儿科低级质瘤的非侵入性分子亚型与自我监督的转移学习
Divyanshu Tak1, Zezhong Ye1, Anna Zapaischykova1
1From the Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Mass (D.T., Z.Y., A.Z., Y.Z., A.B., R.C., H.H., H.J.W.L.A., B.H.K.); Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Boston Children's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115 (D.T., Z.Y., A.Z., Y.Z., A.B., R.C., H.H., K.X.L., H.E., H.J.W.L.A., D.A.H.K., B.H.K.); Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, Mass (S.V., S.P.P., T.Y.P.); Center for Data-Driven Discovery in Biomedicine (A.N., A.F.) and Department of Neurosurgery (A.F., A.C.R.), Children's Hospital of Philadelphia, Philadelphia, Pa; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (A.N.); Departments of Neurology, Pediatrics, and Neurologic Surgery, University of California San Francisco, San Francisco, Calif (S.M.); Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Mass (H.J.W.L.A.); Department of Radiology and Nuclear Medicine, CalifRIM & GROW, Maastricht University, Maastricht, the Netherlands (H.J.W.L.A.); and Department of Pediatric Oncology (P.B.) and Department of Pathology (K.L.L.), Dana-Farber Cancer Institute, Boston Children's Hospital, Harvard Medical School, Boston, Mass.
这项研究开发了一个深度学习管道,使用MRI扫描来预测儿科低度质瘤中的BRAF突变,改善非侵入性诊断和治疗规划.
科学领域:
- 医疗成像医学成像
- 在瘤学中使用人工智能
- 儿科神经瘤学 儿科神经瘤学
背景情况:
- 儿科低度结质瘤 (pLGG) 是儿童中最常见的脑瘤.
- 准确的BRAF突变状态对于pLGG的向治疗选择至关重要.
- 预测BRAF状态的非侵入性方法是必要的,以避免侵入性活检.
研究的目的:
- 开发和外部验证一个深度学习管道,用于非侵入性,基于MRI的BRAF突变状态分类在儿科低度质瘤.
- 在此背景下,评估转移学习和自我监督学习方法的表现.
- 为了提高模型的可解释性,使用新的度量.
主要方法:
- 创建了一个两阶段的深度学习管道:3D瘤细分,然后按部分进行分类.
- 从预训练的医学成像网络转移学习和自我监督的标签交叉培训 (TransferX) 被使用.
- 为了模型的可解释性,开发了一种新的"质量中心距离"度量.
主要成果:
- 在内部测试中,TransferX管道实现了高分类性能 (AUC从0.82到0.87).
- 外部验证证明了良好的概括性,AUC范围从0.72到0.78.
- 开发的管道成功预测了BRAF突变状态 (野生类型,融合,V600E).
结论:
- 转移学习和自我监督的交叉训练提高了儿科低度质瘤非侵入性BRAF突变状态预测的性能和通用性.
- 这种方法对儿科瘤学中有限的数据场景有希望.
- 该管道为指导治疗决策提供了一个非侵入性的替代方案.
更多相关视频
06:32Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
Published on: January 9, 2019
09:09Laser Capture Microdissection of Glioma Subregions for Spatial and Molecular Characterization of Intratumoral Heterogeneity, Oncostreams, and Invasion
Published on: April 12, 2020
相关概念视频
Adaptive Mechanisms in Cancer Cells
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...
Adaptive Mechanisms in Cancer Cells
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...
