SEABED: Secure and Efficient AI-Based Breast Cancer Detection Using Low-Cost Edge Devices
CSEF · 2026 Medicine & Physiology (Track 2) (Senior Division)
Overview
SEABED addresses a critical gap in global healthcare: AI-powered breast cancer diagnostics exist but remain inaccessible in low-resource settings due to high hardware costs, bandwidth limitations, and patient privacy constraints. This project designs and validates a novel federated learning system enabling breast cancer detection on a $170 Raspberry Pi 5 edge node-without transmitting any raw patient imagery. Two core algorithmic innovations drive the system: (1) Frozen-Backbone Subspace Optimization, restricting deep learning to a lightweight active learning head; and (2) Top-K Gradient Sparsification with Performance-Weighted Aggregation, compressing model updates to sub-kilobyte payloads while preserving near-baseline diagnostic accuracy. A complete clinical interface with real-time malignancy classification, Grad-CAM visualization, and audible alert was validated on a physical multi-node testbed.
Competition history
- CSEF 2026
Related projects
ISEF · 2026
SEABED: Secure and Efficient AI-Based Breast Cancer Detection Using Low-Cost Edge Devices
ISEF · 2026
KARTHOS: An AI-Integrated Robotic Assistant for Early Breast Cancer Detection via Mammogram Classification, Heatmap Segmentation, and Guided Self-Examination
ISEF · 2022
Designing a Deep Learning-Based Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries
JSHS · 2024
FRISTS: A Novel AI Framework for Interpretable Heart Failure Prediction Through AI Feature Selection and Time Series Recurrent Neural Networks
ISEF · 2019
A Fast, Sensitive, and Non-Invasive Approach to Detecting Breast Cancer Using a Fully Convolutional Neural Network
CWSF · 2026
Operation Oracle: Multi-Modal, Explainable AI Systems for Accessible Cancer Detection
ISEF · 2026
Optimizing Neural Networks for Fast and Accurate Breast Cancer Detection
JSHS · 2025
An Intelligent Bee Health Assessment System Using Cross-Attention-based Multimodal Neural Network for Visual and Audio Signals
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects