基于机器学习的脑胶质瘤多模态影像分析

脑部胶质瘤是临床中常见的一种原发性脑肿瘤，具有复发率高、死亡率高以及治愈率低的特点。常规临床诊断主要依靠计算机断层扫描(CT)和磁共振成像(MRI)检查技术进行鉴别。随着成像技术和机器学习方法的不断发展，多模态影像智能分析技术已经逐步成为研究热点，在脑胶质瘤的病灶分割测量、肿瘤分级、预后生存周期预测和基因型辨别等方面具有重要的应用前景。本文重点介绍基于机器学习和多模态影像在脑胶质瘤临床辅助诊断和预后评估中的应用进展。     

Risk factors associated with delayed methotrexate clearance and increased toxicity in pediatric patients with osteosarcoma

High‐dose methotrexate (HD‐MTX; 12 g/m²) is part of standard therapy for pediatric osteosarcoma (OS). Risk factors associated with MTX toxicity in children with OS are not well defined. We investigated the association between peak MTX levels (four‐hour) and delayed MTX clearance or treatment toxicity. Information was retrieved from electronic medical records of 33 OS patients treated with HD‐MTX at Texas Children's Hospital from 2008 to 2015. We found that the four‐hour MTX level did not contribute to toxicity or delayed MTX clearance. We demonstrated that certain demographic characteristics are associated with delayed clearance and increased toxicity.