( Aim ) Multiple sclerosis is a neurological condition that may cause neurologic disability. Convolutional neural network can achieve good results, but tuning hyperparameters of CNN needs expert knowledge and are difficult and time-consuming. To identify multiple sclerosis more accurately, this article proposed a new transfer-learning-based approach. ( Method ) DenseNet-121, DenseNet-169, and DenseNet-201 neural networks were compared. In addition, we proposed the use of a composite learning factor (CLF) that assigns different learning factor to three types of layers: early frozen layers, middle layers, and late replaced layers. How to allocate layers into those three layers remains a problem. Hence, four transfer learning settings (viz., Settings A, B, C, and D) were tested and compared. A precomputation method was utilized to reduce the storage burden and accelerate the program. ( Results ) We observed that DenseNet-201-D (the layers from CP to T3 are frozen, the layers of D4 are updated with learning factor of 1, and the final new layers of FCL are randomly initialized with learning factor of 10) can achieve the best performance. The sensitivity, specificity, and accuracy of DenseNet-201-D was 98.27± 0.58, 98.35± 0.69, and 98.31± 0.53, respectively. ( Conclusion ) Our method gives better performances than state-of-the-art approaches. Furthermore, this composite learning rate gives superior results to traditional simple learning factor (SLF) strategy.

中文翻译：

---

基于 DenseNet-201 的具有复合学习因子和预计算的多发性硬化分类深度神经网络

(目的) 多发性硬化症是一种可能导致神经功能障碍的神经系统疾病。卷积神经网络可以取得很好的效果，但CNN的超参数调优需要专业知识，难度大且耗时。为了更准确地识别多发性硬化症，本文提出了一种新的基于迁移学习的方法。(方法) DenseNet-121、DenseNet-169 和 DenseNet-201 神经网络进行了比较。此外，我们提出使用复合学习因子（CLF），将不同的学习因子分配给三种类型的层：早期冻结层、中间层和晚期替换层。如何将层分配到这三层仍然是一个问题。因此，测试和比较了四种迁移学习设置（即设置 A、B、C 和 D）。使用预计算方法来减少存储负担并加速程序。(结果) 我们观察到 DenseNet-201-D（从 CP 到 T3 的层被冻结，D4 的层以 1 的学习因子更新，最终的 FCL 的新层以 10 的学习因子随机初始化）可以实现最棒的表演。DenseNet-201-D 的灵敏度、特异性和准确度分别为 98.27±0.58、98.35±0.69 和 98.31±0.53。(结论) 我们的方法比最先进的方法具有更好的性能。此外，这种复合学习率比传统的简单学习因子（SLF）策略提供了更好的结果。