深度学习特征融合单阶段检测器在增强CT上自动检测脑转移瘤
研究纳入127例患者的127次增强CT,由三位放射科医师半自动标注,用97次扫描训练有无特征融合模块的单阶段检测器(SSD),在剩余30次扫描上以50%置信度阈值评估。特征融合SSD总体敏感度88.1%、阳性预测值36.0%、每扫描假阳性13.8;>6 mm病灶敏感度97.4%,3–6 mm为80.0%,<3 mm仅23.1%。
要点
- 特征融合SSD对>6 mm脑转移瘤敏感度97.4%,3–6 mm为80.0%,<3 mm仅23.1%。
- 总体阳性预测值36.0%,每扫描假阳性13.8,阅片时需结合临床排除假阳性。
- 特征融合SSD总体敏感度显著高于基线SSD(p=0.03),<3 mm病灶敏感度亦显著更高(p=0.002)。
诊断标准与关键数值
- 特征融合SSD总体敏感度88.1%(95%CI 85.2%–88.6%;214/243),阳性预测值36.0%(95%CI 33.7%–37.1%;233/648),每扫描假阳性13.8(95%CI 12.7–15.0)。
- <3 mm病灶敏感度23.1%(95%CI 21.2%–40.0%;3/13),每扫描假阳性0.2(95%CI 0.23–0.65)。
- 3–6 mm病灶敏感度80.0%(95%CI 76.0%–79.8%;60/75),每扫描假阳性5.8(95%CI 5.0–6.2)。
- >6 mm病灶敏感度97.4%(95%CI 94.1%–97.4%;151/155),每扫描假阳性7.9(95%CI 7.2–8.5)。
- 特征融合SSD总体敏感度(p=0.03,t=2.75)及<3 mm病灶敏感度(p=0.002,t=4.49)均显著高于基线SSD,总体阳性预测值相似(p=0.96,t=-0.02)。
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: Despite the potential usefulness, no automatic detector is available for brain metastases on contrast-enhanced CT (CECT). The study aims to develop and investigate deep learning-based detectors for brain metastases detection on CECT.
METHOD: The study included 127 CECTs from 127 patients (65.5 years±11.1; 87 men). The ground-truth annotation was performed semi-automatically by applying connected-component analysis to the binarized dataset by three radiologists. Single-shot detector (SSD) algorithms, with and without a feature-fusion module, were developed and trained using 97 scans. The performance was evaluated at the detector's 50 % confidence threshold with the remaining 30 scans using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR).
RESULTS: Feature-fused SSD achieved an overall sensitivity of 88.1 % (95 % confidence interval [CI]: [85.2 %,88.6 %]; 214/243) and PPV of 36.0 % (95 % CI: [33.7 %,37.1 %]; 233/648), with 13.8 FPR (95 % CI: [12.7,15.0]). Lesions < 3 mm had a sensitivity of 23.1 % (95 % CI: [21.2 %,40.0 %]; 3/13), with 0.2 FPR (95 % CI: [0.23,0.65]). Lesions measuring 3-6 mm had a sensitivity of 80.0 % (95 % CI: [76.0 %,79.8 %]); 60/75) with 5.8 FPR (95 % CI: [5.0,6.2]). Lesions > 6 mm had a sensitivity of 97.4 % (95 % CI: [94.1 %,97.4 %]); 151/155) with 7.9 FPR (95 % CI: [7.2,8.5]). Feature-fused SSD had a significantly higher overall sensitivity (p = 0.03, t = 2.75) or sensitivity for lesions < 3 mm (p = 0.002, t = 4.49) than baseline SSD, while the overall PPV was similar (p = 0.96, t = -0.02).
CONCLUSIONS: The SSD algorithm identified brain metastases on CECT with reasonable accuracy for lesions > 3 mm without pre/post-processing.
引用
- Amemiya S, Takao H, Kato S, et al. Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors. Eur J Radiol. 2021. PMID: 33550213. doi:10.1016/j.ejrad.2021.109577
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。