WASHINGTON, April 22, 2020 /PRNewswire/ -- An article published in Experimental Biology and Medicine (Volume 245, Issue 7, April, 2020) (https://journals.sagepub.com/doi/pdf/10.1177/1535370220914285) reports a new strategy for improving photoacoustic tomography (PAT) imaging. The study, led by Dr. Junjie Yao in the Department of Biomedical Engineering at Duke University (USA), describes a deep-learning method for artifact removal that expands the potential clinical uses of PAT imaging.
Photoacoustic tomography (PAT) is a hybrid imaging modality combining optical excitation and ultrasonic detection. PAT has great potential for cancer screening, brain imaging and surgical guidance due to its non-ionizing radiation, deep penetration and sensitivity. However, the diagnostic value of PAT is limited by imaging artifacts that deteriorate the spatial resolution and distort the true shape of the targets.
In the current study, Dr. Yao and colleagues developed a deep-learning-based solution to address PAT's limitations. The methodology is based on stabilized Wasserstein generative adversarial network with gradient penalty (WGAN-GP) and additional mean-squared-error loss function. Quantitatively, WGAN-GP achieved three-fold improvement in signal-to-noise ratio. Such improvement would benefit PAT applications, such as mapping the tumor vasculature in thermal ablation and detecting blood clots during sonothrombolysis. Dr. Yao said, "Our new technology applies artificial intelligence to significantly improve photoacoustic tomography with linear-array transducer and can potentially accelerate the translation of photoacoustic imaging to clinical impact."
Dr. Steven R. Goodman, Editor-in-Chief of Experimental Biology & Medicine, said: "Yao and colleagues have used Deep Learning on reconstruction enhancement of photo acoustic computed tomography images of in vivo mouse vascular data. They successfully reduced artifacts and improved the ability to discern vascular shape. This is an important step towards the clinical application of PACT."
Experimental Biology and Medicine is a global journal dedicated to the publication of multidisciplinary and interdisciplinary research in the biomedical sciences. The journal was first established in 1903. Experimental Biology and Medicine is the journal of the Society of Experimental Biology and Medicine. To learn about the benefits of society membership, visit www.sebm.org. For anyone interested in publishing in the journal, please visit http://ebm.sagepub.com.
SOURCE Experimental Biology and Medicine