Trigeminal neuralgia (TN) is a severe and disabling facial pain condition and is characterized by intermittent, severe, electric shock-like pain in one (or more) trigeminal subdivisions. This pain can be triggered by an innocuous stimulus or can be spontaneous. Presently available therapies for TN include both surgical and pharmacological management; however, the lack of a known etiology for TN contributes to the unpredictable response to treatment and the variability in long-term clinical outcomes. Given this, a range of peripheral and central mechanisms underlying TN pain remain to be understood. We acquired functional magnetic resonance imaging (fMRI) data from TN patients who (1) rested comfortably in the scanner during a resting state session and (2) rated their pain levels in real time using a calibrated tracking ball-controlled scale in a pain tracking session. Following data acquisition, the data was analyzed using the conventional correlation analysis and two artificial intelligence (AI)-inspired deep learning methods: convolutional neural network (CNN) and graph convolutional neural network (GCNN). Each of the three methods yielded a set of brain regions related to the generation and perception of pain in TN. There were six regions that were identified by all three methods, including the superior temporal cortex, the insula, the fusiform, the precentral gyrus, the superior frontal gyrus, and the supramarginal gyrus. Additionally, 17 regions, including dorsal anterior cingulate cortex(dACC) and the thalamus, were identified by at least two of the three methods. Collectively, these 23 regions represent signature centers of TN pain and provide target areas for future studies relating to central mechanisms of TN.

Trigeminal neuralgia (TN) is a severe and disabling facial pain condition and is characterized by intermittent, severe, electric shock-like pain in one (or more) trigeminal subdivisions. This pain can be triggered by an innocuous stimulus or can be spontaneous. Presently available therapies for TN include both surgical and pharmacological management; however, the lack of a known etiology for TN contributes to the unpredictable response to treatment and the variability in long-term clinical outcomes. Given this, a range of peripheral and central mechanisms underlying TN pain remain to be understood. We acquired functional magnetic resonance imaging (fMRI) data from TN patients who (1) rested comfortably in the scanner during a resting state session and (2) rated their pain levels in real time using a calibrated tracking ball-controlled scale in a pain tracking session. Following data acquisition, the data was analyzed using the conventional correlation analysis and two artificial intelligence (AI)-inspired deep learning methods: convolutional neural network (CNN) and graph convolutional neural network (GCNN). Each of the three methods yielded a set of brain regions related to the generation and perception of pain in TN. There were 6 regions that were identified by all three methods, including the superior temporal cortex, the insula, the fusiform, the precentral gyrus, the superior frontal gyrus, and the supramarginal gyrus. Additionally, 17 regions, including dorsal anterior cingulate cortex (dACC) and the thalamus, were identified by at least two of the three methods. Collectively, these 23 regions are taken to represent signature centers of TN pain and provide target areas for future studies seeking to understand the central mechanisms of TN.

Trigeminal neuralgia (TN) is a highly debilitating facial pain condition. Magnetic resonance imaging (MRI) is the main method for generating insights into the central mechanisms of TN pain in humans. Studies have found both structural and functional abnormalities in various brain structures in TN patients as compared with healthy controls. Whereas studies have also examined aberrations in brain networks in TN, no studies have to date investigated causal interactions in these brain networks and related these causal interactions to the levels of TN pain. We recorded fMRI data from 39 TN patients who either rested comfortably in the scanner during the resting state session or tracked their pain levels during the pain tracking session. Applying Granger causality to analyze the data and requiring consistent findings across the two scanning sessions, we found 5 causal interactions, including: (1) Thalamus -> dACC, (2) Caudate -> Inferior temporal gyrus, (3) Precentral gyrus -> Inferior temporal gyrus, (4) Supramarginal gyrus -> Inferior temporal gyrus, and (5) Bankssts -> Inferior temporal gyrus, that were consistently associated with the levels of pain experienced by the patients. Utilizing these 5 causal interactions as predictor variables and the pain score as the predicted variable in a linear multiple regression model, we found that in both pain tracking and resting state sessions, the model was able to explain ~36% of the variance in pain levels, and importantly, the model trained on the 5 causal interaction values from one session was able to predict pain levels using the 5 causal interaction values from the other session, thereby cross-validating the models. These results, obtained by applying novel analytical methods to neuroimaging data, provide important insights into the pathophysiology of TN and could inform future studies aimed at developing innovative therapies for treating TN.

No abstract

Multivoxel pattern analysis (MVPA) examines the differences in fMRI activation patterns associated with different cognitive conditions and provides information not possible with the conventional univariate analysis. Support vector machines (SVMs) are the predominant machine learning method in MVPA. SVMs are intuitive and easy to apply. The limitation is that it is a linear method and mainly suitable for analyzing data that are linearly separable. Convolutional neural networks (CNNs), a class of AI models originally developed for object recognition, are known to have the ability to approximate nonlinear relationships. CNNs are rapidly becoming an alternative to SVMs. The purpose of this study is to compare the two methods when they are applied to the same datasets. Two datasets were considered: (1) fMRI data collected from participants during a cued visual spatial attention task (the attention dataset) and (2) fMRI data collected from participants viewing natural images containing varying degrees of affective content (the emotion dataset). We found that (1) both SVM and CNN are able to achieve above chance level decoding accuracies for attention control and emotion processing in both the primary visual cortex and the whole brain with, (2) the CNN decoding accuracies are consistently higher than that of the SVM, (3) the SVM and CNN decoding accuracies are generally not correlated with each other, and (4) the heatmaps derived from SVM and CNN are not significantly overlapping. These results suggest that (1) there are both linearly separable features and nonlinearly separable features in fMRI data that distinguish cognitive conditions and (2) applying both SVM and CNN to the same data may yield a more comprehensive understanding of neuroimaging data.