Shi Huilan, Jia Junya, Li Dong, Wei Li, Shang Wenya, Zheng Zhenfeng
Department of Radiology, Tianjin Medical University General Hospital, No.154, Anshan Road, Heping District, Tianjin, People's Republic of China.
Department of Nephrology, Tianjin Medical University General Hospital, No.154, Anshan Road, Heping District, Tianjin, People's Republic of China.
BMC Nephrol. 2018 Feb 9;19(1):33. doi: 10.1186/s12882-017-0787-z.
Precise renal histopathological diagnosis will guide therapy strategy in patients with lupus nephritis. Blood oxygen level dependent (BOLD) magnetic resonance imaging (MRI) has been applicable noninvasive technique in renal disease. This current study was performed to explore whether BOLD MRI could contribute to diagnose renal pathological pattern.
Adult patients with lupus nephritis renal pathological diagnosis were recruited for this study. Renal biopsy tissues were assessed based on the lupus nephritis ISN/RPS 2003 classification. The Blood oxygen level dependent magnetic resonance imaging (BOLD-MRI) was used to obtain functional magnetic resonance parameter, R2* values. Several functions of R2* values were calculated and used to construct algorithmic models for renal pathological patterns. In addition, the algorithmic models were compared as to their diagnostic capability.
Both Histopathology and BOLD MRI were used to examine a total of twelve patients. Renal pathological patterns included five classes III (including 3 as class III + V) and seven classes IV (including 4 as class IV + V). Three algorithmic models, including decision tree, line discriminant, and logistic regression, were constructed to distinguish the renal pathological pattern of class III and class IV. The sensitivity of the decision tree model was better than that of the line discriminant model (71.87% vs 59.48%, P < 0.001) and inferior to that of the Logistic regression model (71.87% vs 78.71%, P < 0.001). The specificity of decision tree model was equivalent to that of the line discriminant model (63.87% vs 63.73%, P = 0.939) and higher than that of the logistic regression model (63.87% vs 38.0%, P < 0.001). The Area under the ROC curve (AUROCC) of the decision tree model was greater than that of the line discriminant model (0.765 vs 0.629, P < 0.001) and logistic regression model (0.765 vs 0.662, P < 0.001).
BOLD MRI is a useful non-invasive imaging technique for the evaluation of lupus nephritis. Decision tree models constructed using functions of R2* values may facilitate the prediction of renal pathological patterns.
精确的肾脏组织病理学诊断将指导狼疮性肾炎患者的治疗策略。血氧水平依赖（BOLD）磁共振成像（MRI）已成为肾脏疾病中一种适用的非侵入性技术。本研究旨在探讨BOLD MRI是否有助于诊断肾脏病理类型。
招募患有狼疮性肾炎且经肾脏病理诊断的成年患者进行本研究。根据2003年狼疮性肾炎国际肾脏病学会/肾脏病理学会（ISN/RPS）分类对肾活检组织进行评估。使用血氧水平依赖磁共振成像（BOLD-MRI）获取功能磁共振参数R2值。计算R2值的几个函数，并用于构建肾脏病理类型的算法模型。此外，对算法模型的诊断能力进行比较。
组织病理学和BOLD MRI共检查了12例患者。肾脏病理类型包括5例III级（其中3例为III+V级）和7例IV级（其中4例为IV+V级）。构建了三种算法模型，包括决策树、线性判别和逻辑回归，以区分III级和IV级肾脏病理类型。决策树模型的敏感性优于线性判别模型（71.87%对59.
