{"id":838,"date":"2026-03-08T00:51:40","date_gmt":"2026-03-07T16:51:40","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=838"},"modified":"2026-03-18T14:17:30","modified_gmt":"2026-03-18T06:17:30","slug":"segnet-based-framework-for-robust-lung-tumor-segmentation-from-pet-ct-scans","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=segnet-based-framework-for-robust-lung-tumor-segmentation-from-pet-ct-scans","title":{"rendered":"SegNet-Based Framework for Robust Lung Tumor Segmentation from PET\/CT Scans"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 30<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Yessine Amri1<\/sup><\/i><\/a>, Amine Ben Slama2<\/sup>, and Zouhair Mbarki3<\/sup><\/p>\n\n\n\n

1<\/sup>Biochemistry Laboratory, Bechir Hamza Children\u2019s Hospital, Tunis, 1007, Tunisia<\/p>\n\n\n\n

2<\/sup>Research Laboratory of Biophysics and Medical Technologies LRBTM (LR13ES07), Higher Institute of Medical Technologies of Tunis (ISTMT), University of Tunis El Manar, Tunis,1006, Tunisia<\/p>\n\n\n\n

3<\/sup>RIFTSI Research Laboratory, ENSIT, University of Tunis, Tunis, 1008, Tunisia<\/p>\n<\/div>\n\n\n\n

\n

Received:\u00a0July 25, 2025
Accepted:\u00a0October 12, 2025
Publication Date:\u00a0March 8, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Seg-Net model.<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:\u00a0 RIS<\/a> | BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202607_30.008<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, often due to latestage diagnosis and the complexity of tumor localization in thoracic imaging. Accurate and automated segmentation of lung tumors from PET\/CT images is essential for early diagnosis, treatment planning, and outcome monitoring. Manual segmentation is time-consuming and prone to observer variability, underscoring the need for reliable deep learning-based solutions. This study proposes an automated lung tumor segmentation framework using the SegNet architecture, a deep encoder-decoder convolutional neural network. A dataset of 1, 425PET\/CT images, manually annotated by expert radiologists, was utilized. Data augmentation techniques were applied to improve generalization. SegNet was trained to perform pixel-wise binary classification, and its performance was benchmarked against the widely used U-Net model. Evaluation metrics included Accuracy, Recall, Dice coefficient, and Intersection over Union (IoU).The proposed SegNet model achieved strong segmentation performance across independent experiments. Average results were: Accuracy of 92.24% \u00b1 1.42, Recall of 94.02% \u00b1 1.287, Dice coefficient of 93.47% \u00b1 1.4, and IoU of 93.03% \u00b1 1.2. Compared to U-Net (Dice: 92.18% \u00b1 1.081, IoU: 91.70% \u00b1 1.287 ), SegNet demonstrated improved spatial boundary accuracy, particularly for tumors located near complex anatomical structures. Statistical tests confirmed the significance of the performance difference ( p < 0.05 ). The SegNet-based model provides accurate and robust segmentation of lung tumors in PET\/CT images, outperforming U-Net under the same conditions. Its use of max-pooling indices enhances spatial precision, making it well-suited for clinical applications. Future work will explore 3D extensions, multi-class segmentation, and multi-center validation to enhance its applicability in real-world diagnostic workflows.<\/p>\n\n\n\n

Keywords:\u00a0Lung tumor, PET\/CT, Deep learning, SegNet, Medical image segmentation, U-Net<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] B. Le Goff, J.-M. Berthelot, and Y. Maugars, (2015) \u201c\u00c9chographie du thorax ant\u00e9rieur [Ultrasound of the anterior thorax]” Revue du Rhumatisme Monographies 82(2): 83\u201387. DOI: 10.1016\/j.monrhu.2015.02.005.<\/li>\n
  2. [2] C. Jani, D. C. Marshall, H. Singh, R. Goodall, J. Shalhoub, O. Al Omari, and C. C. Thomson, (2021) \u201cLung cancer mortality in Europe and the USA between 2000 and 2017: An observational analysis” ERJ Open Research 7(4): DOI: 10.1183\/23120541.00311-2021.<\/li>\n
  3. [3] P. B. Bach, J. R. Jett, U. Pastorino, M. S. Tockman, S. J. Swensen, and C. B. Begg, (2007) \u201cComputed tomography screening and lung cancer outcomes” JAMA 297(9): 953\u2013961. DOI: 10.1001\/jama.297.9.953.<\/li>\n
  4. [4] E. B. Jemia, H. Kamoun, S. Louhaichi, H. Smadhi, D. Greb, I. Akrout, and M. L. Megdiche, (2017) \u201cVariation du profil histologique du cancer du poumon durant les 25 derni\u00e8res ann\u00e9es dans un service de pneumologie \u00e0 Tunis [Variation of the histological profile of lung cancer during the last 25 years in a pulmonology department in Tunis]” Revue des Maladies Respiratoires 34: A79. DOI: 10.1016\/j.rmr.2016.10.168.<\/li>\n
  5. [5] Y. Men, Z. Hui, J. Liang, Q. Feng, D. Chen, H. Zhang, and L. Wang, (2016) \u201cFurther understanding of an uncommon disease of combined small cell lung cancer: Clinical features and prognostic factors of 114 cases” Chinese Journal of Cancer Research 28(5): 486. DOI: 10.21147\/j.issn.1000-9604.2016.05.03.<\/li>\n
  6. [6] B. Padovani, J. Mouroux, L. Seksik, S. Chanalet, J. Sedat, C. Rotomondo, and J. J. Serres, (1993) \u201cChest wall invasion by bronchogenic carcinoma: Evaluation with MR imaging” Radiology 187(1): 33\u201338. DOI: 10.1148\/radiology.187.1.8451432.<\/li>\n
  7. [7] N. Suzuki, T. Saitoh, and S. Kitamura, (1993) \u201cTumor invasion of the chest wall in lung cancer: Diagnosis with US” Radiology 187(1): 39\u201342. DOI: 10.1148\/radiology. 187.1.8451433.<\/li>\n
  8. [8] S. J. Swensen, R. W. Viggiano, D. E. Midthun, N. L. M\u00fcller, A. Sherrick, K. Yamashita, and A. L. Weaver, (2000) \u201cLung nodule enhancement at CT: Multicenter study” Radiology 214(1): 73\u201380. DOI: 10.1148\/radiology.214.1.r00ja1473.<\/li>\n
  9. [9] D. F. Yankelevitz, A. P. Reeves, W. J. Kostis, B. Zhao, and C. I. Henschke, (2000) \u201cSmall pulmonary nodules: Volumetrically determined growth rates based on CT evaluation” Radiology 217(1): 251\u2013256. DOI: 10.1148\/radiology.217.1.r00oc33251.<\/li>\n
  10. [10] G. Ferretti, A. Jankowski, A. Calizzano, D. MoroSibilot, and J. P. Vuillez, (2008) \u201cImagerie radiologique et TEP Scanner dans les cancers du poumon [Radiological imaging and PET scans in lung cancer]” Journal de Radiologie 89(3): 387\u2013402. DOI: 10.1016\/S0221-0363(08)89016-6.<\/li>\n
  11. [11] N. A. Dewan, S. D. Reeb, N. C. Gupta, L. S. Gobar, and W. J. Scott, (1995) \u201cPET-FDG imaging and transthoracic needle lung aspiration biopsy in evaluation of pulmonary lesions: A comparative risk-benefit analysis” Chest 108(2): 441\u2013446. DOI: 10.1378\/chest.108.2.441.<\/li>\n
  12. [12] J. E. Bibault, A. Oudoux, J. Durand-Labrunie, X. Mirabel, \u00c9. Lartigau, and H. Kolesnikov-Gauthier, (2015) \u201cTEP et radioth\u00e9rapie st\u00e9r\u00e9otaxique pulmonaire : r\u00f4les dans la pr\u00e9paration du traitement et le suivi de la maladie [Positron emission tomography and stereotactic body radiation therapy for lung cancer: From treatment planning to response evaluation]” Cancer\/Radioth\u00e9rapie 19(8): 790\u2013794. DOI: 10.1016\/j.canrad.2015.05.027.<\/li>\n
  13. [13] S. S. Gambhir, J. Czernin, J. Schwimmer, D. H. Silverman, R. E. Coleman, and M. E. Phelps, (2001) \u201cA tabulated summary of the FDG PET literature” Journal of Nuclear Medicine 42(5 suppl): 1S\u201393S.<\/li>\n
  14. [14] M. K. Gould, C. C. Maclean, W. G. Kuschner, C. E. Rydzak, and D. K. Owens, (2001) \u201cAccuracy of positron emission tomography for diagnosis of pulmonary nodules and mass lesions: A meta-analysis” JAMA 285(7): 914\u2013924. DOI: 10.1001\/jama.285.7.914.<\/li>\n
  15. [15] C. Perrotin, P. Lemeunier, D. Grahek, T. Molina, A. Petino, M. Alifano, F. Bellenot, P. Magdeleinat, J. N. Talbot, and J. F. Regnard, (2005) \u201cR\u00e9sultats de la TEP [18F]-FDG dans la stadification pr\u00e9op\u00e9ratoire des tumeurs pulmonaires [Results of FDG-PET scanning in the preoperative staging of broncho-pulmonary tumors]” Revue des Maladies Respiratoires 22(4): 579\u2013585. DOI: 10.1016\/s0761-8425(05)85610-4.<\/li>\n
  16. [16] J. F. Vansteenkiste, S. G. Stroobants, P. J. Dupont, P. R. De Leyn, E. K. Verbeken, G. J. Deneffe, and M. G. Demedts, (1999) \u201cPrognostic importance of the standardized uptake value on 18F-fluoro-2-deoxy-glucose\u2013positron emission tomography scan in non\u2013small-cell lung cancer: An analysis of 125 cases” Journal of Clinical Oncology 17(10): 3201\u20133206.<\/li>\n
  17. [17] M. Valli\u00e8res, C. R. Freeman, S. R. Skamene, and I. El Naqa, (2015) \u201cA radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities” Physics in Medicine & Biology 60(14): 5471. DOI: 10.1088\/0031-9155\/60\/14\/5471.<\/li>\n
  18. [18] Z. Li, J. Zhang, T. Tan, X. Teng, X. Sun, H. Zhao, and G. Litjens, (2020) \u201cDeep learning methods for lung cancer segmentation in whole-slide histopathology images\u2014the acdc@ lunghp challenge 2019″ IEEE Journal of Biomedical and Health Informatics 25(2): 429\u2013440. DOI: 10.1109\/JBHI.2020.3039741.<\/li>\n
  19. [19] H. Hu, Q. Li, Y. Zhao, and Y. Zhang, (2020) \u201cParallel deep learning algorithms with hybrid attention mechanism for image segmentation of lung tumors” IEEE Transactions on Industrial Informatics 17(4): 2880\u20132889. DOI: 10.1109\/TII.2020.3022912.<\/li>\n
  20. [20] P. Li, S. Wang, T. Li, J. Lu, Y. HuangFu, and D. Wang. A large-scale CT and PET\/CT dataset for lung cancer diagnosis (Lung PET-CT-Dx) [Data set]. 2020. DOI: 10.7937\/TCIA.2020.NNC2-0461.<\/li>\n
  21. [21] M. Wang, X. Zhou, M. Jin, Y. Zhang, L. Liu, and G. Huang, (2024) \u201cMultiroimix: A data augmentation method for PET\/CT multimodal medical images” Journal of Medical and Biological Engineering 44(3): 366\u2013374. DOI: 10.1007\/s40846-024-00862-y.<\/li>\n
  22. [22] A. Klaengkaew, S. Sutthigran, N. Thammasiri, K. Yuwatanakorn, C. Thanaboonnipat, S. Ponglowhapan, and N. Choisunirachon, (2021) \u201cThe evaluation of non-anesthetic computed tomography for detection of pulmonary parenchyma in feline mammary gland carcinoma: a preliminary study” BMC Veterinary Research 17(1): 237. DOI: 10.1186\/s12917-021-02950-6.<\/li>\n
  23. [23] X. Zhang, G. Xu, X. Wu, W. Liao, L. Xiao, Y. Jiang, and H. Xing, (2024) \u201cFast-SegNet: Fast semantic segmentation network for small objects” Multimedia Tools and Applications 83(34): 81039\u201381055. DOI: 10.1007\/s11042-024-18829-1.<\/li>\n
  24. [24] R. Pang, H. Tan, Y. Yang, X. Xu, N. Liu, and P. Zhang. \u201cA Novel SegNet Model for Crack Image Semantic Segmentation in Bridge Inspection\u201d. In: Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Ed. by D. Yang, X. Xie, V. Tseng, J. Pei, J. Huang, and J. Lin. 14647. Lecture Notes in Computer Science. Singapore: Springer, 2024, 26. DOI: 10.1007\/978-981-97-2259-4_26.<\/li>\n
  25. [25] N. \u00b8Sahin, N. Alpaslan, and D. Hanbay, (2022) \u201cRobust optimization of SegNet hyperparameters for skin lesion segmentation” Multimedia Tools and Applications 81(25): 36031\u201336051. DOI: 10.1007\/s11042-021-11032-6.<\/li>\n
  26. [26] Y. Zhang, (2025) \u201cImage denoising based on deep feature fusion and U-Net network” Journal of Applied Science and Engineering 28(10): 2077\u20132085. DOI: 10.6180\/jase.202510_28(10).0020.<\/li>\n
  27. [27] H. Chen and Z. Xu, (2021) \u201cA new end-to-end network model for medical image segmentation” Journal of Applied Science and Engineering 24(2): 207\u2013213. DOI: 10.6180\/jase.202104_24(2).0009.<\/li>\n
  28. [28] G. Athanasiou, J. L. Arcos, and J. Cerquides, (2023) \u201cEnhancing medical image segmentation: Ground truth optimization through evaluating uncertainty in expert annotations” Mathematics 11(17): 3771. DOI: 10.3390\/math11173771.<\/li>\n
  29. [29] S. Alqazzaz, X. Sun, X. Yang, and L. Nokes, (2019) \u201cAutomated brain tumor segmentation on multi-modal MR image using SegNet” Computational Visual Media 5(2): 209\u2013219. DOI: 10.1007\/s41095-019-0139-y.<\/li>\n
  30. [30] G. Di Leo and F. Sardanelli, (2020) \u201cStatistical significance: p value, 0.05 threshold, and applications to radiomics\u2014reasons for a conservative approach” European Radiology Experimental 4(1): 18. DOI: 10.1186\/s41747-020-0145-y.<\/li>\n
  31. [31] J. M. Rogasch, N. Frost, S. Bluemel, L. Michaels, T. Penzkofer, M. von Laffert, and C. Furth, (2021) \u201cFDG-PET\/CT for pretherapeutic lymph node staging in non-small cell lung cancer: a tailored approach to the ESTS\/ESMO guideline workflow” Lung Cancer 157: 66\u201374. DOI: 10.1016\/j.lungcan.2021.05.003.<\/li>\n
  32. [32] S. N. Kumar, P. M. Bruntha, S. I. Daniel, J. A. Kirubakar, R. E. Kiruba, S. Sam, and S. I. A. Pandian. \u201cLung nodule segmentation using U-Net\u201d. In: 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS). 1. 2021, 420\u2013424. DOI: 10.1109\/ICACCS51430.2021.9441977.<\/li>\n
  33. [33] G. M. Alshmrani, Q. Ni, R. Jiang, and N. Muhammed, (2023) \u201cHyper-dense_lung_seg: Multimodal-fusion-based modified U-Net for lung tumor segmentation using multimodality of CT-PET scans” Diagnostics 13(22): 3481. DOI: 10.3390\/diagnostics13223481.<\/li>\n
  34. [34] J. Park, S. K. Kang, D. Hwang, H. Choi, S. Ha, J. M. Seo, and J. S. Lee, (2023) \u201cAutomatic lung cancer segmentation in [18F] FDG PET\/CT using a two-stage deep learning approach” Nuclear Medicine and Molecular Imaging 57(2): 86\u201393. DOI: 10.1007\/s13139-022-00745-7.<\/li>\n
  35. [35] L. Zhou, C. Wu, Y. Chen, and Z. Zhang, (2024) \u201cMultitask connected U-Net: automatic lung cancer segmentation from CT images using PET knowledge guidance” Frontiers in Artificial Intelligence 7: 1423535. DOI: 10.3389\/frai.2024.1423535.<\/li>\n
  36. [36] G. Saimassay, M. Begenov, U. Sadyk, R. Baimukashev, A. Maratov, and B. Omarov, (2024) \u201cEnhanced U-Net architecture for lung segmentation on computed tomography and X-ray images” International Journal of Advanced Computer Science and Applications 15(5): DOI: 10.14569\/IJACSA.2024.0150594.<\/li>\n
  37. [37] A. Ben Slama, Y. Amri, A. Fnaiech, and H. Sahli, (2025) \u201cAutomated ECG arrhythmia classification using hybrid CNN-SVM architectures” Journal of Electronic Science and Technology 23(3): 100316. DOI: 10.1016\/j.jnlest.2025.100316.<\/li>\n
  38. [38] Y. Amri, A. Ben Slama, Z. Mbarki, R. Selmi, and H. Trabelsi, (2025) \u201cAutomatic glioma segmentation based on efficient U-Net model using MRI images” Intelligence-Based Medicine: 100216. DOI: 10.1016\/j.ibmed.2025.100216.<\/li>\n
  39. [39] A. Ben Slama, Y. Amri, S. Barbaria, H. B. Rahmouni, and H. Trabelsi, (2025) \u201cLung diseases classification using pre-trained based deep learning model and support vector machine” Polish Journal of Medical Physics and Engineering 31(3): 178\u2013194. DOI: 10.2478\/pjmpe2025-0021.<\/li>\n
  40. [40] I. Domingues, G. Pereira, P. Martins, H. Duarte, J. Santos, and P. H. Abreu, (2020) \u201cUsing deep learning techniques in medical imaging: a systematic review of applications on CT and PET” Artificial Intelligence Review 53(6): 4093\u20134160. DOI: 10.1007\/s10462-019-09850-2.<\/li>\n
  41. [41] S. Yin, H. Li, L. Teng, and et al., (2024) \u201cBrain CT image classification based on mask R-CNN and attention mechanism” Scientific Reports 14: 29300. DOI: 10.1038\/s41598-024-78566-1.<\/li>\n
  42. [42] S. Yin, L. Wang, T. Chen, H. Huang, J. Gao, J. Zhang, M. Liu, P. Li, and C. Xu, (2025) \u201cLKAFormer: A lightweight Kolmogorov-Arnold transformer model for image semantic segmentation” ACM Transactions on Intelligent Systems and Technology:<\/li>\n
  43. [43] Q. Shi, S. Yin, K. Wang, L. Teng, and H. Li, (2021) \u201cMultichannel convolutional neural network-based fuzzy active contour model for medical image segmentation” Evolving Systems 13: 535\u2013549. DOI: 10.1007\/s12530-021-09392-3.<\/li>\n<\/ol>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,16,6],"tags":[25],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:\u00a0 RIS | BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202607_30.008\u00a0\u00a0 Download PDF Lung cancer remains one of the leading causes of…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/838"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=838"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=838"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=838"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}