Fu Zunfeng, Wang Jing, Shen Wenyi, Wu Yanqing, Zhang Jiajun, Liu Yan, Wang Chongqiang, Shen Yanlin, Zhu Ye, Zhang Weifu, Lv Chunju, Peng Lin
Department of Ultrasound, The Second Affiliated Hospital of Shandong First Medical University, No. 366 Taishan Street, Taishan District, Tai'an, 271000, Shandong Province, China.
Department of Ultrasound, The Affiliated Hospital of Qilu Medical University, Xintai, China.
Sci Rep. 2025 Jul 2;15(1):23595. doi: 10.1038/s41598-025-09115-7.
To evaluate the effectiveness of deep learning radiomics nomogram in distinguishing early intracranial hypertension (IH) following primary decompressive craniectomy (DC) in patients with severe traumatic brain injury (TBI) and to demonstrate its potential clinical value as a noninvasive tool for guiding timely intervention and improving patient outcomes. This study included 238 patients with severe TBI (training cohort: n = 166; testing cohort: n = 72). Postoperative ultrasound images of the optic nerve sheath (ONS) and Spectral doppler imaging of middle cerebral artery (MCASDI) were obtained at 6 and 18 h after DC. Patients were grouped according to threshold values of 15 mmHg and 20 mmHg based on invasive intracranial pressure (ICPi) measurements. Clinical-semantic features were collected, and radiomics features were extracted from ONS images, and Additionally, deep transfer learning (DTL) features were generated using RseNet101. Predictive models were developed using the Light Gradient Boosting Machine (light GBM) machine learning algorithm. Clinical-ultrasound variables were incorporated into the model through univariate and multivariate logistic regression. A combined nomogram was developed by integrating DLR (deep learning radiomics) features with clinical-ultrasound variables, and its diagnostic performance over different thresholds was evaluated using Receiver Operating Characteristic (ROC) curve analysis and decision curve analysis (DCA). The nomogram model demonstrated superior performance over the clinical model at both 15 mmHg and 20 mmHg thresholds. For 15 mmHg, the AUC was 0.974 (95% confidence interval [CI]: 0.953-0.995) in the training cohort and 0.919 (95% CI: 0.845-0.993) in the testing cohort. For 20 mmHg, the AUC was 0.968 (95% CI: 0.944-0.993) in the training cohort and 0.889 (95% CI: 0.806-0.972) in the testing cohort. DCA curves showed net clinical benefit across all models. Among DLR models based on ONS, MCASDI, or their pre-fusion, the ONS-based model performed best in the testing cohorts. The nomogram model, incorporating clinical-semantic features, radiomics, and DTL features, exhibited promising performance in predicting early IH in post-DC patients. It shows promise for enhancing non-invasive ICP monitoring and supporting individualized therapeutic strategies.
评估深度学习影像组学列线图在鉴别重度创伤性脑损伤（TBI）患者初次减压颅骨切除术（DC）后早期颅内高压（IH）中的有效性，并证明其作为指导及时干预和改善患者预后的非侵入性工具的潜在临床价值。本研究纳入了238例重度TBI患者（训练队列：n = 166；测试队列：n = 72）。在DC术后6小时和18小时获取视神经鞘（ONS）的术后超声图像和大脑中动脉频谱多普勒成像（MCASDI）。根据有创颅内压（ICPi）测量值的15 mmHg和20 mmHg阈值对患者进行分组。收集临床语义特征，并从ONS图像中提取影像组学特征，此外，使用RseNet101生成深度迁移学习（DTL）特征。使用轻梯度提升机（light GBM）机器学习算法开发预测模型。通过单变量和多变量逻辑回归将临床超声变量纳入模型。通过将深度学习影像组学（DLR）特征与临床超声变量相结合，开发了一个联合列线图，并使用受试者操作特征（ROC）曲线分析和决策曲线分析（DCA）评估其在不同阈值下的诊断性能。在15 mmHg和20 mmHg阈值下，列线图模型均表现出优于临床模型的性能。对于15 mmHg，训练队列中的AUC为0.974（95%置信区间[CI]：0.953 - 0.995），测试队列中的AUC为0.919（95% CI：0.845 - 0.993）。对于20 mmHg，训练队列中的AUC为0.968（95% CI：0.944 - 0.993），测试队列中的AUC为0.889（95% CI：0.806 - 0.972）。DCA曲线显示所有模型均有净临床获益。在基于ONS、MCASDI或其预融合的DLR模型中，基于ONS的模型在测试队列中表现最佳。纳入临床语义特征、影像组学和DTL特征的列线图模型在预测DC术后患者的早期IH方面表现出良好的性能。它在增强非侵入性颅内压监测和支持个体化治疗策略方面显示出前景。
