相关实验视频

Updated: Jun 13, 2025

Modeling Brain Metastasis by Internal Carotid Artery Injection of Cancer Cells

Modeling Brain Metastasis by Internal Carotid Artery Injection of Cancer Cells

Published on: August 2, 2022

使用基于MRI放射学模型预测质瘤增强模式

Wen Wang^1,2, Yu Wang^1,2, WenYi Meng¹

¹Department of Medical Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, China.

|September 10, 2024

概括

这项研究开发了一种机器学习放射学模型,使用T2-FLAIR MRI来预测质瘤增强模式. 该模型准确地识别了增强,可能减少了MRI扫描中对比剂的需求.

科学领域:

放射学放射学是一门学科.
人工智能的人工智能
在瘤学瘤学.

背景情况:

增强对比度的MRI扫描带有化学剂的风险.
精确预测质瘤增强模式可以最大限度地减少对比剂的使用.
质瘤增强模式对于诊断和治疗计划至关重要.

研究的目的:

开发和验证一种机器学习放射学模型,用于预测质瘤增强模式.
用T2流体减弱反转恢复 (T2-FLAIR) 图像来评估模型的性能.
探索非对比性MRI在质瘤表征方面的潜力.

主要方法:

追溯收集了385个病理证明的质瘤病例,并进行了手术前的T2-FLAIRMRI.
在训练队列 (n=201) 上开发具有6个分类器的机器学习放射学模型.
在内部 (n=85) 和外部 (n=99) 队列中使用ROC分析验证表现最好的模型.

主要成果:

使用高斯过程分类的15个特征放射学模型实现了最高的预测性能.
曲线下的面积 (AUC) 在培训队列中为0.88,在内部验证队列中为0.80.
在外部验证队列中,该模型显示AUC为0.81,灵敏度为0.98,特异性为0.61.

结论:

基于T2-FLAIR的机器学习放射学模型可以准确预测质瘤增强模式.
这种方法有望减少对MRI对比剂的依赖.
开发的模型提供了一种可行的非对比方法,用于预测质瘤增强.

更多相关视频

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Published on: June 7, 2020

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

相关概念视频

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...