Deep learning-enabled quantification of simultaneous PET/MRI for cell transplantation monitoring.
Deep learning-enabled quantification of simultaneous PET/MRI for cell transplantation monitoring.
复制标题
DOI：
10.1016/j.isci.2023.107083
复制
发表时间：
2023-07-21
期刊：
影响因子：
5.8
通讯作者：
Wang, Ping
中科院分区：
文献类型：
--
作者：
Hayat, Hasaan;Wang, Rui;Sun, Aixia;Mallett, Christiane L.;Nigam, Saumya;Redman, Nathan;Bunn, Demarcus;Gjelaj, Elvira;Talebloo, Nazanin;Alessio, Adam;Moore, Anna;Zinn, Kurt;Wei, Guo-Wei;Fan, Jinda;Wang, Ping
目前利用磁共振成像（MRI）对糖尿病胰岛细胞移植进行体内成像的方法因灵敏度低而受限。正电子发射断层扫描（PET）/MRI一体机具有更高的灵敏度以及对细胞代谢进行可视化的能力。然而，这种双模态工具目前在细胞监测方面面临两大挑战。首先，PET的动态条件，如信号衰减和放射性的时空变化，阻碍了对移植细胞数量的准确定量。此外，不同放射科医生的选择偏差导致分割过程中出现人为误差。这就需要开发人工智能算法来对细胞移植的PET/MRI进行自动分析。在此，我们将用于分割的K - means++算法与卷积神经网络相结合，以预测细胞移植小鼠模型中的放射性。这项研究提供了一种将机器学习与深度学习算法相结合的工具，用于通过PET/MRI监测胰岛细胞移植。它还开启了一种对PET/MRI中的放射性进行自动分割和定量的动态方法。
开发了用于分析移植细胞PET/MRI的算法
用体外和体内数据集对三种算法进行了训练和测试
3D卷积神经网络预测细胞移植小鼠模型中实际的移植细胞数量
我们提供了一种通过PET/MRI监测胰岛移植的新工具
细胞生物学；人工智能应用
Current methods of in vivo imaging islet cell transplants for diabetes using magnetic resonance imaging (MRI) are limited by their low sensitivity. Simultaneous positron emission tomography (PET)/MRI has greater sensitivity and ability to visualize cell metabolism. However, this dual-modality tool currently faces two major challenges for monitoring cells. Primarily, the dynamic conditions of PET such as signal decay and spatiotemporal change in radioactivity prevent accurate quantification of the transplanted cell number. In addition, selection bias from different radiologists renders human error in segmentation. This calls for the development of artificial intelligence algorithms for the automated analysis of PET/MRI of cell transplantations. Here, we combined K-means++ for segmentation with a convolutional neural network to predict radioactivity in cell-transplanted mouse models. This study provides a tool combining machine learning with a deep learning algorithm for monitoring islet cell transplantation through PET/MRI. It also unlocks a dynamic approach to automated segmentation and quantification of radioactivity in PET/MRI. Algorithms were developed for the analysis of PET/MRI of transplanted cell Three algorithms were trained and tested with in vitro and in vivo datasets 3D CNN predicts actual transplanted cell numbers in cell-transplanted mouse models We provide a novel tool for monitoring islet transplantation through PET/MRI Cell biology; Artificial intelligence applications
登录
查看更多内容
影响因子：
--
作者：
Ullah W;Siddique I;Zulqarnain RM;Alam MM;Ahmad I;Raza UA
通讯作者：
Raza UA
影响因子：
5.5
作者：
Sun A;Hayat H;Liu S;Tull E;Bishop JO;Dwan BF;Gudi M;Talebloo N;Dizon JR;Li W;Gaudet J;Alessio A;Aguirre A;Wang P
通讯作者：
Wang P
影响因子：
9.3
作者：
Hope, Thomas A.;Fayad, Zahi A.;Catana, Ciprian
通讯作者：
Catana, Ciprian
影响因子：
6.7
作者：
Beiderwellen, Karsten J.;Poeppel, Thorsten D.;Lauenstein, Thomas C.
通讯作者：
Lauenstein, Thomas C.
DOI：
10.1007/s00259-012-2278-6
发表时间：
2013-02-01
影响因子：
9.1
作者：
Mueller, Wolfgang Peter;Melzer, Henriette Ingrid;Pfluger, Thomas
通讯作者：
Pfluger, Thomas