AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction

Xiao Yu, Zhaojie Fang, Guanyu Zhou, Yin Shen, Huoling Luo, Ye Li, Ahmed Elazab, Xiang Wan, Ruiquan Ge, Changmiao Wang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dual-graph construction and graph feature fusion (ablation)DGSAN · NLST-cmstaccuracy: 86.84 -> 90.79Improved
add graph feature fusion (GFF) (ablation)DGSAN · NLST-cmstaccuracy: 88.47 -> 90.79Improved
add clinical features to t1 image (ablation)single-timepoint model · NLST-cmstaccuracy: 87.24 -> 88.16Improved
use proposed inter/intra-modal graph scheme vs separate graphs (ablation)DGSAN · NLST-cmstaccuracy: 88.21 -> 90.79Improved
use self-cross-self attention order instead of cross-self-cross (ablation)HCMGFM · NLST-cmstaccuracy: 89.53 -> 90.79Improved
use SAB-CAB-SAB instead of CAB-SAB (ablation)HCMGFM · NLST-cmstaccuracy: 90.43 -> 90.79Improved
DGSAN vs best baseline HGCN with fewer paramsDGSAN · NLST-cmstaccuracy: 87.66 -> 90.79Improved
DGSAN on external CLST (not trained on)DGSAN · CLST (external)accuracy: 62.86 -> 65.28Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy