LwMLA-NET: A Lightweight Multi-Level Attention-based NETwork for Segmentation of COVID-19 Lungs Abnormalities from CT Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F22%3A50019099" target="_blank" >RIV/62690094:18450/22:50019099 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9740186" target="_blank" >https://ieeexplore.ieee.org/document/9740186</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TIM.2022.3161690" target="_blank" >10.1109/TIM.2022.3161690</a>

Jazyk výsledku

angličtina

Název v původním jazyce

LwMLA-NET: A Lightweight Multi-Level Attention-based NETwork for Segmentation of COVID-19 Lungs Abnormalities from CT Images

Popis výsledku v původním jazyce

COVID-19 emerged as a global pandemic in past two years. Typical abnormal findings in chest CT images of COVID-19 patients are ground glass opacities (GGO) and consolidation, which signify the extent of damage caused to the lungs. The manual annotation of those abnormalities for severity analysis is complex, tedious, and time-consuming. This motivated us to develop a vision-based analysis framework for automated segmentation of lungs abnormalities. We proposed a deep learning framework, namely LwMLA-NET “Lightweight Multi-Level Attention-based NETwork”, to segment GGO and consolidation. The LwMLA-NET is based on an encoder-decoder architecture where depth-wise separable convolutions are employed at each stage, making it a light-weighted framework that significantly reduces the computational cost. Another distinguishable module in LwMLA-NET is the multilevel attention (MLA) mechanism which focuses on dominant and relevant features and avoids propagation of insignificant features from the encoder to the decoder, thereby aiding faster optimization. Integrating the Atrous Spatial Pyramid Pooling (ASPP) module in the bottleneck helps to handle scale variations. The LwMLA-NET was evaluated on two databases, MedSeg and Radiopedia, and obtained F1-scores of 76.7% and 73.1%, respectively. The experimental evaluation justifies that LwMLA-NET outperforms other state-of-the-art deep learning frameworks like Attention U-Net, PSP-Net, Cople-Net, Inf-Net, and Mobile-Net V2 in terms of segmentation performance and has an acceptable generalization capability. Moreover, our team“, LwMLA-NET-Team-KDD-JU”, participated in Kaggle’s “Covid 19 CT Images Segmentation” open challenge. The performance was evaluated on a separate test set, and we obtained 4th rank on the leaderboard among 40 teams with an F1-score of 71.196%. IEEE

Název v anglickém jazyce

LwMLA-NET: A Lightweight Multi-Level Attention-based NETwork for Segmentation of COVID-19 Lungs Abnormalities from CT Images

Popis výsledku anglicky

COVID-19 emerged as a global pandemic in past two years. Typical abnormal findings in chest CT images of COVID-19 patients are ground glass opacities (GGO) and consolidation, which signify the extent of damage caused to the lungs. The manual annotation of those abnormalities for severity analysis is complex, tedious, and time-consuming. This motivated us to develop a vision-based analysis framework for automated segmentation of lungs abnormalities. We proposed a deep learning framework, namely LwMLA-NET “Lightweight Multi-Level Attention-based NETwork”, to segment GGO and consolidation. The LwMLA-NET is based on an encoder-decoder architecture where depth-wise separable convolutions are employed at each stage, making it a light-weighted framework that significantly reduces the computational cost. Another distinguishable module in LwMLA-NET is the multilevel attention (MLA) mechanism which focuses on dominant and relevant features and avoids propagation of insignificant features from the encoder to the decoder, thereby aiding faster optimization. Integrating the Atrous Spatial Pyramid Pooling (ASPP) module in the bottleneck helps to handle scale variations. The LwMLA-NET was evaluated on two databases, MedSeg and Radiopedia, and obtained F1-scores of 76.7% and 73.1%, respectively. The experimental evaluation justifies that LwMLA-NET outperforms other state-of-the-art deep learning frameworks like Attention U-Net, PSP-Net, Cople-Net, Inf-Net, and Mobile-Net V2 in terms of segmentation performance and has an acceptable generalization capability. Moreover, our team“, LwMLA-NET-Team-KDD-JU”, participated in Kaggle’s “Covid 19 CT Images Segmentation” open challenge. The performance was evaluated on a separate test set, and we obtained 4th rank on the leaderboard among 40 teams with an F1-score of 71.196%. IEEE

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

<a href="/cs/project/EF18_069%2F0010054" target="_blank" >EF18_069/0010054: IT4Neuro(degeneration)</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Instrumentation and Measurement

ISSN

0018-9456

e-ISSN

1557-9662

Svazek periodika

71

Číslo periodika v rámci svazku

March

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

"Article Number: 5007813"

Kód UT WoS článku

000778909800005

EID výsledku v databázi Scopus

2-s2.0-85127065324