脑深部刺激
神经科学
帕金森病
神经影像学
计算机科学
功能连接
心理学
疾病
数据科学
人工智能
机器学习
医学
病理
作者
Yu Liu,Aiping Liu,Liangyong Li,WU Yun-xia,Martin J. McKeown,Xun Chen,Feng Wu
出处
期刊:IEEE Transactions on Biomedical Engineering
[Institute of Electrical and Electronics Engineers]
日期:2023-05-01
卷期号:70 (5): 1539-1552
被引量:6
标识
DOI:10.1109/tbme.2022.3222072
摘要
Connectivity-based parcellation (CBP) studies for exploring cerebral topographic organization have emerged rapidly, likely due to the joint developments of non-invasive imaging technologies and advances in computing science. CBP studies have extended our understanding of human brain development and many brain-related disorders such as Parkinson's Disease (PD), and have provided promising approaches to guide electrode placement during the planning of deep brain stimulation (DBS) surgery. This work reviews prevalent CBP methods, summarizing the methodological advantages and limitations of each. As PD is the second most common neurodegenerative disorder, we particularly focus on data-driven parcellation studies in this disease, providing researchers with a comprehensive overview of PD-specific atlases and their applications. We show that, while many advances have been achieved, heterogeneity in the PD population still provides an ongoing challenge to find a robust consensus on regional representation. Although some parcellation-driven studies exhibit encouraging achievements, these PD-specific parcellations are still limited and most approaches depend on a single modality. We discuss the future directions of parcellation-driven PD exploration and surgical planning, with the aim to inspire future investigation into connectivity-based parcellation for PD.
科研通智能强力驱动
Strongly Powered by AbleSci AI