EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning for automatic detection of hepatocellular carcinoma in dynamic contrast-enhanced MRI

Killian Monnin, Patrick Jeltsch, Lucia Fernandes-Mendes, Vasco Cazzagon, Marianna Gulizia, Mario Jreige, Montserrat Fraga Christinet, Raphael Girardet, Clarisse Dromain, Jonas Richiardi, Naik Vietti-Violi

Abdominal Radiology · 2025

DOI: 10.1007/s00261-025-05249-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, 2025. Verfasst von Killian Monnin und 10 weiteren Autor:innen. Beteiligte Einrichtung: University of Lausanne, Lausanne, Switzerland. killian.monnin@chuv.ch. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Liver Neoplasms, Contrast Media, Deep Learning. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Lausanne.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Develop a deep learning model for automatic hepatocellular carcinoma (HCC) detection in T1 weighted imaging (WI) Dynamic Contrast-Enhanced (DCE) liver MRI using extracellular contrast agent, and to analyze its performance at both patient and lesion levels. Materials and methods This retrospective study included two cohorts, the first included patients ( N = 296) undergoing HCC surveillance with diagnosed HCC as well as negative cases. The 233 HCC negative patients and 12 HCC positive patients were used to create the HCC Surveillance test set, aiming to evaluate patient level performance on simulated screening conditions. The second included Pre-Ablation patients ( N = 67), all positive for HCC, used as test set for lesion level evaluation and to measure generalization performance. The two largest public liver lesion datasets (CT, N = 1037 and MRI, N = 485) were used for pre-training the algorithms. An attention U-Net model was trained to segment and detect HCC and was compared to the state-of-art nnU-Netv2. Diagnostic accuracy was evaluated using sensitivity, specificity, mean false positives per patient, PPV and NPV, the Area Under the Curve (AUC) of the Free-Response Operating Characteristic (FROC) curves and the Receiver Operating Characteristic (ROC) curves.

Results

The final population included 363 patients (58 ± 11 years; 284 men; 247 lesions): 51 HCC positive patients (113 lesions) used in training set, 245 patients (12 HCC positive with 21 lesions, 233 HCC negative) in the HCC Surveillance testing set, 67 HCC positive patients (113 lesions) in the HCC Pre-Ablation testing set. At patient level, 83% sensitivity and 72% specificity [AUC of 0.80 (95% CI: 0.66–0.91)] was measured on the HCC Surveillance test set. At lesion level, 80% of sensitivity for a mean false positive per patient of 1 was measured on the HCC Pre-Ablation test set with the pre-trained model with a FROC AUC of 0.82 (95% CI: 0.77–0.88), significantly outperforming the nnU-Netv2 at 0.61 (95% CI: 0.52–0.69, p < 0.01).

Conclusions

Both patient-level and lesion-level achieved 80% HCC detection sensitivity by using a deep learning segmentation neural network pre-trained from large open datasets. This performance highlights the translational potential of such tools in the clinical workup of patients at risk of HCC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularLiver NeoplasmsContrast MediaDeep LearningMagnetic Resonance ImagingImage Interpretation, Computer-AssistedHumansMaleRetrospective StudiesFemaleMiddle AgedSensitivity and SpecificityAgedImage EnhancementAdult

Stichwörter der Autor:innen

HCCLesion detectionLiverMRIMachine learning

Substanzen

Contrast Media

Autor:innen und Institutionen

  • University of Lausanne, Lausanne, Switzerland. killian.monnin@chuv.ch.
  • Department of Radiology, Lausanne University Hospital, Lausanne, Switzerland. killian.monnin@chuv.ch.
  • Department of Radiology, Lausanne University Hospital, Lausanne, Switzerland.
  • University of Lausanne, Lausanne, Switzerland.
  • Department of Gastro-enterology, Lausanne University Hospital, Lausanne, Switzerland.
  • Department of Radiology, South Metropolitan Health Service, Murdoch, Australia.

Förderung

  • University of Lausanne

Zitieren

APA

Monnin, K., Jeltsch, P., Fernandes-Mendes, L., Cazzagon, V., Gulizia, M., Jreige, M., Fraga Christinet, M., Girardet, R., Dromain, C., Richiardi, J., & Vietti-Violi, N. (2025). Deep learning for automatic detection of hepatocellular carcinoma in dynamic contrast-enhanced MRI. Abdominal Radiology. https://doi.org/10.1007/s00261-025-05249-4

Vancouver

Monnin K, Jeltsch P, Fernandes-Mendes L, Cazzagon V, Gulizia M, Jreige M, et al. Deep learning for automatic detection of hepatocellular carcinoma in dynamic contrast-enhanced MRI. Abdominal Radiology. 2025. doi:10.1007/s00261-025-05249-4

BibTeX
@article{Monnin2025,
  author = {Monnin, Killian and Jeltsch, Patrick and Fernandes-Mendes, Lucia and Cazzagon, Vasco and Gulizia, Marianna and Jreige, Mario and Fraga Christinet, Montserrat and Girardet, Raphael and Dromain, Clarisse and Richiardi, Jonas and Vietti-Violi, Naik},
  title = {Deep learning for automatic detection of hepatocellular carcinoma in dynamic contrast-enhanced MRI},
  journal = {Abdominal Radiology},
  year = {2025},
  doi = {10.1007/s00261-025-05249-4}
}
Kostenlos starten →