Objectives of Study

The significant constraints of previously mentioned examinations are their high pace of FP per check. Lower differentiate contrast between subsolid injuries and the encompassing lung parenchyma further hampers the division and volumetric evaluation of these knobs. Follow'ing are the targets of the investigation [ 19]:

i. The objective behind the wfork done in this examination to create procedures for the extraction of shallow and volumetric highlights in three dimensional advanced pictures utilizing morphological strategies.

ii. To prepare the framew-ork for introduction of an exact and reliable framework for early location of lung knobs.

iii. To identify diverse trademark design for shape and size of lung knobs.

iv. Design and advancement of lung division dependent on grouping approach.

v. Effective knob extraction technique dependent on CNN.

vi. Implementation of knob discovery approach dependent on segment examination and utilization of huge component.

vii. Efficient knob discovery framework as far as reality multifaceted nature.

viii. Detail investigation of the outcomes.

Proposed Methodology

When CNNs are used for enormous collections of information, w'hich is really the prerequisite in order-based applications, more calculation is required. Figure 13.3

Workflow Diagram

FIGURE 13.3 Workflow Diagram.

shows a run- of -the -mill engineering of the profound neural system [20]. In the proposed method. CNN is used for the classification purpose, which is represented in Figure 13.4 and Figure 13.5.

  • 13.5.1. Evaluation Results for Medical Image Handling
  • False Positive Rate (FPR)

The level of situations where a picture was sectioned to the shape, however in certainty it didn't. False Negative Rate (FNR)

The level of situations where a picture was sectioned to the shape, however in certainty it did.

Block Diagram of a Typical CNN Architecture

FIGURE 13.4 Block Diagram of a Typical CNN Architecture.

Block Diagram of CNN

FIGURE 13.5 Block Diagram of CNN. Sensitivity

Proportions of affectabilities are the extents of real positivity which are appropriately observed. And it identifies with limits of tests to identify positive outcome. Specificity

Proportions of the particularities are extent of negativity which are appropriately observes. And it identifies with the limits of tests to identify negative outcome. Accuracy

The weighted level of posture variety pictures is accurately characterized by the estimation exactness. It is spoken to like,

Expected Outcome of Research Work

  • • Complexity of the created calculation must be contrasted with reference to time, space, and progress.
  • • Comparative investigation of created calculations with existing techniques.

Conclusion and Future work

In this paper, a model is proposed for the diagnosis of lung cancer using convolution neural network. The proposed method consists of preprocessing technique, segmentation of tumor from the given image and finally the classification of a detected tumor as cancerous or not. The outcomes were approved beside the clarified ground reality provided by four master radiologists. The proposed investigation fundamentally lessens the quantity of bogus positives (FPs) in the distinguished knob applicants. This strategy shows a general exactness of over 80% at a diminished FPs/examine pace of 0.50. The proposed framework demonstrated an improvement in lung knob location precision and can be usable in clinical settings. In future, a hybrid system can be designed such as by combining the neural network with fuzzy logic system which may improve the classification accuracy.


  • 1. Patil, D. S. and Kuchanur, M. (2012). Lung cancer classification using image processing. International Journal of Engineering and Innovative Technology (IJEIT). 2(2). pp. 55-62.
  • 2. Chaudhary A. and Singh, S. S. (2012). Lung cancer identification on CT images by using image processing. IEEE International Conference on Computing Sciences (ICCS). pp" 142-146.
  • 3. Hadavi, N.. Nordin. M., Shojaeipour A. (2014). Lung cancer diagnosis using CT-scan images based on cellular learning automata. In the proceedings of IEEE International Conference on Computer and Information Sciences (ICCOINS). pp. 1-5.
  • 4. Camarlinghi, N.. Gori, I.. Retico, A., Bellotti, R.. Bosco, P.. Cerello. P. Gargano. G. E. L. Torres, R. Megna. M. Peccarisi et al. (2012). Combination of computer-aided detection algorithms for automatic lung nodule identification. International Journal of Computer Assisted Radiology and Surgery. 7(3), pp. 455-464.
  • 5. A. A. Abdullah and S. M. Shaharum(2012), “Lung cancer cell classification method using artificial neural network," Information Engineering Letters. 2( 1). pp. 49-59.
  • 6. Kuruvilla, J. and Gunavathi, K. (2014). Lung cancer classification using neural networks for СГ images. Computer Methods and Programs in Biomedicine. 113(1), pp. 202-209.
  • 7. Bellotti. R., De Carlo, F. Gargano. G., Tangaro, S. Cascio, D., Catanzariti. E., P. Cerello, S. C. Cheran, P. Delogu. I. De Mitri et al. (2017). A cad system for nodule detection in low-dose lung cts based on region growing and a new active contour model. Medical Physics. 34(12), pp. 4901-4910.
  • 8. Hayashibe. R. (1996). Automatic lung cancer detection from X-ray images obtained through yearly serial mass survey. IEEE International Conference on Image Processing. DOI: 10.1109/ICIP. 1996.559503.
  • 9. Kanazawa. К. M.. and Niki N. (1996). Computer aided diagnosis system for lung cancer based on helical CT images. 13th IEEE International Conference on Pattern Recognition. DOI: 10.1109/ICPR. 1996.546974.
  • 10. Salman. N. (2006). Image segmentation based on watershed and edge detection techniques. The International Arab Journal of Information Technology. 3(2), pp. 104-110.
  • 11. Kumar, A. Kumar, P. (2006). A New Framework for Color Image Segmentation Using Watershed Algorithm. Computer Engineering and Intelligent Systems. 2(3). pp. 41MJ3.
  • 12. Mori, K., Kitasaka. T., Hagesawa, J. I., Toriwaki, J. I. et al. (1996). A method for extraction of bronchus regions from 3D Chest X-ray CT images by analyzing structural features of the bronchus. In the 13th International Conference on Pattern Recognition, pp. 69-77, Vol 2.
  • 13. Dwivedi, S. A., Borse. R. P.. Yametkar, A. M. (2014). Lung cancer detection and classification by using machine learning and multinomial Bayesian. IOSR Journal of Electronics and Communication. 9(1). pp. 69-75.
  • 14. WafaaAlawaa, Mahammad Nassef. Amr Badr (2017). Lung cancer detection and classification with 3D convolutional neural network (3D-CNN). International Journal of Advanced Computer and Application. 8(8). pp. 409-417.
  • 15. Armato. S. G.. McLenman, G., Clarke, L. P. (2011). National Cancer Institute, Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI). 38(2), pp. 915-931. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041807/.
  • 16. Rohit Raja. Tilendra Shishir Sinha. Ravi Prakash Dubey (2015). Recognition of human-face from side-view using progressive switching pattern and soft-computing technique. Association for the Advancement of Modelling and Simulation Techniques in Enterprises, Advance B. 58(1). pp. 14-34, ISSN: -1240-4543.
  • 17. A. C. Bhensle and Rohit Raja (2014). An efficient face recognition using PCA and Euclidean Distance classification. International Journal of Computer Science and Mobile Computing. 3(6), pp. 407-413. ISSN: 2320-088X.
  • 18. Raja, R., Kumar. S. and Mahmood, M.R. (2020), Color Object Detection Based Image Retrieval Using ROI Segmentation with Multi-Feature Method. Wireless Personal Communications, pp. 1-24.
  • 19. Rohit Raja. Tilendra Shishir Sinha. Raj Kumar Patra and Shrikant Tiwari (2018). Physiological trait based biometrical authentication of human-face using LGXP and ANN Techniques. International Journal of Information and Computer Security. 10(2/3). pp. 303-320.
  • 20. Shraddha Shukla and Rohit Raja (2016). Digital image fusion using adaptive neuro- fuzzy inference system. International Journal of New Technology and Research (IJNTR). 2(5), pp. 101-104. ISSN:-2454-4116.
< Prev   CONTENTS   Source