U-WNO:U-Net-enhanced Wavelet Neural Operator for fetal head segmentation
Authors: Pranava Seth, Deepak Mishra, Veena Iyer
Organizations: Thapar Institute of Engineering & Technology, Patiala, 147004, Punjab, India. · Department of Avionics, Indian Institute of Space Science & Technology, Thiruvananthapuram, 695547, Kerela, India. · Indian Institute of Public Health , Gandhinagar , 382042, Gujarat, India.
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.
Figures & tables
Figure 1: 2D USG Image (left) and it’s mask(right). This is a sample from the used dataset.
Figure 3: Samples from the test set and their corresponding segmentation outputs obtained through U-WNO. The top and bottom rows show two different test samples and their respective results.
Automated fetal head segmentation in ultrasound images is critical for accurate biometric measurements in prenatal care. While existing deep learning approaches have achieved a reasonable performance, they struggle with issues like low contrast, noise, and complex anatomical boundaries which are inherent to ultrasound imaging. This paper presents Attention-ResUNet. It is a novel architecture that synergistically combines residual learning with multi-scale attention mechanisms in order to achieve enhanced fetal head segmentation. Our approach integrates attention gates at four decoder levels to focus selectively on anatomically relevant regions while suppressing the background noise, and complemented by residual connections which facilitates gradient flow and feature reuse. Extensive evaluation on the HC18 Challenge dataset where n = 200 demonstrates that Attention ResUNet achieves a superior performance with a mean Dice score of 99.30 +/- 0.14% against similar architectures. It significantly outperforms five baseline architectures including ResUNet (99.26%), Attention U-Net (98.79%), Swin U-Net (98.60%), Standard U-Net (98.58%), and U-Net++ (97.46%). Through statistical analysis we confirm highly significant improvements (p < 0.001) with effect sizes that range from 0.230 to 13.159 (Cohen's d). Using Saliency map analysis, we reveal that our architecture produces highly concentrated, anatomically consistent activation patterns, which demonstrate an enhanced interpretability which is crucial for clinical deployment. The proposed method establishes a new state of the art performance for automated fetal head segmentation whilst maintaining computational efficiency with 14.7M parameters and a 45 GFLOPs inference cost. Code repository: https://github.com/Ammar-ss
Ammar Bhilwarawala, Mainak Bandyopadhyay
School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India
Head circumference (HC) measured from 2D ultrasound is a routine marker of fetal growth, and automating it needs segmentations whose boundaries hold up on individual scans, not only on average. We present FETALFusion, a dual-path CNN-Mamba encoder-decoder for fetal head segmentation across acquisition types. It applies four-directional state-space scans only at the two highest-resolution stages, routes bottleneck features through domain-specific channel gates that are averaged at test time, and adds a weak landmark shape prior. We train jointly on transabdominal (HC-18) and transperineal (PSFHS) images and compare ten methods on a held-out test set of 471 images, each trained under one schedule and scored by surface distances at native resolution. FETALFusion reaches a Dice score of 0.963 and an HD95 of 2.10 mm without test-time augmentation or a domain label. It improves on U-Mamba on all five reported metrics (HD95 reduced by 0.31 mm; Holm-corrected (p<10−4), a lead that holds under test-time augmentation and across two independent training runs, and in the mean on U-Net, Attention U-Net and TransUNet. Residual encoders close the gap: a ResNet-34 UNet++ exceeds FETALFusion, and an ImageNet initialised ResNet-34 U-Net is best overall (HD95 1.75 mm). The ablation agrees. Calibrated against run-to-run variation, it attributes FETALFusion's measurable gains to the landmark shape prior and, on transperineal images, to the domain gates, while removing the state-space branch does not measurably change accuracy. HC from the predicted masks agrees with the clinical reference at an intraclass correlation of 0.9986.
Ammar Bhilwarawala, Mainak Bandyopadhyay
School of Computer Engineering, KIIT Deemed to be University Bhubaneswar, India
We present Mixture-of-Wavelet-Experts (MoWE), a spatially adaptive routing mechanism that replaces max-pooling and strided convolutions in U-Net architectures for ultrasound lesion segmentation. Standard pooling operations suppress high-frequency spatial details, including potential boundary cues in speckled regions. Recent frequency-domain methods preserve some of these details, but a single wavelet family applies the same spectral bias across the image. MoWE instead uses a context-aware router to assign local regions to fixed wavelet families according to local texture and global feature context. The decoder reuses the encoder's spatial routing maps during the inverse transform. Learnable channel-wise gates rescale the high-frequency subbands before reconstruction. We evaluate MoWE with U-Net on four ultrasound lesion benchmarks (BUSI, TN3K, UDIAT, BUS-UCLM) and one cardiac dataset (CAMUS), and with nnU-Net on BUSI. On BUSI, MoWE improves U-Net Dice from 72.59% to 74.55% and reduces HD95 from 47.01 to 43.49,px. With nnU-Net, MoWE improves Dice from 80.18% to 81.97% and reduces ASSD from 20.07 to 17.25,px. On U-Net, MoWE reduces trainable parameters by 6.4%.