Ma 2 SP: Missing-Aware Prompting With Modality-Adaptive Integration for Incomplete Multi-Modal Survival Prediction
IEEE Signal Processing Letters · 2024 · 31 · 2455-2459
DOI: 10.1109/lsp.2024.3453196 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Jiaqi Cui und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sichuan Science and Technology Program, 2023 Science and Technology Project.
Abstract (Originalsprache)
Survival prediction is crucial for head and neck (H&N) cancer patients. Recently, deep learning-based multi-modal models have achieved promising performance in accurate survival prediction. However, their clinical application is hindered by the difficulty of acquiring complete sets of multi-modal data. To tackle this limitation, in this paper, we propose a novel framework, namely Ma2SP, for incomplete multi-modal survival prediction in H&N cancer. Specifically, we develop missing-aware integration (MAI) modules to align heterogeneous multi-modal data and encourage dynamic interactions among available modalities, thereby achieving flexible multi-modal integration and enhancing robustness to incomplete data. Moreover, we employ missing-aware prompting (MAP) to provide explicit guidance on missing states during training, enabling effective training with incomplete data. In addition, we introduce tumor segmentation as an auxiliary task to capture tumor-related information, which further improves prediction accuracy. Experiments demonstrate our superior performance.
Förderung
- National Natural Science Foundation of China
- Sichuan Science and Technology Program
- 2023 Science and Technology Project
- Sichuan Provincial Science and Technology Innovation Seedling Project
Zitieren
APA
Cui, J., Zheng, H., Liu, Y., Wu, X., & Wang, Y. (2024). Ma 2 SP: Missing-Aware Prompting With Modality-Adaptive Integration for Incomplete Multi-Modal Survival Prediction. IEEE Signal Processing Letters, 31, 2455-2459. https://doi.org/10.1109/lsp.2024.3453196
Vancouver
Cui J, Zheng H, Liu Y, Wu X, Wang Y. Ma 2 SP: Missing-Aware Prompting With Modality-Adaptive Integration for Incomplete Multi-Modal Survival Prediction. IEEE Signal Processing Letters. 2024;31:2455-2459. doi:10.1109/lsp.2024.3453196
BibTeX
@article{Cui2024,
author = {Cui, Jiaqi and Zheng, Hanci and Liu, Yuanjun and Wu, Xi and Wang, Yan},
title = {Ma 2 SP: Missing-Aware Prompting With Modality-Adaptive Integration for Incomplete Multi-Modal Survival Prediction},
journal = {IEEE Signal Processing Letters},
year = {2024},
volume = {31},
pages = {2455--2459},
doi = {10.1109/lsp.2024.3453196}
}
EUVIMED