Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation

Ethan Street, Lubomir Hadjiiski, Berkman Sahiner, Sachin Gujar, Mohannad Ibrahim, Suresh K. Mukherji, Heang Ping Chan

Research output: Contribution to journalArticlepeer-review

37 Scopus citations


The authors have developed a semiautomatic system for segmentation of a diverse set of lesions in head and neck CT scans. The system takes as input an approximate bounding box, and uses a multistage level set to perform the final segmentation. A data set consisting of 69 lesions marked on 33 scans from 23 patients was used to evaluate the performance of the system. The contours from automatic segmentation were compared to both 2D and 3D gold standard contours manually drawn by three experienced radiologists. Three performance metric measures were used for the comparison. In addition, a radiologist provided quality ratings on a 1 to 10 scale for all of the automatic segmentations. For this pilot study, the authors observed that the differences between the automatic and gold standard contours were larger than the interobserver differences. However, the system performed comparably to the radiologists, achieving an average area intersection ratio of 85.4% compared to an average of 91.2% between two radiologists. The average absolute area error was 21.1% compared to 10.8%, and the average 2D distance was 1.38 mm compared to 0.84 mm between the radiologists. In addition, the quality rating data showed that, despite the very lax assumptions made on the lesion characteristics in designing the system, the automatic contours approximated many of the lesions very well.

Original languageEnglish (US)
Pages (from-to)4399-4408
Number of pages10
JournalMedical physics
Issue number11
StatePublished - 2007
Externally publishedYes


  • 3D segmentation
  • CT scans
  • Head and neck cancer
  • Level sets

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation'. Together they form a unique fingerprint.

Cite this