Structured Learning for 3-D Perivascular Space Segmentation Using Vascular Features

Jun Zhang, Yaozong Gao, Sang Hyun Park, Xiaopeng Zong, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticlepeer-review

24 Citations (Scopus)


Objective: The goal of this paper is to automatically segment perivascular spaces (PVSs) in brain from high-resolution 7T magnetic resonance (MR) images. Methods: We propose a structured-learning-based segmentation framework to extract the PVSs from high-resolution 7T MR images. Specifically, we integrate three types of vascular filter responses into a structured random forest for classifying voxels into two categories, i.e., PVS and background. In addition, we propose a novel entropy-based sampling strategy to extract informative samples in the background for training an explicit classification model. Since the vascular filters can extract various vascular features, even thin and low-contrast structures can be effectively extracted from noisy backgrounds. Moreover, continuous and smooth segmentation results can be obtained by utilizing patch-based structured labels. Results: The performance of our proposed method is evaluated on 19 subjects with 7T MR images, with the Dice similarity coefficient reaching 66%. Conclusion: The joint use of entropy-based sampling strategy, vascular features, and structured learning can improve the segmentation accuracy. Significance: Instead of manual annotation, our method provides an automatic way for PVS segmentation. Moreover, our method can be potentially used for other vascular structure segmentation because of its data-driven property.

Original languageEnglish
Article number7865910
Pages (from-to)2803-2812
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Issue number12
Publication statusPublished - 2017 Dec


  • 7T magnetic resonance (MR) images
  • Perivascular spaces (PVSs)
  • segmentation
  • structured random forest (SRF)
  • vascular features

ASJC Scopus subject areas

  • Biomedical Engineering


Dive into the research topics of 'Structured Learning for 3-D Perivascular Space Segmentation Using Vascular Features'. Together they form a unique fingerprint.

Cite this