Budginaite Elzbieta, Magee Derek R, Kloft Maximilian, Woodruff Henry C, Grabsch Heike I
Department of Pathology, GROW - Research Institute for Oncology and Reproduction, Maastricht University Medical Center+, Maastricht, The Netherlands.
Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University Medical Center+, Maastricht, The Netherlands.
J Pathol Inform. 2024 Feb 4;15:100367. doi: 10.1016/j.jpi.2024.100367. eCollection 2024 Dec.
Histological examination of tumor draining lymph nodes (LNs) plays a vital role in cancer staging and prognostication. However, as soon as a LN is classed as metastasis-free, no further investigation will be performed and thus, potentially clinically relevant information detectable in tumor-free LNs is currently not captured.
To systematically study and critically assess methods for the analysis of digitized histological LN images described in published research.
A systematic search was conducted in several public databases up to December 2023 using relevant search terms. Studies using brightfield light microscopy images of hematoxylin and eosin or immunohistochemically stained LN tissue sections aiming to detect and/or segment LNs, their compartments or metastatic tumor using artificial intelligence (AI) were included. Dataset, AI methodology, cancer type, and study objective were compared between articles.
A total of 7201 articles were collected and 73 articles remained for detailed analyses after article screening. Of the remaining articles, 86% aimed at LN metastasis identification, 8% aimed at LN compartment segmentation, and remaining focused on LN contouring. Furthermore, 78% of articles used patch classification and 22% used pixel segmentation models for analyses. Five out of six studies (83%) of metastasis-free LNs were performed on publicly unavailable datasets, making quantitative article comparison impossible.
Multi-scale models mimicking multiple microscopy zooms show promise for computational LN analysis. Large-scale datasets are needed to establish the clinical relevance of analyzing metastasis-free LN in detail. Further research is needed to identify clinically interpretable metrics for LN compartment characterization.
肿瘤引流淋巴结（LN）的组织学检查在癌症分期和预后评估中起着至关重要的作用。然而，一旦一个淋巴结被归类为无转移，就不会再进行进一步的检查，因此，目前无法获取在无肿瘤淋巴结中可检测到的潜在临床相关信息。
系统研究并严格评估已发表研究中描述的数字化组织学淋巴结图像分析方法。
截至2023年12月，使用相关搜索词在多个公共数据库中进行了系统检索。纳入使用苏木精和伊红或免疫组织化学染色的淋巴结组织切片的明场光学显微镜图像，旨在使用人工智能（AI）检测和/或分割淋巴结、其区域或转移性肿瘤的研究。对各文章之间的数据集、AI方法、癌症类型和研究目的进行了比较。
共收集到7201篇文章，经过文章筛选后，有73篇文章留作详细分析。在其余文章中，86%旨在识别淋巴结转移，8%旨在分割淋巴结区域，其余文章则侧重于勾勒淋巴结轮廓。此外，78%的文章使用图像块分类，22%使用像素分割模型进行分析。关于无转移淋巴结的六项研究中有五项（83%）是在公开不可用的数据集上进行的，这使得无法进行定量的文章比较。
模仿多个显微镜放大倍数的多尺度模型在计算淋巴结分析方面显示出前景。需要大规模数据集来确定详细分析无转移淋巴结的临床相关性。需要进一步研究以确定用于淋巴结区域特征描述的临床可解释指标。
