Skip to main content
SpringerLink
Log in

Transfer learning-based classification model for the Computed Tomography scan pulmonary images

  • 1233: Robust Enhancement, Understanding and Assessment of Low-quality Multimedia Data
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In recent years, transfer learning has emerged as the most effective method for detecting and classifying lung cancer. Early-stage lung cancer diagnosis using multiple slices of computed tomography scan lung images is challenging. The manual diagnosis of such images is tedious, time-consuming, and biased. Several automated diagnosis systems have been widely used to process computed tomography scan lung images. However, existing diagnostic systems are dependent on annotated datasets. To address the stated problems, a robust automated diagnosis solution has been proposed to classify computed tomography scan lung images without relying on annotations. The proposed model utilizes a transfer learning-based architecture to classify segmented lung images. Segmentation of CT scan lung images is performed using K-means clustering with parameter tuning followed by morphological operations. The number of clusters has been chosen based on the value of the silhouette score. The best silhouette score of 0.66 was obtained during analysis for k=2 clusters. The proposed model achieved a test accuracy; 0.926, a precision; 0.932, recall and F1 score; 0.926, a kappa score; 0.848, and an AUC of 0.904 on the LIDC dataset. For the NLST dataset, it achieved test results; 0.970 accuracy, precision, recall, 0.956 F1 score, 0.934 kappa value, and 0.978 AUC. In addition, the proposed method outperforms state-of-art models with an accuracy of 1-3%, recall of 2-3%, a precision of 2-3%, and an F1 score of 2-4% for the classification of lung cancer. These results justify that the proposed model improves the performance of diagnosis of lung images. Overall performance improvement, robustness in handling various sizes and shapes of lung images, and use of the silhouette score to choose the number of clusters for segmentation make the proposed approach distinct from the existing techniques.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data Availability

The LIDC data is publicly available on the following link: https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=1966254.

References

  1. Sung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71(3):209–249

    Article  Google Scholar 

  2. Siegel RL, Miller KD, Fedewa SA et al (2017) (2017) Colorectal cancer statistics. CA Cancer J Clin 67(3):177–193

    Article  Google Scholar 

  3. Valente IRS, Cortez PC, Neto EC et al (2016) Automatic 3d pulmonary nodule detection in ct images: a survey. Comput Methods Programs Biomed 124:91–107

    Article  Google Scholar 

  4. Jiang H, Ma H, Qian W et al (2017) An automatic detection system of lung nodule based on multigroup patch-based deep learning network. IEEE J Biomed Health Inform 22(4):1227–1237

    Article  Google Scholar 

  5. Rodrigues MB, Da Nobrega RVM, Alves SSA et al (2018) Health of things algorithms for malignancy level classification of lung nodules. IEEE Access 6:18,592-18,601

    Article  Google Scholar 

  6. Rebouças Filho PP, Sarmento RM, Holanda GB et al (2017) New approach to detect and classify stroke in skull ct images via analysis of brain tissue densities. Comput Methods Programs Biomed 148:27–43

    Article  Google Scholar 

  7. Reboucas Filho PP, Reboucas EdS, Marinho LB et al (2017) Analysis of human tissue densities: A new approach to extract features from medical images. Pattern Recogn Lett 94:211–218

    Article  Google Scholar 

  8. Liu Y, Gadepalli K, Norouzi M, et al (2017) Detecting cancer metastases on gigapixel pathology images. arXiv:1703.02442

  9. Goel N, Kaur S, Gunjan D et al (2022) Investigating the significance of color space for abnormality detection in wireless capsule endoscopy images. Biomed Signal Process Control 75(103):624

    Google Scholar 

  10. Bishnoi V, Goel N (2023) A color-based deep-learning approach for tissue slide lung cancer classification. Biomed Signal Process Control 86(105):151

    Google Scholar 

  11. Thawani R, McLane M, Beig N et al (2018) Radiomics and radiogenomics in lung cancer: a review for the clinician. Lung Cancer 115:34–41

    Article  Google Scholar 

  12. Goel N, Kaur S, Gunjan D et al (2022) Dilated cnn for abnormality detection in wireless capsule endoscopy images. Soft Comput 1–17

  13. Khan SA, Nazir M, Khan MA et al (2019) Lungs nodule detection framework from computed tomography images using support vector machine. Microsc Res Tech 82(8):1256–1266

    Article  Google Scholar 

  14. Saba T, Sameh A, Khan F et al (2019) Lung nodule detection based on ensemble of hand crafted and deep features. J Med Syst 43(12):1–12

    Article  Google Scholar 

  15. Makaju S, Prasad P, Alsadoon A et al (2018) Lung cancer detection using ct scan images. Procedia Comput Sci 125:107–114

    Article  Google Scholar 

  16. Shi Z, Ma J, Zhao M et al (2016) Many is better than one: an integration of multiple simple strategies for accurate lung segmentation in ct images. BioMed Res Int 2016

  17. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577

    Article  Google Scholar 

  18. Liao L, Chen W, Xiao J et al (2022) Unsupervised foggy scene understanding via self spatial-temporal label diffusion. IEEE Trans Image Process 31:3525–3540

    Article  Google Scholar 

  19. Zabihollahy F, Schieda N, Krishna Jeyaraj S et al (2019) Automated segmentation of prostate zonal anatomy on t2-weighted (t2w) and apparent diffusion coefficient (adc) map mr images using u-nets. Med Phys 46(7):3078–3090

    Article  Google Scholar 

  20. Liu Y, Yang G, Mirak SA et al (2019) Automatic prostate zonal segmentation using fully convolutional network with feature pyramid attention. IEEE Access 7:163,626-163,632

    Article  Google Scholar 

  21. Bishnoi V, Gooel N, Tayal A (2022) Automated system-based classification of lung cancer using machine learning. Int J Med Eng Inform 1:1. https://doi.org/10.1504/IJMEI.2022.10047638

    Article  Google Scholar 

  22. Xie Y, Zhang J, Xia Y et al (2018) Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest ct. Inf Fusion 42:102–110

    Article  Google Scholar 

  23. Kaur S, Goel N (2020) A dilated convolutional approach for inflammatory lesion detection using multi-scale input feature fusion (workshop paper). In: 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM). IEEE, pp 386–393

  24. Ali I, Hart GR, Gunabushanam G et al (2018) Lung nodule detection via deep reinforcement learning. Front Oncol 8:108

    Article  Google Scholar 

  25. Shen W, Zhou M, Yang F et al (2017) Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification. Pattern Recogn 61:663–673

    Article  Google Scholar 

  26. Xu M, Qi S, Yue Y et al (2019) Segmentation of lung parenchyma in ct images using cnn trained with the clustering algorithm generated dataset. Biomed Eng Online 18(1):1–21

    Article  Google Scholar 

  27. Li C, Zhu G, Wu X et al (2018) False-positive reduction on lung nodules detection in chest radiographs by ensemble of convolutional neural networks. IEEE Access 6:16,060-16,067

    Article  Google Scholar 

  28. Charron O, Lallement A, Jarnet D et al (2018) Automatic detection and segmentation of brain metastases on multimodal mr images with a deep convolutional neural network. Comput Biol Med 95:43–54

    Article  Google Scholar 

  29. Alakwaa W, Nassef M, Badr A (2017) Lung cancer detection and classification with 3d convolutional neural network (3d-cnn). Lung Cancer 8(8):409

    Google Scholar 

  30. Dou Q, Chen H, Yu L et al (2016) Multilevel contextual 3-d cnns for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 64(7):1558–1567

    Article  Google Scholar 

  31. Song Q, Zhao L, Luo X et al (2017) Using deep learning for classification of lung nodules on computed tomography images. J Healthc Eng 2017

  32. Sun W, Zheng B, Qian W (2016) Computer aided lung cancer diagnosis with deep learning algorithms. In: Medical imaging 2016: computer-aided diagnosis. International Society for Optics and Photonics, p 97850Z

  33. Sun W, Zheng B, Qian W (2017) Automatic feature learning using multichannel roi based on deep structured algorithms for computerized lung cancer diagnosis. Comput Biol Med 89:530–539

    Article  Google Scholar 

  34. Orenstein EC, Beijbom O (2017) Transfer learning and deep feature extraction for planktonic image data sets. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pp 1082–1088

  35. Nibali A, He Z, Wollersheim D (2017) Pulmonary nodule classification with deep residual networks. Int J Comput Assist Radiol Surg 12(10):1799–1808

    Article  Google Scholar 

  36. Deniz E, Şengür A, Kadiroğlu Z et al (2018) Transfer learning based histopathologic image classification for breast cancer detection. Health Inf Sci Syst 6(1):1–7

    Article  Google Scholar 

  37. Al-Shabi M, Lan BL, Chan WY et al (2019) Lung nodule classification using deep local-global networks. Int J Comput Assist Radiol Surg 14(10):1815–1819

    Article  Google Scholar 

  38. da Nobrega RVM, Reboucas Filho PP, Rodrigues MB et al (2020) Lung nodule malignancy classification in chest computed tomography images using transfer learning and convolutional neural networks. Neural Comput Appl 32(15):11,065-11,082

    Article  Google Scholar 

  39. Zhou L, Zhang Z, Chen YC et al (2019) A deep learning-based radiomics model for differentiating benign and malignant renal tumors. Translat Oncol 12(2):292–300

    Article  Google Scholar 

  40. Harsono IW, Liawatimena S, Cenggoro TW (2020) Lung nodule detection and classification from thorax ct-scan using retinanet with transfer learning. J King Saud Univ - Comput Inf Sci

  41. Bishnoi V, Goel N (2023) Tensor-rt-based transfer learning model for lung cancer classification. J Digit Imaging 1–12

  42. Yang Y, Yan LF, Zhang X et al (2018) Glioma grading on conventional mr images: a deep learning study with transfer learning. Front Neurosci 12:804

    Article  Google Scholar 

  43. Ahmed KB, Hall LO, Goldgof DB, et al (2017) Fine-tuning convolutional deep features for mri based brain tumor classification. In: Medical Imaging 2017: Computer-Aided Diagnosis. International Society for Optics and Photonics, p 101342E

  44. Talo M, Baloglu UB, Yıldırım Ö et al (2019) Application of deep transfer learning for automated brain abnormality classification using mr images. Cogn Syst Res 54:176–188

    Article  Google Scholar 

  45. Hussein S, Kandel P, Bolan CW et al (2019) Lung and pancreatic tumor characterization in the deep learning era: novel supervised and unsupervised learning approaches. IEEE Trans Med Imaging 38(8):1777–1787

    Article  Google Scholar 

  46. Jain R, Jain N, Aggarwal A et al (2019) Convolutional neural network based alzheimer’s disease classification from magnetic resonance brain images. Cogn Syst Res 57:147–159

    Article  Google Scholar 

  47. Apostolopoulos ID, Pintelas EG, Livieris IE et al (2021) Automatic classification of solitary pulmonary nodules in pet/ct imaging employing transfer learning techniques. Med Biol Eng Comput 59(6):1299–1310

    Article  Google Scholar 

  48. Zheng S, Shen Z, Peia C, et al (2021) Interpretative computer-aided lung cancer diagnosis: from radiology analysis to malignancy evaluation. arXiv:2102.10919

  49. Armato SG III, McLennan G, Bidaut L et al (2011) The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Med Phys 38(2):915–931

    Article  Google Scholar 

  50. Clark K, Vendt B, Smith K et al (2013) The cancer imaging archive (tcia): maintaining and operating a public information repository. J Digit Imaging 26:1045–1057

    Article  Google Scholar 

  51. Aberle D, Adams A, Team NLSTR et al (2011) B. lack wc, clapp jd, fagerstrom rm, gareen if, gatsonis c., marcus pm, sicks jd reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 365(5):395–409

  52. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  53. Shi Z, Hao H, Zhao M et al (2019) A deep cnn based transfer learning method for false positive reduction. Multimed Tools Appl 78(1):1017–1033

    Article  Google Scholar 

  54. Zhao X, Qi S, Zhang B et al (2019) Deep cnn models for pulmonary nodule classification: model modification, model integration, and transfer learning. J Xray Sci Technol 27(4):615–629

    Google Scholar 

Download references

Author information

Author notes

  1. Nidhi Goel contributed equally to this work.

Authors and Affiliations

  1. Electronics and Communication Engineering, Indira Gandhi Delhi Technical University for Women, Kashmere gate, Delhi, 110006, India

    Vidhi Bishnoi & Nidhi Goel

  2. KIET group of Institutions, Ghaziabad, Department of Electronics and Communication Engineering, Ghaziabad, India

    Vidhi Bishnoi

Authors
  1. Vidhi Bishnoi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nidhi Goel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nidhi Goel.

Ethics declarations

Conflicts of interest

The authors declare that they have no known competing financial interests in this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bishnoi, V., Goel, N. Transfer learning-based classification model for the Computed Tomography scan pulmonary images. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-19098-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11042-024-19098-8

Keywords

Search

Navigation