[1Q3-OS-7a] 統合AIへの展望

[1Q3-OS-7a-04] The foundation of brain-inspired artificial intelligence extracting of anatomical projections from images

Extraction of graphical structures from brain schematics in the literature

〇Iriya Horiguchi¹, Yuta Ashihara², Hiroshi Yamakawa³ (1. Department of Mathematical Engineering and Information Physics, The University of Tokyo, 2. College of Humanities and Sciences, Nihon University. School of Engineering, The University of Tokyo. The Whole Brain Architecture Initative., 3. School of Engineering, The University of Tokyo. The Whole Brain Architecture Initative.)

Keywords:Brain-inspired Artificial Intelligence, graph structure, cerebral neural network, Brain Reference Architecture-driven development

Brain Reference Architecture (BRA), an approach to developing brain-based software, uses Brain Information Flow (BIF), which extracts mesoscopic-level information about brain anatomy, to design a functional component diagram (HCD).While the vast and varied anatomically consistent findings needed to be extracted comprehensively, BIF is manually extracted from the neuroscience literature.Therefore, in this paper, we develop an object detection model that extracts connections between brain regions from the neuroscience literature. In our experiments, we achieved mAP of 0.899 for the position of text representing the names of brain regions, and mAP of 0.856 for the arrows representing the connections between brain regions.