Cellular Pathology, University Hospitals Coventry and Warwickshire NHS Trust, Coventry, Coventry, UK
Tissue Image Analytics Laboratory, Department of Computer Science, University of Warwick, Coventry, West Midlands, UK.
J Clin Pathol. 2021 Jul;74(7):448-455. doi: 10.1136/jclinpath-2020-206764. Epub 2020 Sep 15.
Digital pathology (DP) has the potential to fundamentally change the way that histopathology is practised, by streamlining the workflow, increasing efficiency, improving diagnostic accuracy and facilitating the platform for implementation of artificial intelligence-based computer-assisted diagnostics. Although the barriers to wider adoption of DP have been multifactorial, limited evidence of reliability has been a significant contributor. A meta-analysis to demonstrate the combined accuracy and reliability of DP is still lacking in the literature.
We aimed to review the published literature on the diagnostic use of DP and to synthesise a statistically pooled evidence on safety and reliability of DP for routine diagnosis (primary and secondary) in the context of validation process.
A comprehensive literature search was conducted through PubMed, Medline, EMBASE, Cochrane Library and Google Scholar for studies published between 2013 and August 2019. The search protocol identified all studies comparing DP with light microscopy (LM) reporting for diagnostic purposes, predominantly including H&E-stained slides. Random-effects meta-analysis was used to pool evidence from the studies.
Twenty-five studies were deemed eligible to be included in the review which examined a total of 10 410 histology samples (average sample size 176). For overall concordance (clinical concordance), the agreement percentage was 98.3% (95% CI 97.4 to 98.9) across 24 studies. A total of 546 major discordances were reported across 25 studies. Over half (57%) of these were related to assessment of nuclear atypia, grading of dysplasia and malignancy. These were followed by challenging diagnoses (26%) and identification of small objects (16%).
The results of this meta-analysis indicate equivalent performance of DP in comparison with LM for routine diagnosis. Furthermore, the results provide valuable information concerning the areas of diagnostic discrepancy which may warrant particular attention in the transition to DP.
数字病理学（DP）有可能通过简化工作流程、提高效率、提高诊断准确性并为人工智能辅助计算机辅助诊断的实施平台提供便利，从根本上改变组织病理学的实践方式。尽管 DP 广泛应用的障碍是多方面的，但可靠性方面的证据有限是一个重要因素。文献中仍然缺乏证明 DP 的综合准确性和可靠性的荟萃分析。
我们旨在回顾 DP 诊断应用的已发表文献，并综合评估 DP 在验证过程中进行常规诊断（主要和次要）的安全性和可靠性的循证医学证据。
通过 PubMed、Medline、EMBASE、Cochrane 图书馆和 Google Scholar 进行了全面的文献检索，检索了 2013 年至 2019 年 8 月期间发表的所有比较 DP 与主要用于诊断目的的光镜（LM）报告的 DP 研究，这些研究主要包括 H&E 染色载玻片。使用随机效应荟萃分析汇总来自研究的证据。
有 25 项研究被认为符合纳入标准，这些研究共检查了 10410 个组织学样本（平均样本量为 176）。在 24 项研究中，总体一致性（临床一致性）的一致性百分比为 98.3%（95%CI 97.4 至 98.9）。在 25 项研究中总共报告了 546 项重大分歧。其中超过一半（57%）与核异型性评估、发育不良和恶性程度分级有关。其次是具有挑战性的诊断（26%）和小物体的识别（16%）。
这项荟萃分析的结果表明 DP 在常规诊断方面与 LM 性能相当。此外，这些结果提供了有关诊断差异领域的有价值信息，这些信息可能需要在向 DP 过渡时特别关注。
