Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation

<b>Background/Objectives:</b> Rapid and accurate assessment of lung diseases, like pneumonia, is critical for effective clinical decision-making, particularly during pandemics when disease progression can be severe. Early diagnosis plays a crucial role in preventing complications, necess...

Full description

Saved in:
Bibliographic Details
Main Authors: Bouthaina Slika, Fadi Dornaika, Karim Hammoudi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/11/1301
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129460548861952
author Bouthaina Slika
Fadi Dornaika
Karim Hammoudi
author_facet Bouthaina Slika
Fadi Dornaika
Karim Hammoudi
author_sort Bouthaina Slika
collection DOAJ
description <b>Background/Objectives:</b> Rapid and accurate assessment of lung diseases, like pneumonia, is critical for effective clinical decision-making, particularly during pandemics when disease progression can be severe. Early diagnosis plays a crucial role in preventing complications, necessitating the development of fast and efficient AI-based models for automated severity assessment. <b>Methods:</b> In this study, we introduce a novel approach that leverages VMamba, a state-of-the-art vision model based on the VisualStateSpace (VSS) framework and 2D-Selective-Scan (SS2D) spatial scanning, to enhance lung severity prediction. Integrated in a parallel multi-image regions approach, VMamba effectively captures global and local contextual features through structured state-space modeling, improving feature representation and robustness in medical image analysis. Additionally, we integrate a segmented lung replacement augmentation strategy to enhance data diversity and improve model generalization. The proposed method is trained on the RALO and COVID-19 datasets and compared against state-of-the-art models. <b>Results:</b> Experimental results demonstrate that our approach achieves superior performance, outperforming existing techniques in prediction accuracy and robustness. Key evaluation metrics, including Mean Absolute Error (MAE) and Pearson Correlation (PC), confirm the model’s effectiveness, while the incorporation of segmented lung replacement augmentation further enhances adaptability to diverse lung conditions. <b>Conclusions:</b> These findings highlight the potential of our method for reliable and immediate clinical applications in lung infection assessment.
format Article
id doaj-art-73c07ccc2fbf424589ee35d0b6f9c152
institution OA Journals
issn 2075-4418
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-73c07ccc2fbf424589ee35d0b6f9c1522025-08-20T02:32:57ZengMDPI AGDiagnostics2075-44182025-05-011511130110.3390/diagnostics15111301Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement AugmentationBouthaina Slika0Fadi Dornaika1Karim Hammoudi2Department of Computer Science and Artificial Intelligence, University of the Basque Country UPV/EHU, 200018 San Sebastian, SpainDepartment of Computer Science and Artificial Intelligence, University of the Basque Country UPV/EHU, 200018 San Sebastian, SpainDepartment of Computer Science, Institut de Recherche en Informatique, Mathématiques, Automatique et Signal, Université de Haute-Alsace, 68093 Mulhouse, France<b>Background/Objectives:</b> Rapid and accurate assessment of lung diseases, like pneumonia, is critical for effective clinical decision-making, particularly during pandemics when disease progression can be severe. Early diagnosis plays a crucial role in preventing complications, necessitating the development of fast and efficient AI-based models for automated severity assessment. <b>Methods:</b> In this study, we introduce a novel approach that leverages VMamba, a state-of-the-art vision model based on the VisualStateSpace (VSS) framework and 2D-Selective-Scan (SS2D) spatial scanning, to enhance lung severity prediction. Integrated in a parallel multi-image regions approach, VMamba effectively captures global and local contextual features through structured state-space modeling, improving feature representation and robustness in medical image analysis. Additionally, we integrate a segmented lung replacement augmentation strategy to enhance data diversity and improve model generalization. The proposed method is trained on the RALO and COVID-19 datasets and compared against state-of-the-art models. <b>Results:</b> Experimental results demonstrate that our approach achieves superior performance, outperforming existing techniques in prediction accuracy and robustness. Key evaluation metrics, including Mean Absolute Error (MAE) and Pearson Correlation (PC), confirm the model’s effectiveness, while the incorporation of segmented lung replacement augmentation further enhances adaptability to diverse lung conditions. <b>Conclusions:</b> These findings highlight the potential of our method for reliable and immediate clinical applications in lung infection assessment.https://www.mdpi.com/2075-4418/15/11/1301pneumonialung diseasesautomatic predictionchest X-rayseverity quantificationmamba
spellingShingle Bouthaina Slika
Fadi Dornaika
Karim Hammoudi
Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
Diagnostics
pneumonia
lung diseases
automatic prediction
chest X-ray
severity quantification
mamba
title Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
title_full Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
title_fullStr Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
title_full_unstemmed Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
title_short Parallel VMamba and Attention-Based Pneumonia Severity Prediction from CXRs: A Robust Model with Segmented Lung Replacement Augmentation
title_sort parallel vmamba and attention based pneumonia severity prediction from cxrs a robust model with segmented lung replacement augmentation
topic pneumonia
lung diseases
automatic prediction
chest X-ray
severity quantification
mamba
url https://www.mdpi.com/2075-4418/15/11/1301
work_keys_str_mv AT bouthainaslika parallelvmambaandattentionbasedpneumoniaseveritypredictionfromcxrsarobustmodelwithsegmentedlungreplacementaugmentation
AT fadidornaika parallelvmambaandattentionbasedpneumoniaseveritypredictionfromcxrsarobustmodelwithsegmentedlungreplacementaugmentation
AT karimhammoudi parallelvmambaandattentionbasedpneumoniaseveritypredictionfromcxrsarobustmodelwithsegmentedlungreplacementaugmentation