EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparison of Manual, Semi-Automatic, and Automatic CT-Based Methods for Liver Volume Segmentation

Berna Dogan iD, Sadik Bugrahan Simsek iD, Sefa Sonmez iD, Merve Nur Ozgen Sonmez iD, Omur Dasci, Zafer Ozmen

Diagnostics · 09.03.2026 · 16 (5) · 817

DOI: 10.3390/diagnostics16050817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 09.03.2026. Verfasst von Berna Dogan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anatomy, Faculty of Medicine, Tokat Gaziosmanpasa University, Tokat 60100, Türkiye. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: To evaluate whether semi-automatic and automatic CT-based liver segmentation methods can provide clinically acceptable volumetric agreement compared with manual segmentation while improving processing efficiency in routine practice.

Methods

CT images from 86 individuals were retrospectively analyzed. Liver volumes were calculated using manual segmentation, RVX Semi-Automatic, RVX Deep Learning, and TotalSegmentator. Differences among methods were assessed using repeated-measures ANOVA. Agreement with manual segmentation was evaluated using a Bland–Altman analysis, while the Dice Similarity Coefficient (DICE) and Hausdorff Distance (HD) quantified spatial overlap and boundary deviation, respectively. Processing times were recorded.

Results

Mean liver volumes were 1503.9 ± 356.0 cm3 (manual), 1512.6 ± 373.6 cm3 (RVX Semi-Automatic), 1549.8 ± 367.9 cm3 (RVX Deep Learning), and 1518.3 ± 365.8 cm3 (TotalSegmentator). RVX Deep Learning produced significantly higher volumes compared with manual segmentation (p < 0.001), whereas RVX Semi-Automatic and TotalSegmentator showed no significant differences (p > 0.05). DICE values were 0.911 ± 0.032, 0.946 ± 0.018, and 0.938 ± 0.021 for RVX Semi-Automatic, RVX Deep Learning, and TotalSegmentator, respectively. HD values were highest for the deep learning-based method. Processing times were shortest for RVX Deep Learning and longest for manual segmentation.

Conclusions

Semi-automatic and automatic liver segmentation methods substantially reduce processing time while maintaining clinically acceptable volumetric agreement. Among the evaluated approaches, TotalSegmentator showed the closest agreement with manual segmentation, supporting its use in routine CT-based liver volumetry. Deep learning-based segmentation, although faster, tended to overestimate volume, potentially limiting its use in applications requiring high volumetric precision.

Schlagwörter

Stichwörter der Autor:innen

automatic segmentationcomputed tomographydeep learningliver volumesemi-automatic segmentation

Autor:innen und Institutionen

  • Department of Anatomy, Faculty of Medicine, Tokat Gaziosmanpasa University, Tokat 60100, Türkiye.
  • Department of Radiology, Faculty of Medicine, Tokat Gaziosmanpasa University, Tokat 60100, Türkiye.

ORCID-Profile: Berna Dogan, Sadik Bugrahan Simsek, Sefa Sonmez, Merve Nur Ozgen Sonmez

Zitieren

APA

Dogan, B., Simsek, S. B., Sonmez, S., Ozgen Sonmez, M. N., Dasci, O., & Ozmen, Z. (2026). Comparison of Manual, Semi-Automatic, and Automatic CT-Based Methods for Liver Volume Segmentation. Diagnostics, 16(5), 817. https://doi.org/10.3390/diagnostics16050817

Vancouver

Dogan B, Simsek SB, Sonmez S, Ozgen Sonmez MN, Dasci O, Ozmen Z. Comparison of Manual, Semi-Automatic, and Automatic CT-Based Methods for Liver Volume Segmentation. Diagnostics. 2026;16(5):817. doi:10.3390/diagnostics16050817

BibTeX
@article{Dogan2026,
  author = {Dogan, Berna and Simsek, Sadik Bugrahan and Sonmez, Sefa and Ozgen Sonmez, Merve Nur and Dasci, Omur and Ozmen, Zafer},
  title = {Comparison of Manual, Semi-Automatic, and Automatic CT-Based Methods for Liver Volume Segmentation},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {5},
  pages = {817},
  doi = {10.3390/diagnostics16050817}
}
Kostenlos starten →