Hybrid Automatic Lung Segmentation on Chest CT Scans

Tao Peng, Thomas Canhao Xu, Yihuai Wang, Hailing Zhou, Sema Candemir, Wan Mimi Diyana Wan Zaki, Shanq Jang Ruan, Jing Wang, Xinjian Chen

Research output: Contribution to journalArticlepeer-review

20 Scopus citations


Accurate lung segmentation in chest Computed Tomography (CT) scans is a challenging problem because of variations in lung volume shape, susceptibility to partial volume effects that affect thin antero-posterior junction lines, and lack of contrast between the lung and surrounding tissues. To address the need for a robust method for lung segmentation, we present a new method, called Pixel-based two-Scan Connected Component Labeling-Convex Hull-Closed Principal Curve method (PSCCL-CH-CPC), which automatically detects lung boundaries, and surpasses state-of-the-art performance. The proposed method has two main steps: 1) an image preprocessing step to extract coarse lung contours, and 2) a refinement step to refine the coarse segmentation result on the basis of the improved principal curve model and the machine learning model. Experimental results show that the proposed method has good performance, with a Dice Similarity Coefficient (DSC) as high as 98.21%. When compared with state-of-the-art methods, our proposed method achieved superior segmentation results, with an average DSC of 96.9%.

Original languageEnglish (US)
Article number9066949
Pages (from-to)73293-73306
Number of pages14
JournalIEEE Access
StatePublished - 2020


  • Automatic lung segmentation
  • chest CT scans
  • closed principal curve method
  • machine learning
  • principal curve

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering


Dive into the research topics of 'Hybrid Automatic Lung Segmentation on Chest CT Scans'. Together they form a unique fingerprint.

Cite this