研究人员开发了新的AI模型ATCS和MTS，利用PET/CT扫描预测肺癌患者的总生存期。这些模型优于基线TCS模型，分别取得了0.794和0.793的AUC。ATCS在短期预测（0.5-3年）方面表现更好，而MTS在长期预测（3.5-5年）方面表现更优。该研究使用了848名非小细胞肺癌患者的数据，并发现结合不同的影像学特征可以提高准确性。 AI
影响 这些模型为肺癌患者提供了改进的风险分层，可能指导个性化治疗和随访策略。
排序理由 该集群包含一篇详细介绍用于医学图像分析和生存期预测的新AI模型的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follow-up strategies in oncology. However, the impact of temporal modeling on imaging-based survival prediction remains insufficientl…
arXiv:2606.12140v1 Announce Type: new Abstract: Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follow-up strategies in oncology. However, the impact of temporal modeling on imaging…
Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follow-up strategies in oncology. However, the impact of temporal modeling on imaging-based survival prediction remains insufficientl…