机器学习在脑肿瘤分类中的应用:系统综述与Meta分析
该系统综述与Meta分析检索PubMed、Embase和Web of Science至2023年3月14日,纳入51项研究,评估机器学习算法区分不同脑肿瘤类型的诊断准确性。汇总结果显示机器学习在脑肿瘤图像分类中表现优异,曲线下面积、敏感度和特异度接近最大值。
要点
- 胶质母细胞瘤与淋巴瘤鉴别的汇总AUC为0.99(95%CI:0.98-1.00)。
- 低级别与高级别胶质瘤鉴别的汇总敏感度0.99(95%CI:0.97-1.00),特异度0.94(95%CI:0.79-0.99)。
- 胶质瘤与垂体瘤鉴别的汇总敏感度和特异度均为0.99,为原发性脑肿瘤分类中最高。
核心结论
- 机器学习在脑肿瘤图像分类中表现优异,曲线下面积、敏感度和特异度接近最大值。
研究设计与样本
- 系统综述与Meta分析,检索PubMed、Embase和Web of Science至2023年3月14日,共纳入51项研究。
- 排除仅研究图像分割准确性或脑肿瘤检测而非分类的研究。
- 提取二分类诊断准确性数据,构建列联表以得出敏感度和特异度。
主要发现
- 胶质母细胞瘤与淋巴瘤鉴别的汇总曲线下面积为0.99(95%CI:0.98-1.00),低级别与高级别胶质瘤鉴别的汇总曲线下面积为0.89。
- 良性 vs 恶性肿瘤鉴别的汇总敏感度为0.90(95%CI:0.85-0.93),特异度为0.93(95%CI:0.90-0.95)。
- 低级别 vs 高级别胶质瘤鉴别的汇总敏感度为0.99(95%CI:0.97-1.00),特异度为0.94(95%CI:0.79-0.99)。
- 原发性 vs 转移性肿瘤鉴别的汇总敏感度为0.89(95%CI:0.83-0.93),特异度为0.87(95%CI:0.82-0.91)。
- 胶质瘤与垂体瘤鉴别的汇总敏感度为0.99(95%CI:0.99-1.00),特异度为0.99(95%CI:0.98-1.00),为原发性脑肿瘤分类中最高。
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)。
原文
BACKGROUND: Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types. METHODS: A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity. RESULTS: Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00). CONCLUSIONS: ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.
引用
- Silva Santana L, Borges Camargo Diniz J, Mothé Glioche Gasparri L, et al. Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis. World Neurosurg. 2024. PMID: 38580093. doi:10.1016/j.wneu.2024.03.152
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。