背景:脑动静脉畸形(bAVM)的轮廓对后续治疗计划至关重要。手动分割是耗时且费力的。应用深度学习来自动检测和分割bAVM可能有助于提高临床实践效率。
目的:开发一种使用深度学习方法在飞行时间磁共振血管造影术中检测bAVM并分割其病灶的方法。
方法:回顾性。
方法:从2003年到2020年,221例7-79岁的bAVM患者接受了放射外科治疗。他们被分成177个训练,22验证,和22个测试数据。
■1.5T,基于三维梯度回波的飞行时间磁共振血管成像[J].
结果:利用YOLOv5和YOLOv8算法检测bAVM病变,利用U-Net和U-Net++模型从边界框中分割出病灶。平均精度,F1,精度,和召回被用来评估bAVM检测的模型性能。为了评估模型在Nidus分割上的性能,采用骰子系数和平衡平均豪斯多夫距离(rbAHD)。
方法:交叉验证结果采用t检验(P<0.05)。采用Wilcoxon秩检验比较参考值的中位数和模型推断结果(P<0.05)。
结果:检测结果表明,具有预训练和增强的模型表现最佳。具有随机扩张机制的U-Net++导致较高的Dice和较低的rbAHD,与没有这种机制的情况相比,在不同的扩张边界框条件下(P<0.05)。当结合检测和分割时,Dice和rbAHD与使用检测到的边界框计算的参考有统计学差异(P<0.05)。对于测试数据集中检测到的病变,它显示出最高的骰子0.82和最低的rbAHD5.3%。
结论:这项研究表明,预训练和数据增强提高了YOLO检测性能。适当限制病变范围允许适当的bAVM分割。
方法:4技术效率阶段:1.
The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time-consuming and labor-intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency.
To develop an approach for detecting bAVM and segmenting its nidus on Time-of-flight magnetic resonance angiography using deep learning methods.
Retrospective.
221 bAVM patients aged 7-79 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data.
1.5 T, Time-of-flight magnetic resonance angiography based on 3D gradient echo.
The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U-Net and U-Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model\'s performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed.
The Student\'s t-test was used to test the cross-validation results (P < 0.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results (P < 0.05).
The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U-Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions (P < 0.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes (P < 0.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%.
This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation.
4 TECHNICAL EFFICACY STAGE: 1.