PURPOSE: To develop a neural network for the estimation of visual acuity from optical coherence tomography (OCT) images of patients with neovascular age-related macular degeneration (AMD) and to demonstrate its use to model the impact of specific con...
The early diagnosis of disease is critical to preventing the occurrence of severe complications. Diabetes is a serious health problem. A variety of methods have been developed for diagnosing diabetes. The majority of these methods have been developed...
Parallel distributed processing (PDP) models in psychology are the precursors of deep networks used in computer science. However, only PDP models are associated with two core psychological claims, namely that all knowledge is coded in a distributed f...
Proceedings of the National Academy of Sciences of the United States of America
Oct 31, 2017
Inside the cell nucleus, genomes fold into organized structures that are characteristic of cell type. Here, we show that this chromatin architecture can be predicted de novo using epigenetic data derived from chromatin immunoprecipitation-sequencing ...
Wearable soft robotic systems are enabling safer human-robot interaction and are proving to be instrumental for biomedical rehabilitation. In this manuscript, we propose a novel, modular, wearable robotic device for human (lumbar) spine assistance th...
MOTIVATION: Although clinical aspirations for new technology to accurately measure and diagnose Parkinsonian tremors exist, automatic scoring of tremor severity using machine learning approaches has not yet been employed.
The hippocampus places us both in time and space. It does so over remarkably large spans: milliseconds to years, and centimeters to kilometers. This works for sensory representations, for memory, and for behavioral context. How does it fit in such wi...
IEEE/ACM transactions on computational biology and bioinformatics
Oct 30, 2017
In gene expression data analysis, the problems of cancer classification and gene selection are closely related. Successfully selecting informative genes will significantly improve the classification performance. To identify informative genes from a l...
Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Oct 30, 2017
Accurate quantification of uptake on PET images depends on accurate attenuation correction in reconstruction. Current MR-based attenuation correction methods for body PET use a fat and water map derived from a 2-echo Dixon MRI sequence in which bone ...
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.