SavedAdd your journal

Journals / Advances in Artificial Intelligence Research / 2026 / Cilt: 6

Lung Nodule Classification for Clinical Decision Support Systems: A Comparative Analysis of DenseNet-121 and Xception Architectures

Klinik Karar Destek Sistemleri için Akciğer Nodülü Sınıflandırması: DenseNet-121 ve Xception Mimarilerinin Karşılaştırmalı Analizi

Mesut Ulu(BANDIRMA ONYEDİ EYLÜL ÜNİVERSİTESİ)0000-0002-5591-8674
Pages
—
Publication Date
2026-10-19
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

DenseNet-121 showed a slight overall advantage over Xception, achieving an Accuracy of 0.894, Balanced Accuracy of 0.895, and F1-Score of 0.894.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The early and accurate assessment of lung nodules is an important clinical requirement worldwide, as it contributes to the timely evaluation of potential malignancy risk.
📊
Key Findings & Data:In this study, the performances of DenseNet-121 and Xception architectures were compared for the automatic classification of lung nodules from computed tomography (CT) images.
💡
Conclusion & Impact:DenseNet-121 showed a slight overall advantage over Xception, achieving an Accuracy of 0.894, Balanced Accuracy of 0.895, and F1-Score of 0.894.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Akciğer nodülü · Derin öğrenme · Transfer öğrenme

Abstract

The early and accurate assessment of lung nodules is an important clinical requirement worldwide, as it contributes to the timely evaluation of potential malignancy risk. In this study, the performances of DenseNet-121 and Xception architectures were compared for the automatic classification of lung nodules from computed tomography (CT) images. A total of 20,432 images were evaluated in two classes, Healthy and Lung_Nodule, and both models were trained using a transfer learning approach under the same data-splitting and preprocessing conditions. DenseNet-121 showed a slight overall advantage over Xception, achieving an Accuracy of 0.894, Balanced Accuracy of 0.895, and F1-Score of 0.894. For Xception, these values were obtained as 0.892, 0.894, and 0.892, respectively. When the clinical error profiles were examined, DenseNet-121 provided higher Specificity (0.946) and a lower FPR (0.054), whereas Xception showed a small advantage in reducing missed nodule images with a lower FNR (0.152). Grad-CAM analyses indicated that both models focused more clearly on nodule regions in correctly classified images. The findings suggest that, despite their similar overall performance, the two architectures differ in terms of their clinical error behavior.

Özet

Akciğer nodüllerinin erken ve doğru değerlendirilmesi, potansiyel malignite riskinin zamanında değerlendirilmesine katkıda bulunduğu için dünya çapında önemli bir klinik gerekliliktir. Bu çalışmada, bilgisayarlı tomografi (BT) görüntülerinden akciğer nodüllerinin otomatik sınıflandırılması için DenseNet-121 ve Xception mimarilerinin performansları karşılaştırılmıştır. Toplam 20.432 görüntü, Sağlıklı ve Akciğer_Nodülü olmak üzere iki sınıfta değerlendirilmiş ve her iki model de aynı veri bölme ve ön işleme koşulları altında transfer öğrenme yaklaşımı kullanılarak eğitilmiştir. DenseNet-121, Xception'a göre genel olarak hafif bir avantaj göstermiş ve 0,894 doğruluk, 0,895 dengeli doğruluk ve 0,894 F1 puanı elde etmiştir. Xception için bu değerler sırasıyla 0,892, 0,894 ve 0,892 olarak elde edilmiştir. Klinik hata profilleri incelendiğinde, DenseNet-121 daha yüksek özgüllük (0,946) ve daha düşük yanlış pozitif oranı (0,054) sağlarken, Xception daha düşük yanlış negatif oranı (0,152) ile kaçırılan nodül görüntülerinin azaltılmasında küçük bir avantaj gösterdi. Grad-CAM analizleri, her iki modelin de doğru sınıflandırılmış görüntülerde nodül bölgelerine daha net odaklandığını gösterdi. Bulgular, genel performansları benzer olmasına rağmen, iki mimarinin klinik hata davranışları açısından farklılık gösterdiğini düşündürmektedir.

🔖

Cite This Article

Ulu, M. (2026). Lung Nodule Classification for Clinical Decision Support Systems: A Comparative Analysis of DenseNet-121 and Xception Architectures. Advances in Artificial Intelligence Research, Cilt: 6. https://doi.org/10.54569/aair.2022049

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (24)

  1. National Lung Screening Trial Research Team. “Reduced lung-cancer mortality with low-dose computed tomographic screening”, The New England Journal of Medicine 365(5) (2011) 395–409; doi: 10.1056/NEJMoa1102873.
  2. MacMahon H, Naidich DP, Goo JM, Lee KS, Leung ANC, Mayo JR, Mehta AC, Ohno Y, Powell CA, Prokop M, Rubin GD, Schaefer-Prokop CM, Travis WD, Van Schil PE, Bankier AA. “Guidelines for management of incidental pulmonary nodules detected on CT images: From the Fleischner Society 2017”, Radiology 284(1) (2017) 228–243; doi: 10.1148/radiol.2017161659.
  3. Armato SG III, McNitt-Gray MF, Reeves AP, Meyer CR, McLennan G, Aberle DR, Kazerooni EA, MacMahon H, van Beek EJR, Yankelevitz D, Hoffman EA, Henschke CI, Roberts RY, Brown MS, Engelmann RM, Pais RC, Piker CW, Qing D, Kocherginsky M,. Clarke LP. “The Lung Image Database Consortium (LIDC): An evaluation of radiologist variability in the identification of lung nodules on CT scans”, Academic Radiology 14(11) (2007) 1409–1421; doi: 10.1016/j.acra.2007.07.008.
  4. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI. “A survey on deep learning in medical image analysis”, Medical Image Analysis 42 (2017) 60–88; doi: 10.1016/j.media.2017.07.005.
  5. Liu X, Faes L, Kale AU, Wagner SK, Fu DJ, Bruynseels A, Mahendiran T, Moraes G, Shamdas M, Kern C, Ledsam JR, Schmid MK, Balaskas K, Topol EJ, Bachmann LM, Keane PA, Denniston AK. “A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: A systematic review and meta-analysis”, The Lancet Digital Health 1(6) (2019) e271–e297; doi: 10.1016/S2589-7500(19)30123-2.
  6. Li D, Vilmun BM, Carlsen JF, Albrecht-Beste E, Lauridsen CA, Nielsen MB, Lindskov Hansen K. “The performance of deep learning algorithms on automatic pulmonary nodule detection and classification tested on different datasets that are not derived from LIDC-IDRI: A systematic review”, Diagnostics 9(4) (2019) 207; doi: 10.3390/diagnostics9040207.
  7. Masood A, Yang P, Sheng B, Li H, Li P, Qin J, Lanfranchi V, Kim J, Feng DD. “Cloud-based automated clinical decision support system for detection and diagnosis of lung cancer in chest CT”, IEEE Journal of Translational Engineering in Health and Medicine 8 (2020) 1–13; doi: 10.1109/JTEHM.2019.2955458.
  8. Setio AAA, Ciompi F, Litjens G, Gerke P, Jacobs C, van Riel SJ, Wille MMW, Naqibullah M, Sánchez CI, van Ginneken B. “Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks”, IEEE Transactions on Medical Imaging 35(5) (2016) 1160–1169; doi: 10.1109/TMI.2016.2536809.
  9. Dou Q, Chen H, Yu L, Qin J, Heng PA. “Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection”, IEEE Transactions on Biomedical Engineering 64(7) (2017) 1558–1567; doi: 10.1109/TBME.2016.2613502.
  10. Nasrullah N, Sang J, Alam MS, Mateen M, Cai B, Hu H. “Automated lung nodule detection and classification using deep learning combined with multiple strategies”, Sensors 19(17) (2019) 3722; doi: 10.3390/s19173722.
  11. Shen W, Zhou M, Yang F, Yu D, Dong D, Yang C, Zang Y, Tian J. “Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification”, Pattern Recognition 61 (2017) 663–673; doi: 10.1016/j.patcog.2016.05.029.
  12. Xie Y, Xia Y, Zhang J, Song Y, Feng DD, Fulham M, Cai W. “Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT”, IEEE Transactions on Medical Imaging 38(4) (2019) 991–1004; doi: 10.1109/TMI.2018.2876510.
  13. Mastouri R, Khlifa N, Neji H, Hantous-Zannad S. “A bilinear convolutional neural network for lung nodules classification on CT images”, International Journal of Computer Assisted Radiology and Surgery 16(1) (2021) 91–101; doi: 10.1007/s11548-020-02283-z.
  14. Zhu W, Liu C, Fan W, Xie X. “DeepLung: Deep 3D dual path nets for automated pulmonary nodule detection and classification”, In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), (2018) 673–681; doi: 10.1109/WACV.2018.00079.
  15. Ardila D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L, Tse D, Etemadi M, Ye W, Corrado G, Naidich DP, Shetty S. “End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography”, Nature Medicine 25(6) (2019) 954–961; doi: 10.1038/s41591-019-0447-x.
  16. Venkadesh KV, Setio AAA, Schreuder A, Scholten ET, Chung K, Wille MMW, Saghir Z, van Ginneken B, Prokop M, Jacobs C. “Deep learning for malignancy risk estimation of pulmonary nodules detected at low-dose screening CT”, Radiology 300(2) (2021) 438–447; doi: 10.1148/radiol.2021204433.
  17. Canayaz M, Şehribanoğlu S, Özgökçe M, Akıncı MB. “A comprehensive exploration of deep learning approaches for pulmonary nodule classification and segmentation in chest CT images”, Neural Computing and Applications 36 (2024) 7245–7264; doi: 10.1007/s00521-024-09457-9.
  18. Li D, Yuan S, Yao G. “Classification of lung nodules based on the DCA-Xception network”, Journal of X-Ray Science and Technology 30(5) (2022) 993–1008; doi: 10.3233/XST-221219.
  19. Kaggle, Lung Nodule Dataset [Online]. Available: https://www.kaggle.com/datasets/ucimachinelearning/lung-nodule-dataset.
  20. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. “Densely connected convolutional networks”, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017) 4700–4708.
  21. Chollet F. “Xception: Deep learning with depthwise separable convolutions”, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017) 1251–1258.
  22. Tharwat A. “Classification assessment methods”, Applied Computing and Informatics 17(1) (2021) 168–192.
  23. Zhang Q, Wang H, Yoon SW, Won D, Srihari K. “Lung nodule diagnosis on 3D computed tomography images using deep convolutional neural networks”, Procedia Manufacturing 39 (2019) 363–370.
  24. Armato SG III, McNitt-Gray MF, Reeves AP, Meyer CR, McLennan G, Aberle DR, Kazerooni EA, MacMahon H, van Beek EJR, Yankelevitz D, Hoffman EA, Henschke CI, Roberts RY, Brown MS, Engelmann RM, Pais RC, Piker CW, Qing D, Kocherginsky M,. Clarke LP. “The Lung Image Database Consortium (LIDC): An evaluation of radiologist variability in the identification of lung nodules on CT scans”, Academic Radiology 14(11) (2007) 1409–1421; doi: 10.1016/j.acra.2007.07.008.