RED-MAM: A residual encoder-decoder network based on multi-attention fusion for ultrasound image denoising

LI, Yancheng; Zeng, Xianhua; Qian, Dong; Wang, Xinyu

doi:10.1016/j.bspc.2022.104062

Cited by 15 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power of the denoising filter should be checked at different noise levels to prove its robustness. However, only three DL studies evaluated denoising results in different noise levels 20,22,26 . In the present study, we evaluated the denoising performance of AdaRes in three different noise levels and the results indicated that it can denoise images effectively at all levels.…”

Section: Discussionmentioning

confidence: 85%

“…However, only three DL studies evaluated denoising results in different noise levels. 20,22,26 In the present study, we evaluated the denoising performance of AdaRes in three different noise levels and the results indicated that it can denoise images effectively at all levels. The capability of a denoising filter should be checked for both speckle and Gaussian noises as Gaussian noise cannot be neglected in ultrasound images.…”

Section: Birads Evaluationmentioning

confidence: 94%

“…On the other hand, all previous DL studies have not implemented comprehensive evaluation methods to show the performance of their proposed models. For instance, some either used only full-reference image quality metrics (IQMs) 23,25 or improper IQMs like signal (or peak signal) to noise ratio (SNR) 20,21,[23][24][25][26] and mean square error (MSE). 21,26 Besides, the effect of denoising filters on the quantitative features of the ultrasound image, radiomics, and the performance of radiologists in lesions' characterization has not been investigated yet.…”

mentioning

confidence: 99%

See 2 more Smart Citations

AdaRes: A deep learning‐based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

Abbasian Ardakani,

Mohammadi,

Vogl

et al. 2023

J of Clinical Ultrasound

View full text Add to dashboard Cite

PurposeThe quality of ultrasound images is degraded by speckle and Gaussian noises. This study aims to develop a deep‐learning (DL)‐based filter for ultrasound image denoising.MethodsA novel DL‐based filter using adaptive residual (AdaRes) learning was proposed. Five image quality metrics (IQMs) and 27 radiomics features were used to evaluate denoising results. The effect of our proposed filter, AdaRes, on four pre‐trained convolutional neural network (CNN) classification models and three radiologists was assessed.ResultsAdaRes filter was tested on both natural and ultrasound image databases. IQMs results indicate that AdaRes could remove noises in three different noise levels with the highest performances. In addition, a radiomics study proved that AdaRes did not distort tissue textures and it could preserve most radiomics features. AdaRes could also improve the performance classification using CNNs in different settings. Finally, AdaRes also improved the mean overall performance (AUC) of three radiologists from 0.494 to 0.702 in the classification of benign and malignant lesions.ConclusionsAdaRes filtered out noises on ultrasound images more effectively and can be used as an auxiliary preprocessing step in computer‐aided diagnosis systems. Radiologists may use it to remove unwanted noises and improve the ultrasound image quality before the interpretation.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Birads Evaluationmentioning

confidence: 94%

mentioning

confidence: 99%

See 1 more Smart Citation

AdaRes: A deep learning‐based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

Abbasian Ardakani,

Mohammadi,

Vogl

et al. 2023

J of Clinical Ultrasound

View full text Add to dashboard Cite

show abstract

“…U-Net is originally proposed for image segmentation tasks [ 31 ]. With the powerful multi-scale representation advantage, more and more computer vision tasks are realized by using U-Net as the backbone network, such as image dehazing [ 32 ], salient object detection [ 33 ], facial emotion recognition [ 34 ], image denoising [ 35 ], image fusion [ 13 , [36] , [37] , [38] , [39] ]. U-Net architecture adopts a symmetric encoder-decoder manner that overcomes the disadvantages of local and global features loss in fully convolutional networks.…”

Section: Technical Backgroundsmentioning

confidence: 99%

Image fusion using Y-net-based extractor and global-local discriminator

Yang,

Zhu,

Wang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Hybrid attention effectively integrates channel attention and spatial attention, learns the relation between spatial regions and channel pixels, distinguishes important features from insignificant ones, and strengthens the reconstruction of high-frequency information. For the blurred edges and unclear texture of traditional computed tomography (CT) images, a super-resolution network of CT images based on hybrid attention and global feature fusion was presented by Chi et al [85] for CT image restoration. The hybrid attention mechanism adaptively maps feature information from feature maps at different levels, and the connections between feature maps at different levels are established by the hybrid attention mechanism.…”

Section: Hybrid Attention In Medical Image Enhancement Taskmentioning

confidence: 99%

Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds

Li²,

Yan³

et al. 2023

IJNDI

View full text Add to dashboard Cite

Survey/review study Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds Xiang Li 1, Minglei Li 1, Pengfei Yan 1, Guanyi Li 1, Yuchen Jiang 1, Hao Luo 1,*, and Shen Yin 2 1 Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China 2 Department of Mechanical and Industrial Engineering, Faculty of Engineering, Norwegian University of Science and Technology, Trondheim 7034, Norway * Correspondence: hao.luo@hit.edu.cn Received: 16 October 2022 Accepted: 25 November 2022 Published: Abstract: With the improvement of hardware computing power and the development of deep learning algorithms, a revolution of "artificial intelligence (AI) + medical image" is taking place. Benefiting from diversified modern medical measurement equipment, a large number of medical images will be produced in the clinical process. These images improve the diagnostic accuracy of doctors, but also increase the labor burden of doctors. Deep learning technology is expected to realize an auxiliary diagnosis and improve diagnostic efficiency. At present, the method of deep learning technology combined with attention mechanism is a research hotspot and has achieved state-of-the-art results in many medical image tasks. This paper reviews the deep learning attention methods in medical image analysis. A comprehensive literature survey is first conducted to analyze the keywords and literature. Then, we introduce the development and technical characteristics of the attention mechanism. For its application in medical image analysis, we summarize the related methods in medical image classification, segmentation, detection, and enhancement. The remaining challenges, potential solutions, and future research directions are also discussed.

show abstract

RED-MAM: A residual encoder-decoder network based on multi-attention fusion for ultrasound image denoising

Cited by 15 publications

References 28 publications

AdaRes: A deep learning‐based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

AdaRes: A deep learning‐based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

Image fusion using Y-net-based extractor and global-local discriminator

Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds

Contact Info

Product

Resources

About