• 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

基于数字病理学图像的颜色恢复。

Color restoration based on digital pathology image.

机构信息

School of Clinical Medicine, Qingdao University, Qingdao, China.

Department of Pathology, Qingdao Central Hospital, Qingdao, China.

出版信息

PLoS One. 2023 Jun 28;18(6):e0287704. doi: 10.1371/journal.pone.0287704. eCollection 2023.

DOI:10.1371/journal.pone.0287704
PMID:37379301
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10306179/
Abstract

OBJECTIVE

Protective color restoration of faded digital pathology images based on color transfer algorithm.

METHODS

Twenty fresh tissue samples of invasive breast cancer from the pathology department of Qingdao Central Hospital in 2021 were screened. After HE staining, HE stained sections were irradiated with sunlight to simulate natural fading, and every 7 days was a fading cycle, and a total of 8 cycles were experienced. At the end of each cycle, the sections were digitally scanned to retain clear images, and the color changes of the sections during the fading process were recorded. The color transfer algorithm was applied to restore the color of the faded images; Adobe Lightroom Classic software presented the histogram of the image color distribution; UNet++ cell recognition segmentation model was used to identify the color restored images; Natural Image Quality Evaluator (NIQE), Information Entropy (Entropy), and Average Gradient (AG) were applied to evaluate the quality of the restored images.

RESULTS

The restored image color met the diagnostic needs of pathologists. Compared with the faded images, the NIQE value decreased (P<0.05), Entropy value increased (P<0.01), and AG value increased (P<0.01). The cell recognition rate of the restored image was significantly improved.

CONCLUSION

The color transfer algorithm can effectively repair faded pathology images, restore the color contrast between nucleus and cytoplasm, improve the image quality, meet the diagnostic needs and improve the cell recognition rate of the deep learning model.

摘要

目的

基于颜色传递算法恢复褪色的数字病理学图像的保护色。

方法

筛选 2021 年青岛中心医院病理科的 20 例浸润性乳腺癌新鲜组织样本。经 HE 染色后，将 HE 染色切片用阳光照射以模拟自然褪色，每个 7 天为一个褪色周期，共经历 8 个周期。在每个周期结束时，对切片进行数字扫描以保留清晰的图像，并记录切片在褪色过程中的颜色变化。应用颜色传递算法恢复褪色图像的颜色；Adobe Lightroom Classic 软件呈现图像颜色分布的直方图；UNet++ 细胞识别分割模型用于识别颜色恢复图像；自然图像质量评估器（NIQE）、信息熵（Entropy）和平均梯度（AG）用于评估恢复图像的质量。

结果

恢复后的图像颜色满足病理学家的诊断需求。与褪色图像相比，NIQE 值降低（P<0.05），Entropy 值增加（P<0.01），AG 值增加（P<0.01）。恢复图像的细胞识别率显著提高。

结论

颜色传递算法可有效修复褪色的病理学图像，恢复核质之间的颜色对比度，提高图像质量，满足诊断需求，提高深度学习模型的细胞识别率。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/69b3d9b01b73/pone.0287704.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/034684fe933f/pone.0287704.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/649b4669b35c/pone.0287704.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/a148567ef2bb/pone.0287704.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/f5538bae9c59/pone.0287704.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/47448f58a4cb/pone.0287704.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/69b3d9b01b73/pone.0287704.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/034684fe933f/pone.0287704.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/649b4669b35c/pone.0287704.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/a148567ef2bb/pone.0287704.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/f5538bae9c59/pone.0287704.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/47448f58a4cb/pone.0287704.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2384/10306179/69b3d9b01b73/pone.0287704.g006.jpg

相似文献

1
Color restoration based on digital pathology image.基于数字病理学图像的颜色恢复。
PLoS One. 2023 Jun 28;18(6):e0287704. doi: 10.1371/journal.pone.0287704. eCollection 2023.
2
Normalization of HE-stained histological images using cycle consistent generative adversarial networks.使用循环一致生成对抗网络对 HE 染色组织学图像进行归一化。
Diagn Pathol. 2021 Aug 6;16(1):71. doi: 10.1186/s13000-021-01126-y.
3
Deep unsupervised endoscopic image enhancement based on multi-image fusion.基于多图像融合的深度无监督内窥镜图像增强。
Comput Methods Programs Biomed. 2022 Jun;221:106800. doi: 10.1016/j.cmpb.2022.106800. Epub 2022 Apr 26.
4
Color normalization of faded H&E-stained histological images using spectral matching.使用光谱匹配对褪色的 H&E 染色组织学图像进行颜色归一化。
Comput Biol Med. 2019 Aug;111:103344. doi: 10.1016/j.compbiomed.2019.103344. Epub 2019 Jun 28.
5
Fast unsupervised nuclear segmentation and classification scheme for automatic allred cancer scoring in immunohistochemical breast tissue images.快速无监督的核分割和分类方案，用于免疫组织化学乳腺组织图像中的自动 Allred 癌症评分。
Comput Methods Programs Biomed. 2018 Oct;165:37-51. doi: 10.1016/j.cmpb.2018.08.005. Epub 2018 Aug 10.
6
Color Correction of Stained Tissue Section Images by Histogram Transfer According to Control Images.根据对照图像通过直方图转移对染色组织切片图像进行颜色校正。
Anal Quant Cytopathol Histpathol. 2015 Jun;37(3):177-86.
7
Application of automated image analysis reduces the workload of manual screening of sentinel lymph node biopsies in breast cancer.自动化图像分析的应用减少了乳腺癌前哨淋巴结活检的手动筛选工作量。
Histopathology. 2017 Dec;71(6):866-873. doi: 10.1111/his.13305. Epub 2017 Sep 22.
8
Automated cell nuclear segmentation in color images of hematoxylin and eosin-stained breast biopsy.苏木精和伊红染色的乳腺活检彩色图像中的自动细胞核分割
Anal Quant Cytol Histol. 2003 Dec;25(6):321-31.
9
A color-based tumor segmentation method for clinical ex vivo breast tissue assessment utilizing a multi-contrast brightfield imaging strategy.一种基于颜色的肿瘤分割方法，用于利用多对比度明场成像策略进行临床离体乳腺组织评估。
J Biophotonics. 2024 May;17(5):e202300241. doi: 10.1002/jbio.202300241. Epub 2024 Feb 13.
10
Automated quantitative analysis of Ki-67 staining and HE images recognition and registration based on whole tissue sections in breast carcinoma.基于乳腺癌全组织切片的 Ki-67 染色的自动定量分析和 HE 图像识别及配准。
Diagn Pathol. 2020 May 29;15(1):65. doi: 10.1186/s13000-020-00957-5.

引用本文的文献

1
Diagnostic challenges of faded hematoxylin and eosin slides: limitations of re-staining and re-sectioning and possible reason to go digital.苏木精和伊红染色切片褪色后的诊断挑战：重新染色和重新切片的局限性以及采用数字化的可能原因
Virchows Arch. 2025 Aug 14. doi: 10.1007/s00428-025-04209-z.

本文引用的文献

1
Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors.基于超拉普拉斯反射先验的水下图像增强
IEEE Trans Image Process. 2022;31:5442-5455. doi: 10.1109/TIP.2022.3196546. Epub 2022 Aug 17.
2
Underwater Image Enhancement via Minimal Color Loss and Locally Adaptive Contrast Enhancement.基于最小颜色损失和局部自适应对比度增强的水下图像增强
IEEE Trans Image Process. 2022 Jun 3;PP. doi: 10.1109/TIP.2022.3177129.
3
Histological Stains in the Past, Present, and Future.过去、现在和未来的组织学染色剂。
Cureus. 2021 Oct 4;13(10):e18486. doi: 10.7759/cureus.18486. eCollection 2021 Oct.
4
UNet retinal blood vessel segmentation algorithm based on improved pyramid pooling method and attention mechanism.基于改进金字塔池化方法和注意力机制的 UNet 视网膜血管分割算法。
Phys Med Biol. 2021 Aug 26;66(17). doi: 10.1088/1361-6560/ac1c4c.
5
A Hybrid-Attention Nested UNet for Nuclear Segmentation in Histopathological Images.用于组织病理学图像中细胞核分割的混合注意力嵌套UNet
Front Mol Biosci. 2021 Feb 17;8:614174. doi: 10.3389/fmolb.2021.614174. eCollection 2021.
6
Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries.《全球癌症统计数据 2020：全球 185 个国家和地区 36 种癌症的发病率和死亡率估计》。
CA Cancer J Clin. 2021 May;71(3):209-249. doi: 10.3322/caac.21660. Epub 2021 Feb 4.
7
UNet++: A Nested U-Net Architecture for Medical Image Segmentation.U-Net++：一种用于医学图像分割的嵌套U-Net架构。
Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:3-11. doi: 10.1007/978-3-030-00889-5_1. Epub 2018 Sep 20.
8
Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma.多模态磁共振成像中影像预处理方法对胶质母细胞瘤放射组学特征可重复性的影响。
J Appl Clin Med Phys. 2020 Jan;21(1):179-190. doi: 10.1002/acm2.12795. Epub 2019 Dec 27.
9
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation.UNet++：重新设计跳过连接以利用图像分割中的多尺度特征。
IEEE Trans Med Imaging. 2020 Jun;39(6):1856-1867. doi: 10.1109/TMI.2019.2959609. Epub 2019 Dec 13.
10
Color normalization of faded H&E-stained histological images using spectral matching.使用光谱匹配对褪色的 H&E 染色组织学图像进行颜色归一化。
Comput Biol Med. 2019 Aug;111:103344. doi: 10.1016/j.compbiomed.2019.103344. Epub 2019 Jun 28.