Directional 3D Wavelet Transform Based on Gaussian Mixtures for the Analysis of 3D Ultrasound Ovarian Volumes | IEEE Journals & Magazine | IEEE Xplore

Directional 3D Wavelet Transform Based on Gaussian Mixtures for the Analysis of 3D Ultrasound Ovarian Volumes


Abstract:

The success of in-vitro fertilization can be predicted by a correct quantitative and qualitative assessment of ovarian follicles. Several ovarian follicle detection and r...Show More

Abstract:

The success of in-vitro fertilization can be predicted by a correct quantitative and qualitative assessment of ovarian follicles. Several ovarian follicle detection and recognition algorithms have been published. Their effectiveness is inferior to human follicle annotations due to various kinds of noise, degradations, and artefacts in ultrasonic images. This paper deals with an approach to recognize antral follicles from 2 mm in diameter in 3D ultrasound data. Its detection phase looks for candidate follicular regions, while the recognition phase assesses the likelihood of a region to correspond to a follicle. Three innovative definitions underpin the detection: Laplacian-of-Gaussian-based directional 3D wavelet transform, adaptive multiscale search based on Gaussian mixtures, and recursive convexity-based region splitting. A likelihood index is also introduced to support follicle recognition. The proposed approach was tested on 30 ultrasound ovarian volumes generated by different sonographic machines in stimulated and non-stimulated examination cycles. The obtained follicle recognition rates exceed those of the best 3D approaches known by about 10 percent, while qualitative assessments yield comparable values.
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 41, Issue: 1, 01 January 2019)
Page(s): 64 - 77
Date of Publication: 06 December 2017

ISSN Information:

PubMed ID: 29990234

Funding Agency:


1 Introduction

Infertiliy management has received increased attention during the last two decades since technology of ultrasound scans has undergone very fast evolution and ultrasound imaging became an important tool in the process of In-Vitro Fertilization (IVF). Endovaginal ultrasound paved the way for efficient analysis of women's ovarian scans with improved resolution and image quality [1]. The success of IVF can be predicted by a correct quantitative and qualitative assessment of ovarian follicles [2]. Follicles are fluid-filled sacs that contain and can release ova for fertilization. They develop inside ovaries during a longer preantral period to their antral form when they reach about 1 to 2 mm in diameter. In a natural menstrual cycle, one of them becomes dominant when its size grows up to 4 to 5 mm. After 5 days, it increases to about 7 mm, after 10 days to about 14 mm, and, before ovulation, its diameter range is 18 to over 30 mm [4]. In a stimulated cycle, all or most of the antral follicles may grow, and several can be triggered by hormonal treatment to ovulate.

Contact IEEE to Subscribe

References

References is not available for this document.