Call for Paper - May 2021 Edition
IJCA solicits original research papers for the May 2021 Edition. Last date of manuscript submission is April 20, 2021. Read More

End-to-End Lung Cancer Diagnosis on Computed Tomography Scans using 3D CNN and Explainable AI

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2020
Chaitanya Rahalkar, Anushka Virgaonkar, Dhaval Gujar, Sumedh Patkar

Chaitanya Rahalkar, Anushka Virgaonkar, Dhaval Gujar and Sumedh Patkar. End-to-End Lung Cancer Diagnosis on Computed Tomography Scans using 3D CNN and Explainable AI. International Journal of Computer Applications 176(15):1-6, April 2020. BibTeX

	author = {Chaitanya Rahalkar and Anushka Virgaonkar and Dhaval Gujar and Sumedh Patkar},
	title = {End-to-End Lung Cancer Diagnosis on Computed Tomography Scans using 3D CNN and Explainable AI},
	journal = {International Journal of Computer Applications},
	issue_date = {April 2020},
	volume = {176},
	number = {15},
	month = {Apr},
	year = {2020},
	issn = {0975-8887},
	pages = {1-6},
	numpages = {6},
	url = {},
	doi = {10.5120/ijca2020920111},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Lung cancer is one of the most common malignant neoplasms all over the world. It accounts for more cancer deaths than any other cancer. It is increasingly being recognized in hospitals all across the globe. With the increasing prevalence of smoking, Lung cancer has reached epidemic proportions. Thus, we propose a 3D-CNN-based model [6] that uses a patient’s Computed Tomography scans to detect nodules and check for malignancy. We intend to add an explainable aspect to the result since the central problem of such models is that they are regarded as black-box models, and they lack an explicit declarative knowledge representation [9]. This calls for systems enabling to make decisions transparent, understandable and explainable.


  1. D. R. Aberle et al. Reduced lung-cancer mortality with lowdose computed tomographic screening. pages 395–409. 365, 2011.
  2. The Data Science Bowl. 2017.
  3. The Luna16 Challenge. 2016.
  4. T. Chen and C. XGBoost: A Guestrin. Scalable tree boosting system. In Proc. 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016.
  5. E. R. DeLong, D. M. DeLong, and D. L. Clarke-Pearson. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics, pages 837–845, 1988.
  6. Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 3d convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1):221231, Jan 2013.
  7. J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. CoRR, abs/, 1411:4038, 2014.
  8. S. J. Mason and N. E. Graham. Areas beneath the relative operating characteristics (roc) and relative operating levels (rol) curves: Statistical significance and interpretation. Quarterly Journal of the Royal Meteorological Society, 128:2145–2166, 2002.
  9. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. ”why should i trust you?”: Explaining the predictions of any classifier. arXiv:1602.04938 [cs, stat], Aug 2016. arXiv: 1602.04938.
  10. R. Siegel, K. Miller, and Jemal A. Cancer statistics. Ca cancer journal of clinicians 68. pages 7–30, 2018.
  11. The DICOM Standard.


Supervised Learning, Convolutional Neural Networks