qMRI enhances standard-of-care for hepatocellular carcinoma detection: proof-of-concept using Bayesian networks

Motivation: Current standard-of-care (SOC) using ultrasound and alpha fetoprotein (AFP) to detect hepatocellular carcinoma (HCC) has low specificity. Quantitative MRI (qMRI) shows promise, but is not yet widely used. Goal(s): Using Bayesian networks (BNs) to demonstrate "what if" reasoning that assess the added value of qMRI over SOC. Approach: Data from the ELEGANCE study were curated to train general linear models (GLMs) and BNs. BNs performed incremental probabilistic inference to rule out HCC. Results: Each qMRI metric increased confidence in ruling out HCC, when combined, approximately a 10% confidence boost was observed. Validation showed comparable performance between GLMs and BNs for classifying cirrhosis. Impact: qMRI information increases a clinician's confidence in ruling out HCC using either GLMs or BNs. Additionally, Bayesian networks enable incremental assessment of new metrics before the completion of data collection.

Authors

Publication Details

Journal
Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
Published
2025-09-16
DOI
https://doi.org/10.58530/2025/0110
Primary Topic
Spectroscopy Techniques in Biomedical and Chemical Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

qMRI enhances standard-of-care for hepatocellular carcinoma detection: proof-of-concept using Bayesian networks

Jason Pik Eu Chang, Wei Yang, Cheryl Min En Chua, Carmay Lim et al.
Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
Spectroscopy Techniques in Biomedical and Chemical Research
article

qMRI enhances standard-of-care for hepatocellular carcinoma detection: proof-of-concept using Bayesian networks

Jason Pik Eu Chang, Wei Yang, Cheryl Min En Chua, Carmay Lim, Daniel P. Bulte, Oi Fong Chong, Ngiap Chuan Tan, Jade Shu Qi Goh, Han Chong Toh, Pierce K. H. Chow, Kee Tung Tan, Kok Kiong Ong, Michael Brady, Yu Jun Wong, Guan Huei Lee, Sulaiha Binte Ithnin, Yichun Wang, Yu Ki Sim, Marianne Anastasia De Roza, Joan Choo, Xin Yi Yeap, Jacelyn Siou Sze Chua, Patricia Ching Yen Chia
article en

Abstract

Motivation: Current standard-of-care (SOC) using ultrasound and alpha fetoprotein (AFP) to detect hepatocellular carcinoma (HCC) has low specificity. Quantitative MRI (qMRI) shows promise, but is not yet widely used. Goal(s): Using Bayesian networks (BNs) to demonstrate "what if" reasoning that assess the added value of qMRI over SOC. Approach: Data from the ELEGANCE study were curated to train general linear models (GLMs) and BNs. BNs performed incremental probabilistic inference to rule out HCC. Results: Each qMRI metric increased confidence in ruling out HCC, when combined, approximately a 10% confidence boost was observed. Validation showed comparable performance between GLMs and BNs for classifying cirrhosis. Impact: qMRI information increases a clinician's confidence in ruling out HCC using either GLMs or BNs. Additionally, Bayesian networks enable incremental assessment of new metrics before the completion of data collection.

Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
Openalex Percentile: Top 82%
Spectroscopy Techniques in Biomedical and Chemical Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.