Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification

Guangyi Zhang; Xiaohong Wang; Eugene Cheah; Peng Guo; Brian A. Telfer; Theodore T. Pierce; Anthony E. Samir

eess.IVSep 3, 2026

Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification

Authors: Guangyi Zhang, Xiaohong Wang, Eugene Cheah, Peng Guo, Brian A. Telfer, Theodore T. Pierce, Anthony E. Samir

Organizations: Center for Ultrasound Research & Translation, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA · Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA, USA

Abstract

Metabolic dysfunction-associated steatotic liver disease (MASLD) affects approximately 30% of the general population. Ultrasound-based imaging, including B-mode imaging and shear wave elastography (SWE), is widely used for noninvasive fibrosis assessment; however, the role of deep learning-based ultrasound image learning for MASLD risk stratification remains insufficiently characterized. In this study, we developed and evaluated ultrasound image learning pipelines using B-mode and SWE images for fibrosis staging and identification of patients with at-risk metabolic dysfunction-associated steatohepatitis (MASH). A total of 250 ultrasound examinations, one exam per subject, were included. Model performance was evaluated using 3-fold cross-validation with area under the receiver operating characteristic curve (AUROC). End-to-end SWE image learning achieved performance comparable to operator-guided SWE across fibrosis stages. Overall, SWE-based learning consistently outperformed B-mode image learning in fibrosis staging, with AUROC improvements from 0.64 (95%CI: [0.56, 0.72]) to 0.72 (95% CI: [0.65, 0.79]) for F>=2 (significant fibrosis, p=0.11), from 0.67 (95%CI: [0.58, 0.75]) to 0.78 (95% CI:[0.72, 0.85]) for F>=3 (advanced fibrosis, p=0.02), and from 0.69 (95%CI: [0.56, 0.82]) to 0.80 (95%CI: [0.72, 0.89]) for F4 (cirrhosis, p=0.10). These findings highlight the potential of SWE image learning for MASLD risk stratification.

Figures & tables

Figure 1: Schematic of data modalities and representations. a , Conventional B-mode ultrasound. Grayscale liver ultrasound images capturing parenchymal echotexture and anatomical structures were used as imaging inputs. b , SWE ultrasound. the elastography map is shown as a rectangular acquisition box overlaid on the B-mode image. Within this SWE box, a circular ROI is placed to sample liver stiffness measurements.

	$\bm{\textbf{F}\geq 2}$	$\bm{\textbf{F}\geq 3}$	$\bm{\textbf{F}4}$	At-Risk MASH
Cases	71 (28%)	39 (16%)	14 (6%)	41 (16%)

Table I : Prevalence of Prediction Targets in the Cohort.

Figure 2: B-mode learning pipeline. B-mode images containing liver tissue are identified using a pre-trained liver segmentation model [ 15 ] , and liver masks (shown in green) are applied to extract liver regions.

Figure 3: Proposed Siamese network for paired SWE and ROI image learning. The architecture consists of two parallel Conv2D branches for SWE and ROI inputs, followed by a Soft Attention Block for adaptive feature fusion. Four operational modes are supported: SWE-Only, ROI-First, Single Attention, and Dual Attention. Numbers in brackets denote the number of neurons in linear or BatchNorm layers, while Conv2D annotations indicate input channels, output channels, and kernel size.

Family	Architecture	Input	Seg.	Pretrain	$\bm{\textbf{F}\geq 2}$	$\bm{\textbf{F}\geq 3}$	$\textbf{F}4$	At-Risk MASH
ResNet [ 17 ]	ResNet-50	224	✗	✗	0.41	0.41	0.61	0.48
			✗	✓	$\mathbf{0.64}$	0.55	0.62	$\mathbf{0.61}$
			✓	✗	0.45	0.45	0.62	0.45
			✓	✓	0.63	$\mathbf{0.67}$	$\mathbf{0.69}$	0.52
EfficientNet [ 18 ]	EfficientNet-B3	300	✗	✗	0.40	0.46	0.64	0.51
			✗	✓	0.63	0.53	0.65	0.58

Table II : AUROC of Best-Performing B-mode Ultrasound Models for Liver Fibrosis Prediction Across Architecture Families

Task	Pretraining		Segmentation
	Mean $\Delta$	$p$ -value	Mean $\Delta$	$p$ -value
F $\geq 2$	+0.09	$<0.001$	+0.01	0.046
F $\geq 3$	+0.06	$<0.001$	+0.02	0.094
F $4$	+0.02	0.020	$-0.01$	0.446
At-Risk MASH	+0.05	$<0.001$	$-0.02$	0.059

Table III : Impact of Pretraining and Segmentation Across All Evaluated B-mode Image Learning Architectures

Method Type	Method	ROI Extraction	$\bm{\textbf{F}\geq 2}$	$\bm{\textbf{F}\geq 3}$	$\textbf{F}4$	At-Risk MASH
Operator-guided SWE	Median LS	Sonographer-guided	$0.70$	$0.78$	$\mathbf{0.86}$	$\mathbf{0.63}$
Deep learning	ROI-First	Automatic	$0.67$	$0.77$	$0.79$	$0.55$
Deep learning	SWE-Only	None	$\mathbf{0.72}$	$\mathbf{0.78}$	$0.76$	$0.59$
Deep learning	Single Attention	Automatic	$0.70$	$0.77$	$0.80$	$0.59$
Deep learning	Dual Attention	Automatic	$0.72$	$0.76$	$0.76$	$0.58$

Table IV : AUROC for SWE Discrimination of Liver Fibrosis

Figure 4: Performance comparison among B-mode learning, operator-guided SWE, as well as SWE learning approaches.

Explore similar work

Learning from Complementary Ultrasound Representations for Liver Disease Classification
Jul 13, 2026Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun +5Medical Image Classification Ultrasound Imaging
PONS Incorporated, Newark, NJ, USA · Department of Radiology, Mayo Clinic, Jacksonville, FL, USA · Department of Radiology, Department of Medicine, University of British Columbia, Vancouver, Canada
VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis
Sep 26, 2026Ziyang Xu, Shuli An, Hao Zhou +5Ultrasound Imaging Fine-Grained Image Classification
Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China · Jiangsu Provincial Key Laboratory on Parasite and Vector Control Technology, National Health Commission Key Laboratory of Parasitic Disease Control and Prevention, Jiangsu Institute of Parasitic Diseases, Wuxi, Jiangsu, China · New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences +4
Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models
May 19, 2026Athanasios Angelakis, Gabriele De Vito, Eleni-Myrto Trifylli +1Shallow Neural Networks Tabular ML
BioML Lab, RI CODE, UniBw, Munich, Germany · Department of Epidemiology and Data Science, Amsterdam UMC, Amsterdam, Netherlands · Alpha Indicium, Rijswijk, Netherlands +2

Jul 13, 2026J/K move · Enter open · S save

Learning from Complementary Ultrasound Representations for Liver Disease Classification

Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun, Senanur Sahin+4

PONS Incorporated, Newark, NJ, USA · Department of Radiology, Mayo Clinic, Jacksonville, FL, USA · Department of Radiology, Department of Medicine, University of British Columbia, Vancouver, Canada

Medical Image Classification Ultrasound Imaging Medical Image Representation Learning

Open paper AskPDF arXiv

Differentiating non-alcoholic steatohepatitis (NASH) from non-alcoholic fatty liver disease (NAFLD) using ultrasound remains challenging due to subtle tissue alterations and the limited information available in conventional B-mode imaging. In this work, we investigate whether complementary ultrasound representations derived from the same acquisition can improve NASH versus NAFLD classification. Specifically, we combine conventional B-mode ultrasound with physics-guided and local phase-based image representations and evaluate their effectiveness using self-supervised masked autoencoders (MAEs) and graph convolutional networks (GCNs). Experiments were conducted on a multi-site Mayo Clinic cohort consisting of 2,547 liver ultrasound scans from 125 patients. Compared with conventional B-mode ultrasound alone, complementary ultrasound representations consistently improved classification performance, yielding gains of up to 32.4% in accuracy and 91.2% in F1-score. Furthermore, performance improvements were consistently observed across age groups, sex, race, ethnicity,and acquisition sites.

Abstract

Explore similar work

Learning from Complementary Ultrasound Representations for Liver Disease Classification

VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis

Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models