深度学习联合3D黑血与梯度回波序列自动检测分割脑转移瘤
研究纳入训练集188例脑转移瘤患者(917个病灶)和测试集45例患者(203个病灶)及49例无转移患者,构建基于3D U-net的深度学习模型,比较联合3D黑血(BB)与3D梯度回波(GRE)成像与单用3D GRE的检测分割性能。联合模型敏感度93.1%,高于单用3D GRE的76.8%(p<0.001),尤其在小转移瘤中优势更显著;联合模型Dice系数0.822,单用3D GRE为0.756,联合模型每例假阳性0.59。
要点
- 联合3D BB与3D GRE的DL模型检测脑转移瘤敏感度93.1%,显著高于单用3D GRE的76.8%。
- 联合模型对<3 mm转移瘤敏感度82.4%,对≥3 mm且<10 mm为93.2%,对≥10 mm为100%。
- 联合模型分割Dice系数0.822,高于单用3D GRE的0.756,每例假阳性0.59。
关键影像表现/征象
- 联合3D BB与3D GRE模型检测脑转移瘤敏感度93.1%,单用3D GRE模型为76.8%(p<0.001)。
- 联合模型在小转移瘤亚组中的优势显著更强(交互作用p<0.001)。
- 联合模型对<3 mm转移瘤敏感度82.4%,对≥3 mm且<10 mm为93.2%,对≥10 mm为100%。
- 联合模型每例假阳性0.59,Dice系数0.822;单用3D GRE模型Dice系数0.756。
诊断标准与关键数值
- 检测敏感度:联合3D BB与3D GRE模型93.1%,单用3D GRE模型76.8%(p<0.001)。
- 按转移瘤大小分层敏感度(联合模型):<3 mm为82.4%,≥3 mm且<10 mm为93.2%,≥10 mm为100%。
- 分割性能:联合模型Dice系数0.822,单用3D GRE模型Dice系数0.756。
- 每例假阳性数:联合模型在测试集为0.59。
临床应用与阅片要点
- 联合3D BB与3D GRE的DL模型可辅助检测脑转移瘤,尤其对小转移瘤的检出敏感度高于单用3D GRE模型。
- 联合模型每例假阳性0.59,阅片时需结合原始图像确认AI提示病灶。
- 联合模型Dice系数0.822,可用于脑转移瘤分割,但单用3D GRE模型分割Dice系数较低为0.756。
局限性
- 原文未述局限性
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: To evaluate whether a deep learning (DL) model using both three-dimensional (3D) black-blood (BB) imaging and 3D gradient echo (GRE) imaging may improve the detection and segmentation performance of brain metastases compared to that using only 3D GRE imaging.
METHODS: A total of 188 patients with brain metastases (917 lesions) who underwent a brain metastasis MRI protocol including contrast-enhanced 3D BB and 3D GRE were included in the training set. DL models based on 3D U-net were constructed. The models were validated in the test set consisting of 45 patients with brain metastases (203 lesions) and 49 patients without brain metastases.
RESULTS: The combined 3D BB and 3D GRE model yielded better performance than the 3D GRE model (sensitivities of 93.1% vs 76.8%, p < 0.001), and this effect was significantly stronger in subgroups with small metastases (p interaction < 0.001). For metastases < 3 mm, ≥ 3 mm and < 10 mm, and ≥ 10 mm, the sensitivities were 82.4%, 93.2%, and 100%, respectively. The combined 3D BB and 3D GRE model showed a false-positive per case of 0.59 in the test set. The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while 3D GRE model showed a lower Dice coefficient of 0.756.
CONCLUSIONS: The combined 3D BB and 3D GRE DL model may improve the detection and segmentation performance of brain metastases, especially in detecting small metastases.
KEY POINTS: • The combined 3D BB and 3D GRE model yielded better performance for the detection of brain metastases than the 3D GRE model (p < 0.001), with sensitivities of 93.1% and 76.8%, respectively. • The combined 3D BB and 3D GRE model showed a false-positive rate per case of 0.59 in the test set. • The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while the 3D GRE model showed a lower Dice coefficient of 0.756.
引用
- Park YW, Jun Y, Lee Y, et al. Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging. Eur Radiol. 2021. PMID: 33738598. doi:10.1007/s00330-021-07783-3
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。