EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Residual-Aware Feature Mapping for Anomaly Detection in Pre-Analytical Medical Specimens

Xiangjie Li, Jie Chen, Yaqin Dai

Journal of Imaging · 19.11.2026 · 12 (11) · 587

DOI: 10.3390/jimaging12110587 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 19.11.2026. Verfasst von Xiangjie Li und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates reference-based few-shot anomaly detection for pre-analytical medical specimens. Spec-ResAD forms residual features by matching each query feature to a small target-class normal reference pool, constrains the residual representation, and estimates its normal distribution with a normalizing flow. The learned feature extractor, Feature Constraintor, and Feature Distribution Estimator remain fixed for an unseen target class, while one, two, or four normal target images provide inference-time reference information. The verified hospital evaluation contains a fixed test list of 4854 images and a separate 109-image normal reference pool. Because the hospital collection has image-level hemolysis, icterus, and lipemia labels but no independent pixel-level ground truth, hospital results are reported at image level. Repeated reference selections are summarized by their mean and sample standard deviation, with the repetition unit stated for each result. The evaluation also includes MVTec data, for which official pixel masks support localization metrics. The results are interpreted descriptively under the reported protocols and do not establish statistical superiority or prospective clinical utility.

Zitieren

APA

Li, X., Chen, J., & Dai, Y. (2026). Residual-Aware Feature Mapping for Anomaly Detection in Pre-Analytical Medical Specimens. Journal of Imaging, 12(11), 587. https://doi.org/10.3390/jimaging12110587

Vancouver

Li X, Chen J, Dai Y. Residual-Aware Feature Mapping for Anomaly Detection in Pre-Analytical Medical Specimens. Journal of Imaging. 2026;12(11):587. doi:10.3390/jimaging12110587

BibTeX
@article{Li2026,
  author = {Li, Xiangjie and Chen, Jie and Dai, Yaqin},
  title = {Residual-Aware Feature Mapping for Anomaly Detection in Pre-Analytical Medical Specimens},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {11},
  pages = {587},
  doi = {10.3390/jimaging12110587}
}
Kostenlos starten →