De-Bing Zhuo

Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules

A tri-view pulmonary nodule classification framework that combines Lesion-Guided Attention (LGA) with View-Weighted Fusion (VWF) and learns sample-dependent weights to adaptively aggregate the three view representations that extracts complementary representations from axial, coronal, and sagittal slices is proposed.