Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan;42(1):71-79.
doi: 10.1002/jum.16045. Epub 2022 Jun 30.

Deep Learning for FAST Quality Assessment

Mesfin Taye  1   2 , Dustin Morrow  3 , John Cull  4 , Dane Hudson Smith  5 , Martin Hagan  6
Affiliations

Deep Learning for FAST Quality Assessment

Mesfin Taye et al. J Ultrasound Med. 2023 Jan.

Abstract

Objectives: To determine the feasibility of using a deep learning (DL) algorithm to assess the quality of focused assessment with sonography in trauma (FAST) exams.

Methods: Our dataset consists of 441 FAST exams, classified as good-quality or poor-quality, with 3161 videos. We first used convolutional neural networks (CNNs), pretrained on the Imagenet dataset and fine-tuned on the FAST dataset. Second, we trained a CNN autoencoder to compress FAST images, with a 20-1 compression ratio. The compressed codes were input to a two-layer classifier network. To train the networks, each video was labeled with the quality of the exam, and the frames were labeled with the quality of the video. For inference, a video was classified as poor-quality if half the frames were classified as poor-quality by the network, and an exam was classified as poor-quality if half the videos were classified as poor-quality.

Results: The results with the encoder-classifier networks were much better than the transfer learning results with CNNs. This was primarily because the Imagenet dataset is not a good match for the ultrasound quality assessment problem. The DL models produced video sensitivities and specificities of 99% and 98% on held-out test sets.

Conclusions: Using an autoencoder to compress FAST images is a very effective way to obtain features that can be used to predict exam quality. These features are more suitable than those obtained from CNNs pretrained on Imagenet.

Keywords: FAST; autoencoder; convolutional neural network; deep learning; ultrasound.

PubMed Disclaimer

References

    1. Bahner D, Blaivas M, Cohen HL, et al. American Institute of Ultrasound in Medicine. AIUM practice guideline for the performance of the focused assessment with sonography for trauma (FAST) examination. J Ultrasound Med 2008; 27:313-318.
    1. Lewiss RE, Tayal VS, Hoffmann B, et al. The core content of clinical ultrasonography fellowship training. Acad Emerg Med 2014; 21:456-461.
    1. Morrow D, Cupp J, Schrift D, Nathanson R, Soni NJ. Point-of-care ultrasound in established settings. South Med J 2018; 111:373-381.
    1. Steinemann S, Fernandez M. Variation in training and use of the focused assessment with sonography in trauma (FAST). Am J Surg 2018; 215:255-258.
    1. POLICY STATEMENT Ultrasound Guidelines: Emergency, point-of-care, and clinical ultrasound guidelines in medicine. Published online 2016.

LinkOut - more resources