Transfer Learning Approach to Vascular Permeability Changes in Brain Metastasis Post-Whole-Brain Radiotherapy.
Transfer Learning Approach to Vascular Permeability Changes in Brain Metastasis Post-Whole-Brain Radiotherapy.
复制标题
转移学习方法，用于脑转移后全脑放射疗法的血管通透性变化。
作者：
动态对比增强（DCE）MRI已成为评估血管通透性和灌注的定量标准。然而，DCE MRI中的传统药代动力学（PK）建模对于每张图像具有数千像素的动态MR扫描是复杂且耗时的。我们之前已经开发了一种深度学习方法，使用卷积神经网络（CNN）作为一种有效且准确的工具，用于从胶质母细胞瘤（GBM）小鼠的DCE MRI生成PK参数图。在本研究中，通过GBM训练的CNN和全脑放疗（WBRT）治疗的脑转移（BM）小鼠之间的转移学习进一步建立了这种方法的实用性。本研究的目的是通过迁移学习进一步验证我们先前开发的CNN在BM的替代小动物模型中的实用性。与胶质瘤模型不同，BM小鼠模型出现多灶性颅内转移，包括DCE MRI上的对比增强和非增强病变，因此可作为研究肿瘤血管通透性的极佳脑肿瘤模型。在这里，我们通过将先前训练的GBM CNN转移到BM小鼠的DCE MRI数据集来进行转移学习。重新训练CNN以了解BM DCE图像与从扩展Tofts模型（ETM）提取的目标渗透率图之间的关系。发现转移的网络准确地预测BM渗透性，并且与目标ETM PK图具有良好的空间相关性。在用WBRT治疗的另一组BM小鼠中进一步测试CNN模型，以评估通过放射疗法诱导的血管通透性变化。CNN在WBRT处理的肿瘤中检测到显著增加的渗透性参数Ktranss（p < 0.01），这与靶ETM PK图非常一致。总之，所提出的CNN可以作为一种有效和准确的工具，用于表征小动物脑肿瘤模型中的血管通透性和治疗反应。
Dynamic contrast-enhanced (DCE) MRI has become a quantitative standard for assessing vascular permeability and perfusion. However, conventional pharmacokinetic (PK) modeling in DCE MRI is complex and time-consuming for dynamic MR scans with thousands of pixels per image. We have previously developed a deep learning approach using convolutional neural networks (CNN) as an efficient and accurate tool for the generation of PK parameter maps from DCE MRI of glioblastoma (GBM) mice. In the present study, the utility of this approach is further established through transfer learning between GBM-trained CNN and whole-brain radiotherapy (WBRT)-treated brain metastasis (BM) mice. The purpose of this study is to further validate the utility of our previously developed CNN in an alternative small animal model of BM through transfer learning. Unlike the glioma model, the BM mouse model develops multifocal intracranial metastases, including both contrast enhancing and non-enhancing lesions on DCE MRI, thus serving as an excellent brain tumor model to study tumor vascular permeability. Here, we conducted transfer learning by transferring the previously trained GBM CNN to DCE MRI datasets of BM mice. The CNN was re-trained to learn about the relationship between BM DCE images and target permeability maps extracted from the Extended Tofts Model (ETM). The transferred network was found to accurately predict BM permeability and presented with excellent spatial correlation with the target ETM PK maps. The CNN model was further tested in another cohort of BM mice treated with WBRT to assess vascular permeability changes induced via radiotherapy. The CNN detected significantly increased permeability parameter Ktrans in WBRT-treated tumors (p < 0.01), which was in good agreement with the target ETM PK maps. In conclusion, the proposed CNN can serve as an efficient and accurate tool for characterizing vascular permeability and treatment responses in small animal brain tumor models.
登录
查看更多内容
影响因子：
3.6
作者：
Nematollahi, Hamide;Moslehi, Masoud;Aminolroayaei, Fahimeh;Maleki, Maryam;Shahbazi-Gahrouei, Daryoush
通讯作者：
Shahbazi-Gahrouei, Daryoush
影响因子：
4.7
作者：
Yamashita R;Nishio M;Do RKG;Togashi K
通讯作者：
Togashi K
影响因子：
3.1
作者：
Arledge, Chad A.;Sankepalle, Deeksha M.;Crowe, William N.;Liu, Yang;Wang, Lulu;Zhao, Dawen
通讯作者：
Zhao, Dawen
DOI：
10.4261/1305-3825.dir.2537-08.1
发表时间：
2010-09
期刊：
Diagnostic and interventional radiology (Ankara, Turkey)
影响因子：
--
作者：
Türkbey B;Thomasson D;Pang Y;Bernardo M;Choyke PL
通讯作者：
Choyke PL
影响因子：
2.6
作者：
Crowe, William;Wang, Lulu;Zhao, Dawen
通讯作者：
Zhao, Dawen