Data augmentation for medical image segmentation

DOI IR Web Site Open Access

Bibliographic Information

Other Title
  • 医用画像セグメンテーションのための画像水増し法の検証
  • イヨウ ガゾウ セグメンテーション ノ タメ ノ ガゾウ ミズマシ ホウ ノ ケンショウ

Search this article

Description

Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human interaction. The success of semantic segmentation using deep learning techniques is contingent on the availability of a large amount of imaging data with corresponding labels provided by experts. In contrast, a large amount of labeled medical image data is not available in many cases. In this study, we investigate an efficient data augmentation method using various filters. The experimental results showed that the combination between Gaussian and Median filters is adequate for semantic segmentation for bone images.

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top