2020/02/23 by Sema Candemir, Xuan V. Nguyen, Candemir, Sema +9
Medicine · Neuroscience · #Brain Tumor Detection and Classification #Dementia and Cognitive Impairment Research #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neurons and Cognition (q-bio.NC) #Quantitative Methods (q-bio.QM) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2002.10034
openalex publication_date 2020/02/23 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Purpose: This study investigates whether a machine-learning-based system can\npredict the rate of cognitive decline in mildly cognitively impaired patients\nby processing only the clinical and imaging data collected at the initial\nvisit.\n Approach: We built a predictive model based on a supervised hybrid neural\nnetwork utilizing a 3-Dimensional Convolutional Neural Network to perform\nvolume analysis of Magnetic Resonance Imaging and integration of non-imaging\nclinical data at the fully connected layer of the architecture. The experiments\nare conducted on the Alzheimers Disease Neuroimaging Initiative dataset.\n Results: Experimental results confirm that there is a correlation between\ncognitive decline and the data obtained at the first visit. The system achieved\nan area under the receiver operator curve (AUC) of 0.70 for cognitive decline\nclass prediction.\n Conclusion: To our knowledge, this is the first study that predicts slowly\ndeteriorating/stable or rapidly deteriorating classes by processing routinely\ncollected baseline clinical and demographic data (Baseline MRI, Baseline MMSE,\nScalar Volumetric data, Age, Gender, Education, Ethnicity, and Race). The\ntraining data is built based on MMSE-rate values. Unlike the studies in the\nliterature that focus on predicting Mild Cognitive Impairment-to-Alzheimer`s\ndisease conversion and disease classification, we approach the problem as an\nearly prediction of cognitive decline rate in MCI patients.\n