基于平扫CT的多任务学习模型同时分割脑出血与水肿并预测血肿扩大
本研究为多中心回顾性研究,纳入4个中心981例自发性脑出血患者基线平扫CT,429例训练、183例内部验证、369例外部测试。构建基于3D U-Net的多任务模型MTsICHM,同时分割血肿和周围水肿并预测血肿扩大。结果显示血肿分割Dice为0.909,HE预测AUC为0.888。
要点
- MTsICHM可在单次平扫CT上同时量化血肿与周围水肿,无需造影剂
- HE预测敏感度为0.949、特异度为0.710,提示漏判风险较低
- 模型对血肿分割Dice达0.909,与人工分割一致性较高
核心结论
- MTsICHM能从单次平扫CT中准确分割血肿和周围水肿,并有效预测血肿扩大,展现临床应用潜力
研究设计与样本
- 多中心回顾性研究,收集4个中心981例自发性脑出血患者基线平扫CT图像
- 数据划分:429例训练、183例内部验证、369例外部测试
- 采用基于3D U-Net骨干的硬参数共享多任务架构,输入双窗平扫CT
- 模型输出三部分:血肿二值掩膜、周围水肿二值掩膜、血肿扩大二值标签
- 构建4个对照模型进行对比与消融研究:多任务分割对照、多任务分类对照、单任务分割对照、单任务分类对照
关键影像表现/征象
- 模型输出血肿二值掩膜、周围水肿二值掩膜及血肿扩大二值标签三类结果
- 血肿与周围水肿分割表现优于各对照模型
诊断标准与关键数值
- 血肿分割平均Dice为0.909,Intersection over Union为0.872
- 周围水肿分割平均Dice为0.686,Intersection over Union为0.644
- 血肿扩大预测AUC为0.888,准确度为0.765
- 血肿扩大预测敏感度为0.949,特异度为0.710
临床应用与阅片要点
- 可用于急诊平扫CT场景下快速量化血肿及周围水肿体积
- 血肿扩大预测敏感度较高,适合作为初筛或风险评估工具
- 模型输入为双窗平扫CT,报告时可关注血肿与水肿分割结果
局限性
- 本研究为回顾性设计
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: To develop a multi-task learning (MTL) framework for the simultaneous segmentation of spontaneous intracerebral hemorrhage (sICH) and perihematomal edema (PHE), along with the prediction of hematoma expansion (HE).
METHODS: This multicenter retrospective study collected baseline noncontrast CT (NCCT) images of 981 patients with sICH from 4 centers, with 429 cases for training, 183 cases for internal validation, and 369 cases for external testing. A multi-task sICH model (MTsICHM) was designed to simultaneously segment hematoma and PHE and predict HE, which employs a hard parameter-sharing architecture based on a 3D U-Net backbone. The model processes dual-window NCCT inputs and generates 3 outputs: a binary hematoma mask, a binary PHE mask, and a binary HE label. For comparative evaluation and ablation studies, 4 control models were constructed: a multi-task segmentation comparative model, a multi-task classification comparative model, a single-task segmentation comparative model, and a single-task classification comparative model.
RESULTS: For hematoma segmentation, MTsICHM achieved mean Dice of 0.909 and Intersection over Union of 0.872; for PHE segmentation, it attained 0.686 and 0.644, respectively, consistently outperforming the comparative models. For HE prediction, it yielded an AUC of 0.888, with corresponding accuracy, sensitivity, and specificity of 0.765, 0.949, and 0.710.
CONCLUSIONS: The MTsICHM accurately segments hematoma and PHE while effectively predicting HE, demonstrating substantial potential for clinical application.
ADVANCES IN KNOWLEDGE: MTsICHM simultaneously quantifies hematoma and PHE and predicts HE from a single NCCT, with high consistency with manual segmentation and clinical utility for risk identification.
引用
- Zhou, Zhou, Zhou, et al. A non-contrast CT-based multi-task learning framework for co-segmenting hematoma and edema and predicting hematoma expansion in spontaneous intracerebral hemorrhage. Br J Radiol. 2026. PMID: 42565547. doi:10.1093/bjr/tqag179
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。