相关实验视频
Updated: Jun 16, 2025

Whole-body PET/MRI of Pediatric Patients: The Details That Matter
Published on: December 19, 2017
使用多参数MRI进行儿科脑髓母细胞瘤瘤子组件的基于nnU-Net的细分:一个多机构研究
Rohan Bareja1, Marwa Ismail1, Douglas Martin1
1From the Department of Radiology, University of Wisconsin-Madison, Madison, Wis (R.B., M.I., I.Y.); University Hospitals, Cleveland, Ohio (D.M., A.N.); Departments of Biomedical Engineering (M.L., S.G., S.I.) and Neurosciences (P.D.), Case Western Reserve University, Cleveland, Ohio; Department of Radiology, Children's Hospital Los Angeles, Los Angeles, Calif (B.T.); Division of Hematology, Oncology & Bone Marrow Transplant, Nationwide Children's Hospital, Columbus, Ohio (R.S.); Department of Pediatrics, Keck School of Medicine of University of Southern California, Children's Hospital Los Angeles, Los Angeles, Calif (A.M.); Department of Pathology, Children's Hospital Los Angeles, Los Angeles, Calif (A.J.); Division of Oncology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio (P.d.B.); William S. Middleton Memorial Veterans Affairs (VA) Healthcare, Madison, Wis (P.T.); and Department of Radiology and Biomedical Engineering, University of Wisconsin-Madison, 750 Highland Ave, Madison, WI 53726 (P.T.).
nnU-Net模型在多机构MRI扫描上准确地细分了儿科脑髓母细胞瘤. 转移学习和直接深度学习方法显示出稳健性,有助于放射治疗规划.
科学领域:
- 放射学 放射学是一门学科.
- 人工智能的人工智能
- 在瘤学瘤学.
背景情况:
- 脑髓母细胞瘤在MRI上的细分对于儿科治疗至关重要.
- 自动化细分可以提高准确性和效率.
研究的目的:
- 评估nnU-Net模型用于在多机构MRI上的自动化脑髓母细胞瘤划分.
- 为了比较转移学习和直接深度学习的方法.
主要方法:
- 在三个地点对78名儿科脑髓母细胞瘤患者进行了回顾性分析.
- nnU-Net模型训练有或没有从质瘤数据转移学习.
- 在不同培训/测试场地组合中评估模型稳定性.
主要成果:
- 这两种nnU-Net模型在各个站点都表现出强大的性能.
- 瘤息地的子得分在0.80-0.86.6之间.
- 细分分类,如增强瘤和瘤,显示出良好的结果.
结论:
- nnU-Net模型对精确的,自动化的脑髓母细胞瘤子区划划界有希望.
- 这些模型可能会增强儿科脑髓母细胞瘤的放射治疗计划.
- 对位点变化的稳定性表明其具有广泛的临床适用性.

