基于深度学习框架利用头颅平扫CT预测脑出血血肿扩大
本研究基于2484例来自84个中心的回顾性数据和500例来自26个中心的前瞻性数据,开发两阶段深度学习框架,仅用入院头颅平扫CT预测脑出血血肿扩大(定义为随访CT血肿体积增加超过6 mL)。框架在回顾性验证集AUC为0.760(95%CI 0.724-0.799),在前瞻性集AUC为0.806(95%CI 0.750-0.859),均优于BAT评分(AUC分别为0.582和0.699)。
要点
- 两阶段深度学习框架仅用入院平扫CT即可自动预测血肿扩大,前瞻性集AUC 0.806。
- 框架在回顾性验证集AUC 0.760(95%CI 0.724-0.799),优于BAT评分的0.582。
- 血肿扩大定义为随访平扫CT血肿体积增加超过6 mL,随访在症状发作后48小时内完成。
核心结论
- 该框架能自动、稳健地利用入院头颅平扫CT识别血肿扩大高风险患者,预测比BAT评分更准确。
研究设计与样本
- 回顾性数据集n=2484来自84个中心,前瞻性数据集n=500来自26个额外中心;基线平扫CT在症状发作后6小时内完成,随访平扫CT在48小时内完成;回顾性数据集按患者纳入时间分为训练集n=1876和验证集n=608;训练两阶段框架预测血肿扩大,在验证集和前瞻性集评估性能。
诊断标准与关键数值
- 血肿扩大定义为随访平扫CT血肿体积增加超过6 mL;框架在回顾性验证集AUC 0.760(95%CI 0.724-0.799),在前瞻性集AUC 0.806(95%CI 0.750-0.859);BAT评分在回顾性验证集AUC 0.582,在前瞻性集AUC 0.699。
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)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Hematoma expansion (HE) in intracerebral hemorrhage (ICH) is a critical factor affecting patient outcomes, yet effective clinical tools for predicting HE are currently lacking. We aim to develop a fully automated framework based on deep learning for predicting HE using only clinical non-contrast CT (NCCT) scans.
MATERIALS AND METHODS: A large retrospective dataset (n = 2484) was collected from 84 centers, while a prospective dataset (n = 500) was obtained from 26 additional centers. Baseline NCCT scans and follow-up NCCT scans were conducted within 6 h and 48 h from symptom onset, respectively. HE was defined as a volume increase of more than 6 mL on the follow-up NCCT. The retrospective dataset was divided into a training set (n = 1876) and a validation set (n = 608) by patient inclusion time. A two-stage framework was trained to predict HE, and its performance was evaluated on both the validation and prospective sets. Receiver operating characteristics area under the curve (AUC), sensitivity, and specificity were leveraged.
RESULTS: Our two-stage framework achieved an AUC of 0.760 (95% CI 0.724-0.799) on the retrospective validation set and 0.806 (95% CI 0.750-0.859) on the prospective set, outperforming the commonly used BAT score, which had AUCs of 0.582 and 0.699, respectively.
CONCLUSION: Our framework can automatically and robustly identify ICH patients at high risk of HE using admission head NCCT scans, providing more accurate predictions than the BAT score.
引用
- Li N, Ding S, Liu Z, et al. A Deep Learning-Based Framework for Predicting Intracerebral Hematoma Expansion Using Head Non-contrast CT Scan. Acad Radiol. 2024. PMID: 39107191. doi:10.1016/j.acra.2024.07.039
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。