Discussion on the Application of Multi-modal Magnetic Resonance Imaging Fusion in Schizophrenia

Structural and functional abnormalities across clinical stages of psychosis: A multimodal neuroimaging investigation

BACKGROUND

Structural and functional neurobiological abnormalities have been observed in schizophrenia. Previous studies have concentrated on specific illness stages, obscuring relationships between functional/structural changes and disorder progression. The present study aimed to quantify structural and functional abnormalities across different clinical stages using functional near-infrared spectroscopy (fNIRS) and structural magnetic resonance imaging (sMRI).

METHODS

Fifty-four participants with first-episode schizophrenia (FES), 120 with clinically high risk of psychosis (CHR), and 111 healthy controls (HCs) underwent functional near-infrared spectroscopy (fNIRS) to measure oxyhemoglobin (Oxy-Hb) during the verbal fluency task. Among them, 28FES, 64CHR and 55HC also finished sMRI. Oxy-Hb and gray matter volume (GMV) were compared among the three groups while controlling for covariates, including age, sex, years of education, and task performance. Mediation analysis was utilized to determine the mediating effect of GMV on Oxy-Hb and cognition.

RESULTS

Compared with the HC group, CHR and FES groups showed significantly reduced brain activity. However, there were no significant differences between the FES and CHR. Pronounced GMV increase in the right frontal pole area (F = 4.234, p = 0.016) was identified in the CHR and FES groups. Mediation analysis showed a significant mediation effect of the right frontal pole GMV between Channel 31 Oxy-Hb and processing speed (z = 2.105, p = 0.035) and attention/vigilance (z = 1.992, p = 0.046).

CONCLUSIONS

Brain activation and anatomical deficits were observed in different brain regions, suggesting that anatomical and functional abnormalities are dissociated in the early stages of psychosis. The relationship between neural activity and anatomy may reflect a specific pathophysiology related to cognitive deterioration in schizophrenia.

Data-driven multimodal fusion: approaches and applications in psychiatric research

In the era of big data, where vast amounts of information are being generated and collected at an unprecedented rate, there is a pressing demand for innovative data-driven multi-modal fusion methods. These methods aim to integrate diverse neuroimaging perspectives to extract meaningful insights and attain a more comprehensive understanding of complex psychiatric disorders. However, analyzing each modality separately may only reveal partial insights or miss out on important correlations between different types of data. This is where data-driven multi-modal fusion techniques come into play. By combining information from multiple modalities in a synergistic manner, these methods enable us to uncover hidden patterns and relationships that would otherwise remain unnoticed. In this paper, we present an extensive overview of data-driven multimodal fusion approaches with or without prior information, with specific emphasis on canonical correlation analysis and independent component analysis. The applications of such fusion methods are wide-ranging and allow us to incorporate multiple factors such as genetics, environment, cognition, and treatment outcomes across various brain disorders. After summarizing the diverse neuropsychiatric magnetic resonance imaging fusion applications, we further discuss the emerging neuroimaging analyzing trends in big data, such as N-way multimodal fusion, deep learning approaches, and clinical translation. Overall, multimodal fusion emerges as an imperative approach providing valuable insights into the underlying neural basis of mental disorders, which can uncover subtle abnormalities or potential biomarkers that may benefit targeted treatments and personalized medical interventions.

Decreased gray matter volume and dynamic functional alterations in medicine-free obsessive-compulsive disorder

BACKGROUND

Previous studies discovered the presence of abnormal structures and functions in the brain regions of patients with obsessive-compulsive disorder (OCD). Nevertheless, whether structural changes in brain regions are coupled with alterations in dynamic functional connectivity (dFC) at rest in medicine-free patients with OCD remains vague.

METHODS

Three-dimensional T₁-weighed magnetic resonance imaging (MRI) and resting-state functional MRI were performed on 50 medicine-free OCD and 50 healthy controls (HCs). Firstly, the differences in gray matter volume (GMV) between OCD and HCs were compared. Then, brain regions with aberrant GMV were used as seeds for dFC analysis. The relationship of altered GMV and dFC with clinical parameters in OCD was explored using partial correlation analysis. Finally, support vector machine was applied to examine whether altered multimodal imaging data might be adopted to distinguish OCD from HCs.

RESULTS

Our findings indicated that GMV in the left superior temporal gyrus (STG) and right supplementary motor area (SMA) was reduced in OCD, and the dFC between the left STG and the left cerebellum Crus I and left thalamus, and between the right SMA and right dorsolateral prefrontal cortex (DLPFC) and left precuneus was decreased at rest in OCD. The brain regions both with altered GMV and dFC values could discriminate OCD from HCs with the accuracy of 0.85, sensitivity of 0.90 and specificity of 0.80.

CONCLUSION

The decreased gray matter structure coupling with dynamic function in the left STG and right SMA at rest may be crucial in the pathophysiology of OCD.

TRIAL REGISTRATION

Study on the mechanism of brain network in obsessive-compulsive disorder with multi-model magnetic resonance imaging (registration date: 08/11/2017; registration number: ChiCTR-COC-17,013,301).

Structural and diffusion MRI based schizophrenia classification using 2D pretrained and 3D naive Convolutional Neural Networks

The ability of automatic feature learning makes Convolutional Neural Network (CNN) potentially suitable to uncover the complex and widespread brain changes in schizophrenia. Despite that, limited studies have been done on schizophrenia identification using interpretable deep learning approaches on multimodal neuroimaging data. Here, we developed a deep feature approach based on pre-trained 2D CNN and naive 3D CNN models trained from scratch for schizophrenia classification by integrating 3D structural and diffusion magnetic resonance imaging (MRI) data. We found that the naive 3D CNN models outperformed the pretrained 2D CNN models and the handcrafted feature-based machine learning approach using support vector machine during both cross-validation and testing on an independent dataset. Multimodal neuroimaging-based models accomplished performance superior to models based on a single modality. Furthermore, we identified brain grey matter and white matter regions critical for illness classification at the individual- and group-level which supported the salience network and striatal dysfunction hypotheses in schizophrenia. Our findings underscore the potential of CNN not only to automatically uncover and integrate multimodal 3D brain imaging features for schizophrenia identification, but also to provide relevant neurobiological interpretations which are crucial for developing objective and interpretable imaging-based probes for prognosis and diagnosis in psychiatric disorders.

Fusion analysis of gray matter and white matter in subjective cognitive decline and mild cognitive impairment by multimodal CCA-joint ICA

BACKGROUND

Previous multimodal neuroimaging studies analyzed each dataset independently in subjective cognitive decline (SCD) and mild cognitive impairment (MCI), missing the cross-information. Multi-modal fusion analysis can provide more integral and comprehensive information regarding the brain. There has been a paucity of research on fusion analysis of sMRI and DTI in SCD and MCI.

MATERIALS AND METHODS

In the present study, we conducted fusion analysis of structural MRI and DTI by applying multimodal canonical correlation analysis with joint independent component analysis (mCCA-jICA) to capture the cross-information of gray matter (GM) and white matter (WM) in 62 SCD patients, 99 MCI patients, and 70 healthy controls (HCs). We further analyzed correlations between the mixing coefficients of mCCA-jICA and neuropsychological scores among the three groups.

RESULTS

A set of joint-discriminative independent components of GM and fractional anisotropy (FA) exhibited significant links between SCD and HCs, as well as between MCI and HCs. The covariant abnormalities primarily involved the frontal lobe/middle temporal gyrus/calcarine sulcus-anterior thalamic radiation/superior longitudinal fasciculus in SCD, and middle temporal gyrus/ fusiform gyrus/caudate necleus-forceps minor/anterior thalamic radiation in MCI. There was no significant difference between SCD and MCI groups.

CONCLUSIONS

The covariant GM-WM abnormalities in SCD and MCI were found in specific brain regions involved in cognitive processing, which confirms the simultaneous GM and WM changes underlying cognitive decline. These findings suggest that multimodal fusion analysis allows for a more comprehensive understanding of the association among different types of brain tissues and its crucial role in the neuropathological mechanism of SCD and MCI.