Automatic Deep Learning Semantic Segmentation of Ultrasound Thyroid Cineclips Using Recurrent Fully Convolutional Networks

Jeremy M. Webb, Duane D. Meixner, Shaheeda A. Adusei, Eric C. Polley, Mostafa Fatemi, Azra Alizad

Research output: Contribution to journalArticlepeer-review

Abstract

Medical segmentation is an important but challenging task with applications in standardized report generation, remote medicine and reducing medical exam costs by assisting experts. In this paper, we exploit time sequence information using a novel spatio-temporal recurrent deep learning network to automatically segment the thyroid gland in ultrasound cineclips. We train a DeepLabv3+ based convolutional LSTM model in four stages to perform semantic segmentation by exploiting spatial context from ultrasound cineclips. The backbone DeepLabv3+ model is replicated six times and the output layers are replaced with convolutional LSTM layers in an atrous spatial pyramid pooling configuration. Our proposed model achieves mean intersection over union scores of 0.427 for cysts, 0.533 for nodules and 0.739 for thyroid. We demonstrate the potential application of convolutional LSTM models for thyroid ultrasound segmentation.

Original languageEnglish (US)
Article number9298766
Pages (from-to)5119-5127
Number of pages9
JournalIEEE Access
Volume9
DOIs
StatePublished - 2021

Keywords

  • Deep learning
  • recurrent neural networks
  • semantic segmentation
  • thyroid nodule
  • thyroid volume
  • ultrasound

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Automatic Deep Learning Semantic Segmentation of Ultrasound Thyroid Cineclips Using Recurrent Fully Convolutional Networks'. Together they form a unique fingerprint.

Cite this