HALO: A Novel Multimodal Approach for 3D Radiomic Diagnosis and Prognosis of Central Nervous System Tumors
CSEF · 2023 Mammalian Biology Honorable_mention Award
Overview
Despite advances in radiomics, diagnosis and prognosis of central nervous system (CNS) cancers rely on manual and algorithmic approaches that are subject to inefficiencies and bias. With 5-year survival rates as low as 6%, timely tumor assessment is crucial to ensure patient health. However, manual analyses use 2D, rather than 3D, magnetic resonance images (MRIs), which may misrepresent a tumor’s spatial distribution. On the other hand, automated deep learning models overfit on high amounts of data, making them unfit for global, real-world use. This project is the first to develop a multi-phase neural network using 3D MRIs to reliably and simultaneously classify tumor severity and predict survival prognosis. The framework achieved an accuracy of 98%, surpassing industry benchmark architecture. Over 900,000 3D MRIs from several institutions were used to reduce overfitting and equally represent minority demographics, creating a democratized tool for developing nations that have a limited collection of representative population data. With only 18 convolutional layers, the framework is extremely computationally efficient for use in the field. Several models were integrated into the HALO mobile device to create a practical and end-to-end tool for clinicians. HALO will help doctors globally plan treatment interventions even with limited resources.
Source coverage
This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.
Awards (1)
- Category Award: HM
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2023
NueROX: A Visual Diagnosing System Using a Fully Optimized Convolutional Neural Network Architecture for Rapid and Efficient Classification of Tumorous and Non-Tumorous Brain MRI's and a Model for the Segmentation, Dimension, and Severity Estimation of Brain Tumors
ISEF · 2024
Predictive Modeling of Brain Tumor Evolution and Anatomical Invasion: A Novel 3D Time Series Forecasting Approach for Enhanced Treatment Planning
ISEF · 2025
A Novel Convolutional Neural Network to Detect and Classify Brain Tumors
ISEF · 2021
Heuristic Oncological Prognosis Evaluator (HOPE): A Novel Approach Implementing a Deep Learning Convolutional Neural Network Framework to Detect Brain Cancer, Breast Cancer, Colorectal Cancer, and Lung Cancer
ISEF · 2018
Deep, Multimodal Representation Learning for Pan-Cancer Prognosis Prediction
CSEF · 2026
3D MRI Inpainting for Structural Reconstruction of Brain Tumor Regions via Composite Spatial–Frequency Optimization
ISEF · 2024
Volumetric Segmentation and Multimodal Classification of Brain Tumors Using Point Sampling and 3D CNNs
ISEF · 2022
Artificial Intelligence Solution for Effective Treatment Planning for Brain Tumor Patients
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects