Three-round Learning Strategy Based On 3d Deep Convolutional Gans For Alzheimer’s Disease Staging

Accurately diagnosing Alzheimer’s disease (AD) and its early stages is critical for prompt treatment or potential intervention. To address the overfitting problem brought on by the insufficient training sample size, a three-round learning strategy that combines transfer learning with generative adversarial learning was proposed. This model achieved accuracies of 92.8%, 78.1%, and 76.4% in the classifications of AD versus cognitively normal (CN), AD versus mild cognitive impairment (MCI), and MCI versus CN, respectively. The proposed model avoids overfitting brought on by a paucity of sMRI data and enables the early detection of AD.