Comparison of Classical Machine Learning & Deep Learning to Characterise Fibrosis & Inflammation Using Quantitative MRI
Comparison of Classical Machine Learning & Deep Learning to Characterise Fibrosis & Inflammation Using Quantitative MRI
复制标题
DOI：
10.1109/isbi48211.2021.9433962
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
E. Chan;Matt Kelly;J. Schnabel
中科院分区：
文献类型：
--
作者：
E. Chan;Matt Kelly;J. Schnabel
定量MRI指标T1已被用于鉴别肝脏中的纤维炎症;然而，单独的T1值无法区分纤维化和炎症。我们评估了经典机器学习技术（K-最近邻，支持向量机和随机森林）的潜在效用，以解决这个问题，使用T1图中的信息。我们还比较了迁移学习，利用多种方法来减轻班级不平衡的影响。自适应合成抽样的随机森林在纤维炎症分类方面上级优于平均T1。尽管样本数量相对较少（n=289），类别不平衡较大，但我们的结果表明，使用整个T1图和机器学习来完成这项任务是有潜力的。
The quantitative MRI metric, T1, has been used to characterise fibroinflammation in the liver; however, the T1 value alone is unable to differentiate between fibrosis and inflammation. We evaluate the potential utility of classical machine learning techniques (K-Nearest Neighbours, Support Vector Machine and Random Forest) to address this problem using information in the T1 map. We also compare to transfer learning, utilising multiple methods to alleviate the effects of class imbalance. Random Forest with Adaptive Synthetic Sampling was superior to mean T1 in categorising fibroinflammation. Despite the relatively small number of samples (n=289) and large class imbalance, our results demonstrate potential in using the whole T1 map with machine learning for this task.