人工智能
计算机科学
卷积神经网络
磁共振成像
深度学习
模式识别(心理学)
人工神经网络
网(多面体)
相似性(几何)
特征(语言学)
机器学习
医学
图像(数学)
放射科
数学
几何学
语言学
哲学
作者
Ashraf Haroon Rashid,Ankur Gupta,Jayesh K. Gupta,M. Tanveer
出处
期刊:IEEE Journal of Biomedical and Health Informatics
[Institute of Electrical and Electronics Engineers]
日期:2023-03-01
卷期号:27 (3): 1205-1213
被引量:9
标识
DOI:10.1109/jbhi.2022.3174033
摘要
Alzheimer's Disease (AD) is a neurodegenerative disease that is one of the significant causes of death in the elderly population. Many deep learning techniques have been proposed to diagnose AD using Magnetic Resonance Imaging (MRI) scans. Predicting AD using 2D slices extracted from 3D MRI scans is challenging as the inter-slice information gets lost. To this end, we propose a novel and lightweight framework termed 'Biceph-net' for AD diagnosis using 2D MRI scans that models both the intra-slice and inter-slice information. 'Biceph-net' has been experimentally shown to perform similar to other Spatio-temporal neural networks while being computationally more efficient. Biceph-net is also superior in performance compared to vanilla 2D convolutional neural networks (CNN) for AD diagnosis using 2D MRI slices. Biceph-net also has an inbuilt neighbourhood-based model interpretation feature that can be exploited to understand the classification decision taken by the network. Biceph-net experimentally achieves a test accuracy of 100% in the classification of Cognitively Normal (CN) vs AD, 98.16% for Mild Cognitive Impairment (MCI) vs AD, and 97.80% for CN vs MCI vs AD.
科研通智能强力驱动
Strongly Powered by AbleSci AI