slides
Gleam Multimodal Learner - HNSCC Recurrence Prediction with HANCOCK
Abstract
Introduction to GLEAM Multimodal Learner
Questions this will address
- How do we combine clinical, text, and image modalities to predict HNSCC recurrence?
- How do we configure Multimodal Learner to respect a predefined train/test split?
- How do we interpret ROC AUC and class-wise performance for recurrence prediction?
Learning Objectives
- Load HANCOCK metadata and CD3/CD8 image archives into Galaxy.
- Train a multimodal model with tabular, text, and image backbones.
- Evaluate test performance and compare to the HANCOCK benchmark.
Licence: Creative Commons Attribution 4.0 International
Keywords: Statistics and machine learning
Target audience: Students
Resource type: slides
Version: 1
Status: Active
Learning objectives:
- Load HANCOCK metadata and CD3/CD8 image archives into Galaxy.
- Train a multimodal model with tabular, text, and image backbones.
- Evaluate test performance and compare to the HANCOCK benchmark.
Date modified: 2026-03-25
Date published: 2026-03-25
Authors: Khai Van Dang, 
Jeremy Goecks, Junhao Qiu, Paulo Cilas Morais Lyra Junior
Contributors: Anup Kumar, Paulo Cilas Morais Lyra Junior, Saskia Hiltemann
Scientific topics: Statistics and probability
External resources:
Activity log
