Lung tumor segmentation from CT images using 2.5D spatial data and 3D volumetric post-processing
DOI:
https://doi.org/10.4108/eetpht.11.10388Keywords:
lung cancer, 2.5D, CT scans, deep learning, 3D post-processing, tumor visualizationAbstract
INTRODUCTION: Nowadays, lung cancer is known as one of the serious threats to human health and life globally. To deal with lung cancer, a problem is to accurately segment tumors from CT scans to help doctors in assessment and treatment planning.
OBJECTIVES: This study proposes a method for segmenting lung tumors from CT scan data based on exploiting spatial information between slices to feed into the deep learning model and applying 3D volumetric post-processing. In addition, we also provide visualization of 3D tumor reconstruction data.
METHODS: We incorporate spatially continuous data into the 2.5D input. In addition, we use a hybrid TransUNet deep learning model, and finally post-process 3D volumes. Our method allows the deep learning model to take advantage of spatial context information along the slices. TransUNet takes advantage of both CNN and Transformer. The 3D volume post-processing technique refines the results, removing discrete noisy blocks. This results in increased continuity and more accurate reconstruction in three-dimensional space.
RESULTS: The segmentation results were satisfactory. In case of 2.5D of 3 slices, results on NSCLC-Radiomics reached the Dice over slices of 0.891 ± 0.277, the Dice over 3D volumes of 0.641 ± 0.235, the IoU over slices of 0.875 ± 0.291, the IoU over 3D volumes of 0.508 ± 0.228, False Positives of 94, and False Negatives of 224. In case of 2.5D of 5 slices, results on NSCLC-Radiogenomics reached the Dice over slices of 0.951 ± 0.186, the Dice over 3D volumes of 0.671 ± 0.231, the IoU over slices of 0.941 ± 0.200, the IoU over 3D volumes of 0.539 ± 0.223, False Positives of 8, and False Negatives of 67.. In addition, the 3D tumor visualization showed good visualization capabilities.
CONCLUSION: The proposed method has proven to be effective in lung tumor segmentation. In this study, the elements of the proposed method have been analyzed comprehensively and comparatively. In the future, we expect to continue to conduct in-depth research and expand the experiment on patient data in Vietnam.
Downloads
References
[1] World Health Organization. World Fact Sheet. 2022. [Online].Available:https://gco.iarc.who.int/media/globocan/factsheets/populations/900-world-fact-sheet.pdf [accessed: 2025 September 23].
[2] World Health Organization. Viet Nam Fact Sheet. 2022.[Online]. Available: https://gco.iarc.who.int/media/globocan/factsheets/populations/704-viet-nam-fact-sheet.pdf [accessed: 2025 September 23].
[3] Ming S., Yang W., Cui S., Huang S., Gong X.. Consistency ofradiologists in identifying pulmonary nodules based on low-dose computed tomography. Journal of thoracic disease.2019;11(7):2973.
[4] Sangamithraa P., Govindaraju S.. Lung tumour detection andclassification using EK-Mean clustering. In: 2016International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). 2016. p. 2201-2206.
[5] Kaucha D.P., Prasad P.W.C., Alsadoon A., Elchouemi A.,Sreedharan S.. Early detection of lung cancer using SVMclassifier in biomedical image processing. In: 2017 IEEEInternational Conference on Power, Control, Signals andInstrumentation Engineering (ICPCSI). 2017. p. 3143-3148.
[6] Patel T., Nayak V.. Hybrid Approach for Feature Extraction of Lung Cancer Detection. In: 2018 Second InternationalConference on Inventive Communication and ComputationalTechnologies (ICICCT). 2018. p. 1431-1433.
[7] Perumal S., Thambusamy V.. Lung cancer detection andclassification on CT scan images using Enhanced ArtificialBee Colony Optimization. International Journal ofEngineering & Technology. 2018;7:74.
[8] Alakwaa W., Nassef M., Badr A.. Lung Cancer Detection andClassification with 3D Convolutional Neural Network (3D-CNN). International Journal of Advanced Computer Scienceand Applications. 2017;8.
[9] Kuan K., Ravaut M., Manek G., Chen H., Lin J., Nazir B.,Chen C., Howe T.C., Zeng Z., Chandrasekhar V.. DeepLearning for Lung Cancer Detection: Tackling the KaggleData Science Bowl 2017 Challenge, arXiv preprintarXiv:1705.09435. 2017.
[10] Hossain S., Najeeb S., Shahriyar A., Abdullah Z.R., ArifulHaque M.. A Pipeline for Lung Tumor Detection andSegmentation from CT Scans Using Dilated ConvolutionalNeural Networks. In: ICASSP 2019 - 2019 IEEE InternationalConference on Acoustics, Speech and Signal Processing(ICASSP). 2019. p. 1348-1352.
[11] Farheen F., Shamil M.S., Ibtehaz N., Rahman M.. Revisitingsegmentation of lung tumors from CT images. Computers inBiology and Medicine. 2022;144:105385.
[12] Kamal U., Rafi A.M., Hoque R., Wu J., Hasan M.K.. LungCancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet, arXiv preprint arXiv:1812.01951. 2020.
[13] Dutande P., Baid U., Talbar S.. LNCDS: A 2D-3D cascadedCNN approach for lung nodule classification, detection andsegmentation. Biomedical Signal Processing and Control.2021;67:102527.
[14] Le V., Saut O.. RRc-UNet 3D for lung tumor segmentationfrom CT scans of Non-Small Cell Lung Cancer patients. In:2023 IEEE/CVF International Conference on ComputerVision Workshops (ICCVW). 2023. p. 2308-2317.
[15] Alhajim D., Ansari-Asl K., Akbarizadeh G., Soorki M.N..Improved lung nodule segmentation with a squeeze excitationdilated attention based residual UNet. Sci Rep. 2025;15(1):3770.
[16] YaXin Z., Cheng J., RenZheng X., Zheng L., Qing Z., DaTongC., DongBin X., Yue S., GongQi L., MingHui L.. CMS-UNet:A CNN-Mamba Synergistic Dual-Encoder u-net for lungtumor segmentation in CT images. Biomedical SignalProcessing and Control. 2026; 116:109451.
[17] Aerts H. J. W. L., Wee L., Rios Velazquez E., Leijenaar R. T.H., Parmar C., Grossmann P., Carvalho S., Bussink J.,Monshouwer R., Haibe-Kains B., Rietveld D., Hoebers F.,Rietbergen M. M., Leemans C. R., Dekker A., Quackenbush J., Gillies R. J., Lambin P. Data From NSCLC-Radiomics (version 4) [Data set]. The Cancer Imaging Archive. 2014.
[18] Bakr S., Gevaert O., Echegaray S., Ayers K., Zhou M., ShafiqM., Zheng H., Zhang W., Leung A., Kadoch M., Shrager J.,Quon A., Rubin D., Plevritis S., Napel S.. Data for NSCLCRadiogenomics Collection (Version 4) [Dataset]. The CancerImaging Archive. 2017.
[19] Chen J., Lu Y., Yu Q., Luo X., Adeli E., Wang Y., Lu L.,Yuille A.L., Zhou Y.. Transunet: Transformers make strongencoders for medical image segmentation. arXiv preprintarXiv:2102.04306. 2021.
[20] Castro E., Cardoso J.S., Pereira J.C.. Elastic deformations fordata augmentation in breast cancer mass detection. In: 2018IEEE EMBS International Conference on Biomedical &Health Informatics (BHI). IEEE. 2018. p. 230-234.
[21] Paszke A., Gross S., Massa F., Lerer A., Bradbury J., ChananG., Killeen T., Lin Z., Gimelshein N., Antiga L., others.Pytorch: An imperative style, high-performance deep learninglibrary. Advances in neural information processing systems.2019;32.
[22] Kingma D.P., Ba J.. Adam: A method for stochasticoptimization. In: Proceedings of the 3rd InternationalConference on Learning Representations (ICLR).. 2015.
[23] Prechelt L.. Automatic early stopping using cross validation:quantifying the criteria. Neural networks. 1998;11(4):761-767.
[24] Lorensen W.E., Cline H.E.. Marching cubes: A high resolution 3D surface construction algorithm. ACM SIGGRAPHComputer Graphics. 1987;21(4):163-169.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nguyen Duc Man, Ha Manh Toan, Le Manh Cuong, Do Nang Toan
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
