How to automatically detect intracranial aneurysms from Three-Dimension Time of Flight Magnetic Resonance Angiography (3D TOF MRA) images is a typical 3D image classification problem. Currently, the commonly used method is the Maximum Intensity Projection- (MIP-) based way. It transfers 3D classification into 2D case by projecting the 3D patch into 2D planes along different directions on the basis of voxel’s intensity. After then, the 2D Convolutional Neural Network (CNN) is established to do classification. It has been shown that the MIP-based method can reduce the demands for the samples and increase the computation efficiency. Meanwhile, the accuracy is comparable with that of 3D image classification. Inspired by the strategy of MIP, we want to further reduce the demands for samples and accelerate the training by transferring the 2D image classification into 1D case, i.e., we want to generate the 1D vectors from the MIP images and then establish a 1D CNN to do intracranial aneurysm detection and classification for 3D TOF MRA image. Specifically, our method first extracts a series of patches as the Region of Interests (ROIs) along the blood vessels from the original 3D TOF MRA 3D image. The corresponding MIP images of each ROI will be obtained through maximum intensity projecting. Then, we generate a series of 1D vectors by accumulating each MIP image along different directions. Meanwhile, a 1D CNN is established to detect aneurysms, in which, the input is the obtained 1D vectors and the output is the binary classification result denoting whether there are intracranial aneurysms in the considered patch. Generally, compared with 2D- and 3D-CNN, the 1D CNN-based way greatly accelerates the training and shows stronger robustness in the case of fewer samples. The efficiency of the proposed method outperforms the 2D CNN about 10 times in CPU training. Yet, their accuracies are close.

中文翻译：

---

基于3D TOF-MRA的基于CNN的一维颅内动脉瘤检测

如何从三维飞行时间磁共振血管造影（3D TOF MRA）图像中自动检测颅内动脉瘤是一个典型的3D图像分类问题。当前，常用的方法是基于最大强度投影（MIP-）的方法。通过将3D补片根据体素的强度沿不同方向投影到2D平面中，它将3D分类转换为2D情况。之后，建立2D卷积神经网络（CNN）进行分类。结果表明，基于MIP的方法可以减少对样本的需求并提高计算效率。同时，其准确性与3D图像分类的准确性相当。受MIP战略的启发，我们希望通过将2D图像分类转换为1D案例来进一步减少对样本的需求，并加快训练速度，即，我们希望从MIP图像生成1D向量，然后建立1D CNN进行颅内动脉瘤的检测和分类3D TOF MRA图像。具体来说，我们的方法首先从原始3​​D TOF MRA 3D图像中提取一系列斑块作为沿血管的感兴趣区域（ROI）。每个ROI的相应MIP图像将通过最大强度投影获得。然后，我们通过沿不同方向累积每个MIP图像来生成一系列一维矢量。同时，建立了一维CNN来检测动脉瘤，其中，输入是获得的一维向量，输出是二进制分类结果，表示所考虑的斑块中是否存在颅内动脉瘤。通常，与2D和3D-CNN相比，基于1D CNN的方法大大加快了训练速度，并且在样本较少的情况下显示出更强的鲁棒性。在CPU训练中，所提方法的效率优于2D CNN。然而，他们的精确度是接近的。