人工智慧與智慧醫療

113-1 開課異動
  • 流水號

    47767

  • 課號

    CommE5064

  • 課程識別碼

    942 U0780

  • 無分班

  • 3 學分
  • 選修

    電機工程學研究所 / 智慧醫療學分學程 / 生醫電子與資訊學研究所 / 電信工程學研究所

      選修
    • 電機工程學研究所

    • 智慧醫療學分學程

    • 生醫電子與資訊學研究所

    • 電信工程學研究所

  • 林 澤
  • 三 7, 8, 9
  • 共103

  • 2 類加選

  • 修課總人數 60 人

    本校 60 人

  • 無領域專長

  • 英文授課
  • NTU COOL
  • 核心能力與課程規劃關聯圖
  • 備註
    電機所, 電信所 本課程以英語授課。 生醫電資所 本課程以英語授課。上課地點:共同103未來教室 智慧醫療學程 本課程以英語授課。智慧醫療學程所屬電資學院「數據領域」課程。
  • 本校選課狀況

    載入中
  • 課程概述
    Artificial intelligence (AI) can be applied to a wide range of areas. Notably, the fast-growing intelligent medicine area has created tremendous business opportunities recently. It also creates an ideal environment for AI-Biomedical interdisciplinary specialists to make considerable contributions and significantly impact the world. Intelligent medicine aims to utilize state-of-the-art AI technologies for many medical applications such as accurate disease risk prediction and essential predictors selection, which are for early precise and efficient treatments. In this course, we will introduce the vast potential of intelligent medicine and help students advance their skills in this area, and motivate them to become AI-Biomedical interdisciplinary scientists. In addition, in this course, we will introduce potential partners for future interdisciplinary collaboration to our students and provide opportunities for practical implementations through several carefully designed experiments, which shall demonstrate how to leverage real-world medical resources and related AI technologies. Meanwhile, we plan to arrange visits to prestigious companies and institutes and several seminars given by domain experts to further inspire and motivate our students.
  • 課程目標
    1. To polish skills for integration of programming, medical data analysis, and machine learning. 2. To train intelligent medicine specialists through practical implementations and connect them to potential future collaborators. 3. Promote the collaboration between the College of EECS and Medicine.
  • 課程要求
    Required pre-request:Machine Learning Recommended pre-request: Python Programming for Intelligent Medicine (智慧醫療程式設計) or Special Topics in Innovative Integration of Medicine and EECS (醫學電資整合創意專題)
  • 預期每週課後學習時數
  • Office Hour
  • 指定閱讀
  • 參考書目
    1. “Machine Learning and AI for Healthcare: Big Data for ImprovedHealth Outcomes,” 2nd Edition, by Arjun Panesar. 2. “Artificial Intelligence in Healthcare: AI, Machine Learning, and Deepand Intelligent Medicine Simplified for Everyone,” by Dr. Parag SureshMahajan MD. 3. “Artificial Intelligence in Healthcare,” edited by Adam Bohr andKaveh Memarzadeh.
  • 評量方式
    30%

    Assignments

    Programming Homework

    22%

    Midterm

    Midterm: Proposal Presentation (by groups) 12% Midterm: Paper Survey Presentation (by groups) 10%

    35%

    Final project

    13%

    Reports

    Expert talk reports 8% Visit report (2024 Taiwan Healthcare Expo) 5%

  • 針對學生困難提供學生調整方式
  • 課程進度
    09/04第 1 週Course announcement Video record: AIIM-wk1-intro AI and IM
    09/11第 2 週Pre-class: 1. The rise of artificial intelligence in healthcare applications 2. Machine learning basics 3. DFN basics Case study: DNN for NSCLC prognosis prediction (genetic data) In-class: Group discussion (pre-class materials)
    09/18第 3 週Pre-class: 1. CNN 2. RNN In-class: Group discussion (pre-class materials)
    09/25第 4 週In-class: Workshop: Gene expression and system biology feature selection Workshop: An illustration of medical images/time series processing
    10/02第 5 週In-class: Professor Guo, Yue-Liang introduces their open topics for the FP Doctor Ting, Sze-Ya/Doctor Chang, Pei-Yeh introduces their open topics for the FP
    10/09第 6 週Pre-class: Transformer-1 Transformer-2 In-class: Group discussion (pre-class materials)
    10/16第 7 週Domain expert talk and panel discussion
    10/23第 8 週In-class: Midterm presentation: Final project proposal
    10/30第 9 週In-class: Workshop: Evaluation metrics, decision threshold, and visualization
    11/06第 10 週Pre-class: Graph Neural Networks (GNN) In-class: Group discussion (pre-class materials) Group discussion (for the final project)
    11/13第 11 週Pre-class: Case study (X-RIM) Case study (EMBC'24 gene paper) Case study (EMBC'24 BCLC paper) In-class: Case study (X-RIM) Case study (EMBC'24 gene paper) Case study (EMBC'24 BCLC paper) Group discussion (for the final project)
    11/20第 12 週Domain expert talk 2 and panel discussion
    11/27第 13 週In-class: Midterm presentation: Paper survey
    12/04第 14 週No class
    12/11第 15 週Domain expert talk 3 and panel discussion
    12/18第 16 週In-class: Mini-workshop of final presentation