深度学习2.5维单次检测器提高对比增强CT上脑转移瘤自动检测的性能
本研究基于127例患者的127次对比增强CT扫描中的696个脑转移瘤,构建并比较了2维与2.5维深度学习单次检测器模型,以50%置信阈值评估。2.5维模型阳性预测值显著高于2维模型(58.9%对39.0%,p<0.001),每例患者假阳性数显著减少(4.9对11.9,p<0.001),敏感度分别为88.7%与88.1%。结论提示利用相邻层面连续信息的2.5维模型可能减少假阳性并提升自动检测性能。
要点
- 2.5维模型利用相邻层面信息,在50%置信阈值下阳性预测值58.9%高于2维模型39.0%。
- 每例患者假阳性数2.5维模型4.9个,显著少于2维模型11.9个。
- 两模型敏感度相近,2.5维88.7%、2维88.1%,提示主要改善在减少假阳性。
核心结论
- 利用相邻层面连续信息的2.5维深度学习目标检测模型,相比普通2维模型可能减少假阳性并提高对比增强CT上脑转移瘤自动检测的性能。
研究设计与样本
- 回顾性分析127例脑转移瘤患者的127次对比增强CT扫描,共696个脑转移瘤,随机分为训练集79例、验证集18例、测试集30例;构建带特征融合模块的单次检测器(SSD)模型,在50%置信阈值下比较基于病灶的敏感度、阳性预测值和每例患者假阳性数。
诊断标准与关键数值
- 在50%置信阈值下,2维模型敏感度88.1%(95%CI 86.6-89.6%)、阳性预测值39.0%(95%CI 36.5-41.4%)、每例患者假阳性数11.9(95%CI 10.7-13.2);2.5维模型敏感度88.7%(95%CI 87.3-90.1%)、阳性预测值58.9%(95%CI 55.2-62.7%)、每例患者假阳性数4.9(95%CI 4.2-5.7)。
临床应用与阅片要点
- 在对比增强CT上自动检测脑转移瘤时,采用2.5维深度学习模型可利用相邻层面连续性信息,在保持敏感度相近的同时减少假阳性,阳性预测值更高。
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
PURPOSE: This study aims to develop a 2.5-dimensional (2.5D) deep-learning, object detection model for the automated detection of brain metastases, into which three consecutive slices were fed as the input for the prediction in the central slice, and to compare its performance with that of an ordinary 2-dimensional (2D) model.
METHODS: We analyzed 696 brain metastases on 127 contrast-enhanced computed tomography (CT) scans from 127 patients with brain metastases. The scans were randomly divided into training (n = 79), validation (n = 18), and test (n = 30) datasets. Single-shot detector (SSD) models with a feature fusion module were constructed, trained, and compared using the lesion-based sensitivity, positive predictive value (PPV), and the number of false positives per patient at a confidence threshold of 50%.
RESULTS: The 2.5D SSD model had a significantly higher PPV (t test, p < 0.001) and a significantly smaller number of false positives (t test, p < 0.001). The sensitivities of the 2D and 2.5D models were 88.1% (95% confidence interval [CI], 86.6-89.6%) and 88.7% (95% CI, 87.3-90.1%), respectively. The corresponding PPVs were 39.0% (95% CI, 36.5-41.4%) and 58.9% (95% CI, 55.2-62.7%), respectively. The numbers of false positives per patient were 11.9 (95% CI, 10.7-13.2) and 4.9 (95% CI, 4.2-5.7), respectively.
CONCLUSION: Our results indicate that 2.5D deep-learning, object detection models, which use information about the continuity between adjacent slices, may reduce false positives and improve the performance of automated detection of brain metastases compared with ordinary 2D models.
引用
- Takao, Amemiya, Kato, et al. Deep-learning 2.5-dimensional single-shot detector improves the performance of automated detection of brain metastases on contrast-enhanced CT. Neuroradiology. 2022. PMID: 35064786. doi:10.1007/s00234-022-02902-3
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。