Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Recognition of tumors is very important in clinical practice and radiomics; however, the segmentation task currently still needs to be done manually by experts. With the development of deep learning, automatic segmentation of tumors is gradually becoming possible. This paper combines the molecular information from PET and the pathology information from CT for tumor segmentation. A dual-branch encoder is designed based on SE-UNet (Squeeze-and-Excitation Normalization UNet) and Transformer, 3D Convolutional Block Attention Module (CBAM) is added to skip-connection, and BCE loss is used in training for improving segmentation accuracy. The new model is named TASE-UNet. The proposed method was tested on the HECKTOR2022 dataset, which obtains the best segmentation accuracy compared with state-of-the-art methods. Specifically, we obtained results of 76.10 and 3.27 for the two key evaluation metrics, DSC and HD95. Experiments demonstrate that the designed network is reasonable and effective. The full implementation is available at https://github.com/LiMingrui1/TASE-UNet .
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s11517-025-03427-6 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A dual-branch encoder network based on squeeze-and-excitation UNet and transformer for 3D PET-CT image tumor segmentation.
Med Biol Eng Comput
September 2025
College of Medicine and Biomedical Information Engineering, Northeastern University, 110169, Shenyang, China.
Recognition of tumors is very important in clinical practice and radiomics; however, the segmentation task currently still needs to be done manually by experts. With the development of deep learning, automatic segmentation of tumors is gradually becoming possible. This paper combines the molecular information from PET and the pathology information from CT for tumor segmentation.
View Article and Find Full Text PDFA dual-branch CNN-encoder model for rapid geographic traceability of Astragalus using near-infrared spectroscopy.
Spectrochim Acta A Mol Biomol Spectrosc
August 2025
Institute for Complexity Science, Henan University of Technology, Zhengzhou 450001, China. Electronic address:
The geographical origin of medicinal herbs significantly affects their chemical composition and pharmacological efficacy. Therefore, developing rapid and non-destructive origin identification techniques is essential for quality control in traditional Chinese medicine (TCM). Astragalus membranaceus, a representative herb with both medicinal and nutritional value, is highly sensitive to environmental conditions across different producing areas.
View Article and Find Full Text PDFDynamic atrous attention and dual branch context fusion for cross scale Building segmentation in high resolution remote sensing imagery.
Sci Rep
August 2025
School of Mining Engineering, Heilongjiang University of Science and Technology, Haerbin, 150000, China.
Building segmentation of high-resolution remote sensing images using deep learning effectively reduces labor costs, but still faces the key challenges of effectively modeling cross-scale contextual relationships and preserving fine spatial details. Current Transformer-based approaches demonstrate superior long-range dependency modeling, but still suffer from the problem of progressive information loss during hierarchical feature encoding. Therefore, this study proposed a new semantic segmentation network named SegTDformer to extract buildings in remote sensing images.
View Article and Find Full Text PDFDB-SNet: A dual branch network for aortic component segmentation and lesion localization.
Comput Med Imaging Graph
September 2025
School of Medical Technology, Beijing Institute of Technology, No.5 Zhongguancun South Street, Haidian District, Beijing 100081, China; Department of Radiology, Chinese PLA General Hospital, No. 28 Fuxing Road, Haidian District, Beijing 100853, China. Electronic address:
Accurate segmentation of aortic components, such as lumen, calcification, and false lumen, and associated lesions, including aneurysm, stenosis, and dissection in CT angiography (CTA) scans is crucial for cardiovascular diagnosis and treatment planning. However, most existing automated methods generate binary masks with limited clinical utility and rely on separate computational pipelines for anatomical and lesion segmentation, resulting in higher resource demands. To address these limitations, we propose DB-SNet, a dual-branch 3D segmentation network based on the MedNeXt architecture.
View Article and Find Full Text PDFFrequency-Based Comprehensive Prompt Learning for Vision-Language Models.
IEEE Trans Pattern Anal Mach Intell
August 2025
This paper targets to learn multiple comprehensive text prompts that can describe the visual concepts from coarse to fine, thereby endowing pre-trained VLMs with better transfer ability to various downstream tasks. We focus on exploring this idea on transformer-based VLMs since this kind of architecture achieves more compelling performances than CNN-based ones. Unfortunately, unlike CNNs, the transformer-based visual encoder of pre-trained VLMs cannot naturally provide discriminative and representative local visual information.
View Article and Find Full Text PDF