Predicting the Prognosis of MCI Patients Using Longitudinal MRI Data

The aim of this study is to develop a computer-aided diagnosis system with a deep-learning approach for distinguishing Mild Cognitive Impairment (MCI) due to Alzheimer's Disease (AD) patients among a list of MCI patients. In this system we are using the power of longitudinal data extracted from magnetic resonance (MR). For this work, a total of 294 MCI patients were selected from the ADNI database. Among them, 125 patients developed AD during their follow-up and the rest remained stable. The proposed computer-aided diagnosis system (CAD) attempts to identify brain regions that are significant for the prediction of developing AD. The longitudinal data were constructed using a 3D Jacobian-based method aiming to track the brain differences between two consecutive follow-ups. The proposed CAD system distinguishes MCI patients who developed AD from those who remained stable with an accuracy of 87.2 percent. Moreover, it does not depend on data acquired by invasive methods or cognitive tests. This work demonstrates that the use of data in different time periods contains information that is beneficial for prognosis prediction purposes that outperform similar methods and are slightly inferior only to those systems that use invasive methods or neuropsychological tests.

Automated summary

The study developed a computer-aided diagnosis system with a deep-learning approach to distinguish MCI patients due to AD using longitudinal MRI data. The proposed CAD system accurately identifies MCI patients who developed AD without relying on invasive methods or cognitive tests. The use of data from different time periods provides beneficial information for prognosis prediction, outperforming similar methods and being slightly inferior only to systems using invasive methods or neuropsychological tests.