deep learning

Sleep Monitoring Using Ear-Centered Setups: Investigating the Influence From Electrode Configurations

Author(s): Mike Lind Rank, Preben Kidmose
Sleep Monitoring Using Ear-Centered Setups: Investigating the Influence From Electrode Configurations IEEE Transactions on Biomedical Engineering (TBME)
We combine ear-EEG sleep recordings with a state-of-the-art sleep scoring model, ‘seqsleepnet’, to investigate the upper limits of mobile sleep scoring. We manage to further improve on the state of the art in this field, and perform a detailed analysis of the influence of electrode positioning. From this, we find a general rule of thumb that as long a data set contain EOG information and electrode distance on the order of the width of the head, then good automatic sleep scoring is possible. We also find indications that the obtained automatic scoring may be more reliable than the manual scoring. read more

Learning Multiparametric Biomarkers for Assessing MR-Guided Focused Ultrasound Treatment of Malignant Tumors

Author(s): Blake Zimmerman, Sara Johnson, Henrik Odéen, Jill Shea, Markus D. Foote, Nicole Winkler, Sarang Joshi, Allison Payne
Learning Multiparametric Biomarkers for Assessing MR-Guided Focused Ultrasound Treatment of Malignant Tumors 170 177 IEEE Transactions on Biomedical Engineering (TBME)
A significant challenge for noninvasive MR-guided focused ultrasound (MRgFUS) treatment is assessing the viability of treated tissue during and immediately after MRgFUS procedures. Current clinical assessment uses contrast agents that prevent continuing MRgFUS treatment if tumor coverage is inadequate. This work presents a novel, noncontrast, learned multiparametric MR biomarker that can be used during treatment for iterative assessment with inhibiting treatment continuation. Trained using a novel volume-conserving registration algorithm, the presented noncontrast biomarker outperformed the current clinical standard on a VX2 rabbit tumor model. Details on the registration and deep learning model are included. read more

Mammography Image Quality Assurance Using Deep Learning

Author(s): Tobias Kretz, Klaus-Robert Müller, Tobias Schaeffter, Clemens Elster
Mammography Image Quality Assurance Using Deep Learning 170 177 IEEE Transactions on Biomedical Engineering (TBME)
Image quality assurance is crucial in mammography to ensure reliable breast cancer diagnostics. Analyzing images of a technical phantom allows to routinely and reliably assess image quality. Current state-of-the-art analysis determines local image quality features by applying pre-processing and regression procedures for a set of repeatedly recorded images. This proof of concept paper demonstrates that mammography image quality assessment can benefit from deep learning. A neural network is trained on a large database of phantom images, and it is shown that the trained net retrieves the local image quality features already from single images without cumbersome pre-processing. This allows to maintain quality standards at significantly less labor. read more

A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound

Author(s): Micha Feigin, Brian W. Anthony, Daniel Freedman
A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound 170 177 IEEE Transactions on Biomedical Engineering (TBME)

Abnormalities in the tissue’s mechanical properties and structure, as well as their spatial arrangement, are useful in disease diagnosis and monitoring of disease progression. To this end, ultrasound shear wave…

read more

Predicting Athlete Ground Reaction Forces and Moments From Spatio-temporal Driven CNN Models

Author(s): William R. Johnson, Jacqueline Alderson, David G. Lloyd, Ajmal Mian
Predicting Athlete Ground Reaction Forces and Moments From Spatio-temporal Driven CNN Models 170 177 IEEE Transactions on Biomedical Engineering (TBME)

Conventional methods to generate ground reaction forces and moments (GRF/M) required for traditional inverse dynamics estimation of athlete joint forces and loads are confined to biomechanics laboratories far removed from…

read more
Medical Image Synthesis with Deep Convolutional Adversarial Networks

Medical Image Synthesis with Deep Convolutional Adversarial Networks

Author(s): Dong Nie, Roger Trullo, Jun Lian, Li Wang, Caroline Petitjean, Su Ruan, Qian Wang, Dinggang Shen
Medical Image Synthesis with Deep Convolutional Adversarial Networks 170 177 IEEE Transactions on Biomedical Engineering (TBME)

Medical imaging plays a critical role in various clinical applications. However, due to multiple considerations such as cost and radiation dose, the acquisition of certain image modalities may be limited.…

read more

Automatic Recognition of fMRI-derived Functional Networks using 3D Convolutional Neural Networks

Author(s): Yu Zhao, Qinglin Dong, Shu Zhang, Wei Zhang, Hanbo Chen, Xi Jiang, Lei Guo, Xintao Hu, Junwei Han, Tianming Liu
Automatic Recognition of fMRI-derived Functional Networks using 3D Convolutional Neural Networks 170 177 IEEE Transactions on Biomedical Engineering (TBME)

Current fMRI data modeling techniques such as Independent Component Analysis (ICA) and Sparse Coding methods can effectively reconstruct dozens or hundreds of concurrent interacting functional brain networks simultaneously from the…

read more