LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning

Abstract Background Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-co...

Full description

Saved in:
Bibliographic Details
Main Authors: Róbert Stollmayer, Selda Güven, Christian Marcel Heidt, Kai Schlamp, Pál Novák Kaposi, Oyunbileg von Stackelberg, Hans-Ulrich Kauczor, Miriam Klauss, Philipp Mayer
Format: Article
Language:English
Published: BMC 2025-03-01
Series:Cancer Imaging
Subjects:
Online Access:https://doi.org/10.1186/s40644-025-00844-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850094828975554560
author Róbert Stollmayer
Selda Güven
Christian Marcel Heidt
Kai Schlamp
Pál Novák Kaposi
Oyunbileg von Stackelberg
Hans-Ulrich Kauczor
Miriam Klauss
Philipp Mayer
author_facet Róbert Stollmayer
Selda Güven
Christian Marcel Heidt
Kai Schlamp
Pál Novák Kaposi
Oyunbileg von Stackelberg
Hans-Ulrich Kauczor
Miriam Klauss
Philipp Mayer
author_sort Róbert Stollmayer
collection DOAJ
description Abstract Background Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-consuming. These limitations could potentially be alleviated using recent deep learning-based segmentation and classification methods such as nnU-Net. The study aims to create and evaluate an automatic segmentation model for HCC risk assessment, according to LI-RADS v2018 using nnU-Net. Methods For this single-center retrospective study, 602 patients at risk for HCC were included, who had dynamic EOB-MRI examinations between 05/2005 and 09/2022, containing ≥ LR-3 lesion(s). Manual lesion segmentations in semantic segmentation masks as LR-3, LR-4, LR-5 or LR-M served as ground truth. A set of U-Net models with 14 input channels was trained using the nnU-Net framework for automatic segmentation. Lesion detection, LI-RADS classification, and instance segmentation metrics were calculated by post-processing the semantic segmentation outputs of the final model ensemble. For the external evaluation, a modified version of the LiverHccSeg dataset was used. Results The final training/internal test/external test cohorts included 383/219/16 patients. In the three cohorts, LI-RADS lesions (≥ LR-3 and LR-M) ≥ 10 mm were detected with sensitivities of 0.41–0.85/0.40–0.90/0.83 (LR-5: 0.85/0.90/0.83) and positive predictive values of 0.70–0.94/0.67–0.88/0.90 (LR-5: 0.94/0.88/0.90). F1 scores for LI-RADS classification of detected lesions ranged between 0.48–0.69/0.47–0.74/0.84 (LR-5: 0.69/0.74/0.84). Median per lesion Sørensen–Dice coefficients were between 0.61–0.74/0.52–0.77/0.84 (LR-5: 0.74/0.77/0.84). Conclusion Deep learning-based HCC risk assessment according to LI-RADS can be implemented as automatically generated tumor risk maps using out-of-the-box image segmentation tools with high detection performance for LR-5 lesions. Before translation into clinical practice, further improvements in automatic LI-RADS classification, for example through large multi-center studies, would be desirable.
format Article
id doaj-art-3af042495bbb4ccbb8ea9a4e42552065
institution DOAJ
issn 1470-7330
language English
publishDate 2025-03-01
publisher BMC
record_format Article
series Cancer Imaging
spelling doaj-art-3af042495bbb4ccbb8ea9a4e425520652025-08-20T02:41:34ZengBMCCancer Imaging1470-73302025-03-0125111710.1186/s40644-025-00844-6LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learningRóbert Stollmayer0Selda Güven1Christian Marcel Heidt2Kai Schlamp3Pál Novák Kaposi4Oyunbileg von Stackelberg5Hans-Ulrich Kauczor6Miriam Klauss7Philipp Mayer8Clinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalDepartment of Radiology, Diskapi Yildirim Beyazit Training and Research Hospital, University of Health SciencesClinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalDepartment of Diagnostic and Interventional Radiology With Nuclear Medicine, Thoraxklinik at University of HeidelbergDepartment of Radiology, Medical Imaging Centre, Semmelweis UniversityClinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalClinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalClinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalClinic for Diagnostic and Interventional Radiology (DIR), Heidelberg University HospitalAbstract Background Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-consuming. These limitations could potentially be alleviated using recent deep learning-based segmentation and classification methods such as nnU-Net. The study aims to create and evaluate an automatic segmentation model for HCC risk assessment, according to LI-RADS v2018 using nnU-Net. Methods For this single-center retrospective study, 602 patients at risk for HCC were included, who had dynamic EOB-MRI examinations between 05/2005 and 09/2022, containing ≥ LR-3 lesion(s). Manual lesion segmentations in semantic segmentation masks as LR-3, LR-4, LR-5 or LR-M served as ground truth. A set of U-Net models with 14 input channels was trained using the nnU-Net framework for automatic segmentation. Lesion detection, LI-RADS classification, and instance segmentation metrics were calculated by post-processing the semantic segmentation outputs of the final model ensemble. For the external evaluation, a modified version of the LiverHccSeg dataset was used. Results The final training/internal test/external test cohorts included 383/219/16 patients. In the three cohorts, LI-RADS lesions (≥ LR-3 and LR-M) ≥ 10 mm were detected with sensitivities of 0.41–0.85/0.40–0.90/0.83 (LR-5: 0.85/0.90/0.83) and positive predictive values of 0.70–0.94/0.67–0.88/0.90 (LR-5: 0.94/0.88/0.90). F1 scores for LI-RADS classification of detected lesions ranged between 0.48–0.69/0.47–0.74/0.84 (LR-5: 0.69/0.74/0.84). Median per lesion Sørensen–Dice coefficients were between 0.61–0.74/0.52–0.77/0.84 (LR-5: 0.74/0.77/0.84). Conclusion Deep learning-based HCC risk assessment according to LI-RADS can be implemented as automatically generated tumor risk maps using out-of-the-box image segmentation tools with high detection performance for LR-5 lesions. Before translation into clinical practice, further improvements in automatic LI-RADS classification, for example through large multi-center studies, would be desirable.https://doi.org/10.1186/s40644-025-00844-6Hepatocellular carcinomaMultiparametric MRIDeep learningClinical guidelines
spellingShingle Róbert Stollmayer
Selda Güven
Christian Marcel Heidt
Kai Schlamp
Pál Novák Kaposi
Oyunbileg von Stackelberg
Hans-Ulrich Kauczor
Miriam Klauss
Philipp Mayer
LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
Cancer Imaging
Hepatocellular carcinoma
Multiparametric MRI
Deep learning
Clinical guidelines
title LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
title_full LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
title_fullStr LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
title_full_unstemmed LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
title_short LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
title_sort li rads based hepatocellular carcinoma risk mapping using contrast enhanced mri and self configuring deep learning
topic Hepatocellular carcinoma
Multiparametric MRI
Deep learning
Clinical guidelines
url https://doi.org/10.1186/s40644-025-00844-6
work_keys_str_mv AT robertstollmayer liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT seldaguven liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT christianmarcelheidt liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT kaischlamp liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT palnovakkaposi liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT oyunbilegvonstackelberg liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT hansulrichkauczor liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT miriamklauss liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning
AT philippmayer liradsbasedhepatocellularcarcinomariskmappingusingcontrastenhancedmriandselfconfiguringdeeplearning