Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab 140401, India.
Centre of Excellence for Speech and Multimodal Laboratory, Chitkara University Institute of Engineering & Technology, Chitkara University, Punjab, India.
Comput Math Methods Med. 2021 Oct 4;2021:4186666. doi: 10.1155/2021/4186666. eCollection 2021.
Alzheimer's disease (AD) is one of the most important causes of mortality in elderly people, and it is often challenging to use traditional manual procedures when diagnosing a disease in the early stages. The successful implementation of machine learning (ML) techniques has also shown their effectiveness and its reliability as one of the better options for an early diagnosis of AD. But the heterogeneous dimensions and composition of the disease data have undoubtedly made diagnostics more difficult, needing a sufficient model choice to overcome the difficulty. Therefore, in this paper, four different 2D and 3D convolutional neural network (CNN) frameworks based on Bayesian search optimization are proposed to develop an optimized deep learning model to predict the early onset of AD binary and ternary classification on magnetic resonance imaging (MRI) scans. Moreover, certain hyperparameters such as learning rate, optimizers, and hidden units are to be set and adjusted for the performance boosting of the deep learning model. Bayesian optimization enables to leverage advantage throughout the experiments: A persistent hyperparameter space testing provides not only the output but also about the nearest conclusions. In this way, the series of experiments needed to explore space can be substantially reduced. Finally, alongside the use of Bayesian approaches, long short-term memory (LSTM) through the process of augmentation has resulted in finding the better settings of the model that too in less iterations with an relative improvement (RI) of 7.03%, 12.19%, 10.80%, and 11.99% over the four systems optimized with manual hyperparameters tuning such that hyperparameters that look more appealing from past data as well as the conventional techniques of manual selection.
阿尔茨海默病（AD）是老年人最重要的死亡原因之一，在疾病早期诊断时，传统的手动程序往往具有挑战性。机器学习（ML）技术的成功实施也表明了其有效性和可靠性，是 AD 早期诊断的较好选择之一。但是，疾病数据的异构维度和组成无疑使诊断更加困难，需要足够的模型选择来克服这一困难。因此，在本文中，提出了四个基于贝叶斯搜索优化的 2D 和 3D 卷积神经网络（CNN）框架，以开发优化的深度学习模型，对磁共振成像（MRI）扫描进行 AD 二进制和三分类的早期发作预测。此外，需要设置和调整某些超参数，如学习率、优化器和隐藏单元，以提高深度学习模型的性能。贝叶斯优化使我们能够在整个实验中利用优势：持续的超参数空间测试不仅提供输出，还提供关于最近结论的信息。通过这种方式，可以大大减少探索空间所需的一系列实验。最后，除了使用贝叶斯方法外，通过扩充过程使用长短期记忆（LSTM）也有助于找到更好的模型设置，与使用手动超参数调整优化的四个系统相比，迭代次数减少了 7.03%、12.19%、10.80%和 11.99%，相对改进（RI）分别为 7.03%、12.19%、10.80%和 11.99%，从而找到了更好的模型设置，这些超参数不仅看起来更吸引人，而且还结合了过去数据的优势以及传统的手动选择技术。
