IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities

TL;DR

IMAN is an adaptive neural network designed to improve NPC mortality prediction accuracy despite incomplete multi-modal data, addressing limitations of traditional and advanced models in handling missing modalities.

Contribution

We propose IMAN, a novel adaptive network that effectively integrates multi-modal data with missing modalities for robust NPC mortality prediction.

Findings

IMAN outperforms existing models on NPC datasets.

IMAN maintains high accuracy with incomplete data.

IMAN demonstrates robustness across various missing modality scenarios.

Abstract

Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities.