Diagnosis support system for skin grafting using GrowCut with an automated seed selection

Kodai Ezaki, Soichiro Kato, Yoshihiro Yamaguchi, Toshiyuki Tanaka

Research output: Contribution to journalArticlepeer-review

Abstract

This paper deals with a method of segmenting skin and skin grafts using GrowCut. The previous lacks system usability because the evaluating physician needed approximately 100–200 mouse clicks for each image to acquire training data. Therefore, we propose a method to automate the acquisition of training data while maintaining the accuracy of domain segmentation from the previous study. Based on the proposed method, the ratio of the two areas-of-interest was calculated as the burn ratio and used to evaluate treatment quantitatively. The results show that the segmentation of skin and skin grafts is as accurate as by mouse clicks. We think that automating the acquisition of training data as preprocessing will improve the usability of the system.

Keywords

  • automated seed selection
  • GrowCut algorithm
  • Skin grafting

ASJC Scopus subject areas

  • Computational Mechanics
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Diagnosis support system for skin grafting using GrowCut with an automated seed selection'. Together they form a unique fingerprint.

Cite this