基于MRI生境成像特征和多血细胞参数分析用于自发性出血转化患者无创快速临床诊断研究

Study on Non-Invasive, Rapid Clinical Diagnosis of Spontaneous Hemorrhagic Transformation Patients Using MRI Habitat Imaging Features and Multiparametric Hematological Indices Analysis

摘要: 目的：探讨基于MRI生境成像特征联合多血细胞参数构建在自发性出血转化患者无创快速临床诊断中的应用价值。方法：回顾性收集2022年1月至2025年12月本院收治的急性脑梗死患者300例，根据随访影像学检查结果分为出血转化组和非出血转化组。所有患者均在发病后72小时内完成多参数MRI扫描(包括T1WI、T2WI、DWI、T2GRE/SWI序列)及全血细胞分析。对梗死区域进行生境分区，提取各生境区域的纹理特征、强度特征和形态学特征。同时记录血小板计数、淋巴细胞计数、中性粒细胞计数等多血细胞参数。通过受试者操作特征分析诊断效能。结果：出血转化组患者梗死区域内生境异质性显著高于非出血转化组，其特征表现为特定生境亚区(微环境)的纹理复杂度增加和信号强度异常。多血细胞参数分析显示，出血转化组患者血小板计数显著降低，中性粒细胞–淋巴细胞比值显著升高。结论：基于MRI生境成像特征联合多血细胞参数的诊断能够实现自发性出血转化的无创快速准确诊断，为临床治疗决策提供重要参考。

Abstract: Objective: To investigate the application value of combining MRI habitat imaging features with multiparametric hematological indices for the non-invasive, rapid clinical diagnosis of spontaneous hemorrhagic transformation (HT) patients. Methods: This retrospective study included 300 patients with acute cerebral infarction admitted to our hospital from January 2022 to December 2025. Patients were categorized into HT and non-HT groups based on follow-up imaging findings. All patients underwent multiparametric MRI (including T1WI, T2WI, DWI, T2GRE/SWI sequences) and complete blood cell analysis within 72 hours of symptom onset. The infarct region was segmented into habitats, from which texture, intensity, and morphological features were extracted. Multiparametric hematological indices such as platelet count, lymphocyte count, and neutrophil count were also recorded. Diagnostic efficacy was evaluated using receiver operating characteristic (ROC) analysis. Results: The intralesional habitat heterogeneity was significantly higher in the HT group compared to the non-HT group, characterized by increased texture complexity and abnormal signal intensity within specific habitat subregions (microenvironments). Multiparametric hematological indices analysis revealed significantly lower platelet counts and significantly higher neutrophil-to-lymphocyte ratios in the HT group. Conclusion: The diagnostic approach integrating MRI habitat imaging features and multiparametric hematological indices enables non-invasive, rapid, and accurate assessment of spontaneous HT, providing crucial information for clinical decision-making.