基于影像组学预测动脉瘤性蛛网膜下腔出血预后的临床研究进展

Advances in Clinical Research on Radiomics-Based Prediction of Prognosis in Aneurysmal Subarachnoid Hemorrhage

摘要: 动脉瘤性蛛网膜下腔出血(aSAH)因其突发性和高致残率，成为神经科临床中的重大挑战，准确的预后评估对优化治疗方案和提高患者生活质量具有重要意义。近年来，影像组学作为一种结合高通量影像特征提取与先进机器学习算法的新兴技术，为aSAH的预后预测提供了新的视角和工具。当前研究主要集中于利用影像组学从CT、MRI等影像数据中提取多维度特征，并通过构建机器学习模型实现对患者预后风险的精准评估。然而，影像组学方法在aSAH领域仍面临特征稳定性、模型泛化能力及临床转化等多重挑战。本文系统综述了基于影像组学的特征提取技术、模型构建策略及其在临床应用中的研究进展，旨在促进该技术在aSAH预后预测中的规范化应用，推动个体化医疗的发展，为未来临床决策提供有力支持。

Abstract: Aneurysmal subarachnoid hemorrhage (aSAH) poses a significant challenge in neurological clinical practice due to its sudden onset and high disability rate. Accurate prognosis assessment is critical for optimizing treatment strategies and improving patients’ quality of life. In recent years, radiomics, an emerging technology that combines high-throughput imaging feature extraction with advanced machine learning algorithms, has provided novel perspectives and tools for predicting aSAH prognosis. Current research primarily focuses on utilizing radiomics to extract multidimensional features from imaging data such as CT and MRI, and constructing machine learning models to achieve precise assessment of patients’ prognostic risks. However, radiomics approaches in the field of aSAH still face multiple challenges, including feature stability, model generalizability, and clinical translation. This article systematically reviews the feature extraction techniques, model construction strategies, and research progress in clinical applications of radiomics, aiming to promote the standardized use of this technology in aSAH prognosis prediction, advance the development of personalized medicine, and provide robust support for future clinical decision-making.