Segmentation of intracranial aneurysm (IA) from computed tomography angiography (CTA) images is of significant importance for quantitative assessment of IA and further surgical treatment. Manual segmentation of IA is a labor-intensive, time-consuming job and suffers from inter- and intra-observer variabilities. Training deep neural networks usually requires a large amount of labeled data, while annotating data is very time-consuming for the IA segmentation task. This paper presents a novel weight-perceptual self-ensembling model for semi-supervised IA segmentation, which employs unlabeled data by encouraging the predictions of given perturbed input samples to be consistent. Considering that the quality of consistency targets is not comparable to each other, we introduce a novel sample weight perception module to quantify the quality of different consistency targets. Our proposed module can be used to evaluate the contributions of unlabeled samples during training to force the network to focus on those well-predicted samples. We have conducted both horizontal and vertical comparisons on the clinical intracranial aneurysm CTA image dataset. Experimental results show that our proposed method can improve at least 3% Dice coefficient over the fully-supervised baseline, and at least 1.7% over other state-of-the-art semi-supervised methods.

从计算机断层扫描血管造影 (CTA) 图像中分割颅内动脉瘤 (IA) 对于 IA 的定量评估和进一步的手术治疗具有重要意义。IA 的手动分割是一项劳动密集型、耗时的工作，并且会受到观察者之间和观察者内部差异的影响。训练深度神经网络通常需要大量的标记数据，而注释数据对于 IA 分割任务来说非常耗时。本文提出了一种用于半监督 IA 分割的新型权重感知自集成模型，该模型通过鼓励给定​​扰动输入样本的预测保持一致来使用未标记数据。考虑到一致性目标的质量彼此之间不具有可比性，我们引入了一种新颖的样本权重感知模块来量化不同一致性目标的质量。我们提出的模块可用于评估训练期间未标记样本的贡献，以迫使网络专注于那些预测良好的样本。我们对临床颅内动脉瘤 CTA 图像数据集进行了水平和垂直比较。实验结果表明，我们提出的方法可以比全监督基线提高至少 3% 的 Dice 系数，比其他最先进的半监督方法提高至少 1.7%。我们对临床颅内动脉瘤 CTA 图像数据集进行了水平和垂直比较。实验结果表明，我们提出的方法可以比全监督基线提高至少 3% 的 Dice 系数，比其他最先进的半监督方法提高至少 1.7%。我们对临床颅内动脉瘤 CTA 图像数据集进行了水平和垂直比较。实验结果表明，我们提出的方法可以比全监督基线提高至少 3% 的 Dice 系数，比其他最先进的半监督方法提高至少 1.7%。