Deep learning-based automatic pipeline for 3D needle localization on intra-procedural 3D MRI.
Deep learning-based automatic pipeline for 3D needle localization on intra-procedural 3D MRI.
复制标题
DOI：
10.1007/s11548-024-03077-3
复制
发表时间：
2024-03
影响因子：
3
通讯作者：
Wenqi Zhou;Xinzhou Li;Fatemeh Zabihollahy;David S Lu;Holden H. Wu
中科院分区：
文献类型：
--
作者：
Wenqi Zhou;Xinzhou Li;Fatemeh Zabihollahy;David S Lu;Holden H. Wu
目的在三维磁共振成像(MRI)上准确、快速地定位针头是MRI引导经皮介入治疗的关键。目前的工作流程需要在3D MRI上手动定位针头，这既耗时又繁琐。使用2D深度学习网络进行针头分割的自动方法需要人工定位图像平面，而3D网络则需要足够的训练数据集。该方法采用移位窗口(Swin)转换器，并采用从粗到细的分割策略：(1)利用3D Swin TRANSFER对初始3D针特征进行分割；(2)生成包含针特征的2D重建图像；(3)利用2D Swin Transform对2D针特征进行精细分割，并计算3D针尖的位置和轴向。为了改进网络训练，进行了预训练和数据增强。通过交叉验证49个来自临床前猪实验的活体内3D磁共振图像来评估该管道。针尖和针轴定位误差与人的读写器内误差比较采用Wilcoxon符号秩次检验，P<； 为0.05显著。结果该管道的平均端到端计算时间为每3D体积6个S。3D Swin UNETR和2D Swin Transformer在管道中的骰子得分中位数分别为0.80和0.93。3D针尖定位误差中位数为1.48 mm(1.09像素)，轴线定位误差中位数为0.98°。针尖定位误差显著小于人类读取器内的变异(中位数1.70 mm；p<； 0.01)。结论所提出的自动化流水线在术中3D磁共振成像上实现了快速像素级3D针定位，不需要大量的3D训练数据集，具有辅助磁共振引导经皮介入治疗的潜力。
PurposeAccurate and rapid needle localization on 3D magnetic resonance imaging (MRI) is critical for MRI-guided percutaneous interventions. The current workflow requires manual needle localization on 3D MRI, which is time-consuming and cumbersome. Automatic methods using 2D deep learning networks for needle segmentation require manual image plane localization, while 3D networks are challenged by the need for sufficient training datasets. This work aimed to develop an automatic deep learning-based pipeline for accurate and rapid 3D needle localization on in vivo intra-procedural 3D MRI using a limited training dataset.MethodsThe proposed automatic pipeline adopted Shifted Window (Swin) Transformers and employed a coarse-to-fine segmentation strategy: (1) initial 3D needle feature segmentation with 3D Swin UNEt TRansfomer (UNETR); (2) generation of a 2D reformatted image containing the needle feature; (3) fine 2D needle feature segmentation with 2D Swin Transformer and calculation of 3D needle tip position and axis orientation. Pre-training and data augmentation were performed to improve network training. The pipeline was evaluated via cross-validation with 49 in vivo intra-procedural 3D MR images from preclinical pig experiments. The needle tip and axis localization errors were compared with human intra-reader variation using the Wilcoxon signed rank test, withp< 0.05 considered significant.ResultsThe average end-to-end computational time for the pipeline was 6 s per 3D volume. The median Dice scores of the 3D Swin UNETR and 2D Swin Transformer in the pipeline were 0.80 and 0.93, respectively. The median 3D needle tip and axis localization errors were 1.48 mm (1.09 pixels) and 0.98°, respectively. Needle tip localization errors were significantly smaller than human intra-reader variation (median 1.70 mm;p< 0.01).ConclusionThe proposed automatic pipeline achieved rapid pixel-level 3D needle localization on intra-procedural 3D MRI without requiring a large 3D training dataset and has the potential to assist MRI-guided percutaneous interventions.