Search

Background: Current fMRI-based classification approaches mostly use functional connectivity or spatial maps as input, instead of exploring the dynamic time courses directly, which does not leverage the full temporal information. Methods: Motivated by the ability of recurrent neural networks (RNN) in capturing dynamic information of time sequences, we propose a multi-scale RNN model, which enables classification between 558 schizophrenia and 542 healthy controls by using time courses of fMRI independent components (ICs) directly. To increase interpretability, we also propose a leave-one-IC-out looping strategy for estimating the top contributing ICs. Findings: Accuracies of 83·2% and 80·2% were obtained respectively for the multi-site pooling and leave-one-site-out transfer classification. Subsequently, dorsal striatum and cerebellum components contribute the top two group-discriminative time courses, which is true even when adopting different brain atlases to extract time series. Interpretation: This is the first attempt to apply a multi-scale RNN model directly on fMRI time courses for classification of mental disorders, and shows the potential for multi-scale RNN-based neuroimaging classifications. Fund: Natural Science Foundation of China, the Strategic Priority Research Program of the Chinese Academy of Sciences, National Institutes of Health Grants, National Science Foundation. Keywords: Recurrent neural network (RNN), Schizophrenia, Multi-site classification, fMRI, Striatum, Cerebellum, Deep learning

Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed. Keywords: Deep learning, Medical ultrasound analysis, Classification, Segmentation, Detection

Background: In the past decades, substantial effort has been made to explore the genetic influence on brain structural/functional abnormalities in schizophrenia, as well as cognitive impairments. In this work, we aimed to extend previous studies to explore the internal mediation pathway among genetic factor, brain features and cognitive scores in a large Chinese dataset. Methods: Gray matter (GM) volume, fractional amplitude of low-frequency fluctuations (fALFF), and 4522 schizophrenia-susceptible single nucleotide polymorphisms (SNP) from 905 Chinese subjects were jointly analyzed, to investigate the multimodal association. Based on the identified imaging-genetic pattern, correlations with cognition and mediation analysis were then conducted to reveal the potential mediation pathways. Findings: One linked imaging-genetic pattern was identified to be group discriminative, which was also associated with working memory performance. Particularly, GM reduction in thalamus, putamen and bilateral temporal gyrus in schizophrenia was associated with fALFF decrease in medial prefrontal cortex, both were also associated with genetic factors enriched in neuron development, synapse organization and axon pathways, highlighting genes including CSMD1, CNTNAP2, DCC, GABBR2 etc. This linked pattern was also replicated in an independent cohort (166 subjects), which although showed certain age and clinical differences with the discovery cohort. A further mediation analysis suggested that GM alterations significantly mediated the association from SNP to fALFF, while fALFF mediated the association from SNP and GM to working memory performance. Interpretation: This study has not only verified the impaired imaging-genetic association in schizophrenia, but also initially revealed a potential genetic-brain-cognition mediation pathway, indicating that polygenic risk factors could exert impact on phenotypic measures from brain structure to function, thus could further affect cognition in schizophrenia. Keywords: Schizophrenia, Multimodal fusion, Genetic-brain-cognition pathway, Working memory, Mediation analysis