DermaSkan: Using Convolutional Neural Networks to Detect and Prevent Skin Cancer in Underrepresented Communities by Using an Android App
ISEF · 2023 Translational Medical Science
Overview
Artificial intelligence is becoming a more widely utilized technology in the healthcare industry to improve predictability and consistency (Science Daily). However, this powerful technology does come with some limitations, one being the datasets used usually neglect people of color (The Verge). This is problematic because the communities most affected by skin disease are people of color (The Atlantic). Skin cancer in people of color is often detected in the late stages, mostly when it is too late to consider life saving treatments. This is caused by skin tone, shortage of dermatologists, and cost of skin checks. The capabilities of artificial intelligence, such as image recognition apps, could revolutionize the dermatology industry by making it more accessible for people to get screened for several skin conditions, including cancer. After creating an app in Android studio and thoroughly testing it on two different phones (One Nord Plus N200 and Motorola Tracfone), the overall accuracy for the One Nord Plus N200 was 71.43% for screening and 48.61% for diagnosing. On the Motorola Tracfone, the overall accuracy was 77% for screening and 52.76% for diagnosing. These are both significant improvements from the machine learning model done in 2022 which had an overall accuracy of 69.33%.
Awards (1)
- University of Texas at Arlington College of Science: Scholarship of $10,000 $10,000
Competition history
- ISEF 2023
Resources
Related projects
ISEF · 2022
Using Machine Learning To Detect and Prevent Early Stages of Skin Cancer in Underrepresented Communities
ISEF · 2022
DermaTech: A Novel, Non-Invasive Technology To Detect Skin Cancer
ISEF · 2024
Improving Racial Equity in Skin Cancer Detection: Using Artificial Intelligence Driven Synthetic Image Generation and Cascading Convolutional Neural Networks to Diagnose Cancer in Lesions of Varying Skin Tones
ISEF · 2024
Rapid Screening for Major Skin Cancers with M-SCAHN: Multimodal Hierarchical CNN-Transformer Hybrid Networks with Advanced Interpretability, Lesion Evolution Tracking, Trait Identification, and Color Constancy for Improved Generalization in Diverse Populations
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair