Page 115 - 南京医科大学自然版

第44卷第12期 南京医科大学学报（自然科学版）
2024年12月 Journal of Nanjing Medical University（Natural Sciences） ·1729 ·

·临床研究·

基于T2WI和DWI影像组学在术前预测垂体腺瘤质地中的应用

价值

夏志伟 ，苏春秋 ，王彬彬 ，陶 超 ，鲁珊珊 ，洪汛宁 1*
1
1
2
2
1
南京医科大学第一附属医院放射科，神经外科，江苏 南京 210029
1 2
［摘 要］ 目的：探讨基于T2WI和DWI影像组学在术前无创预测垂体腺瘤质地中的应用价值。方法：回顾性分析经病理证
实为垂体腺瘤的108例患者临床及术前MRI资料，术中2名神经外科医生评估肿瘤质地，将其分为质软组和质硬组。按7∶3随
机分为训练组和验证组，在 T2WI 和 DWI 图像上手动勾画肿瘤实质区的体积作为感兴趣区容积（volume of interest，VOI），用
FeAture Explorer软件提取特征，采用无监督特征选择（unsupervised feature selection，UFS）进行特征筛选，采用支持向量机（sup⁃
port vector machine，SVM）构建影像组学模型。通过受试者工作特征曲线下面积（area under curve，AUC）及校准曲线评估模型
的效能。结果：在联合T2WI和DWI影像组学模型中，训练组预测垂体腺瘤质地的AUC为0.89，验证组的AUC为0.80。校准曲线
显示模型预测值与实际值一致性较好。结论：联合T2WI和DWI影像组学模型具有较好的诊断效能，有助于术前预测垂体腺瘤的
质地。
［关键词］ 垂体腺瘤；影像组学；磁共振成像

［中图分类号］ R445.2 ［文献标志码］ A ［文章编号］ 1007⁃4368（2024）12⁃1729⁃06
doi：10.7655/NYDXBNSN240381

Application value of radiomics based on T2WI and DWI in preoperative prediction of
pituitary adenoma consistency
1 1 2 2 1 1*
XIA Zhiwei ，SU Chunqiu ，WANG Binbin ，TAO Chao ，LU Shanshan ，HONG Xunning
1 2
Department of Radiology，Department of Neurosurgery，the First Affiliated Hospital of Nanjing Medical University，
Nanjing 210029，China

［Abstract］ Objective：To explore the application value of radiomics based on T2⁃weighted imaging（T2WI）and diffusion⁃weighted
imaging（DWI）in non⁃invasive preoperative prediction of pituitary adenoma consistency. Methods：The clinical and preoperative MRI
data of 108 patients with pathologically confirmed pituitary adenoma were retrospectively analyzed. Two neurosurgeons evaluated
tumor consistency intraoperatively and categorized them into soft and hard groups. Patients were randomly divided into a training set
and a validation set in a 7∶3 ratio. Volume of interest（VOI）representing the tumor solid component were manually delineated on
T2WI and DWI images. Radiomics features were extracted by FeAture Explorer software. Unsupervised feature selection（UFS）was
applied for feature selection. Support vector machine（SVM）was used to conduct the radiomics models. Area under curve（AUC）and
calibration curve were used to assess the performance of the models. Results：In the combined T2WI and DWI radiomics model，the
AUC for predicting the consistency of pituitary adenoma was 0.89 in the training set and 0.80 in the validation set. The calibration
curve showed a good consistency between predicted and actual values. Conclusion：The combined T2WI and DWI radiomics model
demonstrates good diagnostic performance and aids in preoperative prediction of the consistency of pituitary adenoma.
［Key words］ pituitary adenoma；radiomics；magnetic resonance imaging
［J Nanjing Med Univ，2024，44（12）：1729⁃1734］

垂体腺瘤是鞍区最常见的病变，在脑肿瘤中排
［基金项目］ 江苏高校优势学科建设工程三期项目［苏政办
［1］
发〔2018〕87号］ 名第 3 。内镜下经鼻蝶窦手术已被公认为首选的
［2］
∗ 手术方法 。绝大多数的腺瘤质地柔软，易于完整
通信作者（Corresponding author），E⁃mail：hongxunning@sina.com