• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

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

定量分析活检固定和染色面板设计对人类狼疮肾炎中免疫细胞自动实例分割的影响。

Quantifying the effects of biopsy fixation and staining panel design on automatic instance segmentation of immune cells in human lupus nephritis.

机构信息

University of Chicago, Committee on Medical Physics, Department of Radiology, Chicago, Illinois, United States.

University of Chicago, Section of Rheumatology and Gwen Knapp Center for Lupus and Immunology Resear, United States.

出版信息

J Biomed Opt. 2021 Jan;26(2). doi: 10.1117/1.JBO.26.2.022910.

DOI:10.1117/1.JBO.26.2.022910
PMID:33420765
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7791891/
Abstract

SIGNIFICANCE

Lupus nephritis (LuN) is a chronic inflammatory kidney disease. The cellular mechanisms by which LuN progresses to kidney failure are poorly characterized. Automated instance segmentation of immune cells in immunofluorescence images of LuN can probe these cellular interactions.

AIM

Our specific goal is to quantify how sample fixation and staining panel design impact automated instance segmentation and characterization of immune cells.

APPROACH

Convolutional neural networks (CNNs) were trained to segment immune cells in fluorescence confocal images of LuN biopsies. Three datasets were used to probe the effects of fixation methods on cell features and the effects of one-marker versus two-marker per cell staining panels on CNN performance.

RESULTS

Networks trained for multi-class instance segmentation on fresh-frozen and formalin-fixed, paraffin-embedded (FFPE) samples stained with a two-marker panel had sensitivities of 0.87 and 0.91 and specificities of 0.82 and 0.88, respectively. Training on samples with a one-marker panel reduced sensitivity (0.72). Cell size and intercellular distances were significantly smaller in FFPE samples compared to fresh frozen (Kolmogorov-Smirnov, p  ≪  0.0001).

CONCLUSIONS

Fixation method significantly reduces cell size and intercellular distances in LuN biopsies. The use of two markers to identify cell subsets showed improved CNN sensitivity relative to using a single marker.

摘要

意义

狼疮肾炎 (LuN) 是一种慢性炎症性肾病。LuN 进展为肾衰竭的细胞机制尚未得到充分描述。LuN 的免疫荧光图像中免疫细胞的自动实例分割可以探测这些细胞相互作用。

目的

我们的具体目标是量化样本固定和染色面板设计如何影响免疫细胞的自动实例分割和特征描述。

方法

卷积神经网络 (CNN) 被训练来分割狼疮肾炎活检的荧光共聚焦图像中的免疫细胞。使用三个数据集来探测固定方法对细胞特征的影响，以及每个细胞一个标记与两个标记的染色面板对 CNN 性能的影响。

结果

在新鲜冷冻和福尔马林固定、石蜡包埋 (FFPE) 样本上使用双标记面板进行多类实例分割的网络训练，其敏感性分别为 0.87 和 0.91，特异性分别为 0.82 和 0.88。在具有单标记面板的样本上进行训练会降低敏感性（0.72）。与新鲜冷冻相比，FFPE 样本中的细胞大小和细胞间距离明显更小（Kolmogorov-Smirnov，p  ≪  0.0001）。

结论

固定方法显著降低了 LuN 活检中的细胞大小和细胞间距离。与使用单个标记相比，使用两个标记来识别细胞亚群可提高 CNN 的敏感性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f2d59ff44998/JBO-026-022910-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f7177043e23b/JBO-026-022910-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f48854e58cae/JBO-026-022910-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/52a572f7bf0f/JBO-026-022910-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/30e2146f4f9e/JBO-026-022910-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/95b1be4af647/JBO-026-022910-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f2d59ff44998/JBO-026-022910-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f7177043e23b/JBO-026-022910-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f48854e58cae/JBO-026-022910-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/52a572f7bf0f/JBO-026-022910-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/30e2146f4f9e/JBO-026-022910-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/95b1be4af647/JBO-026-022910-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b3fd/7791891/f2d59ff44998/JBO-026-022910-g006.jpg

相似文献

1
Quantifying the effects of biopsy fixation and staining panel design on automatic instance segmentation of immune cells in human lupus nephritis.定量分析活检固定和染色面板设计对人类狼疮肾炎中免疫细胞自动实例分割的影响。
J Biomed Opt. 2021 Jan;26(2). doi: 10.1117/1.JBO.26.2.022910.
2
CryoNuSeg: A dataset for nuclei instance segmentation of cryosectioned H&E-stained histological images.CryoNuSeg：用于分割冷冻切片苏木精和伊红染色组织学图像中细胞核实例的数据集。
Comput Biol Med. 2021 May;132:104349. doi: 10.1016/j.compbiomed.2021.104349. Epub 2021 Mar 22.
3
A comparative study of pre-trained convolutional neural networks for semantic segmentation of breast tumors in ultrasound.用于超声乳腺肿瘤语义分割的预训练卷积神经网络的比较研究
Comput Biol Med. 2020 Nov;126:104036. doi: 10.1016/j.compbiomed.2020.104036. Epub 2020 Oct 8.
4
A deep learning framework for automatic detection of arbitrarily shaped fiducial markers in intrafraction fluoroscopic images.一种用于在分次透视图像中自动检测任意形状基准标记的深度学习框架。
Med Phys. 2019 May;46(5):2286-2297. doi: 10.1002/mp.13519. Epub 2019 Apr 15.
5
Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks.使用卷积神经网络对头颈部CT图像中的危险器官进行分割。
Med Phys. 2017 Feb;44(2):547-557. doi: 10.1002/mp.12045.
6
One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks.基于卷积神经网络的多发性硬化病变分割中单样本域自适应
Neuroimage Clin. 2019;21:101638. doi: 10.1016/j.nicl.2018.101638. Epub 2018 Dec 10.
7
Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.使用基于形状表示模型约束的全卷积神经网络进行头颈部癌症放疗的全自动多器官分割。
Med Phys. 2018 Oct;45(10):4558-4567. doi: 10.1002/mp.13147. Epub 2018 Sep 19.
8
Semi-supervised learning for automatic segmentation of the knee from MRI with convolutional neural networks.基于卷积神经网络的膝关节 MRI 半自动分割的半监督学习。
Comput Methods Programs Biomed. 2020 Jun;189:105328. doi: 10.1016/j.cmpb.2020.105328. Epub 2020 Jan 11.
9
Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images.基于深度学习的超声图像中前列腺临床靶区的准确且稳健分割
Med Image Anal. 2019 Oct;57:186-196. doi: 10.1016/j.media.2019.07.005. Epub 2019 Jul 15.
10
Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks.基于卷积神经网络的随访 CT 图像中脑梗死的自动分割。
J Neurointerv Surg. 2020 Sep;12(9):848-852. doi: 10.1136/neurintsurg-2019-015471. Epub 2019 Dec 23.

引用本文的文献

1
Pseudo-spectral angle mapping for pixel and cell classification in highly multiplexed immunofluorescence images.用于高度多重免疫荧光图像中像素和细胞分类的伪谱角映射
J Med Imaging (Bellingham). 2024 Nov;11(6):067502. doi: 10.1117/1.JMI.11.6.067502. Epub 2024 Dec 10.
2
Pseudo-spectral angle mapping for automated pixel-level analysis of highly multiplexed tissue image data.用于高度多重组织图像数据自动像素级分析的伪谱角映射
bioRxiv. 2024 Jan 11:2024.01.09.574920. doi: 10.1101/2024.01.09.574920.
3
Specific in situ inflammatory states associate with progression to renal failure in lupus nephritis.

本文引用的文献

1
The immune cell landscape in kidneys of patients with lupus nephritis.狼疮肾炎患者肾脏中的免疫细胞图谱。
Nat Immunol. 2019 Jul;20(7):902-914. doi: 10.1038/s41590-019-0398-x. Epub 2019 Jun 17.
2
Quantifying in situ adaptive immune cell cognate interactions in humans.定量分析人类原位适应性免疫细胞同源相互作用。
Nat Immunol. 2019 Apr;20(4):503-513. doi: 10.1038/s41590-019-0315-3. Epub 2019 Feb 18.
3
U-Net: deep learning for cell counting, detection, and morphometry.U-Net：用于细胞计数、检测和形态测量学的深度学习。
特定的原位炎症状态与狼疮性肾炎进展为肾衰竭有关。
J Clin Invest. 2022 Jul 1;132(13). doi: 10.1172/JCI155350.
4
Artificial Intelligence and Cellular Segmentation in Tissue Microscopy Images.人工智能与组织切片图像中的细胞分割。
Am J Pathol. 2021 Oct;191(10):1693-1701. doi: 10.1016/j.ajpath.2021.05.022. Epub 2021 Jun 12.
Nat Methods. 2019 Jan;16(1):67-70. doi: 10.1038/s41592-018-0261-2. Epub 2018 Dec 17.
4
A pathophysiology-based approach to the diagnosis and treatment of lupus nephritis.基于病理生理学的狼疮肾炎诊断和治疗方法。
Kidney Int. 2016 Sep;90(3):493-501. doi: 10.1016/j.kint.2016.05.017. Epub 2016 Jul 1.
5
Insights into the epidemiology and management of lupus nephritis from the US rheumatologist's perspective.从美国风湿病学家的视角洞察狼疮性肾炎的流行病学及管理
Kidney Int. 2016 Sep;90(3):487-92. doi: 10.1016/j.kint.2016.03.042. Epub 2016 Jun 22.
6
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.更快的 R-CNN：基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.
7
Bcl-2 as a Therapeutic Target in Human Tubulointerstitial Inflammation.Bcl-2 作为人类肾小管间质性炎症的治疗靶点。
Arthritis Rheumatol. 2016 Nov;68(11):2740-2751. doi: 10.1002/art.39744.
8
Risk of End-Stage Renal Disease in Patients With Lupus Nephritis, 1971-2015: A Systematic Review and Bayesian Meta-Analysis.1971-2015 年狼疮性肾炎患者终末期肾病风险：系统评价和贝叶斯荟萃分析。
Arthritis Rheumatol. 2016 Jun;68(6):1432-41. doi: 10.1002/art.39594.
9
An Automatic Learning-Based Framework for Robust Nucleus Segmentation.一种基于自动学习的稳健细胞核分割框架。
IEEE Trans Med Imaging. 2016 Feb;35(2):550-66. doi: 10.1109/TMI.2015.2481436. Epub 2015 Sep 23.
10
Correcting the Shrinkage Effects of Formalin Fixation and Tissue Processing for Renal Tumors: toward Standardization of Pathological Reporting of Tumor Size.纠正福尔马林固定和组织处理对肾肿瘤的收缩效应：实现肿瘤大小病理报告标准化。
J Cancer. 2015 Jul 2;6(8):759-66. doi: 10.7150/jca.12094. eCollection 2015.