Laryngeal Tumor Detection and Classification in Endoscopic Video

Corina Barbalata, Leonardo S. Mattos

Research output: Contribution to journalArticlepeer-review

36 Citations (Scopus)


The development of the narrow-band imaging (NBI) has been increasing the interest of medical specialists in the study of laryngeal microvascular network to establish diagnosis without biopsy and pathological examination. A possible solution to this challenging problem is presented in this paper, which proposes an automatic method based on anisotropic filtering and matched filter to extract the lesion area and segment blood vessels. Lesion classification is then performed based on a statistical analysis of the blood vessels' characteristics, such as thickness, tortuosity, and density. Here, the presented algorithm is applied to 50 NBI endoscopic images of laryngeal diseases and the segmentation and classification accuracies are investigated. The experimental results show the proposed algorithm provides reliable results, reaching an overall classification accuracy rating of 84.3%. This is a highly motivating preliminary result that proves the feasibility of the new method and supports the investment in further research and development to translate this study into clinical practice. Furthermore, to our best knowledge, this is the first time image processing is used to automatically classify laryngeal tumors in endoscopic videos based on tumor vascularization characteristics. Therefore, the introduced system represents an innovation in biomedical and health informatics.

Original languageEnglish
Pages (from-to)322-332
Number of pages11
JournalIEEE Journal of Biomedical and Health Informatics
Issue number1
Publication statusPublished - Jan 2016


  • Blood vessel segmentation
  • computer-aided diagnosis
  • laryngoscopy
  • lesion detection
  • narrow-band imaging (NBI)
  • shape analysis
  • visual biopsy
  • HEAD


Dive into the research topics of 'Laryngeal Tumor Detection and Classification in Endoscopic Video'. Together they form a unique fingerprint.

Cite this