Deep Learning Domain Adaptation Methods for Brain Glioma Image Segmentation, Classification and Prognosis Analysis

Project: National Science and Technology CouncilNational Science and Technology Council Academic Grants

Project Details

Abstract

本計畫以深度學習和臨床應用的綜合視角為基礎,致力於研究醫學影像分析中的四個主要方面:切割(術前評估和治療追蹤)、分類(診斷)、預測和預後分析。我們的目標是改進深度學習方法,以解決醫學影像分析中普遍存在的樣本不足或不均的問題,從而提高切割、分類和預測的精確性。這項計畫的成果將有助於同時增強機器學習領域中對預測、分類和切割的應用,並在相應的臨床場景中產生實際效益。

Project IDs

Project ID:PB11307-2735
External Project ID:NSTC113-2221-E182-017
StatusFinished
Effective start/end date01/08/2431/07/25

Keywords

  • Glioma
  • Brain Tumor Classification Prediction
  • 3D semantic segmentation
  • Multimodal MRI Analysis
  • Computer-Aided Diagnosis System
  • Unsupervised Domain Adaptation for Source-free Data
  • Contrastive Learning
  • Image Consistency
  • Model Generalization
  • Feature Diversification