Attention‐enhanced multiscale feature fusion network for pancreas and tumor segmentation
Medical Physics · 2024-12 · 51 (12) · 8999-9016
DOI: 10.1002/mp.17385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 22.09.2024. Verfasst von Kaiqi Dong und 8 weiteren Autor:innen. Beteiligte Einrichtung: Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science, Zh…. Hauptthemen laut MEDLINE: Pancreatic Neoplasms, Image Processing, Computer-Assisted, Pancreas. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research Project of Zhejiang Laboratory, Fundamental Research Funds for Central Universities.
Abstract (Originalsprache)
Background
Accurate pancreas and pancreatic tumor segmentation from abdominal scans is crucial for diagnosing and treating pancreatic diseases. Automated and reliable segmentation algorithms are highly desirable in both clinical practice and research.
Purpose
Segmenting the pancreas and tumors is challenging due to their low contrast, irregular morphologies, and variable anatomical locations. Additionally, the substantial difference in size between the pancreas and small tumors makes this task difficult. This paper proposes an attention‐enhanced multiscale feature fusion network (AMFF‐Net) to address these issues via 3D attention and multiscale context fusion methods.
Methods
First, to prevent missed segmentation of tumors, we design the residual depthwise attention modules (RDAMs) to extract global features by expanding receptive fields of shallow layers in the encoder. Second, hybrid transformer modules (HTMs) are proposed to model deep semantic features and suppress irrelevant regions while highlighting critical anatomical characteristics. Additionally, the multiscale feature fusion module (MFFM) fuses adjacent top and bottom scale semantic features to address the size imbalance issue.
Results
The proposed AMFF‐Net was evaluated on the public MSD dataset, achieving 82.12% DSC for pancreas and 57.00% for tumors. It also demonstrated effective segmentation performance on the NIH and private datasets, outperforming previous State‐Of‐The‐Art (SOTA) methods. Ablation studies verify the effectiveness of RDAMs, HTMs, and MFFM.
Conclusions
We propose an effective deep learning network for pancreas and tumor segmentation from abdominal CT scans. The proposed modules can better leverage global dependencies and semantic information and achieve significantly higher accuracy than the previous SOTA methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China.
- Research Center for Data Hub and Security, Zhejiang Laboratory, Hangzhou, China.
- Department of Hepatobiliary and Pancreatic Surgery, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Förderung
- National Natural Science Foundation of China
- Key Research Project of Zhejiang Laboratory
- Fundamental Research Funds for Central Universities
Zitieren
APA
Dong, K., Hu, P., Zhu, Y., Tian, Y., Li, X., Zhou, T., Bai, X., Liang, T., & Li, J. (2024). Attention‐enhanced multiscale feature fusion network for pancreas and tumor segmentation. Medical Physics, 51(12), 8999-9016. https://doi.org/10.1002/mp.17385
Vancouver
Dong K, Hu P, Zhu Y, Tian Y, Li X, Zhou T, et al. Attention‐enhanced multiscale feature fusion network for pancreas and tumor segmentation. Medical Physics. 2024;51(12):8999-9016. doi:10.1002/mp.17385
BibTeX
@article{Dong2024,
author = {Dong, Kaiqi and Hu, Peijun and Zhu, Yan and Tian, Yu and Li, Xiang and Zhou, Tianshu and Bai, Xueli and Liang, Tingbo and Li, Jingsong},
title = {Attention‐enhanced multiscale feature fusion network for pancreas and tumor segmentation},
journal = {Medical Physics},
year = {2024},
volume = {51},
number = {12},
pages = {8999--9016},
doi = {10.1002/mp.17385}
}
EUVIMED