US-Net : A lightweight network for simultaneous speckle suppression and texture enhancement in ultrasound images
Copyright © 2022 Elsevier Ltd. All rights reserved..
BACKGROUND: Numerous traditional filtering approaches and deep learning-based methods have been proposed to improve the quality of ultrasound (US) image data. However, their results tend to suffer from over-smoothing and loss of texture and fine details. Moreover, they perform poorly on images with different degradation levels and mainly focus on speckle reduction, even though texture and fine detail enhancement are of crucial importance in clinical diagnosis.
METHODS: We propose an end-to-end framework termed US-Net for simultaneous speckle suppression and texture enhancement in US images. The architecture of US-Net is inspired by U-Net, whereby a feature refinement attention block (FRAB) is introduced to enable an effective learning of multi-level and multi-contextual representative features. Specifically, FRAB aims to emphasize high-frequency image information, which helps boost the restoration and preservation of fine-grained and textural details. Furthermore, our proposed US-Net is trained essentially with real US image data, whereby real US images embedded with simulated multi-level speckle noise are used as an auxiliary training set.
RESULTS: Extensive quantitative and qualitative experiments indicate that although trained with only one US image data type, our proposed US-Net is capable of restoring images acquired from different body parts and scanning settings with different degradation levels, while exhibiting favorable performance against state-of-the-art image enhancement approaches. Furthermore, utilizing our proposed US-Net as a pre-processing stage for COVID-19 diagnosis results in a gain of 3.6% in diagnostic accuracy.
CONCLUSIONS: The proposed framework can help improve the accuracy of ultrasound diagnosis.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:152 |
|---|---|
| Enthalten in: |
Computers in biology and medicine - 152(2023) vom: 15. Jan., Seite 106385 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Monkam, Patrice [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Completed 05.01.2023 Date Revised 11.02.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.compbiomed.2022.106385 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM350059861 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM350059861 | ||
| 003 | DE-627 | ||
| 005 | 20231226044107.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2022.106385 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1166.xml |
| 035 | |a (DE-627)NLM350059861 | ||
| 035 | |a (NLM)36493732 | ||
| 035 | |a (PII)S0010-4825(22)01093-9 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Monkam, Patrice |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a US-Net |b A lightweight network for simultaneous speckle suppression and texture enhancement in ultrasound images |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 05.01.2023 | ||
| 500 | |a Date Revised 11.02.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2022 Elsevier Ltd. All rights reserved. | ||
| 520 | |a BACKGROUND: Numerous traditional filtering approaches and deep learning-based methods have been proposed to improve the quality of ultrasound (US) image data. However, their results tend to suffer from over-smoothing and loss of texture and fine details. Moreover, they perform poorly on images with different degradation levels and mainly focus on speckle reduction, even though texture and fine detail enhancement are of crucial importance in clinical diagnosis | ||
| 520 | |a METHODS: We propose an end-to-end framework termed US-Net for simultaneous speckle suppression and texture enhancement in US images. The architecture of US-Net is inspired by U-Net, whereby a feature refinement attention block (FRAB) is introduced to enable an effective learning of multi-level and multi-contextual representative features. Specifically, FRAB aims to emphasize high-frequency image information, which helps boost the restoration and preservation of fine-grained and textural details. Furthermore, our proposed US-Net is trained essentially with real US image data, whereby real US images embedded with simulated multi-level speckle noise are used as an auxiliary training set | ||
| 520 | |a RESULTS: Extensive quantitative and qualitative experiments indicate that although trained with only one US image data type, our proposed US-Net is capable of restoring images acquired from different body parts and scanning settings with different degradation levels, while exhibiting favorable performance against state-of-the-art image enhancement approaches. Furthermore, utilizing our proposed US-Net as a pre-processing stage for COVID-19 diagnosis results in a gain of 3.6% in diagnostic accuracy | ||
| 520 | |a CONCLUSIONS: The proposed framework can help improve the accuracy of ultrasound diagnosis | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Improved diagnostic accuracy | |
| 650 | 4 | |a Speckle suppression | |
| 650 | 4 | |a Texture enhancement | |
| 650 | 4 | |a Ultrasound image | |
| 700 | 1 | |a Lu, Wenkai |e verfasserin |4 aut | |
| 700 | 1 | |a Jin, Songbai |e verfasserin |4 aut | |
| 700 | 1 | |a Shan, Wenjun |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Xiang |e verfasserin |4 aut | |
| 700 | 1 | |a Tang, Bo |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Hua |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Hongmin |e verfasserin |4 aut | |
| 700 | 1 | |a Ding, Xin |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Huan |e verfasserin |4 aut | |
| 700 | 1 | |a Su, Longxiang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 152(2023) vom: 15. Jan., Seite 106385 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:152 |g year:2023 |g day:15 |g month:01 |g pages:106385 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2022.106385 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 152 |j 2023 |b 15 |c 01 |h 106385 | ||