Attention residual network for medical ultrasound image segmentation

Abstract Ultrasound imaging can distinctly display the morphology and structure of internal organs within the human body, enabling the examination of organs like the breast, liver, and thyroid. It can identify the locations of tumors, nodules, and other lesions, thereby serving as an efficacious too...

Full description

Saved in:
Bibliographic Details
Main Authors: Honghua Liu, Peiqin Zhang, Jiamin Hu, Yini Huang, Shanshan Zuo, Lu Li, Mailan Liu, Chang She
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04086-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334729231302656
author Honghua Liu
Peiqin Zhang
Jiamin Hu
Yini Huang
Shanshan Zuo
Lu Li
Mailan Liu
Chang She
author_facet Honghua Liu
Peiqin Zhang
Jiamin Hu
Yini Huang
Shanshan Zuo
Lu Li
Mailan Liu
Chang She
author_sort Honghua Liu
collection DOAJ
description Abstract Ultrasound imaging can distinctly display the morphology and structure of internal organs within the human body, enabling the examination of organs like the breast, liver, and thyroid. It can identify the locations of tumors, nodules, and other lesions, thereby serving as an efficacious tool for treatment detection and rehabilitation evaluation. Typically, the attending physician is required to manually demarcate the boundaries of lesion locations, such as tumors, in ultrasound images. Nevertheless, several issues exist. The high noise level in ultrasound images, the degradation of image quality due to the impact of surrounding tissues, and the influence of the operator’s experience and proficiency on the determination of lesion locations can all contribute to a reduction in the accuracy of delineating the boundaries of lesion sites. In the wake of the advancement of deep learning, its application in medical image segmentation is becoming increasingly prevalent. For instance, while the U-Net model has demonstrated a favorable performance in medical image segmentation, the convolution layers of the traditional U-Net model are relatively simplistic, leading to suboptimal extraction of global information. Moreover, due to the significant noise present in ultrasound images, the model is prone to interference. In this research, we propose an Attention Residual Network model (ARU-Net). By incorporating residual connections within the encoder section, the learning capacity of the model is enhanced. Additionally, a spatial hybrid convolution module is integrated to augment the model’s ability to extract global information and deepen the vertical architecture of the network. During the feature fusion stage of the skip connections, a channel attention mechanism and a multi-convolutional self-attention mechanism are respectively introduced to suppress noisy points within the fused feature maps, enabling the model to acquire more information regarding the target region. Finally, the predictive efficacy of the model was evaluated using publicly accessible breast ultrasound and thyroid ultrasound data. The ARU-Net achieved mean Intersection over Union (mIoU) values of 82.59% and 84.88%, accuracy values of 97.53% and 96.09%, and F1-score values of 90.06% and 89.7% for breast and thyroid ultrasound, respectively.
format Article
id doaj-art-ef81a1d43cb3402eae0cc8bcb39912db
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ef81a1d43cb3402eae0cc8bcb39912db2025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111410.1038/s41598-025-04086-1Attention residual network for medical ultrasound image segmentationHonghua Liu0Peiqin Zhang1Jiamin Hu2Yini Huang3Shanshan Zuo4Lu Li5Mailan Liu6Chang She7Hunan University of Chinese MedicineHunan Traditional Chinese Medical CollegeHunan University of Chinese MedicineChangsha Hospital of Traditional Chinese Medicine (Changsha Eighth Hospital)Changsha Hospital of Traditional Chinese Medicine (Changsha Eighth Hospital)Changsha Hospital of Traditional Chinese Medicine (Changsha Eighth Hospital)Hunan University of Chinese MedicineChangsha Hospital of Traditional Chinese Medicine (Changsha Eighth Hospital)Abstract Ultrasound imaging can distinctly display the morphology and structure of internal organs within the human body, enabling the examination of organs like the breast, liver, and thyroid. It can identify the locations of tumors, nodules, and other lesions, thereby serving as an efficacious tool for treatment detection and rehabilitation evaluation. Typically, the attending physician is required to manually demarcate the boundaries of lesion locations, such as tumors, in ultrasound images. Nevertheless, several issues exist. The high noise level in ultrasound images, the degradation of image quality due to the impact of surrounding tissues, and the influence of the operator’s experience and proficiency on the determination of lesion locations can all contribute to a reduction in the accuracy of delineating the boundaries of lesion sites. In the wake of the advancement of deep learning, its application in medical image segmentation is becoming increasingly prevalent. For instance, while the U-Net model has demonstrated a favorable performance in medical image segmentation, the convolution layers of the traditional U-Net model are relatively simplistic, leading to suboptimal extraction of global information. Moreover, due to the significant noise present in ultrasound images, the model is prone to interference. In this research, we propose an Attention Residual Network model (ARU-Net). By incorporating residual connections within the encoder section, the learning capacity of the model is enhanced. Additionally, a spatial hybrid convolution module is integrated to augment the model’s ability to extract global information and deepen the vertical architecture of the network. During the feature fusion stage of the skip connections, a channel attention mechanism and a multi-convolutional self-attention mechanism are respectively introduced to suppress noisy points within the fused feature maps, enabling the model to acquire more information regarding the target region. Finally, the predictive efficacy of the model was evaluated using publicly accessible breast ultrasound and thyroid ultrasound data. The ARU-Net achieved mean Intersection over Union (mIoU) values of 82.59% and 84.88%, accuracy values of 97.53% and 96.09%, and F1-score values of 90.06% and 89.7% for breast and thyroid ultrasound, respectively.https://doi.org/10.1038/s41598-025-04086-1Image segmentationUltrasound imagesAttention mechanismU-NetResidual connection
spellingShingle Honghua Liu
Peiqin Zhang
Jiamin Hu
Yini Huang
Shanshan Zuo
Lu Li
Mailan Liu
Chang She
Attention residual network for medical ultrasound image segmentation
Scientific Reports
Image segmentation
Ultrasound images
Attention mechanism
U-Net
Residual connection
title Attention residual network for medical ultrasound image segmentation
title_full Attention residual network for medical ultrasound image segmentation
title_fullStr Attention residual network for medical ultrasound image segmentation
title_full_unstemmed Attention residual network for medical ultrasound image segmentation
title_short Attention residual network for medical ultrasound image segmentation
title_sort attention residual network for medical ultrasound image segmentation
topic Image segmentation
Ultrasound images
Attention mechanism
U-Net
Residual connection
url https://doi.org/10.1038/s41598-025-04086-1
work_keys_str_mv AT honghualiu attentionresidualnetworkformedicalultrasoundimagesegmentation
AT peiqinzhang attentionresidualnetworkformedicalultrasoundimagesegmentation
AT jiaminhu attentionresidualnetworkformedicalultrasoundimagesegmentation
AT yinihuang attentionresidualnetworkformedicalultrasoundimagesegmentation
AT shanshanzuo attentionresidualnetworkformedicalultrasoundimagesegmentation
AT luli attentionresidualnetworkformedicalultrasoundimagesegmentation
AT mailanliu attentionresidualnetworkformedicalultrasoundimagesegmentation
AT changshe attentionresidualnetworkformedicalultrasoundimagesegmentation