Deep Lab v3+: A Novel Deep Learning Model for Accurate and Efficient GTV Segmentation and Classification in NSCLC Imaging
Keywords:
NSCLC treatment planning, DeepLab v3 model, GTV segmentation, classification, quantitative results, medical imagingAbstract
This research proposes an innovative methodology for accurate Gross Target Volume (GTV) segmentation and classification in Non-Small Cell Lung Cancer (NSCLC) treatment planning. The proposed method is based on the DeepLab v3+ model and employs a comprehensive strategy to address the challenges of class imbalance, including weighted loss, data augmentation, selective sampling, and post-processing techniques. In this paper, the Kaggle chest CT scan dataset is employed, and the proposed model is trained over 50 epochs. The model achieves remarkable results across various evaluation metrics, including a Dice coefficient of 0.87, Jaccard similarity coefficient of 0.84, true positive rate of 0.94, and false positive rate of 0.0011. The model also achieves an impressive segmentation time of 25 ms per slice. In the classification realm, the model achieves accuracy scores of 96.7% for tumor, 95.3% for lymph node, and 94.2% for healthy tissue classifications. The proposed method outperforms existing methods, such as U-Net and Modified ResNet models, in key metrics. This is due to its complex architecture, multi-scale approach, and employment of dilated convolutions. These distinctive attributes empower the model to excel in accurate and efficient GTV segmentation and classification, enhancing the clinical workflow for NSCLC treatment planning. The implications of this research are vast, as the proposed method's precision and efficiency can revolutionize the accuracy of GTV delineation, paving the way for more informed and effective treatment decisions in NSCLC patients.
Downloads
References
Tan, A. C. (2020). Targeting the PI3K/Akt/mTOR pathway in non‐small cell lung cancer (NSCLC). Thoracic cancer, 11(3), 511-518.
Yegya-Raman, N., Zou, W., Nie, K., Malhotra, J., & Jabbour, S. K. (2018). Advanced radiation techniques for locally advanced non-small cell lung cancer: intensity-modulated radiation therapy and proton therapy. Journal of Thoracic Disease, 10(Suppl 21), S2474.
Ma, C., Tian, Z., Wang, R., Feng, Z., Jiang, F., Hu, Q., ... & Wu, H. (2022). A prediction model for dosimetric‐based lung adaptive radiotherapy. Medical Physics, 49(10), 6319-6333.
El-Baz, A., Beache, G. M., Gimel'farb, G., Suzuki, K., Okada, K., Elnakib, A., ... & Abdollahi, B. (2013). Computer-aided diagnosis systems for lung cancer: challenges and methodologies. International journal of biomedical imaging, 2013.
Gintz, D., Latifi, K., Caudell, J., Nelms, B., Zhang, G., Moros, E., & Feygelman, V. (2016). Initial evaluation of automated treatment planning software. Journal of Applied Clinical Medical Physics, 17(3), 331-346.
Swathi Velugoti, Revuri Harshini Reddy, Sadiya Tarannum, & Sama Sama Tharun Kumar Reddy Kumar Reddy. (2022). Lung Nodule Detection and Classification using Image Processing Techniques. International Journal of Computer Engineering in Research Trends, 9(7), 114–119
Pallavi P. Jadhav, & Prof. U. A. Nuli. (2017). Cancer Detection in Mammograms by Extracting Geometry and Texture Features. International Journal of Computer Engineering in Research Trends, 4(12), 552–555.
Sluimer, I., Prokop, M., & Van Ginneken, B. (2005). Toward automated segmentation of the pathological lung in CT. IEEE transactions on medical imaging, 24(8), 1025-1038.
Brændengen, M., Hansson, K., Radu, C., Siegbahn, A., Jacobsson, H., & Glimelius, B. (2011). Delineation of gross tumor volume (GTV) for radiation treatment planning of locally advanced rectal cancer using information from MRI or FDG-PET/CT: a prospective study. International Journal of Radiation Oncology* Biology* Physics, 81(4), e439-e445.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234-241). Springer International Publishing.
Zunair, H., & Hamza, A. B. (2021). Sharp U-Net: Depthwise convolutional network for biomedical image segmentation. Computers in Biology and Medicine, 136, 104699.
Shaziya, H., Shyamala, K., & Zaheer, R. (2018, April). Automatic lung segmentation on thoracic CT scans using U-net convolutional network. In 2018 International conference on communication and signal processing (ICCSP) (pp. 0643-0647). IEEE.
Greco, C., Rosenzweig, K., Cascini, G. L., & Tamburrini, O. (2007). Current status of PET/CT for tumour volume definition in radiotherapy treatment planning for non-small cell lung cancer (NSCLC). Lung cancer, 57(2), 125-134.
Martin, S., Johnson, C., Brophy, M., Palma, D. A., Barron, J. L., Beauchemin, S. S., ... & Gaede, S. (2015). Impact of target volume segmentation accuracy and variability on treatment planning for 4D-CT-based non-small cell lung cancer radiotherapy. Acta Oncologica, 54(3), 322-332.
Haga, A., Takahashi, W., Aoki, S., Nawa, K., Yamashita, H., Abe, O., & Nakagawa, K. (2018). Classification of early stage non-small cell lung cancers on computed tomographic images into histological types using radiomic features: interobserver delineation variability analysis. Radiological Physics and Technology, 11, 27-35.
Palatnik de Sousa, I., Maria Bernardes Rebuzzi Vellasco, M., & Costa da Silva, E. (2019). Local interpretable model-agnostic explanations for classification of lymph node metastases. Sensors, 19(13), 2969.
Said, Y., Alsheikhy, A. A., Shawly, T., & Lahza, H. (2023). Medical images segmentation for lung cancer diagnosis based on deep learning architectures. Diagnostics, 13(3), 546.
Marentakis, P., Karaiskos, P., Kouloulias, V., Kelekis, N., Argentos, S., Oikonomopoulos, N., & Loukas, C. (2021). Lung cancer histology classification from CT images based on radiomics and deep learning models. Medical & Biological Engineering & Computing, 59, 215-226.
Tyagi, S., Kushnure, D. T., & Talbar, S. N. (2023). An amalgamation of vision transformer with convolutional neural network for automatic Lung tumor segmentation. Computerized Medical Imaging and Graphics, 102258.
Najeeb, S., & Bhuiyan, M. I. H. (2022). Spatial feature fusion in 3D convolutional autoencoders for lung tumor segmentation from 3D CT images. Biomedical Signal Processing and Control, 78, 103996.
Almukhtar, F. H. (2023). Lung cancer diagnosis through CT images using principal component analysis (PCA) and error correcting output codes (ECOC). Journal of Control and Decision, 1-11.
Lian, X., Pang, Y., Han, J., & Pan, J. (2021). Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation. Pattern Recognition, 110, 107622.
Reynaldi, D., Negara, B. S., Sanjaya, S., & Satria, E. (2021, July). Covid-19 classification for chest x-ray images using deep learning and resnet-101. In 2021 International Congress of Advanced Technology and Engineering (ICOTEN) (pp. 1-4). IEEE.
Niu, Z., Zhong, G., & Yu, H. (2021). A review on the attention mechanism of deep learning. Neurocomputing, 452, 48-62.
Liang, Y., Schott, D., Zhang, Y., Wang, Z., Nasief, H., Paulson, E., ... & Li, X. A. (2020). Auto-segmentation of pancreatic tumor in multi-parametric MRI using deep convolutional neural networks. Radiotherapy and Oncology, 145, 193-200.
Katoch, R. ., & Rani, P. . (2023). A Frequency Assessment of Prevalent Prevention Strategies in order to Manage Banks’ NPAs in MSME Loans. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4), 65–80. https://doi.org/10.17762/ijritcc.v11i4.6382
Patil, D. N. N. . (2021). Liver Tissue Based Disease Detection Using Pre-Processing and Feature Extraction Techniques. Research Journal of Computer Systems and Engineering, 2(2), 17:21. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/27
Pandey, J. K., Ahamad, S., Veeraiah, V., Adil, N., Dhabliya, D., Koujalagi, A., & Gupta, A.(2023). Impact of call drop ratio over 5G network. Innovative smart materials used in wireless communication technology (pp. 201-224) doi:10.4018/978-1-6684-7000-8.ch011 Retrieved from www.scopus.com
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
