Subarachnoid hemorrhage (SAH) is bleeding into the subarachnoid space which is the area between the arachnoid pater and the pia mater surrounding the brain (Figure 1). The most common cause is rupture of an aneurysm, and SAH is known as the disease with high mortality rate. Unfortunately, SAHs are sometimes overlooked at the first visit because non-experts examine patients in most medical institutions, and it is difficult to diagnose non-contrast computed tomography (NCCT) images. In this paper , the authors proposed that artificial intelligence (AI) system to diagnose the presence and location of SAH using U-Net, a convolutional neural network suitable for region extraction in medical images (Figure 2). Their AI system was able to diagnose SAH with equal or slightly less accuracy compared to that of neurosurgery specialists and with higher accuracy than non-specialists (Figure 3). In addition, the diagnostic accuracy was improved for non-specialists by the AI system as a reference (Table 1). In the future, the AI system will contribute to the improvement of the treatment outcome of SAH.
 Nishi, Toru, et al. “Artificial intelligence trained by deep learning can improve computed tomography diagnosis of nontraumatic subarachnoid hemorrhage by nonspecialists.” Neurologia medico-chirurgica 61.11 (2021): 652-660.
CAUTION：This is Fujifilm Global Website. Fujifilm makes no representation that products on this website are commercially available in all countries. Approved uses of products vary by country and region. Specifications and appearance of products are subject to change without notice.