EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DyMamba: dynamic Mamba for microscopy image semantic segmentation

Buqing Cai, Xingsheng Wang, Zhuo Jia, Fa Zhang iD, Bin Hu, Xiaohua Wan

Bioinformatics · 01.06.2026 · 42 (6)

DOI: 10.1093/bioinformatics/btag391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 17.06.2026. Verfasst von Buqing Cai und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, 100081, Chin…. Hauptthemen laut MEDLINE: Microscopy, Image Processing, Computer-Assisted. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Segmentation of cell bodies and organelles in microscopy images is critical for biological research, particularly in scenarios with multiple regions of interest where spatial continuity is essential. The Mamba architecture, derived from State Space Models (SSMs), has recently gained attention for efficiently modeling long-range dependencies in sequences, achieving excellent results in both natural and medical image segmentation. However, in vision tasks, current Mamba scanning strategies mainly focus on raster-scanning and local-scanning, which introduce spatial discontinuities, severely affecting the effectiveness of segmentation at the pixel level, especially in dense segmentation tasks. Results In this article, we propose DyMamba, a Mamba-based model featuring a dynamic scanning strategy that adaptively plans scanning paths based on local features and complexity. In addition, to address the challenges of detail prediction and small object detection, we introduce a local aware module that performs pixel-level regional processing on images. DyMamba achieves robust segmentation across diverse microscopy image types, including cell-, organelle- and tissue-scale images. Experiments on six datasets and multiple scanning strategies demonstrate the excellent performance of our method in segmenting microscopy images, achieving an average improvement of 6.9% in mDice and 4.3% in mIoU over state-of-the-art methods across all datasets. Availability The code is released at https://github.com/cbqBit/dymamba.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MicroscopyImage Processing, Computer-AssistedAlgorithmsSemanticsAnimals

Autor:innen und Institutionen

  • Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, 100081, China.
  • School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China.

ORCID-Profile: Fa Zhang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cai, B., Wang, X., Jia, Z., Zhang, F., Hu, B., & Wan, X. (2026). DyMamba: dynamic Mamba for microscopy image semantic segmentation. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag391

Vancouver

Cai B, Wang X, Jia Z, Zhang F, Hu B, Wan X. DyMamba: dynamic Mamba for microscopy image semantic segmentation. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag391

BibTeX
@article{Cai2026,
  author = {Cai, Buqing and Wang, Xingsheng and Jia, Zhuo and Zhang, Fa and Hu, Bin and Wan, Xiaohua},
  title = {DyMamba: dynamic Mamba for microscopy image semantic segmentation},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {6},
  doi = {10.1093/bioinformatics/btag391}
}
Kostenlos starten →