利用MRI放射学上的机器学习技术来识别大脑转移中的初级瘤
1Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
Frontiers in neurology
|January 21, 2025
概括
机器学习模型使用MRI放射学准确预测大脑转移的原发性癌症部位. 将放射学与临床数据相结合,进一步提高了肺,乳腺和胃肠道瘤的预测准确度.
科学领域:
- 放射学 放射学是一门学科.
- 在瘤学瘤学.
- 人工智能的人工智能
- 医学成像分析 医学成像分析
背景情况:
- 在脑转移患者中,确定主要瘤部位对于有效的治疗计划至关重要.
- 多参数磁共振成像 (MRI) 为分析大脑转移特征提供了丰富的数据.
- 机器学习和放射学为提取定量成像特征提供了新的方法,以帮助诊断.
研究的目的:
- 开发和验证基于机器学习的模型,用于预测大脑转移的主要部位.
- 为了评估从多参数MRI中提取的放射学特征的诊断性能.
- 评估结合放射学和临床数据的附加值,以提高预测准确度.
主要方法:
- 从202名肺,乳腺和胃肠道瘤患者中对439例脑转移进行了回顾性分析.
- 从多参数MRI (T1WI,T2WI,FLAIR,T1-CE) 中提取3,404个定量放射学特征.
- 使用特征选择 (ANOVA,RFE,Kruskal-Wallis) 和分类器开发机器学习模型,通过交叉验证和独立测试集进行验证.
主要成果:
- 放射学模型在将胃肠道瘤的大脑转移与肺癌 (AUC=0.915) 和乳腺癌 (AUC=0.954) 的区分方面取得了很高的准确性.
- 肺癌和乳腺癌转移之间的分类仅用放射性基因较不准确 (AUC=0.729).
- 综合放射学和临床特征的综合模型显著改善了预测性能,产生AUC为0.965 (肺与乳房),0.991 (肺与肠道) 和0.935 (乳房与肠道).
结论:
- 基于机器学习的放射学模型显示出区分大脑转移的主要部位的巨大潜力.
- 结合放射学和临床特征的组合模型提供了卓越的诊断性能.
- 这种方法可能有助于查原发性瘤,当怀疑大脑转移并未知主要部位时.
更多相关视频
相关概念视频
Magnetic Resonance Imaging
4.9K
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...
4.9K
Brain Imaging
208
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
208


