Lesion-aware cross-phase attention network for renal tumor subtype classification on multi-phase CT scans

Kwang-Hyun Uhm, Seung-Won Jung, Sung-Hoo Hong, Sung-Jea Ko

Abstract: Highlights•Model classifies renal lesions into five pathological subtypes from multi-phase CT.•A novel lesion-aware cross-phase attention network (LACPANet) is proposed.•LACPANet effectively capture temporal dependencies of renal lesions across CT phases.•It estimates attention describing inter-phase relations of the enhancement patterns.