脑转移瘤自动分割:深入分析假阳性检测
本研究开发了基于两个自适应nnU-Net模型的脑转移瘤MRI自动勾画框架,训练集包含845例患者MRI扫描上的3482个转移灶,测试集包含206例患者MRI扫描上的930个转移灶。逐患者分析中,阳性预测值为90.1%±17.7%,灵敏度为88.4%±18.0%,Dice相似系数为82.2%±9.5%。作者认为该工具可帮助放射科医生和放射肿瘤科医生检测和勾画肿瘤,并对可疑病灶做出精确决策。
要点
- 两个自适应nnU-Net模型在训练集845例患者MRI的3482个转移灶上训练,测试集为206例患者MRI的930个转移灶。
- 逐患者阳性预测值90.1%±17.7%、灵敏度88.4%±18.0%、Dice相似系数82.2%±9.5%、假阳性0.4±1.0。
- ≥6 mm大转移灶逐患者阳性预测值95.6%±17.5%、灵敏度94.5%±18.1%、Dice相似系数86.8%±7.5%、假阳性0.1±0.4。
核心结论
- 作者认为该工具可帮助放射科医生和放射肿瘤科医生从MRI中检测和勾画肿瘤,对可疑病灶做出精确决策,并可能早期发现病灶。
研究设计与样本
- 研究分析了两个自适应nnU-Net模型,模型在接受立体定向放射外科(SRS)患者的增强三维T1加权MRI扫描上训练。
- 训练集包含845例患者MRI扫描上的3482个转移灶,测试集包含206例患者MRI扫描上的930个转移灶。
- 性能通过计算阳性预测值(PPV)、灵敏度和Dice相似系数(DSC)评估。
主要发现
- 逐患者分析中,阳性预测值为90.1%±17.7%,灵敏度为88.4%±18.0%,Dice相似系数为82.2%±9.5%,假阳性为0.4±1.0。
- 对于大转移灶(≥6 mm),逐患者阳性预测值为95.6%±17.5%,灵敏度为94.5%±18.1%,Dice相似系数为86.8%±7.5%,假阳性为0.1±0.4。
- 2名医生采用5分临床可接受性量表评估自动分割真阳性轮廓质量,75%的轮廓评分为4或5分,表明可直接用于临床;其余25%评分为3分,表明仅需少量编辑。
- 对假阳性的深入分析显示,9%为原始影像学审阅未识别、但后续随访影像识别的真阳性转移灶(早期检测)。
- 54%为已识别但有意未勾画为治疗靶区的真阳性转移灶,主要因为患者在SRS治疗前后接受了全脑放疗。
关键数值与推荐
- 逐患者阳性预测值90.1%±17.7%,灵敏度88.4%±18.0%,Dice相似系数82.2%±9.5%,假阳性0.4±1.0。
- ≥6 mm转移灶逐患者阳性预测值95.6%±17.5%,灵敏度94.5%±18.1%,Dice相似系数86.8%±7.5%,假阳性0.1±0.4。
- 75%的自动分割真阳性轮廓评分为4或5分,25%评分为3分。
临床怎么用
- 原文未据此给出推荐。
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)。
原文
PURPOSE: The clinical management of brain metastases after stereotactic radiosurgery (SRS) is difficult, because a physician must review follow-up magnetic resonance imaging (MRI) scans to determine treatment outcome, which is often labor intensive. The purpose of this study was to develop an automated framework to contour brain metastases in MRI to help treatment planning for SRS and understand its limitations. METHODS AND MATERIALS: Two self-adaptive nnU-Net models trained on postcontrast 3-dimensional T1-weighted MRI scans from patients who underwent SRS were analyzed. Performance was evaluated by computing positive predictive value (PPV), sensitivity, and Dice similarity coefficient (DSC). The training and testing sets included 3482 metastases on 845 patient MRI scans and 930 metastases on 206 patient MRI scans, respectively. RESULTS: In the per-patient analysis, PPV was 90.1% ± 17.7%, sensitivity 88.4% ± 18.0%, DSC 82.2% ± 9.5%, and false positive (FP) 0.4 ± 1.0. For large metastases (≥6 mm), the per-patient PPV was 95.6% ± 17.5%, sensitivity 94.5% ± 18.1%, DSC 86.8% ± 7.5%, and FP 0.1 ± 0.4. The quality of autosegmented true-positive (TP) contours was also assessed by 2 physicians using a 5-point scale for clinical acceptability. Seventy-five percent of contours were assigned scores of 4 or 5, which shows that contours could be used as-is in clinical application, and the remaining 25% were assigned a score of 3, which means they needed minor editing only. Notably, a deep dive into FPs indicated that 9% were TP metastases not identified on the original radiology review, but identified on subsequent follow-up imaging (early detection). Fifty-four percent were real metastases (TP) that were identified but purposefully not contoured for target treatment, mainly because the patient underwent whole-brain radiation therapy before/after SRS treatment. CONCLUSIONS: These findings show that our tool can help radiologists and radiation oncologists detect and contour tumors from MRI, make precise decisions about suspicious lesions, and potentially find lesions at early stages.
引用
- Ziyaee H, Cardenas CE, Yeboa DN, et al. Automated Brain Metastases Segmentation With a Deep Dive Into False-positive Detection. Adv Radiat Oncol. 2022. PMID: 36299565. doi:10.1016/j.adro.2022.101085
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。