Region segmentation for lung cancer CT image using 3D U- Net model

Abstract

Background Lung cancer detection through medical imaging is critical for early diagnosis and effective treatment planning. This study proposes a deep learning-based approach for automated lung segmentation in computed tomography (CT) scans, utilizing the Task06_Lung dataset from the Medical Segmentation Decathlon (MSD) Challenge. Methods The dataset underwent preprocessing steps including resampling, normalization, and data augmentation to ensure consistency and diversity. Two U-Net-based architectures Simple U-Net and UNetM were implemented for segmentation. The models employed an encoder–decoder framework with skip connections to facilitate accurate feature extraction and reconstruction of lung regions. Training was performed using the Dice Loss function to address class imbalance, and a sliding window inference technique was applied to optimize memory usage during validation. Results Performance evaluation was conducted using segmentation metrics and confusion matrix analysis. The best model achieved a Dice score of 0.67 at epoch 59. Additionally, the model demonstrated high classification performance, with a precision, recall, and F1-score of 0.99, indicating strong accuracy in segmenting lung regions. Visualizations comparing predicted segmentations with ground truth masks supported the model’s effectiveness, while the confusion matrix highlighted areas requiring further improvement. Conclusion The proposed models showed strong performance in segmenting lung tissue in CT images. However, challenges remain in handling complex cancerous structures and fine anatomical boundaries. Future improvements may involve advanced data augmentation strategies and the integration of more sophisticated architectures, such as Attention U-Net, to enhance overall segmentation accuracy.

Keywords

• Lung Segmentation
• Medical Segmentation Decathlon (MSD)
• Task06_Lung Dataset
• Data Preprocessing
• Resampling and Normalization
• Data Augmentation
• U-Net Architecture
• UNetM Model
• Encoder-Decoder Framework
• Loss Function
• Precision
• Recall
• F1 Score.

References

1. Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023;73:17–48. doi: 10.3322/caac.21763.
2. Chaturvedi A, Khanna R, Kumar V. An analysis of region growing image segmentation schemes. Int J Comput Trends Technol. 2016;34:46–51. doi: 10.14445/22312803/IJCTT-V34P108.
3. Adams R, Bischof L. Seeded region growing. IEEE Trans Pattern Anal Mach Intell. 1994;16:641–7. doi: 10.1109/34.295913.
4. Mansoor A, Bagci U, Foster B, Xu Z, Papadakis GZ, Folio LR, et al. Segmentation and image analysis of abnormal lungs at CT: current approaches, challenges, and future trends. Radiographics. 2015;35:1056–76. doi: 10.1148/rg.2015140232.
5. Zhou SK, Greenspan H, Davatzikos C, Duncan JS, Van Ginneken B, Madabhushi A, et al. A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises. Proc IEEE. 2021;109:820–38. doi: 10.1109/JPROC.2021.3054390.
6. Liu M, Dong J, Dong X, Yu H, Qi L. Segmentation of lung nodule in CT images based on Mask R-CNN. In: 2018 International Conference on Awareness Science and Technology (iCAST). 2018:1–6. doi: N/A.
7. Al-Yasriy HF, Jawad DK, Farhan IA, Salman OH. Diagnosis of lung cancer based on CT scans using CNN. IOP Conf Ser Mater Sci Eng. 2020;928:022035. doi: 10.1088/1757-899X/928/2/022035.
8. Mesanovic N, Grgic M, Huseinagic H, Males M, Skejic E, Smajlovic M. Automatic CT image segmentation of the lungs with region growing algorithm. In: 2011 18th International Conference on Systems, Signals and Image Processing (IWSSIP). 2011: pp. N/A. [Internet]. Available from: https://vcl.fer.hr

9. Sahoo PK, Mishra S, Panigrahi R, Bhoi AK, Barsocchi P. An improvised deep-learning-based Mask R-CNN model for laryngeal cancer detection using CT images. Sensors (Basel). 2022;22:8834. doi: 10.3390/s22228834.
10. Cifci MA. SegChaNet: a novel model for lung cancer segmentation in CT scans. Appl Bionics Biomech. 2022;2022:1139587. doi: 10.1155/2022/1139587.
11. Chen X, Duan Q, Wu R, Yang Z. Segmentation of lung computed tomography images based on SegNet in the diagnosis of lung cancer. J Radiat Res Appl Sci. 2021;14:396–403. doi: 10.1080/16878507.2021.1981753.
12. Naseer I, Akram S, Masood T, Rashid M, Jaffar A. Lung cancer classification using modified U-Net based lobe segmentation and nodule detection. IEEE Access. 2023;11:60279–91. doi: 10.1109/ACCESS.2023.3285821.
13. Kumar V, Altahan BR, Rasheed T, Singh P, Soni D, Alsaab HO, et al. Improved UNet deep learning model for automatic detection of lung cancer nodules. Comput Intell Neurosci. 2023;2023:9739264. doi: 10.1155/2023/9739264.
14. Kurt Z, Işık Ş, Kaya Z, Anagün Y, Koca N, Çiçek S. Evaluation of EfficientNet models for COVID-19 detection using lung parenchyma. Neural Comput Appl. 2023;35(16):12121–32. doi: 10.1007/s00521-023-08344-z.
15. Results [Internet]. [cited 2024 Nov 6]. Available from: http://medicaldecathlon.com/dataaws/
16. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Lect Notes Comput Sci. 2015;9351:234–41. doi: 10.1007/978-3-319-24574-4_28.