Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei City, 112, Taiwan.
Department of Radiation Oncology, Taichung Veterans General Hospital, Taichung, 407, Taiwan.
J Magn Reson Imaging. 2024 Feb;59(2):587-598. doi: 10.1002/jmri.28795. Epub 2023 May 23.
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.
FIELD STRENGTH/SEQUENCE: 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.
脑动静脉畸形（bAVM）的描绘对于后续的治疗计划至关重要。手动分割既耗时又费力。应用深度学习技术自动检测和分割 bAVM 可能有助于提高临床实践效率。
开发一种基于深度学习方法在时间飞越磁共振血管造影上检测和分割 bAVM 核心的方法。
回顾性。
2003 年至 2020 年间，221 名年龄在 7-79 岁的 bAVM 患者接受了放射外科治疗。他们被分为 177 名训练、22 名验证和 22 名测试数据。
磁场强度/序列：1.5T，基于 3D 梯度回波的时间飞越磁共振血管造影。
使用 YOLOv5 和 YOLOv8 算法检测 bAVM 病变，使用 U-Net 和 U-Net++模型从边界框中分割核心。使用平均精度均值、F1、精度和召回率来评估模型在 bAVM 检测上的性能。为了评估模型在核心分割上的性能，使用 Dice 系数和平衡平均 Hausdorff 距离（rbAHD）。
使用学生 t 检验来检验交叉验证结果（P<0.05）。使用 Wilcoxon 秩检验来比较参考值和模型推断结果的中位数（P<0.05）。
检测结果表明，具有预训练和增强功能的模型表现最佳。与没有该机制的模型相比，具有随机扩张机制的 U-Net++在不同扩张边界框条件下具有更高的 Dice 和更低的 rbAHD（P<0.05）。当结合检测和分割时，Dice 和 rbAHD 与使用检测边界框计算的参考值有统计学差异（P<0.05）。在测试数据集的检测病变中，它表现出最高的 Dice 值为 0.82 和最低的 rbAHD 值为 5.3%。
本研究表明，预训练和数据增强可以提高 YOLO 检测性能。适当限制病变范围可以实现充分的 bAVM 分割。
4 技术功效阶段：1
