Deep Learning-Based Segmentation of Nodules in Thyroid Ultrasound: Improving Performance by Utilizing Markers Present in the Images

Mateusz Buda, Benjamin Wildman-Tobriner, Kerry Castor, Jenny K. Hoang, Maciej A. Mazurowski

Research output: Contribution to journalArticlepeer-review

Abstract

Computer-aided segmentation of thyroid nodules in ultrasound imaging could assist in their accurate characterization. In this study, using data for 1278 nodules, we proposed and evaluated two methods for deep learning-based segmentation of thyroid nodules that utilize calipers present in the images. The first method used approximate nodule masks generated based on the calipers. The second method combined manual annotations with automatic guidance by the calipers. When only approximate nodule masks were used for training, the achieved Dice similarity coefficient (DSC) was 85.1%. The performance of a network trained using manual annotations was DSC = 90.4%. When the guidance by the calipers was added, the performance increased to DSC = 93.1%. An increase in the number of cases used for training resulted in increased performance for all methods. The proposed method utilizing the guidance by calipers matched the performance of the network that did not use it with a reduced number of manually annotated training cases.

Original languageEnglish (US)
JournalUltrasound in Medicine and Biology
DOIs
StateAccepted/In press - Jan 1 2019
Externally publishedYes

Keywords

  • Deep learning
  • Segmentation
  • Thyroid nodules
  • Ultrasound

ASJC Scopus subject areas

  • Biophysics
  • Radiological and Ultrasound Technology
  • Acoustics and Ultrasonics

Fingerprint Dive into the research topics of 'Deep Learning-Based Segmentation of Nodules in Thyroid Ultrasound: Improving Performance by Utilizing Markers Present in the Images'. Together they form a unique fingerprint.

Cite this