Convolutional neural networks (CNNs) have been the standard for computer vision tasks including applications in Alzheimer’s disease (AD). Recently, Vision Transformers (ViTs) have been introduced, which have emerged as a strong alternative to CNNs. A common precursor stage of AD is a syndrome called mild cognitive impairment (MCI). However, not all individuals diagnosed with MCI progress to AD. In this exploratory investigation, we aimed to assess whether a ViT can reliably classify converters versus non-converters. A transfer learning approach was used for model training by applying a pretrained ViT model, fine-tuned on the ADNI dataset. The cohort comprised 575 individuals (299 stable MCIs; 276 progressive MCIs who converted within 36 months) from whom axial T1-weighted MRI slices covering the hippocampal region were used as model inputs. Results showed an average area under the receiver operating characteristic curve (AUC-ROC) on the test set of 0.74 ± 0.02 (mean ± SD), an accuracy of 0.69 ± 0.03, a sensitivity of 0.65 ± 0.07, a specificity of 0.72 ± 0.06, and an F1-score for the progressive MCI class of 0.67 ± 0.04. These findings demonstrate that a ViT approach achieves reasonable accuracy for classifying AD converters vs. non-converters, though its generalizability and clinical utility require further validation.
Seiger et al. (Thu,) studied this question.