TY - GEN
T1 - DpDNet
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Liang, Xinglong
AU - Huang, Jiaju
AU - Han, Luyi
AU - Zhang, Tianyu
AU - Wang, Xin
AU - Gao, Yuan
AU - Lu, Chunyao
AU - Cai, Lishan
AU - Tan, Tao
AU - Mann, Ritse
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - 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
AB - 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
KW - Dual-Prompt
KW - Survival analysis
KW - Universal PET-CT Segmentation
UR - https://www.scopus.com/pages/publications/105017854115
U2 - 10.1007/978-3-032-04978-0_16
DO - 10.1007/978-3-032-04978-0_16
M3 - Conference contribution
AN - SCOPUS:105017854115
SN - 9783032049773
T3 - Lecture Notes in Computer Science
SP - 163
EP - 172
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 23 September 2025 through 27 September 2025
ER -
