Precise and fast prediction methods for ischemic areas (core and penumbra) in acute ischemic stroke (AIS) patients are of significant clinical interest: they play an essential role in improving diagnosis and treatment planning. Computed Tomography (CT) scan is one of the primary modalities for early assessment in patients with suspected AIS. CT Perfusion (CTP) is often used as a primary assessment to determine stroke location, severity, and volume of ischemic lesions. Current automatic segmentation methods for CTP mostly use already processed 3D color maps conventionally used for visual assessment by radiologists as input. Alternatively, the raw CTP data is used on a slice-by-slice basis as 2D+time input, where the spatial information over the volume is ignored. In this paper, we investigate different methods to utilize the entire 4D CTP as input to fully exploit the spatio-temporal information. This leads us to propose a novel 4D convolution layer. Our comprehensive experiments on a local dataset comprised of 152 patients divided into three groups show that our proposed models generate more precise results than other methods explored. A Dice Coefficient of 0.70 and 0.45 is achieved for penumbra and core areas, respectively. The code is available on https://github.com/Biomedical-Data-Analysis-Laboratory/4D-mJ-Net.git.

翻译：对急性缺血性卒中（AIS）患者缺血区域（核心区和半暗带）进行精确且快速的预测方法具有重要的临床意义：它们在改善诊断与治疗规划中起着关键作用。计算机断层扫描（CT）是疑似AIS患者早期评估的主要检查手段之一。CT灌注成像（CTP）常作为主要评估工具，用于确定卒中位置、严重程度及缺血病灶体积。当前CTP的自动分割方法大多以放射科医生常规用于视觉评估的已处理三维彩色图谱作为输入；另一种方式是将原始CTP数据按切片逐层作为二维+时间输入，但忽略了体素空间信息。本文研究了利用完整四维CTP作为输入以充分挖掘时空信息的不同方法，并由此提出一种新型四维卷积层。我们在包含152名患者（分为三组）的本地数据集上进行的全面实验表明，所提出的模型比探索的其他方法能生成更精确的结果。半暗带和核心区的Dice系数分别达到0.70和0.45。代码公开于https://github.com/Biomedical-Data-Analysis-Laboratory/4D-mJ-Net.git。