arbiter
JournalsPricingAccount

Automated Anatomical Image Annotation and Clinical Knowledge Mining With Deep Learning

Yangchao Xu & Yiwen Liu

International Journal of Healthcare Information Systems and Informatics2026https://doi.org/10.4018/ijhisi.403436article
ABDC C
Weight
0.50

What the paper says

This study proposed a bidirectional closed-loop deep learning framework integrating convolutional neural network, U-Net, and transformers to achieve automated anatomical image annotation and clinical knowledge association mining. This framework addressed issues of high manual dependency, low efficiency, and poor consistency in medical annotation. The framework enhanced semantic consistency through cross-modal feature fusion and knowledge graph alignment, while introducing sparse mapping and conflict detection feedback mechanisms to improve cross-institution generalization capabilities. Experiments demonstrated that this method achieved approximately 6% improvement in accuracy, 8–12% increase in recall, and 8–12% boost in knowledge matching rate. In clinical trials, physician annotation time decreased by an average of 18%, with clinicians showing greater preference for outputs accompanied by explanation chains. This research not only enhanced annotation efficiency and consistency but also strengthened clinical decision support capabilities, propelling medical artificial intelligence from “data-driven” to a “knowledge-empowered” approach.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.4018/ijhisi.403436

Or copy a formatted citation

@article{yangchao2026,
  title        = {{Automated Anatomical Image Annotation and Clinical Knowledge Mining With Deep Learning}},
  author       = {Yangchao Xu & Yiwen Liu},
  journal      = {International Journal of Healthcare Information Systems and Informatics},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.4018/ijhisi.403436},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Automated Anatomical Image Annotation and Clinical Knowledge Mining With Deep Learning

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.