Fast Lung Image Segmentation Using Lightweight VAEL-Unet




Medical Image Segmentation, Deep learning, VAEL-Unet, Attention module


INTRODUCTION: A lightweght lung image segmentation model was explored. It was with fast speed and low resouces consumed while the accuracy was comparable to those SOAT models.

OBJECTIVES: To improve the segmentation accuracy and computational efficiency of the model in extracting lung regions from chest X-ray images, a lightweight segmentation model enhanced with a visual attention mechanism called VAEL-Unet, was proposed.

METHODS: Firstly, the bneck module from the MobileNetV3 network was employed to replace the convolutional and pooling operations at different positions in the U-Net encoder, enabling the model to extract deeper-level features while reducing complexity and parameters. Secondly, an attention module was introduced during feature fusion, where the processed feature maps were sequentially fused with the corresponding positions in the decoder to obtain the segmented image.

RESULTS: On ChestXray, the accuracy of VAEL-Unet improves from 97.37% in the traditional U-Net network to 97.69%, while the F1-score increases by 0.67%, 0.77%, 0.61%, and 1.03% compared to U-Net, SegNet, ResUnet and DeepLabV3+ networks. respectively. On LUNA dataset. the F1-score demonstrates improvements of 0.51%, 0.48%, 0.22% and 0.46%, respectively, while the accuracy has increased from 97.78% in the traditional U-Net model to 98.08% in the VAEL-Unet model. The training time of the VAEL-Unet is much less compared to other models. The number of parameters of VAEL-Unet is only 1.1M, significantly less than 32M of U-Net, 29M of SegNet, 48M of Res-Unet, 5.8M of DeeplabV3+ and 41M of DeepLabV3Plus_ResNet50.

CONCLUSION: These results indicate that VAEL-Unet’s segmentation performance is slightly better than other referenced models while its training time and parameters are much less.


Gonzalez-Argote, J., Alonso-Galbán, P., VitónCastillo, A.A., Lepez, C.O., Castillo-Gonzalez, W., Bonardi, M.C. and Cano, C.A.G. (2023) Trends in scientific output on artificial intelligence and health in latin america in scopus. EAI Endorsed Transactions on Scalable Information Systems 10(4): e5–e5. doi:

Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H. and Nandi, A.K. (2022) Medical image segmentation using deep learning: A survey. IET Image Processing 16(5):1243–1267. doi:,URL

Wu, M., Lu, Y., Hong, X., Zhang, J., Zheng, B., Zhu, S., Chen, N. et al. (2022) Classification of dry and wet macular degeneration based on the convnext model. Frontiers in Computational Neuroscience 16. doi:10.3389/fncom.2022.1079155, URL

Zhu, S., Zhan, H., Yan, Z., Wu, M., Zheng, B., Xu, S., Jiang, Q. et al. (2023) Prediction of spherical equivalent refraction and axial length in children based on machine learning. Indian Journal of Ophthalmology 71(5): 2115–2131. doi:, URL

Zhu, S., Lu, B., Wang, C., Wu, M., Zheng, B., Jiang, Q., Wei, R. et al. (2022) Screening of common retinal diseases using six-category models based on efficientnet. Frontiers in Medicine 9. doi:10.3389/fmed.2022.808402, URL

Zheng, B., Liu, Y., He, K., Wu, M., Jin, L., Jiang, Q., Zhu, S. et al. (2021) Research on an intelligent lightweight-assisted pterygium diagnosis model based on anterior segment images. Disease Markers 2021: 7651462. doi:,


Sarki, R., Ahmed, K., Wang, H., Zhang, Y., Ma, J. and Wang, K. (2021) Image preprocessing in classification and identification of diabetic eye diseases. Data Science and Engineering 6(4): 455–471. doi:

Sarki, R., Ahmed, K., Wang, H., Zhang, Y. and Wang, K. (2021) Convolutional neural network for multi-class classification of diabetic eye disease. EAI Endorsed Transactions on Scalable Information Systems 9(4). doi:10.4108/eai.16-12-2021.172436.

Cao, Q., Hao, X., Ren, H., Xu, W., Xu, S. and Asiedu, C.J. (2022) Graph attention network based detection of causality for textual emotion-cause pair. World Wide Web : 1–15doi:, URL

Xu, S., Song, Y. and Hao, X. (2022) A comparative study of shallow machine learning models and deep learning models for landslide susceptibility assessment based on imbalanced data. Forests 13(11). doi:10.3390/f13111908, URL

Tawhid, M.N.A., Siuly, S., Wang, K. and Wang, H. (2023) Automatic and efficient framework for identifying multiple neurological disorders from eeg signals. IEEE Transactions on Technology and Society 4(1): 76–86. doi:10.1109/TTS.2023.3239526.

Alvi, A.M., Siuly, S. and Wang, H. (2023) A long shortterm memory based framework for early detection of mild cognitive impairment from eeg signals. IEEE Transactions on Emerging Topics in Computational Intelligence 7(2): 375–388. doi:10.1109/TETCI.2022.3186180.

Alvi, A.M., Siuly, S., Wang, H., Wang, K. and Whittaker, F. (2022) A deep learning based framework for diagnosis of mild cognitive impairment. Knowledge-Based Systems 248: 108815. doi:

Tawhid, M.N.A., Siuly, S., Wang, H., Whittaker, F., Wang, K. and Zhang, Y. (2021) A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from eeg. Plos one 16(6): e0253094. doi:

Singh, R., Subramani, S., Du, J., Zhang, Y., Wang, H., Miao, Y. and Ahmed, K. (2023) Antisocial behavior identification from twitter feeds using traditional machine learning algorithms and deep learning. EAI Endorsed Transactions on Scalable Information Systems 10(4). doi:10.4108/eetsis.v10i3.3184.

Pang, X., Ge, Y.F., Wang, K., Traina, A.J. and Wang, H. (2023) Patient assignment optimization in cloud healthcare systems: a distributed genetic algorithm. Health Information Science and Systems 11(1): 30. doi:

Pandey, K. and Pandey, D. (2023) Mental health evaluation and assistance for visually impaired people. EAI Endorsed Transactions on Scalable Information Systems 10(4): e6–e6. doi:10.4108/

Zhong, Z., Sun, L., Subramani, S., Peng, D. and Wang, Y. (2023) Time series classification for portable medical devices. EAI Endorsed Transactions on Scalable Information Systems 10(4): e19–e19. doi:DOI:10.4108/eetsis.v10i3.3219.

Pandey, D., Wang, H., Yin, X., Wang, K., Zhang, Y. and Shen, J. (2022) Automatic breast lesion segmentation in phase preserved dce-mris. Health Information Science and Systems 10(1): 9. doi:

Long, J., Shelhamer, E. and Darrell, T. (2015) Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition: 3431–3440. doi:

Ronneberger, O., Fischer, P. and Brox, T. (2015) Unet: Convolutional networks for biomedical image segmentation. In Medical Image Computing and ComputerAssisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (Springer): 234–241. URL https: //

Tong, G., Li, Y., Chen, H., Zhang, Q. and Jiang, H. (2018) Improved u-net network for pulmonary nodules segmentation. Optik 174: 460–469. doi:, URL

Maji, D., Sigedar, P. and Singh, M. (2022) Attention res-unet with guided decoder for semantic segmentation of brain tumors. Biomedical Signal Processing and Control 71: 103077. doi:, URL

Cao, G., Wang, Y., Zhu, X., Li, M., Wang, X. and Chen, Y. (2020) Segmentation of intracerebral hemorrhage based on improved u-net. In 2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS): 183–185. doi:

Wen, X., Zhao, B., Yuan, M., Li, J., Sun, M., Ma, L., Sun, C. et al. (2022) Application of multiscale fusion attention u-net to segment the thyroid gland on localized computed tomography images for radiotherapy. Frontiers in Oncology 12: 844052. doi:

Yu, S., Wang, K., He, L. et al. (2022) Pneumothorax segmentation method based on improved unet network. Computer Engineering and Applications 58(3): 207–214. doi:

Lin, A., Chen, B., Xu, J., Zhang, Z., Lu, G. and Zhang, D. (2022) Ds-transunet: Dual swin transformer u-net for medical image segmentation. IEEE Transactions on Instrumentation and Measurement 71: 1–15. doi:, URL

Zhang, J., Du, J., Liu, H., Hou, X., Zhao, Y. and Ding, M. (2019) Lu-net: An improved u-net for ventricular segmentation. IEEE Access 7: 92539–92546. doi:, URL 2925060.

Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L. and Liu, Z. (2022) Mobile-former: Bridging mobilenet and transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition: 5270–5279. doi:

Khan, Z.Y. and Niu, Z. (2021) Cnn with depthwise separable convolutions and combined kernels for rating prediction. Expert Systems with Applications 170: 114528. doi:, URL

Quiñonez, Y., Lizarraga, C., Peraza, J. and Zatarain, O. (2020) Image recognition in uav videos using convolutional neural networks. IET Software 14(2): 176–181. doi:, URL

Zhuxi, M., Li, Y., Huang, M., Huang, Q., Cheng, J. and Tang, S. (2022) A lightweight detector based on attention mechanism for aluminum strip surface defect detection. Computers in Industry 136: 103585. doi:, URL 103585.

Xiao, P., Qin, Z., Chen, D., Zhang, N., Ding, Y., Deng, F., Qin, Z. et al. (2023) Fastnet: A lightweight convolutional neural network for

tumors fast identification in mobile computerassisted devices. IEEE Internet of Things Journal doi:, URL

Fu, H., Song, G. and Wang, Y. (2021) Improved yolov4 marine target detection combined with cbam. Symmetry 13(4): 623. doi:, URL

Pan, X., Ge, C., Lu, R., Song, S., Chen, G., Huang, Z. and Huang, G. (2022) On the integration of self-attention and convolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition: 815–825. doi:

Canayaz, M. (2021) C+ effxnet: A novel hybrid approach for covid-19 diagnosis on ct images based on cbam and efficientnet. Chaos, Solitons & Fractals 151: 111310. doi:

Taud, H. and Mas, J. (2018) Multilayer perceptron (mlp). Geomatic approaches for modeling land change scenarios : 451–455 doi:

van Ginneken, B. and Jacobs, C. (2019), Luna16 part 1/2. URL

van Ginneken, B. and Jacobs, C. (2019), Luna16 part 2/2. URL

Nwankpa, C., Ijomah, W., Gachagan, A. and Marshall, S. (2018) Activation functions: Comparison of trends in practice and research

for deep learning. arXiv preprint arXiv:1811.03378 doi:, URL

Soomro, T.A., Afifi, A.J., Gao, J., Hellwich, O., Paul, M. and Zheng, L. (2018) Strided u-net model: Retinal vessels segmentation using dice loss. In 2018 Digital Image Computing: Techniques and Applications (DICTA) (IEEE): 1–8. doi:

Badrinarayanan, V., Kendall, A. and Cipolla, R. (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(12): 2481–2495. doi:

Xiao, X., Lian, S., Luo, Z. and Li, S. (2018) Weighted res-unet for high-quality retina vessel segmentation. In 2018 9th International Conference on Information Technology in Medicine and Education (ITME): 327–331. doi:

Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y. [eds.] Computer Vision – ECCV 2018 (Cham: Springer International Publishing): 833–851. URL

Murugappan, M., Bourisly, A.K., Prakash, N., Sumithra, M. and Acharya, U.R. (2023) Automated semantic lung segmentation in chest ct images using deep neural network. Neural Computing and Applications : 15343–15364doi:

Du, G., Cao, X., Liang, J., Chen, X. and Zhan, Y. (2020) Medical image segmentation based on unet: A review. Journal of Imaging Science and Technology doi: URL

Jiang, Y., Ye, M., Wang, P., Huang, D. and Lu, X. (2022) Mrf-iunet: A multiresolution fusion brain tumor segmentation network based on improved inception unet. Computational and Mathematical Methods in Medicine 2022. doi:, URL




How to Cite

Hao X, Zhang C, Xu S. Fast Lung Image Segmentation Using Lightweight VAEL-Unet. EAI Endorsed Scal Inf Syst [Internet]. 2024 Apr. 8 [cited 2024 May 18];. Available from:



Research articles