基于卷积神经网络的经鼻垂体腺瘤切除术中脑脊液漏预测模型
该研究回顾性纳入2007年1月至2023年3月在本机构接受内镜下经鼻蝶手术且有术前立体定向MRI的220例成人患者,其中81例(36.8%)发生术中脑脊液漏。经典统计分析显示视觉障碍是唯一有统计学意义的术前危险因素(P=0.008)。训练的二维卷积神经网络模型预测脑脊液漏的准确率为92%,受试者工作特征曲线下面积为0.90(敏感度86%,特异度93%)。
要点
- 220例患者中81例(36.8%)发生术中脑脊液漏。
- 视觉障碍是唯一有统计学意义的术前临床危险因素(P=0.008)。
- 二维卷积神经网络模型预测脑脊液漏准确率92%,AUC 0.90,敏感度86%,特异度93%。
核心结论
- 二维卷积神经网络模型可帮助治疗团队更好地预判和准备术中脑脊液漏。
- 类激活映射显示鞍膈、床突、颞角及视神经区域与术中脑脊液漏风险有解剖学关联。
- 视交叉解剖受压所致的视觉障碍是唯一被识别的临床危险因素。
研究设计与样本
- 回顾性研究,纳入2007年1月至2023年3月在本机构接受内镜下经鼻蝶手术且有可获取术前立体定向MRI的220例成人患者。
- 采用经典统计学分析识别术中脑脊液漏的人口学、临床及解剖危险因素。
- 使用立体定向T2加权脑MRI扫描训练和测试二维卷积神经网络模型。
主要发现
- 220例患者中81例(36.8%)发生术中脑脊液漏。
- 在所有术前变量中,视觉障碍是唯一有统计学意义的危险因素(P=0.008)。
- 训练的二维卷积神经网络模型预测脑脊液漏准确率为92%,受试者工作特征曲线下面积为0.90(敏感度86%,特异度93%)。
- 该模型的类激活映射显示脑脊液流动的解剖区域在预测脑脊液漏中最重要。
- 进一步审查类激活映射梯度显示鞍膈、床突、颞角和视神经区域与术中脑脊液漏风险有解剖学关联。
临床怎么用
- 作者认为二维卷积神经网络模型可帮助治疗团队更好地预判和准备术中脑脊液漏。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Cerebrospinal fluid (CSF) leak during endoscopic endonasal transsphenoidal surgery can lead to postoperative complications. The clinical and anatomic risk factors of intraoperative CSF leak are not well defined. We applied a two-dimensional (2D) convolutional neural network (CNN) machine learning model to identify risk factors from preoperative magnetic resonance imaging. METHODS: All adults who underwent endoscopic endonasal transsphenoidal surgery at our institution from January 2007 to March 2023 who had accessible preoperative stereotactic magnetic resonance imaging were included. A retrospective classic statistical analysis was performed to identify demographic, clinical, and anatomic risk factors of intraoperative CSF leak. Stereotactic T2-weighted brain magnetic resonance imaging scans were used to train and test a 2D CNN model. RESULTS: Of 220 included patients, 81 (36.8%) experienced intraoperative CSF leak. Among all preoperative variables, visual disturbance was the only statistically significant identified risk factor (P = 0.008). The trained 2D CNN model predicted CSF leak with 92% accuracy and area under receiver operating characteristic curve of 0.90 (sensitivity of 86% and specificity of 93%). Class activation mapping of this model revealed that anatomic regions of CSF flow were most important in predicting CSF leak. CONCLUSIONS: Further review of the class activation mapping gradients revealed regions of the diaphragma sellae, clinoid processes, temporal horns, and optic nerves to have anatomic correlation to intraoperative CSF leak risk. Additionally, visual disturbances from anatomic compression of the optic chiasm were the only identified clinical risk factor. Our 2D CNN model can help a treating team to better anticipate and prepare for intraoperative CSF leak.
引用
- Behzadi F, Alhusseini M, Yang SD, et al. A Predictive Model for Intraoperative Cerebrospinal Fluid Leak During Endonasal Pituitary Adenoma Resection Using a Convolutional Neural Network. World Neurosurg. 2024. PMID: 38876190. doi:10.1016/j.wneu.2024.06.043
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。