基于血管先验的多任务UNet用于磁共振血管造影中颅内动脉瘤的弱监督检测与分割
Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior
AI总结：
针对颅内动脉瘤影像分析难、标注数据不足的问题，提出融合血管先验的弱监督3D多任务UNet，在TOF-MRA中联合完成检测与分割，在多个数据集上性能优于现有最优方法。
摘要：
颅内动脉瘤（IAs）是脑血管的异常扩张，一旦破裂可能危及生命。然而，这类病灶体积小、在放射影像中对比度低，往往难以开展精准高效的检测与形态学分析，而这些工作对该疾病的临床诊疗至关重要。此外，缺乏带有体素级专家标注的大型公开数据集，也为开发解决上述问题的深度学习算法带来了挑战。为此，我们提出了一种新颖的弱监督3D多任务UNet，该网络融合血管先验，可在飞行时间磁共振血管造影（TOF-MRA）中联合完成动脉瘤检测与分割。具体而言，为稳健引导颅内动脉瘤的检测与分割，我们采用常用的Frangi血管滤波生成软脑血管先验，既作为网络输入，也用于注意力模块，以实现解码器端的分割与辅助分支的检测。我们在带有粗略分割真值的Lausanne数据集上训练模型，并在同一数据库中带有精细标注的测试集上进行评估。为进一步验证模型的泛化性，我们还在ADAM数据集上开展了外部验证。结果表明，该技术在动脉瘤分割（Dice=0.614，95%HD=1.38mm）与检测（假阳性率=1.47，灵敏度=92.9%）任务上的性能均优于现有SOTA方法。
英文摘要：
Intracranial aneurysms (IAs) are abnormal dilations of cerebral blood vessels that, if ruptured, can lead to life-threatening consequences. However, their small size and soft contrast in radiological scans often make it difficult to perform accurate and efficient detection and morphological analyses, which are critical in the clinical care of the disorder. Furthermore, the lack of large public datasets with voxel-wise expert annotations pose challenges for developing deep learning algorithms to address the issues. Therefore, we proposed a novel weakly supervised 3D multi-task UNet that integrates vesselness priors to jointly perform aneurysm detection and segmentation in time-of-flight MR angiography (TOF-MRA). Specifically, to robustly guide IA detection and segmentation, we employ the popular Frangi's vesselness filter to derive soft cerebrovascular priors for both network input and an attention block to conduct segmentation from the decoder and detection from an auxiliary branch. We train our model on the Lausanne dataset with coarse ground truth segmentation, and evaluate it on the test set with refined labels from the same database. To further assess our model's generalizability, we also validate it externally on the ADAM dataset. Our results demonstrate the superior performance of the proposed technique over the SOTA techniques for aneurysm segmentation (Dice = 0.614, 95%HD =1.38mm) and detection (false positive rate = 1.47, sensitivity = 92.9%).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
