Suppr超能文献

荧光模拟明场成像与苏木精-伊红染色成像的拓扑学比较

A Topological Comparison of the Fluorescence Imitating Brightfield Imaging and H&E Imaging.

作者信息

Xu Meiliong, Anderson Nate, Levenson Richard M, Prasanna Prateek, Chen Chao

机构信息

Department of Computer Science, Stony Brook University, New York, USA.

Department of Pathology and Laboratory Medicine, University of California, Davis, USA.

出版信息

Int Workshop Topol Graph Inf Imaging Inform (2024). 2025;15239:122-133. doi: 10.1007/978-3-031-73967-5_12. Epub 2024 Oct 11.

Abstract

Fluorescence Imitating Brightfield Imaging (FIBI) represents an innovative approach in microscopy, providing real-time, non-destructive imaging of tissue without the need for the preparation of thin sections mounted on glass slides. The non-destructive nature of the technology permits tissue preservation for downstream analysis, which makes FIBI a promising alternative to traditional hematoxylin and eosin (H&E) staining in histopathology. Previous research has shown that FIBI can identify morphological features with similar or, in some cases, higher quality compared with H&E images. To comprehensively quantify the advantages and limitations of FIBI in tissue visualization, we propose a novel framework for characterizing the topological difference of FIBI and H&E slide pairs. Experiments are performed on slide pairs of FIBI and H&E imaging of the same tissue area. The proposed approach shows that FIBI can make morphological structures, like vessels, more salient and holds great promise as a complementary technique to H&E, offering novel insights into tissue architecture and potentially improving histopathological diagnostic accuracy.

摘要

荧光模拟明场成像(FIBI)是显微镜技术中的一种创新方法,可对组织进行实时、无损成像,无需制备安装在载玻片上的薄切片。该技术的无损特性允许保留组织用于下游分析,这使得FIBI在组织病理学中成为传统苏木精和伊红(H&E)染色的一个有前景的替代方法。先前的研究表明,与H&E图像相比,FIBI能够识别出相似的形态特征,在某些情况下质量更高。为了全面量化FIBI在组织可视化中的优势和局限性,我们提出了一个用于表征FIBI和H&E玻片对拓扑差异的新框架。对同一组织区域的FIBI和H&E成像的玻片对进行了实验。所提出的方法表明,FIBI可以使血管等形态结构更加突出,作为H&E的补充技术具有很大的前景,为组织结构提供了新的见解,并有可能提高组织病理学诊断的准确性。

相似文献

1
A Topological Comparison of the Fluorescence Imitating Brightfield Imaging and H&E Imaging.荧光模拟明场成像与苏木精-伊红染色成像的拓扑学比较
Int Workshop Topol Graph Inf Imaging Inform (2024). 2025;15239:122-133. doi: 10.1007/978-3-031-73967-5_12. Epub 2024 Oct 11.
9
Current Landscape of Advanced Imaging Tools for Pathology Diagnostics.病理学诊断中高级成像工具的现状。
Mod Pathol. 2024 Apr;37(4):100443. doi: 10.1016/j.modpat.2024.100443. Epub 2024 Feb 3.

本文引用的文献

1
SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology.SI-MIL:驯服深度多实例学习以实现千兆像素组织病理学中的自解释性
Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2024 Jun;2024:11226-11237. doi: 10.1109/cvpr52733.2024.01067. Epub 2024 Sep 16.
2
Multi-Class Cell Detection Using Spatial Context Representation.基于空间上下文表示的多类细胞检测
Proc IEEE Int Conf Comput Vis. 2021 Oct;2021:3985-3994. doi: 10.1109/iccv48922.2021.00397. Epub 2022 Feb 28.
3
Topology-Guided Multi-Class Cell Context Generation for Digital Pathology.用于数字病理学的拓扑引导多类细胞上下文生成
Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2023 Jun;2023:3323-3333. doi: 10.1109/cvpr52729.2023.00324. Epub 2023 Aug 22.
7
Digital pathology and artificial intelligence.数字病理学与人工智能。
Lancet Oncol. 2019 May;20(5):e253-e261. doi: 10.1016/S1470-2045(19)30154-8.
10
Practicing pathology in the era of big data and personalized medicine.在大数据与个性化医疗时代从事病理学实践。
Appl Immunohistochem Mol Morphol. 2014 Jan;22(1):1-9. doi: 10.1097/PAI.0000000000000022.

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验