EUVIMEDEUVIMED entdecken
Crossref

Deep Learning for Abdominal Multi-Organ Segmentation: Methods, Evaluation, and Clinical Translation

B.M. Daxini, K.H. Parmar, D.C. Shreegod, V.P. Solanki

International Journal of Drug Delivery Technology · 19.05.2026 · 16 (30s)

DOI: 10.25258/ijddt.16.30s.30 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 19.05.2026. Verfasst von B.M. Daxini und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Abdominal multi-organ segmentation has become a core task in computer-aided diagnosis, radiotherapy planning, surgical navigation, and quantitative imaging. Over the last decade, the field has progressed from classical encoder-decoder convolutional networks to self-configuring pipelines, cascaded refinement strategies, adversarial learning frameworks, and transformer-based models. Despite this progress, benchmark accuracy alone is no longer sufficient to judge the real value of a method. A meaningful review must connect reported performance with dataset heterogeneity, small-organ behavior, computational cost, calibration, uncertainty, and reproducibility. This review synthesizes representative literature on abdominal CT segmentation, with selective reference to adjacent CT-MR benchmarks when they inform transferability and robustness. We discuss public datasets, evaluation metrics, major architectural families, loss formulations, semi-supervised and domain-adaptive learning strategies, and reporting practices that support reproducible comparison. The reviewed literature suggests that coarse-to-fine and patch-refinement pipelines remain especially effective for small or low-contrast organs, whereas transformer and hybrid models improve global context at the cost of greater computational demand. We conclude that abdominal multi-organ segmentation is not a solved problem, particularly under scanner shift, partial supervision, and limited-resource deployment, and that future progress will depend as much on reliable evaluation and clinically meaningful reporting as on architectural novelty [1]–[6], [11]–[20].

Zitieren

APA

Daxini, B., Parmar, K., Shreegod, D., & Solanki, V. (2026). Deep Learning for Abdominal Multi-Organ Segmentation: Methods, Evaluation, and Clinical Translation. International Journal of Drug Delivery Technology, 16(30s). https://doi.org/10.25258/ijddt.16.30s.30

Vancouver

Daxini B, Parmar K, Shreegod D, Solanki V. Deep Learning for Abdominal Multi-Organ Segmentation: Methods, Evaluation, and Clinical Translation. International Journal of Drug Delivery Technology. 2026;16(30s). doi:10.25258/ijddt.16.30s.30

BibTeX
@article{Daxini2026,
  author = {Daxini, B.M. and Parmar, K.H. and Shreegod, D.C. and Solanki, V.P.},
  title = {Deep Learning for Abdominal Multi-Organ Segmentation: Methods, Evaluation, and Clinical Translation},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {30s},
  doi = {10.25258/ijddt.16.30s.30}
}
Kostenlos starten →