Cascaded Multi-Column RVFL+ Classifier for Single-Modal Neuroimaging-Based Diagnosis of Parkinson's Disease

• Published in: IEEE transactions on biomedical engineering Vol. 66; no. 8; pp. 2362 - 2371
• Main Authors: Shi, Jun, Xue, Zeyu, Dai, Yakang, Peng, Bo, Dong, Yun, Zhang, Qi, Zhang, Yingchun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; cascaded multi-column RVFL; Classification algorithms; Classifiers; Datasets; Diagnosis; Diseases; Humans; Image Interpretation, Computer-Assisted - methods; learning using privileged information; Machine Learning; Magnetic resonance imaging; Medical imaging; Movement disorders; Neurodegenerative diseases; Neuroimaging; Neuroimaging - methods; Neurology; Parkinson Disease - diagnostic imaging; Parkinson's disease; Prediction algorithms; random vector functional link network plus (RVFL+); Task analysis; Training
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2018.2889398

The neuroimaging-based computer-aided diagnosis for Parkinson's disease (PD) has attracted considerable attention in recent years, where the classifier plays a critical role. Random vector functional link network (RVFL) has shown its effectiveness for classification task, while its extended version, namely RVFL plus (RVFL+), integrates the additional privileged information (PI) about training samples in RVFL to help training a more effective classifier. On the other hand, it is still a popular way to adopt only a single neuroimaging modality for PD diagnosis in a clinical practice. In this work, we construct a novel cascaded multi-column RVFL+ (cmcRVFL+) framework for the single-modal neuroimaging-based PD diagnosis without the additional neuroimaging modality as PI. Specifically, the predicted values of RVFL+ classifiers in the current layers are used as the PI for the following classifiers, and therefore, the PI features are self-generated without additional modality. Furthermore, only the multi-column RVFL+ classifiers in the last layer of cmcRVFL+ are finally ensembled to generate the predictive result in the test stage. The experimental results on both the transcranial sonography data set and the magnetic resonance imaging data set for PD show that the proposed cmcRVFL+ algorithm achieves superior performance to all the compared algorithms. It suggests that the proposed cmcRVFL+ has the potential to be flexibly applied to various single-modal imaging based CAD.