Diagnosis of Medical Images Using Cloud-Deep Learning System

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Diagnosis of brain tumors is one of the most severe medical problems that affect thousands of people each year in the United States. Manual classification of cancerous tumors through examination of MRI images is a difficult task even for trained professionals. It is an error-prone procedure that is dependent on the experience of the radiologist. Brain tumors, in particular, have a high level of complexity.  Therefore, computer-aided diagnosis systems designed to assist with this task are of specific interest for physicians. Accurate detection and classification of brain tumors via magnetic resonance imaging (MRI) examination is a famous approach to analyze MRI images. This paper proposes a method to classify different brain tumors using a Convolutional Neural Network (CNN). We explore the performance of several CNN architectures and examine if decreasing the input image resolution affects the model's accuracy. The dataset used to train the model has initially been 3064 MRI scans. We augmented the data set to 8544 MRI scans to balance the available classes of images. The results show that the design of a suitable CNN architecture can significantly better diagnose medical images. The developed model classification performance was up to 97\% accuracy.


  • Keywords


    Medical Imaging; Brain Tumor; Classification; Deep Learning; Convolutional Neural Network; Google Cloud; MRI

  • References


      [1]American Health Care, “American health care: Health spending and the federal budget,” https://www.crfb.org/papers/american-health-care-health-spending-and-federal-budget, May 2018.

      [2]MayoClinicStaff.Testprocedures:Magneticresonanceimaging.[Online].Avail-able: https://www.mayoclinic.org/tests-procedures/mri/about/pac-20384768#:~:text=Magnetic%20resonance%20imaging%20(MRI)%20is,large%2C%20tube%2Dshaped%20magnets.

      [3]Central Brain Tumor Registry of the United States. CBTRUS fact sheet. [Online]. Avail-able: https://cbtrus.org/cbtrus-fact-sheet-2020/#:~:text=This%20represents%20an%20average%20of,and%2045%20deaths%20per%20day.&text=It%20was%20estimated%20that%20there,and%207%2C830%20occurring%20in%20females.

      [4]American Cancer Society. (2020) Tests for brain and spinal cord tumors in adults. [Online]. Available: https://www.cancer.org/cancer/brain-spinal-cord-tumors-adults/detection-diagnosis-staging/how-diagnosed.html

      [5]——. (2021) Key statistics for brain and spinal cord tumors. [Online]. Available: https://www.cancer.org/cancer/brain-spinal-cord-tumors-adults/about/key-statistics.html

      [6]National Brain Tumor Society. Tumor types: Understanding brain tumors. [Online]. Available: https://braintumor.org/brain-tumor-information/understanding-brain-tumors/tumor-types

      [7]American Society of Clinical Oncology. (2020) Brain tumor statistics. [Online]. Available: https://www.cancer.net/cancer-types/brain-tumor/statistics

      [8]E. Dandıl, M. Çakıroğlu, and Z. Ekşi, “Computer-aided diagnosis of malign and benign brain tumors on MR images,” inICTInnovations 2014, A. M. Bogdanova and D. Gjorgjevikj, Eds. Cham: Springer International Publishing, 2015, pp. 157–166.

      [9]J. Naik and S. Patel, “Tumor detection and classification using decision tree in brain MRI,” inInternational Journal of EngineeringDevelopment and Research, 2013, pp. 49–53.

      [10]N. M. Balasooriya and R. D. Nawarathna, “A sophisticated convolutional neural network model for brain tumor classification,” in2017 IEEE International Conference on Industrial and Information Systems (ICIIS), 2017, pp. 1–5.

      [11]T. Hossain, F. S. Shishir, M. Ashraf, M. A. Al Nasim, and F. Muhammad Shah, “Brain tumor detection using convolutional neuralnetwork,” in2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019,pp. 1–6.

      [12]A. Kharrat, M. B. Halima, and M. B. Ayed, “MRI brain tumor classification using support vector machines and meta-heuristicmethod,”2015 15th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 446–451, 2015

      [13]U. Javed, M. Riaz, A. Ghafoor, and T. Cheema, “MRI brain classification using texture features, fuzzy weighting and supportvector machine,”Progress In Electromagnetics Research, vol. 53, pp. 1–6, July 2013.

      [14]S. S. Saba, D. Sreelakshmi, P. S. Kumar, K. S. Kumar, and S. R. Saba, “Logistic regression machine learning algorithm on MRIbrain image for fast and accurate diagnosis,”International Journal of Scientific Technology Research, vol. 9, no. 3, pp. 7076–7081,Mar 2020.

      [15]K. Sharma, A. Kaur, and S. Gujral, “Brain tumor detection based on machine learning algorithms,”International Journal ofComputer Applications, vol. 103, no. 1, pp. 7–11, Oct 2014.

      [16]The Brain Tumor Charity. Side-effects of a brain tumour. [Online]. Available: https://www.thebraintumourcharity.org/living-with-a-brain-tumour/side-effects/

      [17]A. Sheta, H. Turabieh, S. Aljahdali, and A. Alangari, “Pavement crack detection using convolutional neural network,” inProceedings of 35th International Conference on Computers and Their Applications, ser. EPiC Series in Computing, G. Lee andY. Jin, Eds., vol. 69. EasyChair, 2020, pp. 214–223. [Online]. Available: https://easychair.org/publications/paper/t2BC

      [18]E. Endri, A. Sheta, and H. Turabieh, “Road damage detection utilizing convolution neural network and principal componentanalysis,”International Journal of Advanced Computer Science and Applications, vol. 11, no. 6, 2020. [Online]. Available:http://dx.doi.org/10.14569/IJACSA.2020.0110682

      [19]P. Afshar, K. N. Plataniotis, and A. Mohammadi, “Capsule networks for brain tumor classification based on MRI images andcourse tumor boundaries,”CoRR, vol. abs/1811.00597, 2018.

      [20]A. Rehman, S. Naz, M. Razzak, F. Akram, and M. Imran, “A deep learning-based framework for automatic brain tumorsclassification using transfer learning,”Circuits, Systems, and Signal Processing, vol. 39, pp. 757–775, Feb 2020.

      [21]H. A. Khan, W. Jue, M. Mushtaq, and M. U. Mushtaq, “Brain tumor classification in MRI image using convolutional neuralnetwork,”Mathematical Bioscience and Engineering, vol. 17, pp. 01–14, 09 2020.

      [22] K. O’Shea and R. Nash, “An introduction to convolutional neural networks,”CoRR, vol. abs/1511.08458, 2015.

      [23]A. Bhandari, J. Koppen, and M. Agzarian, “Convolutional neural networks for brain tumour segmentation,”Insights into Imaging,vol. 11, 12 2020.

      [24]M. M. Badža and M. Barjaktarović, “Classification of brain tumors from MRI images using a convolutional neural network,”Applied Sciences, vol. 10, no. 6, 2020.[25]A. K. Rana. (2020) Pooling layer — short and simples. [Online]. Available:https://ai.plainenglish.io/pooling-layer-beginner-to-intermediate-fa0dbdce80eb

      [26]JavaTpoint. Convolutional neural network in pytorch. [Online]. Available:https://www.javatpoint.com/pytorch-convolutional-neural-network

      [27]Shiva Verma. (2019, June) Understanding different loss functions for neural networks. [Online]. Available: https://towardsdatascience.com/understanding-different-loss-functions-for-neural-networks-dd1ed0274718

      [28]J. Cheng, W. Huang, S. Cao, R. Yang, W. Yang, Z. Yun, Z. Wang, and Q. Feng, “Correction: Enhanced performance of braintumor classification via tumor region augmentation and partition,”PLOS ONE, vol. 10, no. 12, pp. 1–1, Dec 2015.

      [29] J. Cheng, “Brain Tumor Dataset,” https://doi.org/10.6084/m9.figshare.1512427.v5, Apr 2017.

      [30]T. Carneiro, R. V. Medeiros Da NóBrega, T. Nepomuceno, G.-B. Bian, V. H. C. De Albuquerque, and P. P. R. Filho, “Performanceanalysis of google colaboratory as a tool for accelerating deep learning applications,”IEEE Access, vol. 6, pp. 61 677–61 685, 2018.

      [31]M. J. Nelson and A. K. Hoover, “Notes on using google colaboratory in ai education,” inProceedings of the 2020 ACM Conferenceon Innovation and Technology in Computer Science Education, ser. ITiCSE ’20. New York, NY, USA: Association for ComputingMachinery, 2020, p. 533–534. [Online]. Available: https://doi.org/10.1145/3341525.3393997

      [32] E. Bisong,Google Colaboratory. Berkeley, CA: Apress, 2019, pp. 59–64.[33]M. Hossin and S. M.N, “A review on evaluation metrics for data classification evaluations,”International Journal of Data MiningKnowledge Management Process, vol. 5, pp. 01–11, Mar 2015


 

View

Download

Article ID: 31643
 
DOI: 10.14419/ijet.v10i2.31643




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.