Operation Oracle: Multi-Modal, Explainable AI Systems for Accessible Cancer Detection
CWSF · 2026 Disease & Illness Silver Medal
Overview
Cancer is often deadly, not always because it cannot be treated, but because it is found too late. In this project, I built two low-cost systems that use artificial intelligence to help detect cancer earlier. One system analyzes images of skin to find signs of skin cancer, while the other uses sound and signals to detect problems inside the lungs. I then combined both the acoustic and microwave subsystems into one model that learns from different types of information at the same time. The combined system was much more accurate than using just one method alone, showing how different types of data can work better together. This project demonstrates the potential for powerful, affordable, and easy-to-understand tools to improve access to early cancer detection, especially in communities where medical resources are limited and access to specialists is especially difficult.
Awards (2)
- Silver Medal
- Selected for CWSF 2026
Competition history
- CWSF 2026
Related projects
ISEF · 2025
Low-Cost Portable Device for At-Home Early Multi-Cancer Detection Using Bioimpedance and Multispectral Imaging Technologies
ISEF · 2024
A Holistic Multi-Modal GenAI System: Early Detection and Predictive Treatment Monitoring Using Chest X-rays and Cough Audio for Tuberculosis
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
ISEF · 2022
Using Machine Learning To Detect and Prevent Early Stages of Skin Cancer in Underrepresented Communities
Closest projects by meaning, across every fair and year in the corpus.