Skip to main content

Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm

Journal of Cancer Research and Clinical Oncology volume 145, pages 829–837 (2019)Cite this article

Abstract

Purpose

Oral cancer is a complex wide spread cancer, which has high severity. Using advanced technology and deep learning algorithm early detection and classification are made possible. Medical imaging technique, computer-aided diagnosis and detection can make potential changes in cancer treatment. In this research work, we have developed a deep learning algorithm for automated, computer-aided oral cancer detecting system by investigating patient hyperspectral images.

Methods

To validate the proposed regression-based partitioned deep learning algorithm, we compare the performance with other techniques by its classification accuracy, specificity, and sensitivity. For the accurate medical image classification objective, we demonstrate a new structure of partitioned deep Convolution Neural Network (CNN) with two partitioned layers for labeling and classify by labeling region of interest in multidimensional hyperspectral image.

Results

The performance of the partitioned deep CNN was verified by classification accuracy. We have obtained classification accuracy of 91.4% with sensitivity 0.94 and a specificity of 0.91 for 100 image data sets training for task classification of cancerous tumor with benign and for task classification of cancerous tumor with normal tissue accuracy of 94.5% for 500 training patterns was obtained.

Conclusions

We compared the obtained results from another traditional medical image classification algorithm. From the obtained result, we identify that the quality of diagnosis is increased by proposed regression-based partitioned CNN learning algorithm for a complex medical image of oral cancer diagnosis.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  • Baljit Singh K, Singh AP, P (2016) Classification of clustered microcalcifications using MLFFBP-ANN and SVM. Egyptian Infor J 17(1):11–20

    Article  Google Scholar 

  • Bradley J, Erickson MD, Panagiotis K et al (2018) Deep learning in radiology: does one size fit all? J Am Coll Rad 15(3):521–526

    Article  Google Scholar 

  • Christodoulidis S, Anthimopoulos M, Ebner L et al (2017) Multisource transfer learning with convolutional neural networks for lung pattern analysis. IEEE J Biomed Health Inf 21(1):76–84

    Article  Google Scholar 

  • Chudgar AV, Conant EF, Weinstein SP (2017) Assessment of disease extent on contrast-enhanced MRI in breast cancer detected at digital breast tomosynthesis versus digital mammography alone. Clin Radiol 72(7):573–579

    CAS  Article  Google Scholar 

  • Deepak Kumar J, Surendra Bilouhan D, Kumar RC (2018) An approach for hyperspectral image classification by optimizing SVM using self-organizing map. J Comput Sci 25(1):252–259

    Google Scholar 

  • Dey D, Chatterjee B, Dalai S, Munshi S, Chakravorti S (2017) A deep learning framework using convolution neural network for classification of impulse fault patterns in transformers with increased accuracy. IEEE Trans Dielectr Electr Insul 24(6):3894–3897

    Article  Google Scholar 

  • Dou Q, Chen H, Yu L et al (2016) Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans Med Imaging 35(5):1182–1195. https://doi.org/10.1109/TMI.2016.2528129

    Article  Google Scholar 

  • Ge H, Wang L, Liu Y, Li C (2018) Hyperspectral image classification based on adaptive-weighted LLE and clustering-based FSVMs. IET Image Proc 12(6):941–947

    Article  Google Scholar 

  • Gregory P, Way VF, Sanchez K La (2018) Machine learning detects pan-cancer ras pathway activation in the cancer genome Atlas. Cell Reports 23(1):172–180

    Article  Google Scholar 

  • He H, Ma Y (2012) Imbalanced learning: foundations, algorithms and applications, 1st edn. Wiley, New York

    Google Scholar 

  • Heba M, El-Dahshan ESA, El-Horbaty ESM, Abdel-Badeeh M (2018) Classification using deep learning neural networks for brain tumors. Future Comput Inf J 3(1):68–71

    Article  Google Scholar 

  • Hijazi H, Chan C (2012) A classification framework applied to cancer gene expression profiles. J Healthc Eng 4(4):255–284

    Google Scholar 

  • Hinton G, Deng L, Yu D et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82–97

    Article  Google Scholar 

  • Huang W, Xiao L, Wei Z et al (2015) A new pan-sharpening method with deep neural networks. IEEE Geosci Remote Sens Lett 12(5):1037–1041

    Article  Google Scholar 

  • Jie Z, Shufang W, Xizhao W, Guoqing Y, Liyan M (2018) Multi-image matching for object recognition. IET Compt Vis 12(3):350–356

    Article  Google Scholar 

  • Jin KH, McCann MT, Froustey E et al (2017) Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 26(9):4509–4522

    Article  Google Scholar 

  • Kalantari N, Ramamoorthi R (2017) Deep high dynamic range imaging of dynamic scenes. ACM Trans Graph 36(4):1–12

    Article  Google Scholar 

  • Kiranyaz S, Ince T, Gabbouj M (2016) Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng 63(3):664–675

    Article  Google Scholar 

  • Kourou K, Exarchos TP, Exarchos KP et al (2015) Machine learning applications in cancer prognosis and prediction. Comput Struct Biotech J 13(1):8–17

    CAS  Article  Google Scholar 

  • Lustberg T, van Soest J, Mark G et al (2018) Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer. Radio Onco 126:312–317

    Article  Google Scholar 

  • Mathews SM, Kambhamettu C, Barner KE (2018) A novel application of deep learning for single-lead ECG classification. Comput Biol Med 99(1):53–62

    Article  Google Scholar 

  • Murray G, Rourke CO, Hogan J, Fenton FE (2016) Detecting internet search activity for mouth cancer in Ireland. British J of Oral Maxillofacial Surg 54(2):163–165

    CAS  Article  Google Scholar 

  • Ordonez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):1–25

    Article  Google Scholar 

  • Palsson F, Sveinsson J, Ulfarsson M (2017) Multispectral and hyperspectral image fusion using a 3-d-convolutional neural network. IEEE Geosci Remote Sens Lett 14(5):639–643

    Article  Google Scholar 

  • Philippe M, Vincent N, Christophe M, Alex L (2018) Survey on deep learning for radiotherapy. Compt Biol Med 98:126–146

    Article  Google Scholar 

  • Prochzazka A, Vaseghi S, Charvatova H et al (2017) Cycling segments multimodal analysis and classification using neural networks. Appl Sci 7(6):581–591

    Article  Google Scholar 

  • Wang C, Gong L, Yu Q et al (2017) DLAU: a scalable deep learning accelerator unit on FPGA. IEEE Trans Comput Aided Des Integr Circuits Syst 36(3):513–517

    Google Scholar 

  • Yuan Y, Lin J, Wang Q (2015) Hyperspectral image classification via multitask joint sparse representation and stepwise MRF optimization. IEEE Trans Cybern 46(12):2966–2977

    Article  Google Scholar 

  • Zhihuai X, Zhenhua G, Chengshan Q (2018) Palmprint gender classification by convolutional neural network. IET Compt Vis 12(4):476–483

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the Department of Electrical Engineering, Indian Institute of Technology, Delhi and the Management, Principal of Mepco Schlenk Engineering College, Sivakasi for providing us the state-of-art facilities to carry out this research work.

Author information

Affiliations

  1. Department of Electrical and Electronics Engineering, Mepco Schlenk Engineering College (Autonomous), Sivakasi, Tamil Nadu, India

    Pandia Rajan Jeyaraj & Edward Rajan Samuel Nadar

Authors
  1. Pandia Rajan Jeyaraj
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Edward Rajan Samuel Nadar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pandia Rajan Jeyaraj.

Ethics declarations

Conflict of interest

The authors confirm that they have no conflict of interest regarding this research article.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Jeyaraj, P.R., Samuel Nadar, E.R. Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm. J Cancer Res Clin Oncol 145, 829–837 (2019). https://doi.org/10.1007/s00432-018-02834-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00432-018-02834-7

Keywords

  • Deep learning algorithm
  • Medical image classification
  • Hyperspectral image data
  • Image labeling
  • Oral cancer diagnosis