Xian Yang

1. With the evolution of digital workspaces and complex interactive systems, user operations are no longer confined to short-term tasks within a single page; rather, they require continuous adjustm...

Accurate preoperative assessment of breast lesion malignancy and axillary lymph node (ALN) status is important for individualized breast cancer management, yet current approaches are limited by diagnostic variability and invasive nodal staging. We aimed to develop and validate a multicenter artificial intelligence framework for breast lesion classification and ALN metastasis prediction using dynamic contrast‐enhanced magnetic resonance imaging (MRI) and preoperative clinical information. In this multicenter study, 3320 patients from four hospitals were assigned to a training cohort, an internal testing cohort, and two independent external validation cohorts. Lesion classification was based on MRI alone, whereas ALN prediction additionally incorporated clinical characteristics. MRI sequences were analyzed using a Video Swin Transformer Tiny backbone with low‐rank adaptation and attention‐based multiple‐instance learning, with gated multimodal fusion used for ALN prediction. The model achieved AUCs of 1.000, 1.000, 1.000, and 0.994 for lesion classification and 0.991, 0.974, 0.987, and 0.960 for ALN prediction across the four cohorts. Calibration and decision curve analyses further characterized model performance, while exploratory survival analysis showed that AI‐predicted ALN status was associated with disease‐free survival. These findings support the potential of AI‐assisted breast MRI to provide quantitative information for breast lesion characterization and preoperative assessment of ALN involvement.

Icons play a critical role in human-machine interaction scenarios such as autonomous driving. Although icons can effectively overcome language barriers, existing research on icon design for such contexts remains limited. In particular, icon classification methods lack consistency, and prior studies often focus on preference or attention while overlooking underlying cognitive mechanisms. Grounded in cognitive load theory, this study classifies icons based on visual features and investigates their effects on recognition and memory using an electroencephalography-based rapid interaction experiment. Data were collected from 43 participants to compare recognizability and memory load across different icon categories. Results show that visual features do not significantly influence recognition accuracy but have a significant effect on memory load. Specifically, line-based icons perform better under low memory load conditions, whereas plane-based icons demonstrate advantages in high memory load tasks. These findings provide empirical guidance for icon design in automotive user interface.