Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN

Jafari, Mohammad H.; Girgis, Hany; Woudenberg, Nathan Van; Moulson, Nathaniel; Luong, Christina; Fung, Andrea; Balthazaar, Shane; Jue, John; Tsang, Micheal; Nair, Parvathy; Gin, Ken; Rohling, Robert; Abolmaesumi, Purang; Tsang, Teresa S.M.

doi:10.1007/s11548-020-02141-y

Cited by 26 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jafari et al [54] provided a deep learning solution that modified the low quality The deep learning application, which has the most fundamental effect on ultrasound imaging, is to apply it to ultrasonic beamforming. Delay-and-sum (DAS) beamformer, most widely used beamforming method in ultrasound systems, has become an industry standard because it can be applied in real-time with a small amount of computation.…”

Section: Beamformingmentioning

confidence: 99%

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

Kang

Kwon

et al. 2021

Ultrasonography

View full text Add to dashboard Cite

Reviews of the most recent applications of deep learning on ultrasound imaging applications are presented. Architectures of deep learning networks are briefly explained for medical imaging application categories of classification, detection, segmentation, and generation. Ultrasonography applications are then reviewed and summarized for image processing and diagnosis along with some representative study cases of breast, thyroid, heart, kidney, liver, and fetal head. Efforts on workflow enhancement are also reviewed with emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented on image quality Enhancement, diagnostic support, and improving workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.

show abstract

Section: Beamformingmentioning

confidence: 99%

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

Kang

Kwon

et al. 2021

Ultrasonography

View full text Add to dashboard Cite

show abstract

“…DL has been applied to ultrasound images to reduce artefact and to enhance the image quality 10 . Generative adversarial neural networks can improve image quality through mapping low‐quality ultrasound images to corresponding, high‐quality images, and so have the potential to transform the image quality of point‐of‐care ultrasound to that of a high‐end machine 15,16 …”

Section: Image Qualitymentioning

confidence: 99%

Artificial intelligence‐enhanced echocardiography in the emergency department

Stewart

Goudie

Mukherjee

et al. 2021

Emerg Medicine Australasia

View full text Add to dashboard Cite

A focused cardiac ultrasound performed by an emergency physician is becoming part of the standard assessment of patients in a variety of clinical situations. The development of inexpensive, portable handheld devices promises to make point‐of‐care ultrasound even more accessible over the coming decades. Many of these handheld devices are beginning to integrate artificial intelligence (AI) for image analysis. The integration of AI into focused cardiac ultrasound will have a number of implications for emergency physicians. This perspective presents an overview of the current state of AI research in echocardiography relevant to the emergency physician, as well as the future possibilities, challenges and risks of this technology.

show abstract

“…The cone in echo images is also a consistent defining feature in the image which degrades the translational invariance of convolutional networks. CycleGANs have been applied in echo for segmentation with image quality improvement [14] and view conversion [15] , but these works used two real datasets of echo images and thus did not have to address the above challenges of translating from a different modality to echo.…”

Section: Introductionmentioning

confidence: 99%

Generating Synthetic Labeled Data From Existing Anatomical Models: An Example With Echocardiography Segmentation

Gilbert

Marciniak

Rodero

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Deep learning can bring time savings and increased reproducibility to medical image analysis. However, acquiring training data is challenging due to the time-intensive nature of labeling and high inter-observer variability in annotations. Rather than labeling images, in this work we propose an alternative pipeline where images are generated from existing high-quality annotations using generative adversarial networks (GANs). Annotations are derived automatically from previously built anatomical models and are transformed into realistic synthetic ultrasound images with paired labels using a CycleGAN. We demonstrate the pipeline by generating synthetic 2D echocardiography images to compare with existing deep learning ultrasound segmentation datasets. A convolutional neural network is trained to segment the left ventricle and left atrium using only synthetic images. Networks trained with synthetic images were extensively tested on four different unseen datasets of real images with median Dice scores of 91, 90, 88, and 87 for left ventricle segmentation. These results match or are better than inter-observer results measured on real ultrasound datasets and are comparable to a network trained on a separate set of real images. Results demonstrate the images produced can effectively be used in place of real data for training. The proposed pipeline opens the door for automatic generation of training data for many tasks in medical imaging as the same process can be applied to other segmentation or landmark detection tasks in any modality. The source code and anatomical models are available to other researchers. 1 1

show abstract

Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN

Cited by 26 publications

References 40 publications

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

Artificial intelligence‐enhanced echocardiography in the emergency department

Generating Synthetic Labeled Data From Existing Anatomical Models: An Example With Echocardiography Segmentation

Contact Info

Product

Resources

About