Uncertainty-Aware Multimodal Deep Learning for Prediction of Radiation-Induced Xerostomia in Head and Neck Cancer
Jin Yang, Tian Liu, Jose Penagaricano, Jing Wang, Erin L. Moshier, Jerry Liu, Richard Bakst, Ming Chao
Abstract
To develop and evaluate an uncertainty-aware multimodal learning framework for predicting radiation-induced xerostomia in patients receiving head-and-neck cancer radiotherapy. We developed a Bidirectional Attention-enhanced Diffusion Transformer (BA-DiT) that combines self-supervised multimodal representation learning with supervised Bayesian fine-tuning. The model integrates pretreatment CT images and three-dimensional dose distributions, focusing on bilateral parotid glands while incorporating surrounding anatomical and dosimetric information. During pretraining, bidirectional cross-attention integrates anatomical and dosimetric features, while a latent Diffusion Transformer learns joint representations through diffusion-based learning, feature reconstruction, and contrastive alignment. Supervised fine-tuning employs a Bayesian classifier to predict individualized xerostomia risk and quantify predictive uncertainty, with a learnable label-transition model accounting for potential toxicity label uncertainty. BA-DiT was developed using four independent cohorts (Moffitt, Emory, MSHS, and TCIA) and evaluated against baseline and ablation models. Evaluation included predictive performance, calibration, uncertainty quantification, decision curve analysis, and patient-level case studies. In independent MSHS and Emory cohorts, BA-DiT achieved AUCs of 0.83 and 0.80, respectively, outperforming baseline models. Predictive uncertainty peaked near the decision boundary, with aleatoric uncertainty being the predominant component. Uncertainty-based selective prediction generally improved net benefit among retained patients, with greater gains at lower prediction coverage. BA-DiT enables individualized xerostomia risk prediction while providing complementary uncertainty estimates, potentially supporting informed clinical decision-making and personalized toxicity management.
Create a lesson
Related papers
AnyVIO: Feed-Forward Streaming Visual-Inertial Odometry Across Platforms
Omoruyi Atekha, Marcus Greiff, Ray Zhang et al.
Susceptibility source separation via Closed-form Alternating Newton-type Optimization
Ignacio Contreras-Zúñiga, Cristian Tejos, Carlos Milovic
Physics-Informed Deep Learning for Shear Wave Speed Estimation in MR Elastography
Stefan Martin, Jakob Schattenfroh, Patrick Schuenke et al.
LBW-NPS: A Local Band-Weighted Noise Power Spectrum Loss for Texture-Preserving Low-Dose CT Denoising
Fatma Elif Yalçındağ, Mehmet Ozan Ünal, Metin Ertaş et al.
Life-IQA+: Boosting Blind Image Quality Assessment via GCN-enhanced Layer Interaction and Flexible Hierarchical Expert Specialization
Long Tang, Guoquan Zheng, Huiyu Duan et al.
AIstatLab at BraTS-GoAT 2026 Task 3: Quality-Controlled Consensus Pseudo-Labeling and Dense Expert Adaptation
Heeseung Shin, Changwon Lim