Efficient 3D Biomedical Image Segmentation by Parallelly Multiscale Transformer–CNN Aggregation Network
Chemical & Biomedical Imaging · 25.08.2025 · 3 (8) · 522-533
DOI: 10.1021/cbmi.4c00102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemical & Biomedical Imaging, online erschienen am 08.04.2025. Verfasst von Wei Liu und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: State Key Laboratory of Analytical Chemistry for Life Sciences, Natural Science Foundation of Jiangsu Province, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Accurate and automated segmentation of 3D biomedical images is a sophisticated imperative in clinical diagnosis, imaging-guided surgery, and prognosis judgment. Although the burgeoning of deep learning technologies has fostered smart segmentators, the successive and simultaneous garnering global and local features still remains challenging, which is essential for an exact and efficient imageological assay. To this end, a segmentation solution dubbed the mixed parallel shunted transformer (MPSTrans) is developed here, highlighting 3D-MPST blocks in a U-form framework. It enabled not only comprehensive characteristic capture and multiscale slice synchronization but also deep supervision in the decoder to facilitate the fetching of hierarchical representations. Performing on an unpublished colon cancer data set, this model achieved an impressive increase in dice similarity coefficient (DSC) and a 1.718 mm decease in Hausdorff distance at 95% (HD95), alongside a substantial shrink of computational load of 56.7% in giga floating-point operations per second (GFLOPs). Meanwhile, MPSTrans outperforms other mainstream methods (Swin UNETR, UNETR, nnU-Net, PHTrans, and 3D U-Net) on three public multiorgan (aorta, gallbladder, kidney, liver, pancreas, spleen, stomach, etc.) and multimodal (CT, PET-CT, and MRI) data sets of medical segmentation decathlon (MSD) brain tumor, multiatlas labeling beyond cranial vault (BCV), and automated cardiac diagnosis challenge (ACDC), accentuating its adaptability. These results reflect the potential of MPSTrans to advance the state-of-the-art in biomedical imaging analysis, which would offer a robust tool for enhanced diagnostic capacity.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
- Department of Nuclear Medicine, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China.
- School of Environmental and Biological Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
ORCID-Profile: Ying Wan, Shengyuan Deng
Förderung
- State Key Laboratory of Analytical Chemistry for Life Sciences
- Natural Science Foundation of Jiangsu Province
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
- National Major Scientific and Technological Infrastructure for Translational Medicine
Zitieren
APA
Liu, W., He, Y., Man, T., Zhu, F., Chen, Q., Huang, Y., Feng, X., Li, B., Wan, Y., He, J., & Deng, S. (2025). Efficient 3D Biomedical Image Segmentation by Parallelly Multiscale Transformer–CNN Aggregation Network. Chemical & Biomedical Imaging, 3(8), 522-533. https://doi.org/10.1021/cbmi.4c00102
Vancouver
Liu W, He Y, Man T, Zhu F, Chen Q, Huang Y, et al. Efficient 3D Biomedical Image Segmentation by Parallelly Multiscale Transformer–CNN Aggregation Network. Chemical & Biomedical Imaging. 2025;3(8):522-533. doi:10.1021/cbmi.4c00102
BibTeX
@article{Liu2025,
author = {Liu, Wei and He, Yuxiao and Man, Tiantian and Zhu, Fulin and Chen, Qiaoliang and Huang, Yaqi and Feng, Xuyu and Li, Bin and Wan, Ying and He, Jian and Deng, Shengyuan},
title = {Efficient 3D Biomedical Image Segmentation by Parallelly Multiscale Transformer–CNN Aggregation Network},
journal = {Chemical & Biomedical Imaging},
year = {2025},
volume = {3},
number = {8},
pages = {522--533},
doi = {10.1021/cbmi.4c00102}
}
EUVIMED