biostudies-literatureYu MYu Wang42124https://www.ebi.ac.uk/biostudies/studies/S-EPMC12658170biostudies-literatureUnknown15(1)Computational pathology leverages advanced deep-learning techniques to analyze medical images with high resolution. However, a trade-off exists between model lightweight, interpretability, and task performance in such real-world scenarios. Knowledge distillation (KD) is widely applied to compress deep learning models while preserving high performance. Despite this, deep learning-based KD often lacks interpretable design, leading to inaccurate attention to images. Inspired by human vision processing, we developed a human vision attention-inspired knowledge distillation (HVisKD) strategy that captures local and global patch relations to construct differentiated features. We employed it in pathological analysis to balance the tradeoff. HVisKD improves performance across various lightweight moScientific reportsHuman visual attention-inspired knowledge distillation underlying interpretable computational pathology.PMC126581702022-PUMCH-B-113Liang TYu MChen JHuang HZhao DMa KZhong ZWang YLei BZhou XZhou JMa WfalseHuman visual attention-inspired knowledge distillation underlying interpretable computational pathology.Computational pathology leverages advanced deep-learning techniques to analyze medical images with high resolution. However, a trade-off exists between model lightweight, interpretability, and task performance in such real-world scenarios. Knowledge distillation (KD) is widely applied to compress deep learning models while preserving high performance. Despite this, deep learning-based KD often lacks interpretable design, leading to inaccurate attention to images. Inspired by human vision processing, we developed a human vision attention-inspired knowledge distillation (HVisKD) strategy that captures local and global patch relations to construct differentiated features. We employed it in pathological analysis to balance the tradeoff. HVisKD improves performance across various lightweight mo2025-01-01T00:00:00Z2025 Nov2026-06-05T21:15:36.181Z2026-05-21T03:13:15.579ZS-EPMC126581704129868310.1038/s41598-025-26004-1