，同时不损害标注准确性或基于深度学习的分割性能。该研究代表了在仅依赖非专家标注者的情况下使病理图像分割训练标注过程民主化方面的重要进展。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。