Arun Presents A Deep Learning Based Alternative to Beamforming Ultrasound Images at IEEE ICASSP 2018

Congrats to Arun on the successful presentation of his research paper entitled “A Deep Learning Based Alternative to Beamforming Ultrasound Images” at IEEE ICASSP 2018 in Calgary, Alberta, Canada. This work is the first to propose deep learning as an alternative to the traditional ultrasound beamforming process and it was implemented for a single plane wave transmission. Check out  our associated conference paper for more details!

Citation: Nair AA, Tran T, Reiter A, Bell MAL, A deep learning based alternative to beamforming ultrasound images, IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Alberta, Canada, April 15-20, 2018 [pdf]

Journal Paper Accepted to IEEE TMI

Congratulations to Derek Allman! His paper entitled “Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning” was accepted to the IEEE Transactions on Medical Imaging. This paper is expected to appear in the Special Issue on Machine Learning for Image Reconstruction.

This work is the first to use deep convolutional neural networks (CNNs) as an alternative to the photoacoustic beamforming and image reconstruction process. We used simulations to train CNNs to identify sources and reflection artifacts in raw photoacoustic channel data, reformatted the network outputs to usable images that we call CNN-Based images, and transferred these trained networks to operate on experimental data. Multiple parameters were varied during training (e.g., channel noise, number of sources, number of artifacts, sound speed, signal amplitude, transducer model, lateral and axial locations of sources and artifacts, and spacing between sources and artifacts). The classification accuracy of simulation and experimental data  ranged from 96-100% when the channel signal-to-noise ratio was -9 dB or greater and when sources were located in trained locations. Over 99% of the results had submillimeter location accuracy. Our CNN-Based images have high contrast,  no artifacts, and resolution that rivals the traditional photoacoustic image resolution of low-frequency ultrasound probes.

Citation: D Allman, A Reiter, MAL Bell, Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning, IEEE Transactions on Medical Imaging (accepted) [pdf]

Datasets Available:


JMI Paper Accepted

Congrats to undergraduate student Margaret Allard on the acceptance of her first-author journal paper entitled Feasibility of photoacoustic-guided teleoperated hysterectomies. This paper will appear in the Journal of Medical Imaging (JMI) Special Section on Image-Guided Procedures, Robotic Interventions, and Modeling.

This paper is the first to describe the feasibility of photoacoustic integration with the da Vinci surgical robot to potentially guide minimally invasive hysterectomies and other gynecological surgeries.  To implement photoacoustic imaging, a novel light delivery system was designed and implemented  to surround da Vinci tools. This new light delivery system uniquely enabled the investigations described in the paper, including  the first known analysis of the optimal tool orientations for photoacoustic-guided hysterectomies using a da Vinci scissor tool (which partially blocks the transmitted light in some cases). This work can be extended to other da Vinci tools and laparoscopic instruments with similar tip geometry.

Margaret completed this work through her participation in our NSF Research Experience for Undergraduates in Computational Sensing and Medical Robotics.

Journal Paper Accepted to IEEE UFFC

Congrats to Arun Nair on the acceptance of his paper entitled “Robust Short-Lag Spatial Coherence Imaging” to the IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. This paper will appear in the special issue on sparsity driven methods in medical ultrasound.

This work is the first to re-examine the lag summation step of the Short-Lag Spatial Coherence (SLSC) algorithm and achieve additional robustness to coherence outliers through both weighted summation of individual coherence images (i.e., M-weighting) and the application of robust principal component analysis (i.e., Robust SLSC, or R-SLSC). Results show great promise for smoothing out the tissue texture of SLSC images, improving boundary delineation, and enhancing anechoic or hypoechoic target visibility at higher lag values. These improvements could be useful in clinical tasks such as breast cyst visualization, liver vessel tracking, and obese patient imaging.

Citation: AA Nair, T Tran, MAL Bell, Robust Short-Lag Spatial Coherence Imaging, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (accepted) [pdf]

Also Available on Journal Website:

JBO Paper Accepted

Our paper entitled Photoacoustic-based approach to surgical guidance performed with and without a da Vinci robot was accepted for publication in the Journal of Biomedical Optics (JBO) Special Section on Translational Biophotonics.

Congrats to undergraduates Neeraj Gandhi and Margaret Allard!

This work was completed in partnership with the NSF REU in Computational Sensing and Medical Robotics along with collaborators Sungmin Kim and Peter Kazanzides, and it is the first to integrate photoacoustic imaging with the da Vinci surgical robot. It was also featured on the journal homepage.

ECE Department Announcement

BioOptics World Article

ICRA Paper Accepted

Our paper “Improving the Safety of Telerobotic Drilling of the Skull Base Via Photoacoustic Sensing of the Carotid Arteries” was accepted for presentation at the IEEE International Conference on Robotics and Automation (ICRA), Singapore, May 29-June 3, 2017.

IEEE TBME Paper Accepted

Prof. Bell’s co-authored paper, “System integration and in-vivo testing of a robot for ultrasound guidance and monitoring during radiotherapy”, has been accepted for publication in IEEE Transactions on Biomedical Engineering.