Skip to main content
Journal cover image

Semi-automated weak annotation for deep neural network skin thickness measurement.

Publication ,  Journal Article
Jin, FQ; Knight, AE; Cardones, AR; Nightingale, KR; Palmeri, ML
Published in: Ultrason Imaging
July 2021

Correctly calculating skin stiffness with ultrasound shear wave elastography techniques requires an accurate measurement of skin thickness. We developed and compared two algorithms, a thresholding method and a deep learning method, to measure skin thickness on ultrasound images. Here, we also present a framework for weakly annotating an unlabeled dataset in a time-effective manner to train the deep neural network. Segmentation labels for training were proposed using the thresholding method and validated with visual inspection by a human expert reader. We reduced decision ambiguity by only inspecting segmentations at the center A-line. This weak annotation approach facilitated validation of over 1000 segmentation labels in 2 hours. A lightweight deep neural network that segments entire 2D images was designed and trained on this weakly-labeled dataset. Averaged over six folds of cross-validation, segmentation accuracy was 57% for the thresholding method and 78% for the neural network. In particular, the network was better at finding the distal skin margin, which is the primary challenge for skin segmentation. Both algorithms have been made publicly available to aid future applications in skin characterization and elastography.

Duke Scholars

Published In

Ultrason Imaging

DOI

EISSN

1096-0910

Publication Date

July 2021

Volume

43

Issue

4

Start / End Page

167 / 174

Location

England

Related Subject Headings

  • Ultrasonography
  • Neural Networks, Computer
  • Image Processing, Computer-Assisted
  • Humans
  • Algorithms
  • Acoustics
  • 4003 Biomedical engineering
  • 0903 Biomedical Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Jin, F. Q., Knight, A. E., Cardones, A. R., Nightingale, K. R., & Palmeri, M. L. (2021). Semi-automated weak annotation for deep neural network skin thickness measurement. Ultrason Imaging, 43(4), 167–174. https://doi.org/10.1177/01617346211014138
Jin, Felix Q., Anna E. Knight, Adela R. Cardones, Kathryn R. Nightingale, and Mark L. Palmeri. “Semi-automated weak annotation for deep neural network skin thickness measurement.Ultrason Imaging 43, no. 4 (July 2021): 167–74. https://doi.org/10.1177/01617346211014138.
Jin FQ, Knight AE, Cardones AR, Nightingale KR, Palmeri ML. Semi-automated weak annotation for deep neural network skin thickness measurement. Ultrason Imaging. 2021 Jul;43(4):167–74.
Jin, Felix Q., et al. “Semi-automated weak annotation for deep neural network skin thickness measurement.Ultrason Imaging, vol. 43, no. 4, July 2021, pp. 167–74. Pubmed, doi:10.1177/01617346211014138.
Jin FQ, Knight AE, Cardones AR, Nightingale KR, Palmeri ML. Semi-automated weak annotation for deep neural network skin thickness measurement. Ultrason Imaging. 2021 Jul;43(4):167–174.
Journal cover image

Published In

Ultrason Imaging

DOI

EISSN

1096-0910

Publication Date

July 2021

Volume

43

Issue

4

Start / End Page

167 / 174

Location

England

Related Subject Headings

  • Ultrasonography
  • Neural Networks, Computer
  • Image Processing, Computer-Assisted
  • Humans
  • Algorithms
  • Acoustics
  • 4003 Biomedical engineering
  • 0903 Biomedical Engineering