Reliable Tensor-Network Fusion Approach to Medical Informatics: Novel Techniques and Benchmarks

• Project/Area Number: 24K03005
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61030:Intelligent informatics-related; Basic Section 60030:Statistical science-related; Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related
• Research Institution: Institute of Physical and Chemical Research
• Principal Investigator: 李 超 国立研究開発法人理化学研究所, 革新知能統合研究センター, 研究員 (10869837)
• Co-Investigator(Kenkyū-buntansha): 孫 哲 順天堂大学, 健康データサイエンス学部, 助教 (40804662) ; ZHAO QIBIN 国立研究開発法人理化学研究所, 革新知能統合研究センター, チームリーダー (30599618) ; 青木 茂樹 順天堂大学, 大学院医学研究科, 教授 (80222470)
• Project Period (FY): 2024-04-01 – 2028-03-31
• Project Status: Granted (Fiscal Year 2024)
• Budget Amount: ¥18,720,000 (Direct Cost: ¥14,400,000、Indirect Cost: ¥4,320,000); Fiscal Year 2027: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2026: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2025: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2024: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
• Keywords: multi-modal learning / tensor fusion

Outline of Research at the Start

We create a correlation-aware tensor fusion network, enabling the network to learn multi-modal structures directly; explore selective inference within the TFN framework to bolster the reliability of our data fusion methods; and introduce a new multi-modal, multi-task medical benchmark dataset.