脑瘤自动纵向治疗响应评估:系统性审查
Tangqi Shi1, Aaron Kujawa1, Christian Linares1
1School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.
Neuro-oncology
|February 12, 2025
概括
机器学习 (ML) 显示了自动化脑瘤治疗反应评估的前景,比手工方法提高了准确性. 然而,目前的研究存在局限性,需要前性研究以获得更好的概括性.
科学领域:
- 神经瘤学神经瘤学
- 医学成像分析 医学成像分析
- 机器学习在医学中的应用
背景情况:
- 对瘤负担的纵向成像评估对于评估临床试验和现实世界的治疗反应至关重要.
- 无进展生存率是关键的终点,但手动评估是耗时的,容易引起观察者之间的变化.
- 使用机器学习 (ML) 的自动评估提供了提高准确性和减少手工工作的潜力.
研究的目的:
- 评估最近关于使用ML进行自动化脑瘤治疗响应评估的研究的质量和性能准确性.
- 确定基于ML的自动响应评估工具的开发和验证程度.
主要方法:
- 在PUBMED,EMBASE和Web of Science中按照PRISMA指南和CLAIM检查清单 (2010年1月至2024年11月) 进行系统的文献搜索.
- 专注于使用ML方法的成年脑瘤自动化治疗响应评估研究.
- 使用QUADAS-2进行研究评估,以评估偏见和适用性问题.
主要成果:
- 包括20项研究 (17项追溯,3项前性),提取数据集,ML管道和参考标准的数据.
- 高偏差风险和适用性问题,特别是关于参考标准和患者选择,限制了结论.
- 不足够的均数据阻止了元分析.
结论:
- ML具有显著的潜力,可以改善纵向脑瘤治疗响应评估.
- 研究偏见和有限的概括性证据限制了当前的解释.
- 用外部数据集验证当前神经瘤学标准的前性研究对于未来的进展至关重要.
相关概念视频
02:56Treatment Resistant Cancers
Cancer is the second leading cause of death in the United States. A cancer cell is genetically unstable and hence can mutate faster. They can also modify their microenvironment and escape immune surveillance. The difficulties in treating cancer are further compounded by the emergence of rapid resistance to anticancer drugs. The most common ways to attain resistance in cancer cells include alteration in drug transport and metabolism, modification of drug target, elevated DNA damage response, or...
02:56Treatment Resistent Cancers
Cancer is the second leading cause of death in the United States. A cancer cell is genetically unstable and hence can mutate faster. They can also modify their microenvironment and escape immune surveillance. The difficulties in treating cancer are further compounded by the emergence of rapid resistance to anticancer drugs. The most common ways to attain resistance in cancer cells include alteration in drug transport and metabolism, modification of drug target, elevated DNA damage response, or...