DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911048298135552 |
|---|---|
| author | Liang, Xinglong Huang, Jiaju Han, Luyi Zhang, Tianyu Wang, Xin Gao, Yuan Lu, Chunyao Cai, Lishan Tan, Tao Mann, Ritse |
| author_facet | Liang, Xinglong Huang, Jiaju Han, Luyi Zhang, Tianyu Wang, Xin Gao, Yuan Lu, Chunyao Cai, Lishan Tan, Tao Mann, Ritse |
| contents | PET-CT lesion segmentation is challenging due to noise sensitivity, small and variable lesion morphology, and interference from physiological high-metabolic signals. Current mainstream approaches follow the practice of one network solving the segmentation of multiple cancer lesions by treating all cancers as a single task. However, this overlooks the unique characteristics of different cancer types. Considering the specificity and similarity of different cancers in terms of metastatic patterns, organ preferences, and FDG uptake intensity, we propose DpDNet, a Dual-Prompt-Driven network that incorporates specific prompts to capture cancer-specific features and common prompts to retain shared knowledge. Additionally, to mitigate information forgetting caused by the early introduction of prompts, prompt-aware heads are employed after the decoder to adaptively handle multiple segmentation tasks. Experiments on a PET-CT dataset with four cancer types show that DpDNet outperforms state-of-the-art models. Finally, based on the segmentation results, we calculated MTV, TLG, and SUVmax for breast cancer survival analysis. The results suggest that DpDNet has the potential to serve as a valuable tool for personalized risk stratification, supporting clinicians in optimizing treatment strategies and improving outcomes. Code is available at https://github.com/XinglongLiang08/DpDNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation Liang, Xinglong Huang, Jiaju Han, Luyi Zhang, Tianyu Wang, Xin Gao, Yuan Lu, Chunyao Cai, Lishan Tan, Tao Mann, Ritse Image and Video Processing Artificial Intelligence PET-CT lesion segmentation is challenging due to noise sensitivity, small and variable lesion morphology, and interference from physiological high-metabolic signals. Current mainstream approaches follow the practice of one network solving the segmentation of multiple cancer lesions by treating all cancers as a single task. However, this overlooks the unique characteristics of different cancer types. Considering the specificity and similarity of different cancers in terms of metastatic patterns, organ preferences, and FDG uptake intensity, we propose DpDNet, a Dual-Prompt-Driven network that incorporates specific prompts to capture cancer-specific features and common prompts to retain shared knowledge. Additionally, to mitigate information forgetting caused by the early introduction of prompts, prompt-aware heads are employed after the decoder to adaptively handle multiple segmentation tasks. Experiments on a PET-CT dataset with four cancer types show that DpDNet outperforms state-of-the-art models. Finally, based on the segmentation results, we calculated MTV, TLG, and SUVmax for breast cancer survival analysis. The results suggest that DpDNet has the potential to serve as a valuable tool for personalized risk stratification, supporting clinicians in optimizing treatment strategies and improving outcomes. Code is available at https://github.com/XinglongLiang08/DpDNet. |
| title | DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation |
| topic | Image and Video Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2507.07126 |