Identification and Classification of Oral Cancer Using  Convolution Neural Network

Mohammad Shahriyaar Najar; Jasdeep Singh

doi:10.55524/

Authors

Mohammad Shahriyaar Najar M. Tech Scholar, Department of Computer Science and Engineering, RIMT University, Mandi Gobindgarh, Punjab, India Author
Jasdeep Singh Professor, Department of computer science and Engineering, RIMT University, Mandi Gobindgarh, Punjab, India Author

DOI:

https://doi.org/10.55524/

Keywords:

CNN, VGG, Oral Cancer

Abstract

Even though it has proven challenging to achieve, computerised categorization of cell pictures into fit and aggressive cells would be a crucial tool in diagnostic procedures. It has been demonstrated that texture detection and processing are extremely efficient for a variety of picture categorization algorithms. Recent articles have made use of Dense Networks (DENSENETs), a texture based method that has shown to have a lot of potential. Some of these variations employ convolutional neural networks using DENSENETs (CNNs). This work modifies modern texture analysis CNN structures, three, and two of which are based on DENSENETs, to recognize pictures from a collection including both healthy and oral cancer cells. Results from Wieslander and Forslid's use of ResNet and VGG architectures, which weren't designed with texture detection in mind, to use as a benchmark. Our research shows that DENSENET-Embedded CNNs outperform conventional CNNs for this job designs. The performance model by Juefei-Xu ET altop exceeded the best reference model by 0.5 percent in accuracy and 9 percent in F1-score. It had an accuracy of 81.03 percent and an F1-score of 84.85 percent.

Downloads

Download data is not yet available.

References

. Kaiming He, XiangyuZhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.

. FelixJuefei Xu, Vishnu Naresh Boddeti, and MariosSavvides. Local binary convolutional neural networks (lbcnn). https://github.com/juefeix/ lbcnn.torch, 2016.

. Felix Juefei-Xu, Vishnu Naresh Boddeti, and MariosSavvides. Local binary convolutional neural networks. In Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on, volume 1. IEEE, 2017.

. Gil Levi and Tal Hassner. Emotion recognition in the wild via convolutional neural networks and mapped binary patterns. In Proceedings of the 2015 ACM International Conference on Multimodal Interaction, pages 503–510. ACM, 2015.

. Lei Li, Xiaoyi Feng, Zhaoqiang Xia, Xiaoyue Jiang, and Abdenour Hadid. Face spoofing detection with local binary pattern network. Journal of Visual Communication and Image Representation, 54:182–192, 2018.

. LiLiu, Paul Fieguth, Yulan Guo, Xiaogang Wang, and Matti Pietik¨ainen. Local binary features for texture classification: taxonomy and experimental study. Pattern Recognition, 62:135–160, 2017.

. LiLiu, Songyang Lao, Paul W Fieguth, Yulan Guo, Xiaogang Wang, and Matti Pietik¨ainen. Median robust extended local binary pattern for texture classification. IEEE Transactions on Image Processing, 25(3):1368–1381, 2016.

. Diego Marcos, Michele Volpi, Nikos Komodakis, and Devis Tuia. Rotation equivariant vector field networks. In ICCV, pages 5058–5067, 2017.

. Diego Marcos, Michele Volpi, and Devis Tuia. Learning rotation invariant convolutional filters for texture classification. In Pattern Recognition (ICPR), 2016 23rd International Conference on, pages 2012–2017. IEEE, 2016.

. Timo Ojala, Matti Pietik¨ainen, and David Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51–59, 2016.

. TimoOjala, Matti Pietikainen, and Topi Maenpaa. Multiresolution grayscale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7):971– 987, 2002.

. PeterSasieni,Alejandra Castanon, and Jack Cuzick. Effectiveness of cervical screening with age: population based case-control study of prospectively recorded data. BMJ, 339:b2968, 2009.

. Olivier Simon, Rabi Yacoub, Sanjay Jain, John E Tomaszewski, and Pinaki Sarder. Multi-radial DENSENET features as a tool for rapid glomerular detection and assessment in whole slide histopathology images. Scientific Reports, 8(1):2032, 2018.