School of Computer, Electronics and Information, Guangxi University, Nanning, Guangxi, P. R. China.
Guangxi Key Laboratory of Multimedia Communications and Network Technology, Nanning, Guangxi, P. R. China.
Med Phys. 2022 Sep;49(9):5855-5869. doi: 10.1002/mp.15888. Epub 2022 Aug 10.
In recent years, two-dimensional convolutional neural network (2D CNN) have been widely used in the diagnosis of Alzheimer's disease (AD) based on structural magnetic resonance imaging (sMRI). However, due to the lack of targeted processing of the key slices of sMRI images, the classification performance of the CNN model needs to be improved.
Therefore, in this paper, we propose a key slice processing technique called the structural highlighting key slice stacking (SHKSS) technique, and we apply it to a 2D transfer learning model for AD classification.
Specifically, first, 3D MR images were preprocessed. Second, the 2D axial middle-layer image was extracted from the MR image as a key slice. Then, the image was normalized by intensity and mapped to the red, green, and blue (RGB) space, and histogram specification was performed on the obtained RGB image to generate the final three-channel image. The final three-channel image was input into a pretrained CNN model for AD classification. Finally, classification and generalization experiments were conducted to verify the validity of the proposed method.
The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) data set show that our SHKSS method can effectively highlight the structural information in MRI slices. Compared with existing key slice processing techniques, our SHKSS method has an average accuracy improvement of at least 26% on the same test data set, and it has better performance and generalization ability.
Our SHKSS method not only converts single-channel images into three-channel images to match the input requirements of the 2D transfer learning model but also highlights the structural information of MRI slices to improve the accuracy of AD diagnosis.
近年来，二维卷积神经网络（2D CNN）已广泛应用于基于结构磁共振成像（sMRI）的阿尔茨海默病（AD）诊断。然而，由于对 sMRI 图像关键切片的针对性处理不足，CNN 模型的分类性能有待提高。
因此，本文提出了一种称为结构突出关键切片堆叠（SHKSS）的关键切片处理技术，并将其应用于 AD 分类的 2D 迁移学习模型。
具体来说，首先对 3D MR 图像进行预处理；然后从 MR 图像中提取 2D 轴向中层图像作为关键切片；接着，通过强度对图像进行归一化，并将其映射到红、绿、蓝（RGB）空间，对获得的 RGB 图像进行直方图规范，生成最终的三通道图像；最后，将最终的三通道图像输入到预训练的 CNN 模型中进行 AD 分类。最后，通过分类和泛化实验验证了所提出方法的有效性。
在阿尔茨海默病神经影像学倡议（ADNI）数据集上的实验结果表明，我们的 SHKSS 方法可以有效地突出 MRI 切片中的结构信息。与现有的关键切片处理技术相比，我们的 SHKSS 方法在相同的测试数据集上的平均准确率提高了至少 26%，具有更好的性能和泛化能力。
我们的 SHKSS 方法不仅将单通道图像转换为三通道图像以匹配 2D 迁移学习模型的输入要求，而且还突出了 MRI 切片的结构信息，从而提高了 AD 诊断的准确性。
