Kim Han Woong, Lee Ha Eun, Lee Sangwon, Oh Kyeong Taek, Yun Mijin, Yoo Sun Kook
Department of Medical Engineering, Yonsei University College of Medicine, Seoul, Republic of Korea.
Department of Nuclear Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.
Eur J Nucl Med Mol Imaging. 2020 Aug;47(9):2197-2206. doi: 10.1007/s00259-019-04676-y. Epub 2020 Jan 24.
The aim of this feasibility study was to use slice selective learning using a Generative Adversarial Network for external validation. We aimed to build a model less sensitive to PET imaging acquisition environment, since differences in environments negatively influence network performance. To investigate the slice performance, each slice evaluation was performed.
We trained our model using a 18F-fluorodeoxyglucose ([F]FDG) PET/CT dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and tested the model with a Severance Hospital dataset. We applied slice selective learning to reduce computational cost and to extract unbiased features. We extracted features of Alzheimer's disease (AD) and normal cognitive (NC) condition using a Boundary Equilibrium Generative Adversarial Network (BEGAN) for stable convergence. Then, we utilized these features to train a support vector machine (SVM) classifier to distinguish AD from NC.
The slice range that covered the posterior cingulate cortex (PCC) using double slices showed the best performance. The accuracy, sensitivity, and specificity of our proposed network was 94.33%, 91.78%, and 97.06% using the Severance dataset and 94.82%, 92.11%, and 97.45% using the ADNI dataset. The performance on the two independent datasets showed no statistical difference (p > 0.05). Moreover, there was a statistical difference in the performance between using two slices and one slice as input (p < 0.05).
Our model learned the generalized features of AD and NC for external validation when appropriate slices were selected. This study showed the feasibility of this model with consistent performance when tested using datasets acquired from a variety of image-acquisition environments.
本可行性研究的目的是使用生成对抗网络进行切片选择性学习以进行外部验证。我们旨在构建一个对PET成像采集环境不太敏感的模型，因为环境差异会对网络性能产生负面影响。为了研究切片性能，对每个切片进行了评估。
我们使用从阿尔茨海默病神经影像倡议（ADNI）数据库获得的18F-氟脱氧葡萄糖（[F]FDG）PET/CT数据集训练模型，并使用首尔峨山医院数据集对模型进行测试。我们应用切片选择性学习来降低计算成本并提取无偏特征。我们使用边界平衡生成对抗网络（BEGAN）提取阿尔茨海默病（AD）和正常认知（NC）状态的特征以实现稳定收敛。然后，我们利用这些特征训练支持向量机（SVM）分类器以区分AD和NC。
使用双切片覆盖后扣带回皮质（PCC）的切片范围表现出最佳性能。使用首尔峨山医院数据集时，我们提出的网络的准确率、灵敏度和特异性分别为94.33%、91.78%和97.06%，使用ADNI数据集时分别为94.82%、92.11%和97.45%。在两个独立数据集上的性能没有统计学差异（p>0.05）。此外，使用两片和一片作为输入时的性能存在统计学差异（p<0.05）。
当选择合适的切片时，我们的模型学习了AD和NC的通用特征以进行外部验证。本研究表明，使用从各种图像采集环境获取的数据集进行测试时，该模型具有一致性能的可行性。
