Abstract
With the rapid development of machine learning techniques, multivariate pattern analysis (MVPA) is becoming increasingly popular in the field of neuroimaging data analysis. Several software packages have been developed to facilitate its application in neuroimaging studies. As most of these software packages are based on command lines, researchers are required to learn how to program, which has greatly limited the use of MVPA for researchers without programming skills. Moreover, lacking a graphical user interface (GUI) also hinders the standardization of the application of MVPA in neuroimaging studies and, consequently, the replication of previous studies or comparisons of results between different studies. Therefore, we developed a GUI-based toolkit for MVPA of neuroimaging data: MVPANI (MVPA for Neuroimaging). Compared with other existing software packages, MVPANI has several advantages. First, MVPANI has a GUI and is, thus, more friendly for non-programmers. Second, MVPANI offers a variety of machine learning algorithms with the flexibility of parameter modification so that researchers can test different algorithms and tune parameters to identify the most suitable algorithms and parameters for their own data. Third, MVPANI also offers the function of data fusion at two levels (feature level or decision level) to utilize complementary information contained in different measures obtained from multimodal neuroimaging techniques. In this paper, we introduce this toolkit and provide four examples to demonstrate its usage, including (1) classification between patients and controls, (2) identification of brain areas containing discriminating information, (3) prediction of clinical scores, and (4) multimodal data fusion.
Highlights
We introduce this software package and provide four examples to demonstrate the usage of MVPANI in different situations, including (1) classification between patients and healthy controls, (2) identification of brain areas containing discriminating information, (3) prediction of clinical scores of patients, and (4) multimodal data fusion
We can see that none of the 1,000 permutations generated a classification accuracy equal to or greater than the actual accuracy, resulting in a P < 0.001 (i.e., P < 1/1000), indicating that the spatial patterns of regional homogeneity (ReHo) images were distinguishable between patients and controls
MVPANI offers the Save and Load functions in the graphical user interface (GUI): With the Save function, researchers can save all configurations of their analysis pipeline so that they can log the exact settings for their analysis pipeline for future reference; with the load function, researchers can make modifications based on their previously used analysis pipelines and parameters and, make it very convenient to compare results when changing a given parameter while maintaining all other parameters unchanged
Summary
Multivariate pattern analysis (MVPA), a machine learning technique used in neuroimaging data analysis, has rapidly grown in popularity in recent years (Liang et al, 1993; Dosenbach et al, 2010; Wager et al, 2013; Liu et al, 2015, 2017; Moradi et al, 2015; Meng et al, 2016; Hazlett et al, 2017; Chung et al, 2018; Camacho et al, 2019). Using Bonferroni correction, that is, P = 0.006 (< 0.05/5), the result can be considered as significantly higher than chance level, indicating that the spatial patterns of restingstate fALFF maps were predictive of the RTs of the flanker task in healthy participants In this example, we demonstrate how to combine different measures extracted from multimodal neuroimaging data to improve performance of classification between patients and normal controls. Using the Load and Concatenate functions in the Data Fusion module, a concatenated feature vector was generated and stored as a
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
