Oral Cavity Cancer Detection Using Machine Learning

Project Title

Oral Cavity Cancer Detection Using Machine Learning

Project Area of Specialization Artificial IntelligenceProject Summary

The overall prognosis of oral cancer remains poor because over half of patients are diagnosed at

advanced-stages. Previously reported screening and earlier detection methods for oral cancer still largely rely on health workers clinical experience and as yet there is no established method. We aim to develop a rapid, non-invasive, cost-effective, and easy-to-use Machine learning approach for identifying oral cavity squamous cell carcinoma (OCSCC) patients using photographic images.

The User will upload a picture of oral cavity and our trained data will be used to detect newly comes data and generate results whether the user has oral cavity cancer or not.

Project Objectives

The overall prognosis of oral cancer remains poor because over half of patients are diagnosed at

advanced-stages. Previously reported screening and earlier detection methods for oral cancer still largely rely on health workers clinical experience and as yet there is no established method. We aim to develop a rapid, non-invasive, cost-effective, and easy-to-use Machine learning approach for identifying oral cavity squamous cell carcinoma (OCSCC) patients using photographic images.

The User will upload a picture of oral cavity and our trained data will be used to detect newly comes data and generate results whether the user has oral cavity cancer or not.

Project Implementation Method

We will train dataset using Machine learning algorithm to detect OCSCC from photographic images. We included total 1224 images. Images are divided into two sets in two different resolutions. First set composed of 89 histopathological images with the normal epithelium of the oral cavity and 439 images of Oral Squamous Cell Carcinoma (OSCC) in 100x magnification. The second set consists of 201 images with the normal epithelium of the oral cavity and 495 histopathological images of OSCC in 400x magnifications. The images were captured using a Leica ICC50 HD microscope from H&E stained tissue slides collected, prepared and catalogued by medical experts from 230 patients. We will train the algorithm on a randomly selected part of this dataset (development dataset) and used the rest for testing (internal validation dataset).

Benefits of the Project

This project will help in solving all the problems in existing system of Oral Cavity Cancer detection. In existing system Oral Cavity Cancer detection is done in laboratory which is too time consuming and having chances of human error and many problems will be faced by the user. So, this project will help to detect oral cavity cancer by trained machine learning, the user has to upload image of oral cavity in web site and no problem will be faced by the user. The user can easily find results in any time in a few seconds, and it will save time too for the laboratory.

Technical Details of Final Deliverable

The database of the program will be connected with a dynamic web page and the user first must sign in or register the account to use the program. The signing in process is very simple the user will have to provide a user name and   password to enter the page and to register the user will have to provide an email address and a user name and then choose a PIN or a password.

Once the user has logged in using his credentials then the user can upload an image and check the result using the program. The user can also see his previous results that he or she has already used .The page will also provide the user with the option of contacting a certified doctor if he needs the details of the doctor will be provided on the webpage.

Final Deliverable of the Project Software SystemCore Industry MedicalOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development GoalsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	10000
Domain	Miscellaneous	1	10000	10000