Innovator | Entrepreneur | Podcaster| Passionate Medical Researcher |
Get started on the path for best health!
MY SMART COACH.AI
AI powered app that provides professional grade virtual yoga coach and corrects their wrong postures and avoid injuries.
Varin Senthil's Industry Insights Podcast
Having a perspective on working professions, especially their career path, and the skills that helped them succeed. Hearing directly from the experts would help motivate high schoolers to focus on the key skills and to select the appropriate career path.
My publications
Innovation in Early Identification of Brain Tumor
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
In the United States, 700,000 people are affected by brain tumors annually. Of that amount, 200,000 people are involved with some Schwannoma tumors, of which 60% are benign schwannomas, called vestibular schwannomas (acoustic neuromas). Vestibular schwannoma is a benign, slow-growing nerve brain tumor connecting the ear to the brain. 8% of schwannomas are specific to the ear nerve called acoustic neuromas. Schwannoma, at an early stage, can be removed without surgery. My schwannoma study identified a correlation between schwannoma patients and their life events. This article describes an innovative approach to identifying patients for schwannoma based on their life events.
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
Melanoma (Skin cancer) is one of the most dangerous and common diseases in the world. Correctly classifying skin lesions early in the process could aid clinical decision-making by providing an accurate diagnosis, potentially increasing the chances of curing cancer before it spreads. Healthcare has started adopting Artificial intelligence (AI) in broad applications, including dermatology. AI has the potential for the early detection of skin cancer. However, there is the likelihood of errors, which depends on many factors, including the amount and quality of the images and the details used to train the AI model. The AI platform in which machine learning models were created and operated may differ, and the complexity of the overall computing system the platform is embedded in. While in the AI's deep learning approach, the knowledge is developed based on a sample image, there is a rule-based traditional approach with business logic developed based on historical data. Business logic could be based on test results, skin colors, etc. This paper presents a comprehensive study of a hybrid approach combining the AI model with the color pigment analysis to reduce errors and improve detection accuracy. This study also discusses how the solution can be implemented in diagnosing skin cancer.
Early Identification of Ovarian Cancer
Deep learning and rules-based hybrid approach to improve the accuracy of early detection of skin cancer
Early Identification of Ovarian Cancer
Ovarian cancer is the fifth leading cause of cancer death among women 55 to 64 years old and the seventh most common cancer in the United States. Every year, 19,710 women are diagnosed, and 13-270 women die from ovarian cancer. Ovarian cancer is a cell mutation in the ovaries, creating a mass (tumor) of cancer cells. Ovarian cancer proliferates and can progress from early stages to advance in less than a year. Malignant epithelial carcinoma is the most common cancer cell form that grows out of control quickly and spreads in weeks or months. During the early cancers, the ovaries often cause no symptoms. By the time ovarian cancer symptoms are being evaluated and become evident, it usually has already spread. I summarized the study I did during my internship on the increase in IL6 receptors as an indicator of epithelial cells turning to mesenchymal (cancer cells). I also highlighted the expertise I gained in handling sample testing techniques such as Western blot, Immunofluorescence, and Elisa test.
Copyright © 2023 Varin Senthil - All Rights Reserved.
Powered by GoDaddy
This website uses cookies.
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.