Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning

Ahmet Said Kucukkaya, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Tal Zeevi, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Nathan Xianming Chai, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Rajiv Raju, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Stefan Philipp Haider, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Mohamed Elbanan, Department of Diagnostic Radiology, Bridgeport Hospital, Yale New Haven Health System, 267 Grant Street, Bridgeport, CT, 06610, USA.
Alexandra Petukhova-Greenstein, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
MingDe Lin, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
John Onofrey, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Michal Nowak, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Kirsten Cooper, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Elizabeth Thomas, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Jessica Santana, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Bernhard Gebauer, Institute of Radiology, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität, and Berlin Institute of Health, Augustenburger Platz 1, 13353, Berlin, Germany.
David Mulligan, Transplantation and Immunology, Department of Surgery, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA.
Lawrence Staib, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA.
Ramesh Batra, Transplantation and Immunology, Department of Surgery, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA.
Julius Chapiro, Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 330 Cedar Street, New Haven, CT, 06520-8042, USA. julius.chapiro@yale.edu.

Document Type

Article

Publication Title

Scientific reports

Abstract

Tumor recurrence affects up to 70% of early-stage hepatocellular carcinoma (HCC) patients, depending on treatment option. Deep learning algorithms allow in-depth exploration of imaging data to discover imaging features that may be predictive of recurrence. This study explored the use of convolutional neural networks (CNN) to predict HCC recurrence in patients with early-stage HCC from pre-treatment magnetic resonance (MR) images. This retrospective study included 120 patients with early-stage HCC. Pre-treatment MR images were fed into a machine learning pipeline (VGG16 and XGBoost) to predict recurrence within six different time frames (range 1-6 years). Model performance was evaluated with the area under the receiver operating characteristic curves (AUC-ROC). After prediction, the model's clinical relevance was evaluated using Kaplan-Meier analysis with recurrence-free survival (RFS) as the endpoint. Of 120 patients, 44 had disease recurrence after therapy. Six different models performed with AUC values between 0.71 to 0.85. In Kaplan-Meier analysis, five of six models obtained statistical significance when predicting RFS (log-rank p < 0.05). Our proof-of-concept study indicates that deep learning algorithms can be utilized to predict early-stage HCC recurrence. Successful identification of high-risk recurrence candidates may help optimize follow-up imaging and improve long-term outcomes post-treatment.

First Page

7579

DOI

10.1038/s41598-023-34439-7

Publication Date

5-10-2023

Identifier

37165035 (pubmed); PMC10172370 (pmc); 10.1038/s41598-023-34439-7 (doi); 10.1038/s41598-023-34439-7 (pii)

This document is currently not available here.

Share

COinS