Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.

Applications of MRI in Schizophrenia: Current Progress in Establishing Clinical Utility

Schizophrenia is a severe mental illness that significantly impacts the lives of affected individuals and with increasing mortality rates. Early detection and intervention are crucial for improving outcomes but the lack of validated biomarkers poses great challenges in such efforts. The use of magnetic resonance imaging (MRI) in schizophrenia enables the investigation of the disorder's etiological and neuropathological substrates in vivo. After decades of research, promising findings of MRI have been shown to aid in screening high-risk individuals and predicting illness onset, and predicting symptoms and treatment outcomes of schizophrenia. The integration of machine learning and deep learning techniques makes it possible to develop intelligent diagnostic and prognostic tools with extracted or selected imaging features. In this review, we aimed to provide an overview of current progress and prospects in establishing clinical utility of MRI in schizophrenia. We first provided an overview of MRI findings of brain abnormalities that might underpin the symptoms or treatment response process in schizophrenia patients. Then, we summarized the ongoing efforts in the computer-aided utility of MRI in schizophrenia and discussed the gap between MRI research findings and real-world applications. Finally, promising pathways to promote clinical translation were provided. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 3.

The impact of psychosocial adversity on brain and behaviour: an overview of existing knowledge and directions for future research

Environmental experiences play a critical role in shaping the structure and function of the brain. Its plasticity in response to different external stimuli has been the focus of research efforts for decades. In this review, we explore the effects of adversity on brain's structure and function and its implications for brain development, adaptation, and the emergence of mental health disorders. We are focusing on adverse events that emerge from the immediate surroundings of an individual, i.e., microenvironment. They include childhood maltreatment, peer victimisation, social isolation, affective loss, domestic conflict, and poverty. We also take into consideration exposure to environmental toxins. Converging evidence suggests that different types of adversity may share common underlying mechanisms while also exhibiting unique pathways. However, they are often studied in isolation, limiting our understanding of their combined effects and the interconnected nature of their impact. The integration of large, deep-phenotyping datasets and collaborative efforts can provide sufficient power to analyse high dimensional environmental profiles and advance the systematic mapping of neuronal mechanisms. This review provides a background for future research, highlighting the importance of understanding the cumulative impact of various adversities, through data-driven approaches and integrative multimodal analysis techniques.

Addressing Global Environmental Challenges to Mental Health Using Population Neuroscience: A Review

Importance

Climate change, pollution, urbanization, socioeconomic inequality, and psychosocial effects of the COVID-19 pandemic have caused massive changes in environmental conditions that affect brain health during the life span, both on a population level as well as on the level of the individual. How these environmental factors influence the brain, behavior, and mental illness is not well known.

Observations

A research strategy enabling population neuroscience to contribute to identify brain mechanisms underlying environment-related mental illness by leveraging innovative enrichment tools for data federation, geospatial observation, climate and pollution measures, digital health, and novel data integration techniques is described. This strategy can inform innovative treatments that target causal cognitive and molecular mechanisms of mental illness related to the environment. An example is presented of the environMENTAL Project that is leveraging federated cohort data of over 1.5 million European citizens and patients enriched with deep phenotyping data from large-scale behavioral neuroimaging cohorts to identify brain mechanisms related to environmental adversity underlying symptoms of depression, anxiety, stress, and substance misuse.

Conclusions and Relevance

This research will lead to the development of objective biomarkers and evidence-based interventions that will significantly improve outcomes of environment-related mental illness.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

A review on multiple sclerosis prognostic findings from imaging, inflammation, and mental health studies

Magnetic resonance imaging (MRI) of the brain is commonly used to detect where chronic and active lesions are in multiple sclerosis (MS). MRI is also extensively used as a tool to calculate and extrapolate brain health by way of volumetric analysis or advanced imaging techniques. In MS patients, psychiatric symptoms are common comorbidities, with depression being the main one. Even though these symptoms are a major determinant of quality of life in MS, they are often overlooked and undertreated. There has been evidence of bidirectional interactions between the course of MS and comorbid psychiatric symptoms. In order to mitigate disability progression in MS, treating psychiatric comorbidities should be investigated and optimized. New research for the prediction of disease states or phenotypes of disability have advanced, primarily due to new technologies and a better understanding of the aging brain.

Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imaging

BACKGROUND

Identifying individuals at risk for severe mental illness (SMI) is crucial for prevention and early intervention strategies. While MRI shows potential for case identification even before illness onset, no practical model for mental health risk monitoring has been developed. This study aims to develop an initial version of an efficient and practical model for mental health screening among at-risk populations.

METHODS

A deep learning model known as Multiple Instance Learning (MIL) was adopted to train and test a SMI detection model with clinical MRI scans of 14,915 patients with SMI (age 32.98 ± 12.01 years, 9102 women) and 4538 healthy controls (age 40.60 ± 10.95 years, 2424 women) in the primary dataset. Validation analysis was conducted in an independent dataset with 290 patients (age 28.08 ± 10.95 years, 169 women) and 310 healthy participants (age 33.55 ± 11.09 years, 165 women). Another three machine learning models of ResNet, DenseNet and EfficientNet were used for comparison. We also recruited 148 individuals receiving high-stress medical school education to characterize the potential real-world utility of the MIL model in detecting risk of mental illness.

FINDINGS

Similar performance of successful differentiation of individuals with SMI and healthy controls was observed for the MIL model (AUC: 0.82) and other models (ResNet, DenseNet, EfficientNet, 0.83, 0.81, and 0.80 respectively). MIL had better generalization in the validation test than other models (AUC: 0.82 vs 0.59, 0.66 and 0.59), and less drop-off in performance from 3.0T to 1.5T scanners. The MIL model did better in predicting clinician ratings of distress than self-ratings with questionnaires (84% vs 22%) in the medical student sample. Brain regions that contributed to SMI identification were mainly neocortical, including right precuneus, bilateral temporal regions, left precentral/postcentral gyrus, bilateral medial prefrontal cortex and right cerebellum.

INTERPRETATION

Our digital model based on brief clinical MRI protocols identified individual SMI patients with good accuracy and high sensitivity, suggesting that with incremental improvements the approach may offer potentially useful aid for early identification and intervention to prevent illness onset in vulnerable at-risk populations.

FUNDING

This study was supported by the National Natural Science Foundation of China, National Key Technologies R&D Program of China, and Sichuan Science and Technology Program.

Interpreting models interpreting brain dynamics

Brain dynamics are highly complex and yet hold the key to understanding brain function and dysfunction. The dynamics captured by resting-state functional magnetic resonance imaging data are noisy, high-dimensional, and not readily interpretable. The typical approach of reducing this data to low-dimensional features and focusing on the most predictive features comes with strong assumptions and can miss essential aspects of the underlying dynamics. In contrast, introspection of discriminatively trained deep learning models may uncover disorder-relevant elements of the signal at the level of individual time points and spatial locations. Yet, the difficulty of reliable training on high-dimensional low sample size datasets and the unclear relevance of the resulting predictive markers prevent the widespread use of deep learning in functional neuroimaging. In this work, we introduce a deep learning framework to learn from high-dimensional dynamical data while maintaining stable, ecologically valid interpretations. Results successfully demonstrate that the proposed framework enables learning the dynamics of resting-state fMRI directly from small data and capturing compact, stable interpretations of features predictive of function and dysfunction.

Interpreting Brain Biomarkers: Challenges and solutions in interpreting machine learning-based predictive neuroimaging

Predictive modeling of neuroimaging data (predictive neuroimaging) for evaluating individual differences in various behavioral phenotypes and clinical outcomes is of growing interest. However, the field is experiencing challenges regarding the interpretability of the results. Approaches to defining the specific contribution of functional connections, regions, or networks in prediction models are urgently needed, which may help explore the underlying mechanisms. In this article, we systematically review the methods and applications for interpreting brain signatures derived from predictive neuroimaging based on a survey of 326 research articles. Strengths, limitations, and the suitable conditions for major interpretation strategies are also deliberated. In-depth discussion of common issues in existing literature and the corresponding recommendations to address these pitfalls are provided. We highly recommend exhaustive validation on the reliability and interpretability of the biomarkers across multiple datasets and contexts, which thereby could translate technical advances in neuroimaging into concrete improvements in precision medicine.

Artificial Intelligence-Aided Multiple Tumor Detection Method Based on Immunohistochemistry-Enhanced Dark-Field Imaging

The immunohistochemical method serves as one of the most practical tools in clinical cancer detection and thus has great application value to overcome the existing limits of the conventional method and further improve the detecting efficiency and sensitivity. This study employed 3,3'-diaminobenzidine (DAB), a conventional color indicator for immunohistochemistry, as a novel high-sensitive scattering reagent to provide a multidimensional image signal varying with the overexpression rate of tumor markers. Based on the scattering properties of DAB aggregates, an efficient and robust artificial intelligence-aided immunohistochemical method based on dark-field imaging has been established, with improvement in both the imaging quality and interpretation efficiency in comparison with the conventional manual-operated immunohistochemical method. Referencing the diagnosis from three independent pathologists, this method succeeded in detecting HER2 overexpressed breast tumors with a sensitivity of 95.2% and a specificity of 100.0%; meanwhile, it was found to be applicable for non-small-cell lung tumors and malignant lymphoma as well. As demonstrated, this study provided an effective and reliable means for making diagnostic suggestions, which exhibited great potential in multiple tumor pathological detection at low cost.

Forecasting care seekers satisfaction with telemedicine using machine learning and structural equation modeling

Many individuals visit rural telemedicine centres to obtain safe and effective health remedies for their physical and emotional illnesses. This study investigates the antecedents of patients’ satisfaction relating to telemedicine adoption in rural public hospitals settings in Bangladesh through the adaptation of Expectation Disconfirmation Theory extended by Social Cognitive Theory. This research advances a theoretically sustained prediction model forecasting patients’ satisfaction with telemedicine to enable informed decision making. A research model explores four potential antecedents: expectations, performance, disconfirmation, and enjoyment; that significantly contribute to predicting patients’ satisfaction concerning telemedicine adoption in Bangladesh. This model is validated using two-staged structural equation modeling and artificial neural network approaches. The findings demonstrate the determinants of patients’ satisfaction with telemedicine. The presented model will assist medical practitioners, academics, and information systems practitioners to develop high-quality decisions in the future application of telemedicine. Pertinent implications, limitations and future research directions are endorsed securing long-term telemedicine sustainability.