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-Scan AI: A Convolutional Neural Network Based Framework for Early Oral Cancer Risk Assessment in Remote Healthcare Settings |
|---|---|
| ABSTRACT | Oral cancer claims a disproportionate number of lives in areas where trained specialists and diagnostic machinery remain scarce. This paper presents OralScan AI, a web-based screening platform engineered to support preliminary oral cancer risk assessment by combining deep learning image analysis with structured patient symptom data. The system uses a pre-trained Convolutional Neural Network to classify uploaded oral cavity photographs as either high risk or low risk, while simultaneously processing eleven patient-reported clinical indicators. Unlike tools that depend on a single data source, OralScan AI withholds classification until both an image and a completed symptom questionnaire are provided, reducing the likelihood of misleading outputs from incomplete inputs. Beyond classification, the platform stores every patient submission permanently, generates downloadable PDF reports with structured clinical observations, and maintains separate role-specific dashboards for patients and physicians. A built-in asynchronous messaging module supports follow- up consultation without requiring external communication tools. The backend is built on Flask for request handling, TensorFlow for neural network inference, and PostgreSQL for persistent data storage. Functional testing on standard computing hardware confirms that the complete screening workflow — from image upload through report delivery — completes within a few seconds. The system is intended to reduce the diagnostic delay experienced by patients in rural and underserved regions by bringing a credible first-level screening tool within reach of anyone with a smartphone and internet access. |
| AUTHOR | KEERTHI MANJUNATH GEDDAPPANAVAR, POOJA N ANNIGERE, MADHU HIREGOUDA SANKOLLI, MALA P, PROF. ARCHANA K 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 | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404076 |
| pdf/76_Oral-Scan AI A Convolutional Neural Network Based Framework for Early Oral Cancer Risk Assessment in Remote Healthcare Settings.pdf | |
| KEYWORDS | |
| References | [1] P. Gupta and S. Warnakulasuriya, "Global epidemiology of areca nut usage and its association with oral cancer: A ten-year systematic review," Journal of Oral Pathology & Medicine, vol. 51, no. 3, pp. 221–233, 2022. [2] R. Sankaranarayanan, K. Ramadas, and G. Thara, "Clinical trials of screening for oral cancer: A systematic review and meta-analysis," Oral Oncology, vol. 112, art. no. 105418, 2021. [3] D. J. Kim, S. Y. Lee, and J. H. Park, "Comparative analysis of image-based versus questionnaire- based oral cancer screening applications: A usability study," JMIR mHealth and uHealth, vol. 9, no. 8, e28945, 2021. [4] A. S. Bhatia, M. K. Singh, and R. K. Sharma, "Longitudinal photographic monitoring of oral potentially malignant disorders: A systematic review," Clinical Oral Investigations, vol. 26, no. 4, pp. 3415–3429, 2022. [5] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. W. M. van der Laak, B. van Ginneken, and C. I. Sánchez, "A survey on deep learning in medical image analysis," Medical Image Analysis, vol. 42, pp. 60–88, 2017. [6] P. D. Quinn, D. K. Lam, and J. C. Irish, "Anatomical subsites of the oral cavity and oropharynx: A clinical guide," Oral and Maxillofacial Surgery Clinics of North America, vol. 31, no. 4, pp. 551–564, 2019. [7] B. W. Neville, D. D. Damm, C. M. Allen, and A. C. Chi, Oral and Maxillofacial Pathology, 4th ed. St. Louis, MO, USA: Elsevier, 2016, pp. 322–335. [8] Y. Gal and Z. Ghahramani, "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning," in Proc. 33rd Int. Conf. Machine Learning (ICML), New York, NY, USA, 2016, pp. 1050–1059. |
