Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets

  title={Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets},
  author={Mengjie Shi and Tianrui Zhao and Simeon J. West and Adrien E. Desjardins and Tom Vercauteren and Wenfeng Xia},

Figures and Tables from this paper

Enhanced Photoacoustic Visualisation of Clinical Needles by Combining Interstitial and Extracorporeal Illumination of Elastomeric Nanocomposite Coatings

Enhanced visualisation of clinical needles was enhanced by elastomeric nanocomposite coatings with superficial and interstitial illumination and the highly absorbing coatings, which could be helpful in current US-guided minimally invasive surgeries.



Ultrasonic Needle Tracking with a Fibre-Optic Ultrasound Transmitter for Guidance of Minimally Invasive Fetal Surgery

The results demonstrate that ultrasonic needle tracking with a fibre-optic transmitter is feasible in a clinically realistic fetal surgery environment, and that it could be useful to guide minimally invasive procedures by providing accurate visualisation of the medical device tip.

Effect of light pulse width on frequency characteristics of photoacoustic signal – an experimental study using a pulse-width tunable LED-based photoacoustic imaging system

Photoacoustic imaging is a hybrid technique that bridges the depth limits of ballistic optical imaging and the resolution limits of diffuse optical imaging. Using the acoustic waves generated in

Deep Learning for Instrumented Ultrasonic Tracking: From Synthetic Training Data to In Vivo Application

A framework based on a convolutional neural network to maintain spatial resolution with fewer tracking transmissions and enhance signal quality will significantly improve the performance of ultrasonic tracking, leading to faster image acquisition rates and increased localization accuracy.

Generative adversarial network-based photoacoustic image reconstruction from bandlimited and limited-view data

The results from both simulations and experiments show that the proposed approach can remove bandlimited and limited view artifacts and can achieve a better image quality.

Echogenic Surface Enhancements for Improving Needle Visualization in Ultrasound

Among the echogenic needles, coated needles were seemingly better visualized “in vivo” than noncoated needles, despite heterogeneity in study conditions, and no unambiguous comparison revealed which needle was best visualized.

Image Compositing for Segmentation of Surgical Tools Without Manual Annotations

It is shown that by training a vanilla U-Net on semi-synthetic data only and applying a simple post-processing, the results are able to match the results of the same network trained on a publicly available manually labeled real dataset.

Portable and Affordable Light Source-Based Photoacoustic Tomography

This review focuses on the basic theory of photoacoustic imaging; inexpensive light sources and different implementations; important preclinical and clinical applications, demonstrated using affordable light source-based photoacoustics; and the key technological developments in these areas will be thoroughly reviewed.

Deep learning in photoacoustic tomography: current approaches and future directions

A review of the literature on learned image reconstruction, summarizing the current trends and explaining how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods shows how these techniques can be understood from a Bayesian perspective, providing useful insights.