EUVIMEDEUVIMED entdecken
Crossref

SSPF-Net: Learning Organ Shape-Aware and Self-Calibration Prototypes for Few-Shot Medical Image Segmentation

Shihao Zheng, Huisi Wu

IEEE Transactions on Automation Science and Engineering · 2026 · 23 · 8362-8372

DOI: 10.1109/tase.2026.3684495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2026. Verfasst von Shihao Zheng und 1 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, China, Shenzhen Research Foundation for Basic Research, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot medical image segmentation is a promising solution for scarce data scenarios, especially for medical classes with limited labeled data. However, there are still several flaws in the current few-shot medical image segmentation methods. The diversity of the base classes in the training stage is insufficient, so it is still difficult to train a model with strong generalization through a large number of images and classes like natural images. Besides, due to the discrepancy between the query and support images, relying solely on representative prototypes from support features fails to handle intra-class variability. In this paper, we propose a novel network with an organ shape-aware module (OSA) to optimize the prototype-based network and enhance the model’s generalization ability. Specifically, the OSA is designed to obtain a variable number of prototypes that contain the shape and edge information of the organ. Compared with general models using fixed-shape prototypes, the prototypes obtained by our OSA are more precise and informative. In addition, we propose a new inferring prototype self-calibration (IPSC) module with a mechanism to mine the query potential information. Such a scheme can extract foreground and background inferring prototypes from query features to enhance support prototypes, reduce intra-class differences, and eliminate disturbing information around the target class. Furthermore, the self-calibration operation in IPSC can select reliable foreground inferring vectors to generate foreground inferring prototypes. Extensive experiments on two public datasets demonstrate the superiority of our method over state-of-the-art methods. Note to Practitioners—Medical image segmentation is a crucial prerequisite for clinical diagnosis, decision-making, and treatment. Few-shot medical image segmentation has emerged as a solution to reduce the need for large amounts of labeled data in medical image segmentation. This paper proposes a novel few-shot medical image segmentation network, namely SSPF-Net, which has a new organ shape-aware module (OSA) to obtain shape and edge information from organs and tissues and an inferring prototype self-calibration module (IPSC) to mine the query information for self-supervision. We experimentally demonstrate the generalization ability of the proposed method on different abdominal organ datasets. We believe that our proposed method can be further applied in clinical practice as a clinical tool to provide valuable diagnostic information.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangdong Province, China
  • Shenzhen Research Foundation for Basic Research, China

Zitieren

APA

Zheng, S., & Wu, H. (2026). SSPF-Net: Learning Organ Shape-Aware and Self-Calibration Prototypes for Few-Shot Medical Image Segmentation. IEEE Transactions on Automation Science and Engineering, 23, 8362-8372. https://doi.org/10.1109/tase.2026.3684495

Vancouver

Zheng S, Wu H. SSPF-Net: Learning Organ Shape-Aware and Self-Calibration Prototypes for Few-Shot Medical Image Segmentation. IEEE Transactions on Automation Science and Engineering. 2026;23:8362-8372. doi:10.1109/tase.2026.3684495

BibTeX
@article{Zheng2026,
  author = {Zheng, Shihao and Wu, Huisi},
  title = {SSPF-Net: Learning Organ Shape-Aware and Self-Calibration Prototypes for Few-Shot Medical Image Segmentation},
  journal = {IEEE Transactions on Automation Science and Engineering},
  year = {2026},
  volume = {23},
  pages = {8362--8372},
  doi = {10.1109/tase.2026.3684495}
}
Kostenlos starten →