基于Swin Transformer的全自动深度学习流程用于动脉瘤性蛛网膜下腔出血后头颅CT血液分割
本研究回顾性分析确诊动脉瘤性蛛网膜下腔出血患者的平扫CT,采用基于Swin-UNETR架构的人工智能全自动血肿分割工具,并与人工分割金标准对比。模型在内部和外部验证队列中均表现高准确度,Dice系数0.873±0.097,敏感度0.821±0.217,特异度0.996±0.004,处理速度快,但计算需求较高,需进一步在多数据集验证临床可靠性。
要点
- Swin-UNETR模型在动脉瘤性蛛网膜下腔出血平扫CT上自动分割血液,Dice系数0.873±0.097。
- 外部验证队列中模型仍保持稳健性能,提示一定泛化能力。
- 模型处理速度快,在标准硬件上运行,但计算需求较高。
核心结论
- 基于Swin UNETR的模型在动脉瘤性蛛网膜下腔出血患者平扫CT图像自动血液分割方面取得显著进展。
- 尽管计算需求较高,模型在标准硬件上有效运行且界面友好,有助于更广泛的临床采用。
- 需要在多样数据集上进一步验证以确认其临床可靠性。
研究设计与样本
- 回顾性分析确诊动脉瘤性蛛网膜下腔出血患者的平扫CT扫描,使用Swin-UNETR进行分割。
- 纳入外部机构验证队列以测试模型的泛化能力。
- 以人工分割金标准数据为参照,采用Dice评分、交并比、体积相似指数、对称平均表面距离、敏感度和特异度等指标评估性能。
主要发现
- 模型在内部和外部验证队列中均表现出高准确度和稳健的性能指标。
- Dice系数0.873±0.097,交并比0.810±0.092,体积相似指数0.840±0.131。
- 敏感度0.821±0.217,特异度0.996±0.004,对称平均表面距离1.866±2.910。
- 模型处理速度体现其具备实时应用的潜力。
临床怎么用
- 原文结论未据此给出具体临床推荐。
局限性
- 需要在多样数据集上进一步验证以确认其临床可靠性。
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)。
原文
BACKGROUND: Accurate volumetric assessment of spontaneous aneurysmal subarachnoid hemorrhage (aSAH) is a labor-intensive task performed with current manual and semiautomatic methods that might be relevant for its clinical and prognostic implications. In the present research, we sought to develop and validate an artificial intelligence-driven, fully automated blood segmentation tool for subarachnoid hemorrhage (SAH) patients via noncontrast computed tomography (NCCT) scans employing a transformer-based Swin-UNETR architecture. METHODS: We retrospectively analyzed NCCT scans from patients with confirmed aSAH utilizing the Swin-UNETR for segmentation. The performance of the proposed method was evaluated against manually segmented ground truth data using metrics such as Dice score, intersection over union, volumetric similarity index , symmetric average surface distance , sensitivity, and specificity. A validation cohort from an external institution was included to test the generalizability of the model. RESULTS: The model demonstrated high accuracy with robust performance metrics across the internal and external validation cohorts. Notably, it achieved high Dice coefficient (0.873 ± 0.097), intersection over union (0.810 ± 0.092), volumetric similarity index (0.840 ± 0.131), sensitivity (0.821 ± 0.217), and specificity (0.996 ± 0.004) values and a low symmetric average surface distance (1.866 ± 2.910), suggesting proficiency in segmenting blood in SAH patients. The model's efficiency was reflected in its processing speed, indicating potential for real-time applications. CONCLUSIONS: Our Swin UNETR-based model offers significant advances in the automated segmentation of blood in SAH patients on NCCT images. Despite the computational demands, the model operates effectively on standard hardware with a user-friendly interface, facilitating broader clinical adoption. Further validation across diverse datasets is warranted to confirm its clinical reliability.
引用
- García-García S, Cepeda S, Arrese I, et al. A Fully Automated Pipeline Using Swin Transformers for Deep Learning-Based Blood Segmentation on Head Computed Tomography Scans After Aneurysmal Subarachnoid Hemorrhage. World Neurosurg. 2024. PMID: 39111661. doi:10.1016/j.wneu.2024.07.216
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。