文献速递神经技术与安全MR

深度学习/机器学习在区分胶质母细胞瘤(或IV级星形细胞瘤)与原发性中枢神经系统淋巴瘤方面与放射科医生的表现比较:一项Meta分析与系统综述

How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review.
PubMed 文献 · Clin Radiol · 2024-03-19

本Meta分析纳入8项研究共1159例患者,比较MRI上ML/DL与放射科医生鉴别PCNSL与GBM的诊断准确性。ML的合并敏感度0.89、特异度0.88、准确率0.88、AUC 0.94;放射科医生分别为0.82、0.90、0.86、0.90。作者认为基于MRI的ML/DL可辅助放射科医生提高分类准确性,可能减少活检需求并避免对PCNSL的不必要神经外科切除。

要点

  • ML鉴别PCNSL与GBM的合并AUC为0.94,放射科医生为0.90。
  • ML合并敏感度0.89高于放射科医生的0.82,特异度0.88略低于0.90。
  • 作者认为ML/DL可辅助放射科医生,可能减少活检及避免对PCNSL的不必要切除。

核心结论

  • 基于MRI的ML/DL技术可辅助放射科医生提高鉴别GBM与PCNSL的准确性,可能减少活检需求,并避免对PCNSL进行不必要的神经外科切除。

研究设计与样本

  • 系统综述与Meta分析,遵循PRISMA指南,检索到11项研究,其中8项符合纳入标准,每项研究仅纳入准确率最高的模型,总样本量1159例患者;由两位分别有12年和23年经验的研究者提取和解读数据,采用QUADAS-2工具评估质量与偏倚风险。

诊断标准与关键数值

  • ML合并敏感度0.89(95%CI 0.84-0.92),放射科医生0.82(95%CI 0.76-0.87);ML合并特异度0.88(95%CI 0.84-0.91),放射科医生0.90(95%CI 0.81-0.95);ML合并准确率0.88(95%CI 0.86-0.90),放射科医生0.86(95%CI 0.78-0.91);ML合并AUC 0.94(95%CI 0.92-0.96),放射科医生0.90(95%CI 0.84-0.93)。

临床应用与阅片要点

  • 作者认为基于MRI的ML/DL技术可辅助放射科医生提高鉴别GBM与PCNSL的准确性,可能减少活检需求,并避免对PCNSL进行不必要的神经外科切除。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND: Several studies have been published comparing deep learning (DL)/machine learning (ML) to radiologists in differentiating PCNSLs from GBMs with equivocal results. We aimed to perform this meta-analysis to evaluate the diagnostic accuracy of ML/DL versus radiologists in classifying PCNSL versus GBM using MRI.

METHODOLOGY: The study was performed in accordance with PRISMA guidelines. Data was extracted and interpreted by two researchers with 12 and 23 years' experience, respectively, and QUADAS-2 tool was used for quality and risk-bias assessment. We constructed contingency tables to derive sensitivity, specificity accuracy, summary receiver operating characteristic (SROC) curve, and the area under the curve (AUC).

RESULTS: Our search identified 11 studies, of which 8 satisfied our inclusion criteria and restricted the analysis in each study to reporting the model showing highest accuracy, with a total sample size of 1159 patients. The random effects model showed a pooled sensitivity of 0.89 [95% CI:0.84-0.92] for ML and 0.82 [95% CI:0.76-0.87] for radiologists. Pooled specificity was 0.88 [95% CI: 0.84-0.91] for ML and 0.90 [95% CI: 0.81-0.95] for radiologists. Pooled accuracy was 0.88 [95% CI: 0.86-0.90] for ML and 0.86 [95% CI: 0.78-0.91] for radiologists. Pooled AUC of ML was 0.94 [95% CI:0.92-0.96]and for radiologists, it was 0.90 [95% CI: 0.84-0.93].

CONCLUSIONS: MRI-based ML/DL techniques can complement radiologists to improve the accuracy of classifying GBMs from PCNSL, possibly reduce the need for a biopsy, and avoid any unwanted neurosurgical resection of a PCNSL.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Guha A, Halder S, Shinde SH, et al. How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review. Clin Radiol. 2024. PMID: 38614870. doi:10.1016/j.crad.2024.03.007

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。