Feature Enhancement in Medical Ultrasound Videos Using Multifractal and Contrast Adaptive Histogram Equalization Techniques

Type of content
Conference Contributions - Published
Thesis discipline
Degree name
Publisher
IEEE
Journal Title
Journal ISSN
Volume Title
Language
Date
2019
Authors
Singh P
Mukundan R
Ryke RD
Abstract

Speckle noise reduction algorithms are extensively used in the field of ultrasound image analysis with the aim of improving image quality and diagnostic accuracy. However, significant speckle filtering induces blurring, and this would require enhancement of features and fine details. In this paper, we consider the applications of multifractal features and contrast limit adaptive histogram equalization method for improving texture features, contrast, resolvable details, and image structures to which the human visual system is sensitive in ultrasound video frames. The experimental analysis considered various types of ultrasound video scans of the human anatomy e.g. breast cancer, uterine fibroids, transvaginal ovary, ovarian cyst, heart, and chest pleural effusion scan. Subjective assessments by four radiologists and experimental validation using three quality metrics clearly indicate that the proposed algorithm is able to reduce speckle effectively while preserving essential information and enhancing the overall visual quality.

Description
Citation
Singh P, Mukundan R, Ryke RD (2019). Feature Enhancement in Medical Ultrasound Videos Using Multifractal and Contrast Adaptive Histogram Equalization Techniques. 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). 28/03/2019-30/03/2019. Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019. 240-245.
Keywords
medical ultrasound video feature enhancement, multifratals, adaptive histogram equalization, ultrasound video frames quality analysis
Ngā upoko tukutuku/Māori subject headings
ANZSRC fields of research
Field of Research::08 - Information and Computing Sciences::0801 - Artificial Intelligence and Image Processing
Field of Research::11 - Medical and Health Sciences
Rights