1 Ocak 2024 Konferans bildirisi Açık Erişim

Mi, Hancang; Gan, Hong-Seng; Wang, Xiaoyi; Shimizu, Akinobu; Ramlee, Muhammad Hanif; Unlu, Mehmet Zubeyir

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 280071, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Xian Jiaotong Liverpool Univ, Sch AI & Adv Comp, Suzhou, Peoples R China", 
      "name": "Mi, Hancang"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Xian Jiaotong Liverpool Univ, Sch AI & Adv Comp, Suzhou, Peoples R China", 
      "name": "Gan, Hong-Seng"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Xian Jiaotong Liverpool Univ, Sch Math & Phys, Suzhou, Peoples R China", 
      "name": "Wang, Xiaoyi"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Tokyo Univ Agr & Technol, Inst Engn, Tokyo, Japan", 
      "name": "Shimizu, Akinobu"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Teknol Malaysia, Dept Biomed Engn & Hlth Sci, Johor Baharu, Malaysia", 
      "name": "Ramlee, Muhammad Hanif"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Izmir Inst Technol, Dept Elect & Elect Engn, Izmir, Turkiye", 
      "name": "Unlu, Mehmet Zubeyir"
    }
  ], 
  "datePublished": "2024-01-01", 
  "description": "<p>Brain tumours are among the most life-threatening diseases, and automatic segmentation of brain tumours from medical images is crucial for clinicians to identify and quantify tumour regions with high precision. While traditional segmentation models have laid the groundwork, diffusion models have since been developed to better manage complex medical data. However, diffusion models often face challenges related to insufficient parallel computing power and inefficient GPU utilization. To address these issues, we propose the DF-SegDiff model, which includes diffusion segmentation, parallel data processing, a distributed training model, a dynamic balancing parameter and model fusion. This approach significantly reduces training time while achieving an average Dice score of 0.87, with several samples reaching Dice values close to 0.94. By combining BRATS2020 with the Medical Segmentation Decathlon dataset, we also integrated a comprehensive dataset containing 800 training samples and 53 test samples. Evaluation of the model using Dice, IoU, and other relevant metrics demonstrates that our method outperforms current state-of-the-art techniques.</p>", 
  "headline": "DF-SegDiff: ADiffusion Segmentation Model using a New Distributed Parallel Computing Algorithm", 
  "identifier": 280071, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "DF-SegDiff: ADiffusion Segmentation Model using a New Distributed Parallel Computing Algorithm", 
  "url": "https://aperta.ulakbim.gov.tr/record/280071"
}