International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Oral Deep Learning-Based Lesion Identification |
|---|---|
| ABSTRACT | Due in large part to delayed diagnosis and restricted access to specialized dental care, oral cancer continues to be a serious health concern in India. Treatment success and survival rates can be greatly increased by early detection of precancerous disorders such as erythroplakia, leukoplakia, and non-healing ulcers. An AI-powered oral lesion screening system utilizing smartphone imaging and deep learning is presented in this work. To categorize inputs as either normal or lesion-affected, A CNN, or Convolutional Neural Network is trained using labelled images of the oral cavity. A smartphone app that enables users to upload oral images and receive immediate predictions is employed to implement the trained model. The proposed system is intended to support early screening, especially in underserved areas, and is made to be affordable, easily accessible, and user-friendly. High classification performance is shown by experimental results, indicating the viability of deep learning-based tools for supporting early oral cancer detection. Oral cancer is a problem in India because people frequently discover they have it too late and they do not have easy access to special dental care. If people can discover that they have cancer early They have a higher chance of get better and live longer. Oral cancer often starts with things like leukoplakia, erythroplakia and ulcers that do not heal. If we can find these things early people will be off. This work is, about an oral lesion screening system that uses a smartphone and a computer program to help find cancer early. The system uses a smartphone to take pictures and a computer program to look at these pictures and find problems. Cancer of the mouth is an issue and This system can assist with early detection of oral cancer. The oral cavity images are used Convolutional neural network training, which's a special kind of computer program. This program is trained to look at pictures of the mouth and figure out if they are normal or if they have a lesion. A mobile application is used to put this trained program to work. This application is available to the public to send in pictures of the inside of their mouth and get an answer away. The goal of this system is to help find problems especially in places where people do not have a lot of access, to doctors and hospitals. The system is meant to be cheap and easy to use so anyone can use it to check their cavity images. The oral cavity Pictures are crucial for this system to work properly. High classification performance is shown by experimental results, indicating the viability of deep learning-based tools for supporting early oral cancer detection. |
| AUTHOR | GOWRI D K, H NIMITHA, VINUTA R G, PALLAVI G, BHOOMIKA N UG Students, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India Assistant Professor, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312130 |
| pdf/130_Oral Deep Learning-Based Lesion Identification.pdf | |
| KEYWORDS | |
| References | [1] "Image classification utilizing deep convolutional networks,"I. Sutskever, G. Hinton, and A. Krizhevsky, Advances in Neural Information Processing Systems, Developments in Systems for Neural Information Processing pp. 1097– 1105, 2012. [2] "Very deep Convolutional networks for large-scale picture recognition," K. Simonyan along with A. Zisserman, ICLR, pp. 1–14, 2015. [3] CheXNet: Deep learning for medical image analysis, S. Rajpurkar et al., Stanford ML Group, pp. 1–12, 2017. [4] S. Minaee et al., "Deep learning–based medical image classification," IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 18–36, 2020. [5] M. Jaiswal et al., "Deep learning and image processing for oral cancer detection," Journal of Medical Systems, volume 45, issue 12, pp. 1–10, 2021. [6] "Automated oral lesion detection using CNN models," Biomedical Signal Processing and Control, vol. 78, pp. 103– 122, 2022, P. D. Shenoy and R. Shetty. [7] Hussain et al., "AI-assisted oral disease identification using smartphone images," Expert Systems with Applications, vol. 210, pp. 1–16, 2023. [8] V. Bhatia and K. Rao, "Deep learning in dental and oral imaging: A thorough review," Computers in Biology and |
