基于nnU-Net的深度学习用于肺栓塞检测、血栓体积量化及与严重程度的相关性:RSPECT数据集研究
本研究在RSPECT数据集上评估本地开发的nnU-Net算法检测肺栓塞、测量血栓体积及与右心室负荷相关性的性能。训练集含205例肺栓塞和340例阴性,测试集6573例检查。模型检测肺栓塞AUC为0.865,中心性肺栓塞检测AUC为0.937,右心室负荷过载AUC为0.848;血栓体积与肺栓塞存在、中心性肺栓塞及右心室/左心室比值升高显著相关。
要点
- nnU-Net模型检测肺栓塞AUC为0.865,中心性肺栓塞AUC达0.937
- 血栓体积与肺栓塞存在、中心性肺栓塞及右心室负荷过载显著相关
- 血栓体积可作为自动严重程度分层和病例优先级排序的指标
核心结论
- nnU-Net算法展示了准确的肺栓塞检测能力,尤其对中心性肺栓塞;血栓体积是自动严重程度分层和病例优先级排序的准确指标。
研究设计与样本
- 研究使用RSPECT数据集,训练集含205例肺栓塞和340例阴性检查,测试集含6573例检查;用户输入仅限于使用3DSlicer进行分割;采用ROC曲线和逻辑回归进行统计验证。
诊断标准与关键数值
- 肺栓塞检测AUC为0.865,在55 μL阈值下准确率为83%
- 中心性肺栓塞检测AUC为0.937,在850 μL阈值下准确率为91%
- 右心室负荷过载AUC为0.848,准确率为79%
- 阴性检查血栓体积中位数为1 μL,肺栓塞阳性病例为345 μL,中心性肺栓塞为7378 μL
- 血栓体积与肺栓塞存在、中心性肺栓塞及右心室/左心室比值升高显著相关(p < 0.0001)
临床应用与阅片要点
- nnU-Net框架可用于构建可靠的肺栓塞深度学习检测工具,为缺乏AI专业知识者提供用户友好方法并快速提取血栓体积以评估肺栓塞严重程度。
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
OBJECTIVES: CT pulmonary angiography is the gold standard for diagnosing pulmonary embolism, and DL algorithms are being developed to manage the increase in demand. The nnU-Net is a new auto-adaptive DL framework that minimizes manual tuning, making it easier to develop effective algorithms for medical imaging even without specific expertise. This study assesses the performance of a locally developed nnU-Net algorithm on the RSPECT dataset for PE detection, clot volume measurement, and correlation with right ventricle overload.
MATERIALS & METHODS: User input was limited to segmentation using 3DSlicer. We worked with the RSPECT dataset and trained an algorithm from 205 PE and 340 negatives. The test dataset comprised 6573 exams. Performance was tested against PE characteristics, such as central, non-central, and RV overload. Blood clot volume (BCV) was extracted from each exam. We employed ROC curves and logistic regression for statistical validation.
RESULTS: Negative studies had a median BCV of 1 μL, which increased to 345 μL in PE-positive cases and 7,378 μL in central PEs. Statistical analysis confirmed a significant BCV correlation with PE presence, central PE, and increased RV/LV ratio (p < 0.0001). The model's AUC for PE detection was 0.865, with an 83 % accuracy at a 55 μL threshold. Central PE detection AUC was 0.937 with 91 % accuracy at 850 μL. The RV overload AUC stood at 0.848 with 79 % accuracy.
CONCLUSION: The nnU-Net algorithm demonstrated accurate PE detection, particularly for central PE. BCV is an accurate metric for automated severity stratification and case prioritization.
CLINICAL RELEVANCE STATEMENT: The nnU-Net framework can be utilized to create a dependable DL for detecting PE. It offers a user-friendly approach to those lacking expertise in AI and rapidly extracts the Blood Clot Volume, a metric that can evaluate the PE's severity.
引用
- Lanza E, Ammirabile A, Francone M, et al. nnU-Net-based deep-learning for pulmonary embolism: detection, clot volume quantification, and severity correlation in the RSPECT dataset. Eur J Radiol. 2024. PMID: 38968751. doi:10.1016/j.ejrad.2024.111592
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。