Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept… | ScholarDeck

Paper

Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept study.

New research · Radiology

Abdominal radiology (New York) · 2w

AI / informaticsAbdominal radiology (New York)· Jul 2026

Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept study.

Olivia Gaddum, Tal Zeevi, Weicheng Dai … Julius Chapiro

Read paper

Abdominal & Body ImagingAI / informaticsQ1IF 2.7

Machine learning predicted future hepatocellular carcinoma location on prior MRI with AUC 0.80.

Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept study.

Olivia Gaddum … Julius Chapiro

Abdominal radiology (New York) · Jul 2026 · Q1 in Radiology

Purpose

This study evaluates the feasibility of machine-learning (machine-learning)-based image analysis frameworks to identify and localize hepatic parenchyma at elevated risk for hepatocellular carcinoma.

Methods

In this retrospective study, cirrhotic patients with hepatocellular carcinoma diagnosis undergoing MRI between 2008 and 2023 were included.

n = 121 patients

0.80

Results

0.80

AUROC; 1.0 is perfect, model localized future tumor sites well above chance

n = 121 patients

More results

0.66 [0.63-0.70]).

In 36 out of 121 patients (30%), heatmaps showed visually increased probability signals in the region where hepatocellular carcinoma subsequently became visible on follow-up imaging.

“

Conclusion

The results demonstrate the feasibility of machine-learning-based MRI analysis for identifying liver regions at increased risk for hepatocellular carcinoma development prior to radiologic diagnosis, particularly in the presence of precursor lesions.

Read paper