LUV-Net: Multi-Pattern Lung Ultrasound Video Classification through Pattern-Specific Attention with Efficient Temporal Feature Extraction

Jung Hoon Lee, Changi Kim, Jinwoo Lee, Si Mong Yoon, Kyung-Eui Lee, Hyun-Jun Park, Kwonhyung Hyung, Chang Min Park
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:896-913, 2026.

Abstract

Lung ultrasound (LUS) has emerged as a crucial bedside imaging tool for critical care, yet its interpretation remains challenging due to its artifact-based nature and high operator dependency. While deep learning approaches offer promising solutions for LUS pattern analysis, existing methods are limited by their focus on single-pattern recognition or disease-specific classification, and inadequate handling of temporal dynamics in video-based models. We propose LUV-Net (Lung Ultrasound Video Network), a novel deep learning model for multi-label classification of LUS patterns, combining pattern-specific attention mechanisms with temporal feature extraction. Our approach consists of two key modules: a spatial feature extraction module utilizing independent pattern-specific attention mechanisms, and a temporal feature extraction module designed to capture sequential relationships between adjacent frames. The model was evaluated using two distinct datasets: a development set of 341 LUS videos and a temporally separated validation set of 56 videos. Through 5-fold cross-validation, LUV-Net demonstrated superior performance in identifying all four LUS patterns (A-lines, B-lines, consolidation, and pleural effusion) compared to conventional video models, achieving higher AUC scores across patterns. The modelś interpretability was validated through visualization of pattern-specific attention regions, providing insights into its decision-making process. The code is publicly available at https://github.com/iamhxxn2/LungUS_Video.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-lee26a, title = {LUV-Net: Multi-Pattern Lung Ultrasound Video Classification through Pattern-Specific Attention with Efficient Temporal Feature Extraction}, author = {Lee, Jung Hoon and Kim, Changi and Lee, Jinwoo and Yoon, Si Mong and Lee, Kyung-Eui and Park, Hyun-Jun and Hyung, Kwonhyung and Park, Chang Min}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {896--913}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/lee26a/lee26a.pdf}, url = {https://proceedings.mlr.press/v301/lee26a.html}, abstract = {Lung ultrasound (LUS) has emerged as a crucial bedside imaging tool for critical care, yet its interpretation remains challenging due to its artifact-based nature and high operator dependency. While deep learning approaches offer promising solutions for LUS pattern analysis, existing methods are limited by their focus on single-pattern recognition or disease-specific classification, and inadequate handling of temporal dynamics in video-based models. We propose LUV-Net (Lung Ultrasound Video Network), a novel deep learning model for multi-label classification of LUS patterns, combining pattern-specific attention mechanisms with temporal feature extraction. Our approach consists of two key modules: a spatial feature extraction module utilizing independent pattern-specific attention mechanisms, and a temporal feature extraction module designed to capture sequential relationships between adjacent frames. The model was evaluated using two distinct datasets: a development set of 341 LUS videos and a temporally separated validation set of 56 videos. Through 5-fold cross-validation, LUV-Net demonstrated superior performance in identifying all four LUS patterns (A-lines, B-lines, consolidation, and pleural effusion) compared to conventional video models, achieving higher AUC scores across patterns. The modelś interpretability was validated through visualization of pattern-specific attention regions, providing insights into its decision-making process. The code is publicly available at https://github.com/iamhxxn2/LungUS_Video.} }
Endnote
%0 Conference Paper %T LUV-Net: Multi-Pattern Lung Ultrasound Video Classification through Pattern-Specific Attention with Efficient Temporal Feature Extraction %A Jung Hoon Lee %A Changi Kim %A Jinwoo Lee %A Si Mong Yoon %A Kyung-Eui Lee %A Hyun-Jun Park %A Kwonhyung Hyung %A Chang Min Park %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-lee26a %I PMLR %P 896--913 %U https://proceedings.mlr.press/v301/lee26a.html %V 301 %X Lung ultrasound (LUS) has emerged as a crucial bedside imaging tool for critical care, yet its interpretation remains challenging due to its artifact-based nature and high operator dependency. While deep learning approaches offer promising solutions for LUS pattern analysis, existing methods are limited by their focus on single-pattern recognition or disease-specific classification, and inadequate handling of temporal dynamics in video-based models. We propose LUV-Net (Lung Ultrasound Video Network), a novel deep learning model for multi-label classification of LUS patterns, combining pattern-specific attention mechanisms with temporal feature extraction. Our approach consists of two key modules: a spatial feature extraction module utilizing independent pattern-specific attention mechanisms, and a temporal feature extraction module designed to capture sequential relationships between adjacent frames. The model was evaluated using two distinct datasets: a development set of 341 LUS videos and a temporally separated validation set of 56 videos. Through 5-fold cross-validation, LUV-Net demonstrated superior performance in identifying all four LUS patterns (A-lines, B-lines, consolidation, and pleural effusion) compared to conventional video models, achieving higher AUC scores across patterns. The modelś interpretability was validated through visualization of pattern-specific attention regions, providing insights into its decision-making process. The code is publicly available at https://github.com/iamhxxn2/LungUS_Video.
APA
Lee, J.H., Kim, C., Lee, J., Yoon, S.M., Lee, K., Park, H., Hyung, K. & Park, C.M.. (2026). LUV-Net: Multi-Pattern Lung Ultrasound Video Classification through Pattern-Specific Attention with Efficient Temporal Feature Extraction. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:896-913 Available from https://proceedings.mlr.press/v301/lee26a.html.

Related Material