Do We Need Pre-Processing for Deep Learning Based Ultrasound Shear Wave Elastography?

2025-08-01

AI Summary

Conventional ultrasound elastography relies on manual preprocessing of raw radiofrequency (RF) data—such as beamforming and filtering—to enable reliable shear wave speed (SWS) estimation, introducing operator dependency, hardware constraints, and variability. Method: We investigate whether deep learning can bypass these steps by directly estimating SWS from unprocessed RF data. A 3D convolutional neural network was trained and evaluated using four input types: raw RF, partially processed RF, fully beamformed/filtered B-mode images, and conventional time-of-flight (TOF) estimates. Experiments were conducted on gelatin phantoms with four distinct elasticity gradients. Contribution/Results: The model achieved statistically significant inter-group SWS differentiation (p < 0.01) using raw RF alone, matching the accuracy of preprocessed inputs. Preprocessing conferred only marginal gains (<2% accuracy improvement) while increasing bias risk. These findings demonstrate that deep learning can robustly replace conventional preprocessing pipelines, reducing reliance on manual parameter tuning and hardware-specific implementations—thereby enhancing standardization and clinical deployability of ultrasound elastography.

Technology Category

• Machine Learning: Learning with Manifolds
• Intelligent Robots: State Estimation
• Computer Vision: Segmentation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Estimating the elasticity of soft tissue can provide useful information for various diagnostic applications. Ultrasound shear wave elastography offers a non-invasive approach. However, its generalizability and standardization across different systems and processing pipelines remain limited. Considering the influence of image processing on ultrasound based diagnostics, recent literature has discussed the impact of different image processing steps on reliable and reproducible elasticity analysis. In this work, we investigate the need of ultrasound pre-processing steps for deep learning-based ultrasound shear wave elastography. We evaluate the performance of a 3D convolutional neural network in predicting shear wave velocities from spatio-temporal ultrasound images, studying different degrees of pre-processing on the input images, ranging from fully beamformed and filtered ultrasound images to raw radiofrequency data. We compare the predictions from our deep learning approach to a conventional time-of-flight method across four gelatin phantoms with different elasticity levels. Our results demonstrate statistically significant differences in the predicted shear wave velocity among all elasticity groups, regardless of the degree of pre-processing. Although pre-processing slightly improves performance metrics, our results show that the deep learning approach can reliably differentiate between elasticity groups using raw, unprocessed radiofrequency data. These results show that deep learning-based approaches could reduce the need for and the bias of traditional ultrasound pre-processing steps in ultrasound shear wave elastography, enabling faster and more reliable clinical elasticity assessments.

Problem

• Investigates need for ultrasound pre-processing in deep learning elastography
• Evaluates deep learning performance on raw vs processed ultrasound data
• Compares deep learning and conventional methods for elasticity assessment

Innovation

• Deep learning analyzes raw ultrasound radiofrequency data
• 3D CNN predicts shear wave velocity directly
• Reduces need for traditional ultrasound pre-processing