EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Automatic localization and deep convolutional generative adversarial network‐based classification of focal liver lesions in computed tomography images: A preliminary study

Pushpanjali Gupta iD, Yao-Chun Hsu, Li-Lin Liang, Yuan-Chia Chu, Chia-Sheng Chu iD, Jaw-Liang Wu, Jian-An Chen, Wei-Hsiu Tseng, Ya-Ching Yang, Teng-Yu Lee iD, Che-Lun Hung, Chun-Ying Wu

Journal of Gastroenterology and Hepatology · 2025

DOI: 10.1111/jgh.16803 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Gastroenterology and Hepatology, 2025. Verfasst von Pushpanjali Gupta und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Translational Research, Taipei Veterans General Hospital, Taipei, Taiwan. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Deep Learning, Liver, Liver Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Aim Computed tomography of the abdomen exhibits subtle and complex features of liver lesions, subjectively interpreted by physicians. We developed a deep learning‐based localization and classification (DLLC) system for focal liver lesions (FLLs) in computed tomography imaging that could assist physicians in more robust clinical decision‐making.

Methods

We conducted a retrospective study (approval no. EMRP‐109‐058) on 1589 patients with 17 335 slices with 3195 FLLs using data from January 2004 to December 2020. The training set included 1272 patients (male: 776, mean age 62 ± 10.9), and the test set included 317 patients (male: 228, mean age 57 ± 11.8). The slices were annotated by annotators with different experience levels, and the DLLC system was developed using generative adversarial networks for data augmentation. A comparative analysis was performed for the DLLC system versus physicians using external data.

Results

Our DLLC system demonstrated mean average precision at 0.81 for localization. The system's overall accuracy for multiclass classifications was 0.97 (95% confidence interval [CI]: 0.95–0.99). Considering FLLs ≤ 3 cm, the system achieved an accuracy of 0.83 (95% CI: 0.68–0.98), and for size > 3 cm, the accuracy was 0.87 (95% CI: 0.77–0.97) for localization. Furthermore, during classification, the accuracy was 0.95 (95% CI: 0.92–0.98) for FLLs ≤ 3 cm and 0.97 (95% CI: 0.94–1.00) for FLLs > 3 cm.

Conclusion

This system can provide an accurate and non‐invasive method for diagnosing liver conditions, making it a valuable tool for hepatologists and radiologists.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedDeep LearningLiverLiver NeoplasmsLiver DiseasesHumansMaleMiddle AgedRetrospective StudiesFemaleAgedAdultGenerative Adversarial Networks

Stichwörter der Autor:innen

artificial intelligenceearly diagnostic toolfocal liver lesionsgenerative adversarial networkhepatocellular carcinoma

Autor:innen und Institutionen

  • Division of Translational Research, Taipei Veterans General Hospital, Taipei, Taiwan.
  • Health Innovation Center, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Institute of Biomedical Informatics, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Institute of Public Health, National Yang Ming Chiao Tung University, Taipei, Taiwan.
  • Division of Gastroenterology and Hepatology, E-DA Hospital, Kaohsiung, Taiwan.
  • School of Medicine, I-Shou University, Kaohsiung, Taiwan.

ORCID-Profile: Pushpanjali Gupta, Chia-Sheng Chu, Teng-Yu Lee

Förderung

  • National Science and Technology Council

Zitieren

APA

Gupta, P., Hsu, Y. C., Liang, L. L., Chu, Y. C., Chu, C. S., Wu, J. L., Chen, J. A., Tseng, W. H., Yang, Y. C., Lee, T. Y., Hung, C. L., & Wu, C. Y. (2025). Automatic localization and deep convolutional generative adversarial network‐based classification of focal liver lesions in computed tomography images: A preliminary study. Journal of Gastroenterology and Hepatology. https://doi.org/10.1111/jgh.16803

Vancouver

Gupta P, Hsu YC, Liang LL, Chu YC, Chu CS, Wu JL, et al. Automatic localization and deep convolutional generative adversarial network‐based classification of focal liver lesions in computed tomography images: A preliminary study. Journal of Gastroenterology and Hepatology. 2025. doi:10.1111/jgh.16803

BibTeX
@article{Gupta2025,
  author = {Gupta, Pushpanjali and Hsu, Yao-Chun and Liang, Li-Lin and Chu, Yuan-Chia and Chu, Chia-Sheng and Wu, Jaw-Liang and Chen, Jian-An and Tseng, Wei-Hsiu and Yang, Ya-Ching and Lee, Teng-Yu and Hung, Che-Lun and Wu, Chun-Ying},
  title = {Automatic localization and deep convolutional generative adversarial network‐based classification of focal liver lesions in computed tomography images: A preliminary study},
  journal = {Journal of Gastroenterology and Hepatology},
  year = {2025},
  doi = {10.1111/jgh.16803}
}
Kostenlos starten →