Skip to main content
English
中文
Log In
Log in
Log in with ORCID
NTU Single Sign On
Have you forgotten your password?
Home
.National Taiwan University / 國立臺灣大學
Project / 研究計畫
Development of a Deep Learning System for Quantification of Tumor Burden and Metastatic Lymphadenopathy in Patients with Non-Early Stage Lung Cancer in Chest Ct=發展基於深度學習量化系統於胸腔電腦斷層影像之非早期肺癌腫瘤負荷與轉移淋巴病變研究
Development of a Deep Learning System for Quantification of Tumor Burden and Metastatic Lymphadenopathy in Patients with Non-Early Stage Lung Cancer in Chest Ct=發展基於深度學習量化系統於胸腔電腦斷層影像之非早期肺癌腫瘤負荷與轉移淋巴病變研究
Details
Primary Data
Project title
發展基於深度學習量化系統於胸腔電腦斷層影像之非早期肺癌腫瘤負荷與轉移淋巴病變研究
Internal ID
NSTC113-2221-E002-056
Principal Investigator
YEUN-CHUNG CHANG
Start Date
August 1, 2024
End Date
July 31, 2025
Investigators
LING-KAI CHANG
JIN-YUAN SHIH
RUEY-FENG CHANG
JIN-SHING CHEN
Organizations
Radiology
Partner Organizations
National Science and Technology Council
Description
Keywords
Lung Cancer
Non-early Stage
Computed Tomography Image
Deep Learning
TNM Staging
Metastatic Lymph Nodes
Description
本研究旨在利用深度學習技術分析胸腔電腦斷層影像,計畫分為三個部分:發展轉移性淋巴結、分開腫瘤結節和肋膜積水等人工智慧模型,開發自動化的TNM分期系統。本計畫延伸正在執行的國科會計畫「腫瘤負荷預測系統」進行TNM自動化分期,訓練有效預測肺癌患者分期的診斷系統,提高醫師準確診斷及規劃治療方案的能力。第一年開發轉移性淋巴結偵測系統,用於偵測、切割及量化轉移性淋巴結;第二年完善深度學習模型處理分開肺結節,加入肺結節自動偵測系統,並結合原發性腫瘤和轉移性淋巴結;第三年優化深度學習模型,加入肋膜積水偵測、切割,並評估其與傳統臨床分期方法的一致性和準確性,建立完整的自動化肺癌TNM分期系統。
Show more