深度学习单次检测器联合增强与非增强CT自动检测脑转移瘤
本研究纳入116例患者的116次CT扫描(共659个脑转移灶),构建结合增强与非增强CT图像的双输入单次检测器(SSD)模型,并与仅用增强CT的模型比较。结果显示双输入模型的阳性预测值显著更高(44.0% vs 37.2%,p<0.001)、每患者假阳性数显著更少(9.9 vs 13.6,p<0.001),敏感度有升高趋势(88.7% vs 87.6%,p=0.14)。结论提示利用增强与非增强图像对比获得的真实强化信息可抑制假病灶、减少假阳性。
要点
- 联合增强与非增强CT的双输入模型可显著提高脑转移瘤检测的阳性预测值并减少假阳性。
- 双输入模型敏感度88.7%,略高于单用增强CT模型的87.6%,但差异无统计学意义。
- 阅片时对比增强前后的真实强化信息有助于鉴别假病灶,减少假阳性报告。
核心结论
- 联合增强与非增强CT图像的深度学习检测模型较单用增强CT模型显著提高阳性预测值并显著减少每患者假阳性数,敏感度有升高趋势但未达统计学显著。
- 对比增强与非增强图像获得的真实强化信息可能防止假病灶检出、抑制假阳性并改善深度学习检测模型性能。
研究设计与样本
- 回顾性研究,纳入116例脑转移瘤患者的116次CT扫描,共659个转移灶。
- 428个病灶用于训练与验证(平均大小11.3±9.9 mm),231个用于测试(平均大小9.0±7.0 mm)。
- 构建带特征融合模块的单次检测器(SSD)模型,以50%置信度阈值按病灶比较双输入模型(CE+NECT)与单用增强CT模型(CECT)的性能。
诊断标准与关键数值
- CE+NECT模型敏感度88.7%,阳性预测值44.0%,每患者假阳性数9.9。
- CECT模型敏感度87.6%,阳性预测值37.2%,每患者假阳性数13.6。
- CE+NECT模型阳性预测值显著更高(t检验,p<0.001),假阳性数显著更少(t检验,p<0.001),敏感度有升高趋势(t检验,p=0.14)。
- 检测结果按病灶在50%置信度阈值下比较。
临床应用与阅片要点
- 在脑转移瘤自动检测中,同时输入增强与非增强CT图像有助于利用真实强化信息抑制假病灶,减少假阳性。
- 阅片和报告时可关注增强前后对比的真实强化表现,以鉴别类似转移灶的假病灶。
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: To develop a deep-learning object detection model for automatic detection of brain metastases that simultaneously uses contrast-enhanced and non-enhanced images as inputs, and to compare its performance with that of a model that uses only contrast-enhanced images.
METHOD: A total of 116 computed tomography (CT) scans of 116 patients with brain metastases were included in this study. They showed a total of 659 metastases, 428 of which were used for training and validation (mean size, 11.3 ± 9.9 mm) and 231 were used for testing (mean size, 9.0 ± 7.0 mm). Single-shot detector (SSD) models were constructed with a feature fusion module, and their results were compared per lesion at a confidence threshold of 50%.
RESULTS: The sensitivity was 88.7% for the model that used both contrast-enhanced and non-enhanced CT images (the CE + NECT model) and 87.6% for the model that used only contrast-enhanced CT images (the CECT model). The positive predictive value (PPV) was 44.0% for the CE + NECT model and 37.2% for the CECT model. The number of false positives per patient was 9.9 for the CE + NECT model and 13.6 for the CECT model. The CE + NECT model had a significantly higher PPV (t test, p < 0.001), significantly fewer false positives (t test, p < 0.001), and a tendency to be more sensitive (t test, p = 0.14).
CONCLUSIONS: The results indicate that the information on true contrast enhancement obtained by comparing the contrast-enhanced and non-enhanced images may prevent the detection of pseudolesions, suppress false positives, and improve the performance of deep-learning object detection models.
引用
- Takao, Amemiya, Kato, et al. Deep-learning single-shot detector for automatic detection of brain metastases with the combined use of contrast-enhanced and non-enhanced computed tomography images. Eur J Radiol. 2021. PMID: 34742108. doi:10.1016/j.ejrad.2021.110015
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。