Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data

Jeya Maria Jose Valanarasu, Rajeev Yasarla, Puyang Wang, Ilker Hacihaliloglu, Vishal M. Patel

Research output: Contribution to journalArticlepeer-review

18 Scopus citations


Automatic segmentation of anatomical landmarks from ultrasound (US) plays an important role in the management of preterm neonates with a very low birth weight due to the increased risk of developing intraventricular hemorrhage (IVH) or other complications. One major problem in developing an automatic segmentation method for this task is the limited availability of annotated data. To tackle this issue, we propose a novel image synthesis method using multi-scale self attention generator to synthesize US images from various segmentation masks. We show that our method can synthesize high-quality US images for every manipulated segmentation label with qualitative and quantitative improvements over the recent state-of-the-art synthesis methods. Furthermore, for the segmentation task, we propose a novel method, called Confidence-guided Brain Anatomy Segmentation (CBAS) network, where segmentation and corresponding confidence maps are estimated at different scales. In addition, we introduce a technique which guides CBAS to learn the weights based on the confidence measure about the estimate. Extensive experiments demonstrate that the proposed method for both synthesis and segmentation tasks achieve significant improvements over the recent state-of-the-art methods. In particular, we show that the new synthesis framework can be used to generate realistic US images which can be used to improve the performance of a segmentation algorithm.

Original languageEnglish (US)
Article number9113237
Pages (from-to)1221-1234
Number of pages14
JournalIEEE Journal on Selected Topics in Signal Processing
Issue number6
StatePublished - Oct 2020

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering


  • Ultrasound
  • brain
  • confidence map
  • deep
  • learning
  • pellecudi
  • preterm neonate
  • segmentation
  • septum
  • synthesis
  • ventricle


Dive into the research topics of 'Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data'. Together they form a unique fingerprint.

Cite this