U-WNO:U-Net-enhanced Wavelet Neural Operator for fetal head segmentation

TL;DR

This paper introduces U-WNO, a novel neural network combining wavelet decomposition and U-Net architecture for improved fetal head segmentation in ultrasound images, enhancing accuracy and regional pattern learning.

Contribution

The paper presents a new U-WNO model that integrates wavelet-based operator learning with U-Net for superior fetal head segmentation in ultrasound imaging.

Findings

Effective segmentation across different pregnancy trimesters

Improved spatial pattern recognition in ultrasound images

Potential for broader applications in medical imaging

Abstract

This article describes the development of a novel U-Net-enhanced Wavelet Neural Operator (U-WNO),which combines wavelet decomposition, operator learning, and an encoder-decoder mechanism. This approach harnesses the superiority of the wavelets in time frequency localization of the functions, and the combine down-sampling and up-sampling operations to generate the segmentation map to enable accurate tracking of patterns in spatial domain and effective learning of the functional mappings to perform regional segmentation. By bridging the gap between theoretical advancements and practical applications, the U-WNO holds potential for significant impact in multiple science and industrial fields, facilitating more accurate decision-making and improved operational efficiencies. The operator is demonstrated for different pregnancy trimesters, utilizing two-dimensional ultrasound images.