Euri – A Deep Ensemble Architecture For Oral Lesion Segmentation And Detection
Keywords:
ResNet, UNet, Inception V3, Weighted AveragingAbstract
Oral cancer is a dreadful diseases across the globe and the sixth most cancer types ranked with high rates of mortality and morbidity. The proposed study employs a cost-effective approach using digital images that apply deep learning architectures to classify the images using segmentation techniques. The study proposes a EURI - Ensemble of Resent and Inception as a backbone on the Unet model to classify the images as Cancer. The current work consists of total of 285 Images, where 233 are cancer and 52 are non-cancer. The EURI model encompasses two variants of Resents - Resnet-34 and Resnet-101 and Inception V3 are ensembled as backbone on Unet. Thus, the classifier models are contemplated as feature extractors for the Unet. Weighted averaging is carried out on the prediction of each individual model. The model outperformed with an Intersection over Union (IOU) score of 94%.
Downloads
References
Guanghuan Yang,1,† Luqi We “A Systematic Review of Oral Biopsies, Sample Types, and Detection Techniques Applied in Relation to Oral Cancer Detection” BioTech (Basel). 2022 Mar; 11(1): 5.Published online 2022 Mar 2. doi: 10.3390/biotech11010005
María GraciaSarrión PérezaJosé V.Bagán,”Utility of imaging techniques in the diagnosis of oral cancer”,Journal of Cranio-Maxillofacial Surgery Volume 43, Issue 9,November 2015, Pages 1880-1894
Huiping Lin, Hanshen Chen,”Automatic detection of oral cancer in smartphone-based images using deep learning for early diagnosis”,J Biomed Opt. 2021 Aug; 26(8): 086007. Published online 2021 Aug 28. doi: 10.1117/1.JBO.26.8.086007
Kritsasith Warin , Wasit Limprasert “Automatic classification and detection of oral cancer in photographic images using deep learning algorithms”J Oral Pathol Med 2021 Oct;50(9):911-918. doi: 10.1111/jop.13227. Epub 2021 Aug 16.
Fahed Jubair, Omar Al-karadsheh,”A novel lightweight deep convolutional neural network for early detection of oral cancer”,26 February 2021https://doi.org/10.1111/odi.13825.
Roshan Alex Welikala , Paolo Remagnino,”Automated
Andre W Van Zyl, Belinda Bunn “Clinical features of oral cancer Sefako Makgatho Health Sciences UniversTandheelkundige VerenigingNovember 2012 SADJ: journal of the South African Dental Association = tydskrif van die Suid-Afrikaanse Tandheelkundige Vereniging 67(10):566-9.
Mohammed Shamim, Sadatullah Syed 2 , Mohammad Shible “Automated detection of oral precancerous tongue lesions using deep learning for early diagnosis of oral cavity cancer”.
DEEPORCD: Detection of Oral Cancer using Deep Learning R. Dharani and S. Revathy Journal of Physics: Conference Series 1911 (2021) 012006 IOP Publishing doi:10.1088/1742-6596/1911/1/012006.
Fati, S.M.; Senan, E.M.;Javed, Y. Early Diagnosis of Oral Squamous Cell Carcinoma Based on Histopathological Images Using Deep and Hybrid Learning Approaches. Diagnostics 2022, 12,1899. https://doi.org/10.3390/diagnostics12081899.
Jiazhi Liang ”Image classification based on RESNET “Computer technology, Northwest MuZu University, LanZhou, GanShu, China 2020 J. Phys.: Conf. Ser. 1634 012110.
Toqa A. Sadoon and Mohammad H. Ali “An Overview of Medical Images Classification based on CNN” International Journal of Current Engineering and Technology E-ISSN 2277 – 4106, P-ISSN 2347 – 5161.
A. Ramalingam et al 2020 IOP Conf. Ser.: Mater. Sci. Eng. 993 01205 Inceptionv3 Analysis of Oral Squamous Cell Carcinoma into Various Stages using Pre-Trained Convolutional Neural Networks.
Mohanad A. Deif,Hani Attar “Diagnosis of Oral Squamous Cell Carcinoma Using Deep Neural Networks and Binary Particle Swarm Optimization on Histopathological Images: An AIoMT Approach” Volume 2022 | Article ID 6364102 | https://doi.org/10.1155/2022/6364102.
Bofan Song 1 , Shaobai Li “Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images” 2022 Nov;27(11):115001. doi: 10.1117/1.JBO.27.11.115001.
Olaf Ronneberger,Philipp Fische “U-Net: Convolutional Networks for Biomedical Image Segmentation” International Conference on Medical Image Computing and Computer-Assisted Intervention.
MICCAI 2015: Medical Image Computing and Computer- Assisted Intervention – MICCAI 2015 pp 234–241.
Kaiming He, Xiangyu Zhang,”Deep Residual Learning for Image Recognition”Computer Vision and Pattern Recognition, Submitted on 10 Dec 2015 https://doi.org/10.48550/arXiv.1512.03385
Christian Szegedy,Vincent Vanhoucke “Rethinking the Inception Architecture for Computer Vision”CVPR 2016.
Kavitha Shaga Devan, Hans Kestler,“ Weighted average ensemble-based semantic segmentation in biological electron microscopy images”, DOI:10.1007/s00418-022-02148-3, Springer.
Qureshi, D. I. ., & Patil, M. S. S. . (2022). Secure Sensor Node-Based Fusion by Authentication Protocol Using Internet of Things and Rfid. Research Journal of Computer Systems and Engineering, 3(1), 48–55. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/41
Fu, J. ., & Saad, N. H. M. . (2023). Cross Border E-Commerce Uses Blockchain Technology to Solve Payment Risks. International Journal on Recent and Innovation Trends in Computing and Communication, 11(3s), 205–215. https://doi.org/10.17762/ijritcc.v11i3s.6182
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
