Amide Proton Transfer (APT) imaging in tumor with a machine learning approach using partially synthetic data.
Amide Proton Transfer (APT) imaging in tumor with a machine learning approach using partially synthetic data.
复制标题
DOI：
10.1002/mrm.29970
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
Malvika Viswanathan;Leqi Yin;Yashwant Kurmi;Z. Zu
中科院分区：
文献类型：
--
作者：
Malvika Viswanathan;Leqi Yin;Yashwant Kurmi;Z. Zu
机器学习（ML）越来越多地用于量化CEST效果。机器学习模型通常使用测量数据或完全模拟数据进行训练。然而，使用测量数据进行训练往往缺乏足够的训练数据，而使用完全模拟数据进行训练可能会由于有限的模拟池而引入偏差。本研究引入了一个新的平台，将模拟和测量成分结合起来，生成部分合成的CEST数据，并评估其用于训练ML模型预测酰胺质子转移（APT）效应的可行性。
Machine learning (ML) has been increasingly used to quantify CEST effect. ML models are typically trained using either measured data or fully simulated data. However, training with measured data often lacks sufficient training data, whereas training with fully simulated data may introduce bias because of limited simulations pools. This study introduces a new platform that combines simulated and measured components to generate partially synthetic CEST data, and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.