Automated volumetric surveillance of Type B aortic dissection (TBAD) is limited by manual segmentation overhead (60-75 min) in computed tomographic angiography (CTA). We propose AORTA-SCAN, a hierarchical deep-learning network designed to identify the true and false lumina of the aortic dissection (AD) in both primary and post-TEVAR CTA. In addition to the traditional 1D biomarker, aortic diameter, the framework provides the Perfusion Dissection Index (PDI), a 3D clinical indicator of aortic remodeling. The proposed model shows a significant improvement in FL Dice (0.84 vs 0.71, p < 0.001) compared with a 3D U-Net baseline and high agreement for the PDI, with a mean bias of (-0.17%) relative to the expert reference. The pipeline reduces processing time to about 10 minutes, supporting scalable 3D volumetric surveillance.