Shengfeng Liu

TL;DR: Several popular deep learning architectures are briefly introduced, and their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation are discussed.

TL;DR: A multi-scale RNN model is proposed, which enables classification between 558 schizophrenia and 542 healthy controls by using time courses of fMRI independent components (ICs) directly and shows the potential for multi- scale RNN-based neuroimaging classifications.

TL;DR: Using a data-driven, supervised-learning method, it is determined that miR-132 dysregulation in major depressive disorder is associated with multi-facets of brain function and structure in fronto-limbic network (the key network for emotional regulation and memory), which deepens the understanding of how mi R-132 Dysregulation inmajor depressive disorders contribute to the loss of specific brain areas and is linked to relevant cognitive impairments.

TL;DR: A novel composite network, namely CR-Unet, is proposed to simultaneously segment the ovary and follicles in TVUS, which incorporates the spatial recurrent neural network (RNN) into a plain U-Net and adopt deep supervision strategy to make model training more effective and efficient.

TL;DR: A generic deep learning framework for automatic quality control of fetal US cardiac four-chamber plane, which consists of a basic CNN, a deeper CNN, and the aggregated residual visual block net (ARVBNet), detecting the key anatomical structures on a plane is proposed.