New multi-view VAE framework improves glioblastoma MRI radiomics prediction

Researchers have developed a novel multi-view latent representation learning framework using variational autoencoders (VAEs) to predict MGMT promoter methylation status in glioblastoma from MRI scans. This approach preserves modality-specific radiomic structures while enabling late fusion in a compact probabilistic latent space. The multi-view VAE achieved a test AUC of 0.77, significantly outperforming baseline models and demonstrating improved integration of complementary MRI information. AI

影响 This new framework could improve non-invasive prediction of tumor characteristics, aiding in glioblastoma prognosis and treatment.

排序理由 This is a research paper detailing a new machine learning framework for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• Glioblastoma
• Mariya Miteva
• MGMT
• Radiomics
• Variational Autoencoder
• FLAIR MRI

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →