English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 118295/149332 (79%)
造訪人次 : 78136628      線上人數 : 105
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/154268


    題名: W-Net: two-stage segmentation for multi-center kidney ultrasound
    作者: 羅崇銘
    Lo, Chung-Ming;Chang, Yu-Chi;Chen, Yi-Kong;Wu, Ping-Hsun;Luh, Hsing
    貢獻者: 圖檔所
    關鍵詞: W-Net;kidney;ultrasound;segmentation;multicenter
    日期: 2024-06
    上傳時間: 2024-11-15
    摘要: The global death rate of chronic kidney disease (CKD) continues to increase and becomes a serious health issue. Ultrasound imaging is significant in the evaluation of CKD. However, there is a challenge posed by quality differences in multi-center datasets for kidney ultrasound image segmentation. Confronting the problem, this study applied the W-Net based on the double U-Net architecture which was respectively trained in two stages. In the first stage, the pixel-wise nnU-Net was pretrained by 4586 images and fine-tuned by 534 images. In the second stage, the region-wise nnU-Net was trained from the inference of the first stage by 72 images and achieved a 6.95% improvement from the first stage. It can bring more evidence about the practical application of deep learning-based segmentation in kidney ultrasound and its potential use in clinics.
    關聯: 2024 IEEE Conference on Artificial Intelligence, IEEE
    資料類型: conference
    DOI 連結: https://doi.org/10.1109/CAI59869.2024.00274
    DOI: 10.1109/CAI59869.2024.00274
    顯示於類別:[圖書資訊與檔案學研究所] 會議論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML387檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋