透過您的圖書館登入
IP:3.237.34.21
  • Journals

醫學影像分析中的人工智慧、擴增智慧與人類智慧

Artificial, Augmented and Human Intelligence in the Medical Imaging Chain

Abstracts


人工智慧近日快速的發展,在醫學影像分析與應用引起許多研究的投入,也在數個主題獲得令人注目的成果。但從醫學影像鏈以及醫療整體發展來看仍需持續努力,除了充分利用人工智慧外,我們更需要整合各個領域長期累積的智慧,例如:醫學、機器學習、深度學習、數學、統計、資訊科學與工程,方能結合人類與電腦的長處,發展人機協作的更高層智慧,解決醫療相關的問題與挑戰。在這樣的想法下,我們致力於建立人工智慧醫學影像分析平台(Artificial Intelligence for Medical Image Analysis Platform, AIMIA platform)。此平台由「人工智慧引擎」(artificial intelligence engines)和「擴增智慧流程」(augmented intelligence workflows)所組成。人工智慧引擎包括高效能演算法和軟體模組,旨在準確、有效、穩健地從大量醫學影像數據集中提取重要訊息。我們將這些演算法和軟體模組作為構建基礎,在各種臨床應用中建立起創新的擴增智慧醫療流程。此外,AIMIA也是一個結合學術界,醫學界,以及產業界專業人才的跨國、跨領域合作平台,希望透過醫學、數學、資訊科學等產學專家共同努力,達到建立學術影響力與人才培育、創新多元的臨床應用、以及醫療產業商業價值開發等目標。

Parallel abstracts


The rapid development of artificial intelligence (AI) in recent years has resulted in many promising results in AI-based medical image analysis. However, if taking the medical image chain and overall development of the healthcare industry into consideration, continuous efforts remain necessary. These efforts require interdisciplinary knowledge, including medicine, machine learning, deep learning, applied mathematics, statistics, computer science and engineering, and, probably the most critical component, human intelligence. Only in this way could we reach a higher level of knowledge to deal with medicine-related problems and challenges. We thus dedicated to building an "Artificial Intelligence for Medical Image Analysis Platform" (AIMIA Platform). The platform consists of "Artificial Intelligence Engines" and "Augmented Intelligence Workflows." The AI engines include high-performance algorithms along with software modules, designed to extract information from a wide range of medical image dataset accurately and efficiently. Acting as the building blocks of the augmented intelligence workflows, these algorithms and software modules construct augmented intelligence workflows in all kinds of clinical applications. Furthermore, AIMIA is a transnational and interdisciplinary platform that brings professionals together, whether they are from the academia, medical field, or the industry. Through the joint effort of experts from medicine, mathematics, and information technology industry, we hope to bring impacts to the academia, come up with innovative clinical applications, and generate business value in the healthcare industry.

References


Esteva A, Robicquet A, Ramsundar B, et al: A guide to deep learning in healthcare. Nat Med 2019;25:24-9. doi: 10.1038/s41591-018-0316-z
Litjens G, Kooi T, Bejnordi BE, et al: A survey on deep learning in medical image analysis. Med Image Anal 2017;42:60-88. doi: 10.1016/j.media.2017.07.005
Shortliffe EH, Sepúlveda MJ: Clinical decision support in the era of artificial intelligence. JAMA 2018;320:2199-200. doi: 10.1001/jama.2018.17163
Ledley, Robert S, Lee B, et al: Reasoning foundations of medical diagnosis. Science 1959;130:9-21.
Zhou S. Kevin, Hayit Greenspan, Dinggang Shen, eds: Deep learning for medical image analysis. Academic Press 2018;320:1192-3.

Cited by


吳振吉(2022)。人工智慧醫療傷害之損害賠償責任臺大法學論叢51(2),477-536。https://doi.org/10.6199/NTULJ.202206_51(2).0004

Read-around