利用深度学习进行CT扫描中硬脑膜下出血的检测与定位
Detection and Localization of Subdural Hematoma Using Deep Learning on Computed Tomography
AI总结：
本文提出一种多模态深度学习框架，结合临床数据与CT影像，实现硬脑膜下出血的快速准确检测与定位，提升神经外科急诊处理效率。
摘要：
背景。硬脑膜下出血（SDH）是一种常见的神经外科急诊，其在老年人群中的发病率呈上升趋势。快速而准确的识别对于指导及时干预至关重要，但现有的自动化工具主要集中在检测上，提供有限的可解释性或空间定位能力。仍然需要一种透明、高性能的系统，能够整合多模态的临床和影像信息，以支持实时决策。方法。我们开发了一个多模态深度学习框架，该框架整合了结构化临床变量、在CT体积上训练的3D卷积神经网络，以及增强变压器的2D分割模型，用于SDH的检测和定位。使用哈特福德医疗保健（Hartford HealthCare）2015-2024年的25,315例头部CT研究，其中3,774例（14.9%）包含临床确认的SDH，表格模型在人口统计学、共病、药物和实验室结果上进行训练。影像模型用于检测SDH并生成体素级概率图。一种贪婪集成策略结合了互补的预测器。发现。仅临床变量提供了有限的区分能力（AUC 0.75）。在CT体积上训练的卷积模型和分割衍生的地图实现了显著更高的准确性（AUCs 0.922和0.926）。整合所有组件的多模态集成实现了最佳整体性能（AUC 0.9407；95%CI，0.930-0.951），并产生了具有解剖学意义的定位图，与已知的SDH模式一致。解释。这种多模态、可解释的框架能够快速而准确地检测和定位SDH，实现了高检测性能，并提供了透明、具有解剖学基础的输出。将其整合到放射科工作流程中可以加快分诊，减少干预时间，并提高SDH管理的一致性。
英文摘要：
Background. Subdural hematoma (SDH) is a common neurosurgical emergency, with increasing incidence in aging populations. Rapid and accurate identification is essential to guide timely intervention, yet existing automated tools focus primarily on detection and provide limited interpretability or spatial localization. There remains a need for transparent, high-performing systems that integrate multimodal clinical and imaging information to support real-time decision-making. Methods. We developed a multimodal deep-learning framework that integrates structured clinical variables, a 3D convolutional neural network trained on CT volumes, and a transformer-enhanced 2D segmentation model for SDH detection and localization. Using 25,315 head CT studies from Hartford HealthCare (2015--2024), of which 3,774 (14.9\%) contained clinician-confirmed SDH, tabular models were trained on demographics, comorbidities, medications, and laboratory results. Imaging models were trained to detect SDH and generate voxel-level probability maps. A greedy ensemble strategy combined complementary predictors. Findings. Clinical variables alone provided modest discriminatory power (AUC 0.75). Convolutional models trained on CT volumes and segmentation-derived maps achieved substantially higher accuracy (AUCs 0.922 and 0.926). The multimodal ensemble integrating all components achieved the best overall performance (AUC 0.9407; 95\% CI, 0.930--0.951) and produced anatomically meaningful localization maps consistent with known SDH patterns. Interpretation. This multimodal, interpretable framework provides rapid and accurate SDH detection and localization, achieving high detection performance and offering transparent, anatomically grounded outputs. Integration into radiology workflows could streamline triage, reduce time to intervention, and improve consistency in SDH management.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
