Abstract
Accurate and efficient grade assessment of tumor budding (TB) in hematoxylin and eosin-stained whole slide images (H&E-stained WSIs) of colorectal cancer (CRC) remains challenging. This study proposes a full-automated TB annotation approach to assist in manual grade assessment by extracting tumor invasive front boundaries, annotating TBs in tumor invasive front patches, and transferring annotations to WSIs. Our approach demonstrates exceptional performance in tumor invasive front boundary extraction, achieving AUCs of 0.988, 0.921, and 0.929 on three different validation datasets. For TB annotations in tumor invasive front patches, the approach shows better recalls of 0.850, 0.753, and 0.720 on the same datasets. The average time of TB grade assisted by the approach in each WSI from different datasets is limited to 21 s, 15 s, and 18 s, respectively. These results demonstrate that this approach significantly improves assessment efficiency while guaranteeing accuracy, offering a reliable tool for CRC clinicopathological diagnosis.