Detecting COVID-19-infected regions in Lung CT scan through a novel dual-path Swin Transformer-based network
Abstract
Background: Deep learning-based automatic segmentation provides significant advantages over traditional manual segmentation methods in medical imaging. Current approaches for segmenting regions of Coronavirus disease 2019 (COVID-19) infections mainly utilize convolutional neural networks (CNNs), which are limited by their restricted receptive fields (RFs) and consequently struggle to establish global context connections. This limitation negatively impacts their performance in accurately detecting complex details and boundary patterns within medical images. Methods: This study introduces a novel dual-path Swin Transformer-based network to address these limitations and enhance segmentation accuracy. Our proposed model extracts more informative 3D input patches to capture long-range dependencies and represents both large and small-scale features through a dual-branch encoder. Furthermore, it integrates features from the two paths via the new Transformer Interactive Fusion (TIF) module. The architecture also incorporates an inductive bias by including a residual convolution (Res-conv) block within the encoder. Results: The proposed network has been evaluated using a 5-fold cross-validation technique, alongside data augmentation, on the publicly available COVID-19-CT-Seg and MosMed datasets. The model achieved Dice coefficients of 0.872 and 0.713 for the COVID-19-CT-Seg and MosMed datasets, respectively, demonstrating its effectiveness relative to prior methodologies. Conclusion: The significant improvements in segmentation accuracy, demonstrated by the achieved Dice coefficients on the COVID-19-CT-Seg and MosMed datasets, highlight the potential of our approach to enhance automated segmentation in medical imaging.
Filchakova O, Dossym D, Ilyas A, Kuanysheva T, Abdizhamil A, Bukasov R. Review of COVID-19 testing and diagnostic methods. Talanta. 2022;244:123409.
Bernheim A, Mei X, Huang M, Yang Y, Fayad ZA, Zhang N, et al. Chest CT findings in coronavirus disease-19 (COVID-19): relationship to duration of infection. Radiology. 2020;295(3):685-91.
Zhao W, Zhong Z, Xie X, Yu Q, Liu J. Relation between chest CT findings and clinical conditions of coronavirus disease (COVID-19) pneumonia: a multicenter study. AJR Am J Roentgenol. 2020;214(5):1072-7.
Ma J, Ge Y, Wang Y, et al. COVID-19 CT Lung and Infection Segmentation Dataset. Zenodo. Published April 20, 2020..
Morozov SP, Andreychenko AE, Blokhin IA, Gelezhe PB, Gonchar AP, Nikolaev AE, et al. MosMedData: data set of 1110 chest CT scans performed during the COVID-19 epidemic. Digital Diagnostics. 2020;1(1):49-59.
Müller D, Rey IS, Kramer F. Automated chest ct image segmentation of covid-19 lung infection based on 3d u-net. arXiv preprint arXiv:200704774. 2020.
Ma J, Wang Y, An X, Ge C, Yu Z, Chen J, et al. Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation. Medical physics. 2021;48(3):1197-210.
Wang Y, Zhang Y, Liu Y, Tian J, Zhong C, Shi Z, et al. Does non-COVID-19 lung lesion help? investigating transferability in COVID-19 CT image segmentation. Comput Methods Programs Biomed. 2021;202:106004.
Kumar Singh V, Abdel-Nasser M, Pandey N, Puig D. Lunginfseg: Segmenting covid-19 infected regions in lung ct images based on a receptive-field-aware deep learning framework. Diagnostics. 2021;11(2):158.
Zheng R, Zheng Y, Dong-Ye C. Improved 3D U‐Net for COVID‐19 chest CT image segmentation. Scientific Programming. 2021;2021(1):9999368.
Owais M, Hassan T, Afzal N, Khan SH, Velayudhan D, Ganapathi II, et al. Meta-domain adaptive framework for efficient diagnostic assessment of lung infection using CT radiographs. 2024.
Geng P, Tan Z, Wang Y, Jia W, Zhang Y, Yan H. STCNet: Alternating CNN and improved transformer network for COVID-19 CT image segmentation. Biomedical Signal Processing and Control. 2024;93:106205.
Tian Y, Mao Q, Wang W, Zhang Y. Hierarchical agent transformer network for COVID-19 infection segmentation. Biomedical Physics & Engineering Express. 2025;11(2):025055.
Lin A, Chen B, Xu J, Zhang Z, Lu G, Zhang D. Ds-transunet: dual swin transformer u-net for medical image segmentation. IEEE Transactions on Instrumentation and Measurement. 2022;71:1-15.
Wei C, Ren S, Guo K, Hu H, Liang J. High-resolution Swin transformer for automatic medical image segmentation. Sensors. 2023;23(7):3420.
Cai Z, Fan Q, Feris RS, Vasconcelos N, editors. A unified multi-scale deep convolutional neural network for fast object detection. Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14; 2016: Springer.
Cheng B, Xiao B, Wang J, Shi H, Huang TS, Zhang L, editors. Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2020.
Nah S, Hyun Kim T, Mu Lee K, editors. Deep multi-scale convolutional neural network for dynamic scene deblurring. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017.
Chen C-F, Fan Q, Mallinar N, Sercu T, Feris R. Big-little net: An efficient multi-scale feature representation for visual and speech recognition. arXiv preprint arXiv:180703848. 2018.
Zhang Q, Ren X, Wei B. Segmentation of infected region in CT images of COVID-19 patients based on QC-HC U-net. Scientific Reports. 2021;11(1):22854.
Ibrahim MR, Youssef SM, Fathalla KM. Abnormality detection and intelligent severity assessment of human chest computed tomography scans using deep learning: a case study on SARS-COV-2 assessment. J Ambient Intell Humaniz Comput. 2023;14(5):5665-88.
Morozov SP, Andreychenko AE, Pavlov N, Vladzymyrskyy A, Ledikhova N, Gombolevskiy V, et al. Mosmeddata: Chest ct scans with covid-19 related findings dataset. arXiv preprint arXiv:200506465. 2020.
He K, Zhang X, Ren S, Sun J, editors. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.
Tang Y, Yang D, Li W, Roth HR, Landman B, Xu D, et al., editors. Self-supervised pre-training of swin transformers for 3d medical image analysis. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2022.
Ba JL. Layer normalization. arXiv preprint arXiv:160706450. 2016.
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al., editors. Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF international conference on computer vision; 2021.
Li C-F, Xu Y-D, Ding X-H, Zhao J-J, Du R-Q, Wu L-Z, et al. MultiR-net: a novel joint learning network for COVID-19 segmentation and classification. Computers in Biology and Medicine. 2022;144:105340.
Battaglia PW, Hamrick JB, Bapst V, Sanchez-Gonzalez A, Zambaldi V, Malinowski M, et al. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:180601261. 2018.
Oda M, Hayashi Y, Otake Y, Hashimoto M, Akashi T, Mori K, editors. Lung infection and normal region segmentation from CT volumes of COVID-19 cases. Medical Imaging 2021: Computer-Aided Diagnosis; 2021: SPIE.
Sun S, Bauer C, Beichel R, editors. Robust active shape model based lung segmentation in CT scans. Fourth International Workshop on Pulmonary Image Analysis; 2011.
| Files | ||
| Issue | In press | |
| Section | Original article | |
| Keywords | ||
| COVID-19 Long-Range information Vision Transformer Segmentation | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
