相关实验视频

Updated: Jul 26, 2026

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

用机器学习预测微卫星不稳定状态和PD-L1表达的放射基因组学在子宫内膜癌中:一项多中心研究

Qianling Li¹, Ya'nan Huang², Yang Xia³

¹Department of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School of Medicine), Zhejiang University School of Medicine, Shaoxing, 312000, China.

|December 27, 2023

概括

使用MRI放射学的机器学习模型可以预测微卫星不稳定性 (MSI) 状态和子宫内膜癌 (EC) 中的PD-L1表达,帮助精准医学.

科学领域:

在瘤学瘤学.
放射学放射学是一门学科.
人工智能的人工智能

背景情况:

通过了解微卫星不稳定性 (MSI) 状态和PD-L1表达,子宫内膜癌 (EC) 管理将受益.
准确预测这些生物标志物对于指导治疗策略至关重要.

研究的目的:

评估集成磁共振成像 (MRI) 放射学和临床病理学数据的机器学习模型的有效性,以预测MSI状态和EC中的PD-L1表达.
探索非侵入性成像生物标志物在EC患者分层中的潜力.

主要方法:

这是一项回顾性研究,涉及来自两个独立中心的82名EC患者.
从传统的MRI序列 (T2WI,CE-T1WI,DWI,ADC) 中提取了内和周区域的放射性特征.
使用放射学特征和临床病理学数据开发了机器学习模型,在单独的队列上进行了外部验证.

主要成果:

组合模型在训练集中实现了MSI预测的0.889的曲线下的面积 (AUC),在验证集中达到0.848.
对于PD-L1表达预测,组合模型的AUC值为0.834 (训练) 和0.764 (验证).
校准和决策曲线分析证实了组合模型的良好校准和临床实用性.

结论:

结合基于MRI的放射学和临床病理学特征的机器学习模型显示出预测MSI状态和EC中的PD-L1表达的前景.
这种非侵入性方法可以增强EC患者的精准医学策略,潜在地改善治疗选择和结果.

关键词:

这是子宫内膜癌的癌症.机器学习机器学习磁共振成像技术磁共振成像技术微卫星的不稳定性是微观的不匹配的修复缺陷的缺陷在PD-L1中.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Non-Invasive Ultrasound Assessment of Endometrial Cancer Progression in Pax8-Directed Deletion of the Tumor Suppressors Arid1a and Pten in Mice

Non-Invasive Ultrasound Assessment of Endometrial Cancer Progression in Pax8-Directed Deletion of the Tumor Suppressors Arid1a and Pten in Mice

Published on: February 17, 2023

相关概念视频

Non-LTR Retrotransposons

Non-LTR Retrotransposons

As the name suggests, non-LTR retrotransposons lack the long terminal repeats characteristic of the LTR retrotransposons. Additionally, both LTR and non-LTR retrotransposons use distinct mechanisms of mobilization. Non-LTR retrotransposons are further divided into two classes - Long interspersed nuclear elements (LINEs) and short interspersed nuclear elements (SINEs), both of which occur abundantly in most mammals, including humans. Some of the active non-LTR retrotransposons in humans are L1...