• 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

数字病理学中模式识别所需的仔细数据收集

The Need for Careful Data Collection for Pattern Recognition in Digital Pathology.

作者信息

Marée Raphaël

机构信息

Department of Electrical Engineering and Computer Science, Montefiore Institute, University of Liège, 4000 Liège, Belgium.

出版信息

J Pathol Inform. 2017 Apr 10;8:19. doi: 10.4103/jpi.jpi_94_16. eCollection 2017.

DOI:10.4103/jpi.jpi_94_16
PMID:28480122
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5404354/
Abstract

Effective pattern recognition requires carefully designed ground-truth datasets. In this technical note, we first summarize potential data collection issues in digital pathology and then propose guidelines to build more realistic ground-truth datasets and to control their quality. We hope our comments will foster the effective application of pattern recognition approaches in digital pathology.

摘要

有效的模式识别需要精心设计的真值数据集。在本技术说明中，我们首先总结数字病理学中潜在的数据收集问题，然后提出构建更现实的真值数据集并控制其质量的指导方针。我们希望我们的评论将促进模式识别方法在数字病理学中的有效应用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3268/5404354/94c3125fa484/JPI-8-19-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3268/5404354/94c3125fa484/JPI-8-19-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3268/5404354/94c3125fa484/JPI-8-19-g002.jpg

相似文献

1
The Need for Careful Data Collection for Pattern Recognition in Digital Pathology.数字病理学中模式识别所需的仔细数据收集
J Pathol Inform. 2017 Apr 10;8:19. doi: 10.4103/jpi.jpi_94_16. eCollection 2017.
2
Lifting Object Detection Datasets into 3D.将物体检测数据集提升到 3D 。
IEEE Trans Pattern Anal Mach Intell. 2016 Jul;38(7):1342-55. doi: 10.1109/TPAMI.2015.2435707.
3
Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research.合成常见阿拉伯手写体以辅助光学字符识别研究。
Sensors (Basel). 2016 Mar 11;16(3):346. doi: 10.3390/s16030346.
4
Ground truth generalizability affects performance of the artificial intelligence model in automated vertebral fracture detection on plain lateral radiographs of the spine.真实情况的可推广性会影响人工智能模型在脊柱正位侧位X线片自动检测椎体骨折中的性能。
Spine J. 2022 Apr;22(4):511-523. doi: 10.1016/j.spinee.2021.10.020. Epub 2021 Nov 1.
5
Joint Segmentation and Recognition of Categorized Objects from Noisy Web Image Collection.从噪声网络图像集中对分类对象进行联合分割与识别
IEEE Trans Image Process. 2014 Sep;23(9):4070-4086. doi: 10.1109/TIP.2014.2339196. Epub 2014 Jul 14.
6
A template for creating and sharing ground truth data in digital forensics.一种用于在数字取证中创建和共享基础真值数据的模板。
J Forensic Sci. 2024 Jul;69(4):1456-1466. doi: 10.1111/1556-4029.15524. Epub 2024 Apr 21.
7
Spatially Invariant Vector Quantization: A pattern matching algorithm for multiple classes of image subject matter including pathology.空间不变矢量量化：一种用于包括病理学在内的多类图像主题的模式匹配算法。
J Pathol Inform. 2011 Feb 26;2:13. doi: 10.4103/2153-3539.77175.
8
Towards a repository for standardized medical image and signal case data annotated with ground truth.建立一个带有标注的真实数据的标准化医学图像和信号案例数据库。
J Digit Imaging. 2012 Apr;25(2):213-26. doi: 10.1007/s10278-011-9428-4.
9
Synthetic ground truth for validation of brain tumor MRI segmentation.用于脑肿瘤MRI分割验证的合成真值
Med Image Comput Comput Assist Interv. 2005;8(Pt 1):26-33. doi: 10.1007/11566465_4.
10
Cursive-Text: A Comprehensive Dataset for End-to-End Urdu Text Recognition in Natural Scene Images.连笔文本：用于自然场景图像中乌尔都语文本端到端识别的综合数据集。
Data Brief. 2020 May 21;31:105749. doi: 10.1016/j.dib.2020.105749. eCollection 2020 Aug.

引用本文的文献

1
[Chinese expert consensus on the technical and clinical practice specifications of artificial intelligence assisted morphology examination of blood cells (2024)].《人工智能辅助血细胞形态学检验技术及临床实践规范中国专家共识（2024年版）》
Zhonghua Xue Ye Xue Za Zhi. 2024 Apr 14;45(4):330-338. doi: 10.3760/cma.j.cn121090-20240217-00064.
2
Machine learning to detect the SINEs of cancer.机器学习检测癌症中的 SINEs。
Sci Transl Med. 2024 Jan 24;16(731):eadi3883. doi: 10.1126/scitranslmed.adi3883.
3
Performance comparison between multi-center histopathology datasets of a weakly-supervised deep learning model for pancreatic ductal adenocarcinoma detection.

本文引用的文献

1
Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases.用于数字病理学图像分析的深度学习：包含选定用例的全面教程。
J Pathol Inform. 2016 Jul 26;7:29. doi: 10.4103/2153-3539.186902. eCollection 2016.
2
Challenges and Benchmarks in Bioimage Analysis.生物图像分析中的挑战与基准
Adv Anat Embryol Cell Biol. 2016;219:231-62. doi: 10.1007/978-3-319-28549-8_9.
3
Collaborative analysis of multi-gigapixel imaging data using Cytomine.使用Cytomine对多千兆像素成像数据进行协作分析。
多中心弱监督深度学习模型在胰腺导管腺癌检测中的性能比较。
Cancer Imaging. 2023 Jun 26;23(1):66. doi: 10.1186/s40644-023-00586-3.
4
The need for measurement science in digital pathology.数字病理学中对测量科学的需求。
J Pathol Inform. 2022;13:100157. doi: 10.1016/j.jpi.2022.100157. Epub 2022 Nov 10.
5
Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology.用于评估病理学人工智能解决方案的测试数据集编制建议。
Mod Pathol. 2022 Dec;35(12):1759-1769. doi: 10.1038/s41379-022-01147-y. Epub 2022 Sep 10.
6
Semantic annotation for computational pathology: multidisciplinary experience and best practice recommendations.计算病理学的语义标注：多学科经验和最佳实践建议。
J Pathol Clin Res. 2022 Mar;8(2):116-128. doi: 10.1002/cjp2.256. Epub 2022 Jan 10.
7
Open Practices and Resources for Collaborative Digital Pathology.协作数字病理学的开放实践与资源
Front Med (Lausanne). 2019 Nov 14;6:255. doi: 10.3389/fmed.2019.00255. eCollection 2019.
8
Gastric Pathology Image Classification Using Stepwise Fine-Tuning for Deep Neural Networks.基于深度神经网络的逐步微调进行胃病理图像分类。
J Healthc Eng. 2018 Jun 21;2018:8961781. doi: 10.1155/2018/8961781. eCollection 2018.
Bioinformatics. 2016 May 1;32(9):1395-401. doi: 10.1093/bioinformatics/btw013. Epub 2016 Jan 10.
4
Large-scale tracking and classification for automatic analysis of cell migration and proliferation, and experimental optimization of high-throughput screens of neuroblastoma cells.用于神经母细胞瘤细胞迁移和增殖自动分析的大规模跟踪与分类，以及高通量筛选的实验优化。
Cytometry A. 2015 Jun;87(6):524-40. doi: 10.1002/cyto.a.22632. Epub 2015 Jan 28.
5
Phenotype classification of zebrafish embryos by supervised learning.通过监督学习对斑马鱼胚胎进行表型分类。
PLoS One. 2015 Jan 9;10(1):e0116989. doi: 10.1371/journal.pone.0116989. eCollection 2015.
6
Evaluation of CellSolutions BestPrep® automated thin-layer liquid-based cytology Papanicolaou slide preparation and BestCyte® cell sorter imaging system.CellSolutions BestPrep® 自动薄层液基细胞学巴氏涂片制备及 BestCyte® 细胞分选成像系统的评估
Acta Cytol. 2014;58(5):469-77. doi: 10.1159/000367837. Epub 2014 Sep 27.
7
Screening for cervical cancer using automated analysis of PAP-smears.使用 PAP 涂片的自动化分析进行宫颈癌筛查。
Comput Math Methods Med. 2014;2014:842037. doi: 10.1155/2014/842037. Epub 2014 Mar 20.
8
Cytological artifacts masquerading interpretation.伪装解释的细胞学假象。
J Cytol. 2013 Oct;30(4):241-6. doi: 10.4103/0970-9371.126649.
9
Pathology imaging informatics for quantitative analysis of whole-slide images.病理学成像信息学用于全切片图像的定量分析。
J Am Med Inform Assoc. 2013 Nov-Dec;20(6):1099-108. doi: 10.1136/amiajnl-2012-001540. Epub 2013 Aug 19.
10
Automated classification of immunostaining patterns in breast tissue from the human protein atlas.来自人类蛋白质图谱的乳腺组织免疫染色模式的自动分类
J Pathol Inform. 2013 Mar 30;4(Suppl):S14. doi: 10.4103/2153-3539.109881. Print 2013.