Robust CNN multi-nested-LSTM framework with compound loss for patch-based multi-push ultrasound shear wave imaging and segmentation.
Authors
Affiliations (4)
Affiliations (4)
- Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Electrical and Computer Engineering (ECE) Building, Dhaka, Dhaka, 1205, BANGLADESH.
- Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Electrical and Computer Engineering (ECE) Building, Dhaka, Dhaka, Dhaka District, 1205, BANGLADESH.
- Department of Electrical and Computer Engineering, Department of Computer Science, Johns Hopkins University, 208 Barton Hall, 3400 N. Charles St., Baltimore, Maryland, 21218-2625, UNITED STATES.
- Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1205, Dhaka, 1205, BANGLADESH.
Abstract
Ultrasound shear wave imaging enables noninvasive, quantitative assessment of tissue pathology with mechanical elasticity measurements. However, shear wave elastography (SWE) reconstructions are challenged by noise sensitivity, inefficient multi-push strategies for scalable ROI coverage, and limited annotated data, leading to suboptimal reconstruction and unreliable inclusion segmentation. In this work, we present a novel two-stage deep learning framework that addresses these limitations through a CNN-based Multi-Nested-LSTM reconstruction network followed by a compound-loss-driven CNN-denoiser. The reconstruction stage begins with a ResNet3D-encoder that extracts spatiotemporal features from sequential multi-push acoustic radiation force (ARF) data. These features are temporally windowed with Nested CNN-LSTM, converted from 3D to 2D with temporal attention module (TAM), and enhanced by FFT-based frequency attention. The resulting 2D maps are subsequently decoded into primary 2D elasticity reconstructions. To mitigate data-scarcity and improve generalization, a patch-based training regime is also proposed. The second stage introduces a dual-decoder denoising network that separately processes inclusion and background stiffness features, followed by a fusion module that produces a denoised modulus map and a segmentation mask. A multi-objective compound loss is designed to accommodate the denoising, fusing, and mask generation. The method is validated on sequential multi-push (simulation and experimental) SWE motion data with multiple overlapping regions. The method was tested on simulated and CIRS phantom datasets with four overlapping push regions, yielding 26.33 dB PSNR, 30.73 dB CNR, and 0.813 IoU in simulation, and 22.44 dB PSNR, 36.88 dB CNR, and 0.781 IoU experimentally. Evaluation on an ex vivo swine liver confirmed elasticity estimates within reported biological stiffness ranges. Compared to DSWE-Net and Spatio-Temporal CNNs, our approach shows superior reconstruction, segmentation, and noise insensitivity. This framework provides a robust approach to SWE reconstruction and inclusion segmentation, demonstrating strong potential for clinical translation.