|
Deep learning-based classification of lung nodules on CT images: A multicenter study of early lung cancer detection
|
C. Qi   , Q. Jiang |
| Baicheng Central Hospital, Baicheng, Jilin, 137000, China , 77073199@bcmc.edu.cn |
|
|
Abstract: (329 Views) |
Background: Early lung cancer detection relies on accurate characterization of pulmonary nodules on computed tomography (CT). However, variability in CT acquisition and radiological interpretation may reduce reproducibility across institutions. This study evaluated a deep learning (DL) framework for benign-malignant lung nodule classification using multicenter CT datasets. Materials and Methods: Publicly available anonymized CT datasets from LUNA16 and LIDC-IDRI were used. Images were rescaled to a uniform resolution, denoised with Gaussian filtering, and normalized by Min-Max scaling. Nodule regions were segmented using a U-Net encoder-decoder network. Gray-Level Co-Occurrence Matrix (GLCM) texture features were extracted and combined with latent representations learned by an Effective Beetle Antennae Search-driven Variational Autoencoder (EBAS-VAE). Model performance was assessed using accuracy, precision, recall, F1-score, true-positive rate (TPR), false-positive rate (FPR), false discovery rate (FDR), and area under the receiver operating characteristic curve (AUC). Results: On LUNA16, EBAS-VAE achieved accuracy 0.9838, precision 0.94, recall 0.89, F1-score 0.96, and AUC 0.98. On LIDC-IDRI, accuracy was 0.97, TPR 0.97, FPR 0.04, and FDR 0.0001. EBAS-VAE outperformed 3D-CNN and SEOA-DBN comparators. Conclusion: The proposed EBAS-VAE pipeline improved lung nodule classification and reduced false-positive detection in multicenter CT images, supporting its potential as a radiologist-assistive screening tool. |
|
| Keywords: Computed tomography, Deep learning, Lung cancer, Pulmonary nodule, Variational autoencoder. |
|
|
Full-Text [PDF 908 kb]
(85 Downloads)
|
|
Type of Study: Original Research |
Subject:
Radiation Biology
|
|
|
|
|
|
|
| References |
1. 1. Wahab Sait AR (2023) Lung cancer detection model using deep learning technique. Applied Sciences, 13(22): 12510. [ DOI:10.3390/app132212510] 2. Sajja TK, Devarapalli RM, Kalluri HK (2019) Lung cancer detection based on CT scan images by using deep transfer learning. Traitement du Signal, 36(4): 339-344. [ DOI:10.18280/ts.360406] 3. Gao S, Zhang G, Lian Y, Yan L, Gao H (2020) Exploration and analysis of the value of tumor-marker joint detection in the pathological type of lung cancer. Cellular and Molecular Biology, 66(6): 93-97. [ DOI:10.14715/cmb/2020.66.6.17] 4. Kırca K and Kutlutürkan S (2021) The effect of progressive relaxation exercises on treatment-related symptoms and self-efficacy in patients with lung cancer receiving chemotherapy. Complement Ther Clin Pract, 45: 101488. [ DOI:10.1016/j.ctcp.2021.101488] 5. Asuntha A and Srinivasan A (2020) Deep learning for lung cancer detection and classification. Multimed Tools Appl, 79(11): 7731-7762. [ DOI:10.1007/s11042-019-08394-3] 6. Kummer S, Waller J, Ruparel M, Cass J, et al. (2020) Mapping the spectrum of psychological and behavioral responses to low-dose CT lung cancer screening offered within a lung health check. Health Expect, 23(2): 433-441. [ DOI:10.1111/hex.13030] 7. Nazir I, Haq IU, Khan MM, Qureshi MB, (2021) Efficient pre-processing and segmentation for lung cancer detection using fused CT images. Electronics, 11(1): 34. [ DOI:10.3390/electronics11010034] 8. Yang Y, Yang J, Liang Y, Liao B, Zhu W, Mo X, et al. (2021) Identification and validation of the efficacy of immunological therapy for lung cancer from histopathological images based on deep learning. Front Genet, 12: 642981. [ DOI:10.3389/fgene.2021.642981] 9. Lu D, Shangguan Z, Su Z, Lin C, Huang Z, Xie H (2024) Artificial intelligence-based plasma exosome label-free SERS profiling strategy for early lung cancer detection. Anal Bioanal Chem, 416(23): 5089-5096. [ DOI:10.1007/s00216-024-05445-z] 10. Chiet CC, How KW, Han PY, Yen YH (2024) A lung cancer detection with pre-trained CNN models. J Informatics and Web Engineering, 3(1): 41-54. [ DOI:10.33093/jiwe.2024.3.1.3] 11. Obayya M, Arasi MA, Alruwais N, Alsini R, et al. (2023) Biomedical image analysis for colon and lung cancer detection using tuna swarm algorithm with deep learning model. IEEE Access, 11: 94705-94712. [ DOI:10.1109/ACCESS.2023.3309711] 12. Wankhade S and Vigneshwari S (2023) A novel hybrid deep learning method for early detection of lung cancer using neural networks. Healthcare Analytics, 3: 100195. [ DOI:10.1016/j.health.2023.100195] 13. Sreeprada V and Vedavathi K (2023) Lung cancer detection from X-ray images using hybrid deep learning technique. Procedia Comput Sci, 230: 467-474. [ DOI:10.1016/j.procs.2023.12.102] 14. Alsheikhy AA, Said Y, Shawly T, Alzahrani AK, Lahza H (2023) A CAD system for lung cancer detection using hybrid deep learning techniques. Diagnostics, 13(6): 1174. [ DOI:10.3390/diagnostics13061174] 15. Navaneethakrishnan M, Anand MV, Vasavi G, Rani VV (2023) Deep Fuzzy SegNet-based lung nodule segmentation and optimized deep learning for lung cancer detection. Pattern Anal Appl, 26(3): 1143-1159. [ DOI:10.1007/s10044-023-01135-1] 16. Crasta LJ, Neema R, Pais AR (2024) A novel deep learning architecture for lung cancer detection and diagnosis from computed tomography image analysis. Healthcare Analytics, 5: 100316. [ DOI:10.1016/j.health.2024.100316] 17. Wang X, Sharpnack J, Lee T (2024) Improving lung cancer diagnosis and survival prediction with deep learning and CT imaging. arXiv, 2024: 2408.09367. 18. Thanammal KK (2024) Lung cancer detection via deep learning-based pyramid network with honey badger algorithm. Measurement: Sensors, 31: 100993. [ DOI:10.1016/j.measen.2023.100993] 19. Sangeetha SKB, Mathivanan SK, Karthikeyan P, Rajadurai H, S, et al. 2024An enhanced multimodal fusion deep learning neural network for lung cancer classification. Systems and Soft Computing, 6: 200068. [ DOI:10.1016/j.sasc.2023.200068] 20. Subash J and Kalaivani S (2024) Dual-stage classification for lung cancer detection and staging using hybrid deep learning techniques. Neural Comput Appl, 36(14): 8141-8161. [ DOI:10.1007/s00521-024-09425-3] 21. Dawood H, Nawaz M, Ilyas MU, Nazir T, Javed A (2025) Attention-guided CenterNet deep learning approach for lung cancer detection. Comput Biol Med, 186: 109613. [ DOI:10.1016/j.compbiomed.2024.109613] 22. Diao S, Wan Y, Huang D, Huang S, et al. (2025) Optimizing Bi-LSTM networks for improved lung cancer detection accuracy. PLoS One, 20(2): e0316136. [ DOI:10.1371/journal.pone.0316136] 23. Ozdemir B, Aslan E, Pacal I (2025) Attention enhanced InceptionNeXt based hybrid deep learning model for lung cancer detection. IEEE Access, 2025. [ DOI:10.1109/ACCESS.2025.3539122] 24. Neal Joshua ES, Bhattacharyya D, Chakkravarthy M, Byun YC (2021) 3D CNN with visual insights for early detection of lung cancer using gradient-weighted class activation. J Healthc Eng, 2021: 6695518. [ DOI:10.1155/2021/6695518] 25. Shanid M and Anitha A (2020) Lung cancer detection from CT images using salp-elephant optimization-based deep learning. Biomed Eng Appl Basis Commun, 32(01): 2050001. [ DOI:10.4015/S1016237220500015] 26. Xu R, Xu W, Liu D, Pan S, et al. (2025) Application value of low-dose computed tomography combined with serum tumor markers in diagnosis of early non-small cell lung cancer. Int J Radiat Res, 23(1): 77-81. [ DOI:10.61186/ijrr.23.1.77] 27. Tanabe Y, Deguchi T, Kiritani M, Hira N, et al. (2024) Evaluation of statistical prediction model fitting by combining fiducial markers and lung volume for stereotactic body radiotherapy. Int J Radiat Res, 22(1): 17-22. [ DOI:10.61186/ijrr.22.1.17] 28. Takano H, Kondo Y, Ishizawa Y, Onodera S, et al. (2025) Generation of computed tomography images with different tube voltages by generative adversarial network. Int J Radiat Res, 23(4): 873-879. [ DOI:10.66224/ijrr.23.4.6] |
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
|
Qi C, Jiang Q. Deep learning-based classification of lung nodules on CT images: A multicenter study of early lung cancer detection. Int J Radiat Res 2026; 24 (3) :749-754 URL: http://ijrr.com/article-1-7233-en.html
|
