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
. 2021 Sep 28;10(19):4479.
doi: 10.3390/jcm10194479.

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Antoine Guilcher  1 , Damien Laneelle  2 , Guillaume Mahé  1   3   4
Affiliations

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Antoine Guilcher et al. J Clin Med. .

Abstract

Background: Arterial Doppler flow waveform analysis is a tool recommended for the management of lower extremity peripheral arterial disease (PAD). To standardize the waveform analysis, classifications have been proposed. Neural networks have shown a great ability to categorize data. The aim of the present study was to use an existing neural network to evaluate the potential for categorization of arterial Doppler flow waveforms according to a commonly used classification.

Methods: The Pareto efficient ResNet-101 (ResNet-101) neural network was chosen to categorize 424 images of arterial Doppler flow waveforms according to the Simplified Saint-Bonnet classification. As a reference, the inter-operator variability between two trained vascular medicine physicians was also assessed. Accuracy was expressed in percentage, and agreement was assessed using Cohen's Kappa coefficient.

Results: After retraining, ResNet-101 was able to categorize waveforms with 83.7 ± 4.6% accuracy resulting in a kappa coefficient of 0.79 (0.75-0.83) (CI 95%), compared with a kappa coefficient of 0.83 (0.79-0.87) (CI 95%) between the two physicians.

Conclusion: This study suggests that the use of transfer learning on a pre-trained neural network is feasible for the automatic classification of images of arterial Doppler flow waveforms.

Keywords: Doppler waveform; neural network classification; peripheral artery disease.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The simplified Saint-Bonnet classification. There was no waveform in categories A–CF and 0 in the present study.
Figure 2
Figure 2
Illustration of the 10-fold cross-validation process. Legend: For the 10-fold cross validation, 10 sub datasets were used and for each of the 10 training and validation procedures, training was performed on 9 sub datasets (white boxes) and tested on the remaining sub dataset (black box). The subset used for testing changed between each procedure. Average accuracy and agreement compared with a vascular physician (physician 1) were calculated.
Figure 3
Figure 3
Example of waveforms categorized by ResNet-101 in comparison with the waveform categorization performed by physician 1, according to the simplified Saint-Bonnet classification. Physician 1: reference physician.
See this image and copyright information in PMC

References

    1. Fowkes F.G.R., Rudan D., Rudan I., Aboyans V., Denenberg J.O., McDermott M.M., Norman P.E., Sampson U.K., Williams L.J., Mensah G.A., et al. Comparison of Global Estimates of Prevalence and Risk Factors for Peripheral Artery Disease in 2000 and 2010: A Systematic Review and Analysis. Lancet. 2013;382:1329–1340. doi: 10.1016/S0140-6736(13)61249-0. - DOI - PubMed
    1. Hirsch A.T., Criqui M.H., Treat-Jacobson D., Regensteiner J.G., Creager M.A., Olin J.W., Krook S.H., Hunninghake D.B., Comerota A.J., Walsh M.E., et al. Peripheral Arterial Disease Detection, Awareness, and Treatment in Primary Care. JAMA. 2001;286:1317–1324. doi: 10.1001/jama.286.11.1317. - DOI - PubMed
    1. Riviere A.B., Bouée S., Laurendeau C., Torreton E., Gourmelen J., Thomas-Delecourt F. Outcomes and Management Costs of Peripheral Arterial Disease in France. J. Vasc. Surg. 2018;67:1834–1843. doi: 10.1016/j.jvs.2017.09.041. - DOI - PubMed
    1. Hirsch A.T., Hartman L., Town R.J., Virnig B.A. National Health Care Costs of Peripheral Arterial Disease in the Medicare Population. Vasc. Med. 2008;13:209–215. doi: 10.1177/1358863X08089277. - DOI - PubMed
    1. Mahoney E.M., Wang K., Keo H.H., Duval S., Smolderen K.G., Cohen D.J., Steg G., Bhatt D.L., Hirsch A.T. Vascular Hospitalization Rates and Costs in Patients with Peripheral Artery Disease in the United States. Circ. Cardiovasc. Qual. Outcomes. 2010;3:642–651. doi: 10.1161/CIRCOUTCOMES.109.930735. - DOI - PubMed