N1 Magnitude of Auditory Evoked Potentials and Spontaneous Functional Connectivity Between Bilateral Heschl's Gyrus Are Coupled at Interindividual Level

Abstract To determine the neural mechanism underlying the effects of sound therapy on tinnitus, we hypothesize that sound therapy may be effective by modulating both local neural activity and functional connectivity that is associated with auditory perception, auditory information storage or emotional processing. In this prospective observational study, 30 tinnitus patients underwent resting-state functional magnetic resonance imaging scans at baseline and after 12 weeks of sound therapy. Thirty-two age- and gender-matched healthy controls also underwent two scans over a 12-week interval; 30 of these healthy controls were enrolled for data analysis. The amplitude of low-frequency fluctuation was analysed, and seed-based functional connectivity measures were shown to significantly alter spontaneous local brain activity and its connections to other brain regions. Interaction effects between the two groups and the two scans in local neural activity as assessed by the amplitude of low-frequency fluctuation were observed in the left parahippocampal gyrus and the right Heschl's gyrus. Importantly, local functional activity in the left parahippocampal gyrus in the patient group was significantly higher than that in the healthy controls at baseline and was reduced to relatively normal levels after treatment. Conversely, activity in the right Heschl's gyrus was significantly increased and extended beyond a relatively normal range after sound therapy. These changes were found to be positively correlated with tinnitus relief. The functional connectivity between the left parahippocampal gyrus and the cingulate cortex was higher in tinnitus patients after treatment. The alterations of local activity and functional connectivity in the left parahippocampal gyrus and right Heschl’s gyrus were associated with tinnitus relief. Resting-state functional magnetic resonance imaging can provide functional information to explain and ‘visualize’ the mechanism underlying the effect of sound therapy on the brain.

Download Full-text

Single-participant structural similarity matrices lead to greater accuracy in classification of participants than function in autism in MRI

Molecular Autism ◽

10.1186/s13229-021-00439-5 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Matthew J. Leming ◽

Simon Baron-Cohen ◽

John Suckling

Keyword(s):

Machine Learning ◽

Functional Connectivity ◽

Grey Matter ◽

Structural Similarity ◽

Single Subject ◽

Large Sample Size ◽

Intracranial Volume ◽

Heschl’S Gyrus ◽

Heschl's Gyrus ◽

Similarity Matrices

Abstract Background Autism has previously been characterized by both structural and functional differences in brain connectivity. However, while the literature on single-subject derivations of functional connectivity is extensively developed, similar methods of structural connectivity or similarity derivation from T1 MRI are less studied. Methods We introduce a technique of deriving symmetric similarity matrices from regional histograms of grey matter volumes estimated from T1-weighted MRIs. We then validated the technique by inputting the similarity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42–78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs. Limitations While this study used a large sample size, the majority of data was from a young age group; furthermore, to make a viable machine learning study, we treated autism, a highly heterogeneous condition, as a binary label. Thus, these results are not necessarily generalizable to all subtypes and age groups in autism. Results Our models gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural similarity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural similarity and functional connectivity gave an AUROC of 0.7354 (69.40% accuracy). Analysis of classification performance across age revealed the greatest accuracy in adolescents, in which most data were present. Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl’s gyrus and upper vermis for structural similarity. Conclusion This study provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models. Our methods revealed a unique emphasis of the deep learning model on the structure of the bilateral Heschl’s gyrus when characterizing autism.

Download Full-text