Research Cell: An International Journal of Engineering Sciences

Open Access Open Access  Restricted Access Subscription Access

Brain Tumor Classification Through MRI Images Using DenseNet169 – Statistical Evaluation


Affiliations
1 Research Scholar, USICT, GGSIPU, New Delhi, India
2 Assistant Professor, CSED, Thapar Institute of Engineering and Technology, Punjab, India
 

According to world statistics, Cancer is the 10th leading cause of death in both men and women. Adding to this, the worldwide incidence rate of brain tumors was marked as 3.5 per 100,000 population(s) in 2020. One of the major reasons behind this alarming statistics is the high probability of tumors going undetected through the medical imaging practices in earlier stages of tumor development. This particular fact has drawn the attention of researchers working in the medical field to devise rapid and accurate diagnostic methods to reduce the mortality rate from brain tumors through identification at nascent stage and providing the requisite treatment. As digital image processing paves its way through Computer aided diagnostic in the medical field, exploring utility of deep learning techniques in medical image processing is a promising research avenue. This paper takes this cue to statistically evaluate DenseNet-169, a model based on DenseNet architecture as defined under Convolution Neural Network (CNN) for classifying Brain MRI images on the basis of presence or absence of brain tumor. Densenet-169 model along with a total of eight optimizers have been applied on publicly available brain tumor datasets to assess the performance of the said model in brain tumor classification. The performance of the model has been studied using a total of seven metrics and results obtained have been compared with the previous works in this field. The results obtained aid in concluding that DenseNet-169 with AdaDelta or AdaMax as the optimizer provide better results from the previous studies made. This in turn shall help in establishing DenseNet 169 as a model that can be effectively employed for tumor classification and extend the undertaken study further.

Keywords

Brain Tumor, CAD, CNN, DenseNet, Deep Learning, MRI, Medical Image Processing.
User
Notifications
Font Size

  • H.-C. Shin et al. “Deep convolutional neural networks for computer aided detection: CNN architectures, dataset characteristics and transfer learning”, IEEE transactions on medical imaging, Vol.35, pp. 1285–1298, 2016.

  • D. Ravi et al. “Deep learning for health informatics”, IEEE journal of biomedical and health informatics, Vol. 21, pp. 4–21, 2017.

  • D. S. Kermany et.al, “Identifying-medical diagnoses and treatable diseases by image-based deep learning”, Cell, vol. 172, pp.1122–1131, 2018.

  • G. Litjens, et. al “A survey on deep learning in medical image analysis”, Medical image analysis, Vol.42, pp. 60–88, 2017.

  • I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016.

  • A. Krizhevsky, I. Sutskever, Geoffrey E. Hinton "Imagenet classification with deep convolutional neural networks.", Communications of the ACM, Vol. 60, pp.84-90, 2017.

  • MZ Alom et.al , The history began from alexnet: A comprehensive survey on deep learning approachs, 2018. [

  • Tao Zhou et. al, “Dense Convolutional Network and Its Application in Medical Image Analysis”, BioMed Research International, vol.2022, 2022.

  • G Huang et.al, "Densely connected convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708. 2017.

  • C. Szegedy, et. al “Going deeper with convolutions”, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015.

  • K. He et al., “Deep residual learning for image recognition”, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.

  • C. Shorten, T.M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, Vol. 6, pp.60, 2019.

  • D. Filatov, Ahmad Hassan Yar, G. N, “Brain Tumor Diagnosis and Classification via Pre-Trained Convolutional Neural Networks”, medRxiv, Vol. 7, 2022.

  • D. C. Febrianto, I. Soesanti, H. A. Nugroho, "Convolutional neural network for brain tumor detection," IOP Conference Series: Materials Science and Engineering, Vol. 771, No. 1, 2020.

  • E. Irmak, "Multi-classification of brain tumor MRI images using deep convolutional neural network with fully optimized framework." Iranian Journal of Science and Technology, Transactions of Electrical Engineering, Vol. 45, No.3, pp 1015-1036, 2021.

  • S. Deepak, P.M. Ameer, “Brain tumor classification using deep CNN features via transfer learning”, Computers in Biology and Medicine, 2019.


Abstract Views: 123

PDF Views: 0




  • Brain Tumor Classification Through MRI Images Using DenseNet169 – Statistical Evaluation

Abstract Views: 123  |  PDF Views: 0

Authors

Anjali Jain
Research Scholar, USICT, GGSIPU, New Delhi, India
Anjali Jain
Assistant Professor, CSED, Thapar Institute of Engineering and Technology, Punjab, India
Rajesh Mehta
Assistant Professor, CSED, Thapar Institute of Engineering and Technology, Punjab, India

Abstract


According to world statistics, Cancer is the 10th leading cause of death in both men and women. Adding to this, the worldwide incidence rate of brain tumors was marked as 3.5 per 100,000 population(s) in 2020. One of the major reasons behind this alarming statistics is the high probability of tumors going undetected through the medical imaging practices in earlier stages of tumor development. This particular fact has drawn the attention of researchers working in the medical field to devise rapid and accurate diagnostic methods to reduce the mortality rate from brain tumors through identification at nascent stage and providing the requisite treatment. As digital image processing paves its way through Computer aided diagnostic in the medical field, exploring utility of deep learning techniques in medical image processing is a promising research avenue. This paper takes this cue to statistically evaluate DenseNet-169, a model based on DenseNet architecture as defined under Convolution Neural Network (CNN) for classifying Brain MRI images on the basis of presence or absence of brain tumor. Densenet-169 model along with a total of eight optimizers have been applied on publicly available brain tumor datasets to assess the performance of the said model in brain tumor classification. The performance of the model has been studied using a total of seven metrics and results obtained have been compared with the previous works in this field. The results obtained aid in concluding that DenseNet-169 with AdaDelta or AdaMax as the optimizer provide better results from the previous studies made. This in turn shall help in establishing DenseNet 169 as a model that can be effectively employed for tumor classification and extend the undertaken study further.

Keywords


Brain Tumor, CAD, CNN, DenseNet, Deep Learning, MRI, Medical Image Processing.

References