DITTO: A Visual Digital Twin for Interventions and Temporal Treatment Outcomes in Head and Neck Cancer

Andrew Wentzel; Serageldin Attia; Xinhua Zhang; Guadalupe Canahuate; Clifton David Fuller; G.Elisabeta Marai

doi:10.1109/TVCG.2024.3456160

Back

DITTO: A Visual Digital Twin for Interventions and Temporal Treatment Outcomes in Head and Neck Cancer

Journal article

Peer reviewed

DITTO: A Visual Digital Twin for Interventions and Temporal Treatment Outcomes in Head and Neck Cancer

Andrew Wentzel, Serageldin Attia, Xinhua Zhang, Guadalupe Canahuate, Clifton David Fuller and G.Elisabeta Marai

IEEE transactions on visualization and computer graphics, Vol.31(1), pp.65-75

01/2025

DOI: 10.1109/TVCG.2024.3456160

PMCID: PMC11879760

PMID: 39255169

Files and links (1)

url

https://pmc.ncbi.nlm.nih.gov/articles/PMC11879760/pdf/nihms-2022365.pdfView

Open Access

Abstract

Digital twin models are of high interest to Head and Neck Cancer (HNC) oncologists, who have to navigate a series of complex treatment decisions that weigh the efficacy of tumor control against toxicity and mortality risks. Evaluating individual risk profiles necessitates a deeper understanding of the interplay between different factors such as patient health, spatial tumor location and spread, and risk of subsequent toxicities that can not be adequately captured through simple heuristics. To support clinicians in better understanding tradeoffs when deciding on treatment courses, we developed DITTO, a digital-twin and visual computing system that allows clinicians to analyze detailed risk profiles for each patient, and decide on a treatment plan. DITTO relies on a sequential Deep Reinforcement Learning digital twin (DT) to deliver personalized risk of both long-term and short-term disease outcome and toxicity risk for HNC patients. Based on a participatory collaborative design alongside oncologists, we also implement several visual explainability methods to promote clinical trust and encourage healthy skepticism when using our system. We evaluate the efficacy of DITTO through quantitative evaluation of performance and case studies with qualitative feedback. Finally, we discuss design lessons for developing clinical visual XAI applications for clinical end users.

Details

Title: Subtitle: DITTO: A Visual Digital Twin for Interventions and Temporal Treatment Outcomes in Head and Neck Cancer
Creators: Andrew Wentzel - University of Illinois Chicago
Serageldin Attia - The University of Texas MD Anderson Cancer Center
Xinhua Zhang - University of Illinois Chicago
Guadalupe Canahuate - University of Iowa
Clifton David Fuller - University of Illinois Chicago
G.Elisabeta Marai - University of Illinois Chicago
Resource Type: Journal article
Publication Details: IEEE transactions on visualization and computer graphics, Vol.31(1), pp.65-75
DOI: 10.1109/TVCG.2024.3456160
PMID: 39255169
PMCID: PMC11879760
NLM abbreviation: IEEE Trans Vis Comput Graph
ISSN: 1077-2626
eISSN: 1941-0506
Language: English
Electronic publication date: 2024
Date published: 01/2025
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984702846102771

Metrics

10 Record Views