Prognosis Prediction of Alzheimer's Disease: Multi-Horizon MMSE Prediction from MRI and Metadata

알츠하이머병 예후 예측: MRI 및 메타데이터를 활용한 MMSE 점수 예측 모델

This study aims to predict MMSE scores in Alzheimer's disease (AD) patients using a CNN-LSTM model that processes MRI images and metadata. The OASIS-2 dataset was used, with MRI slices (central, ±10mm, and ±15mm) and metadata. Two datasets were created: one with central and ±10mm slices (10mm dataset), and another with central, ±10mm, and ±15mm slices (combined dataset). The CNN-LSTM model extracted features using VGG16 and combined them with metadata to predict MMSE scores. The 10mm model outperformed the combined model, achieving an MSE of 0.527 and MAE of 0.509. This study highlights the potential of predicting MMSE scores using MRI and metadata for early diagnosis of AD.