Minimizing the intra- pathologist disagreement for tumor bud detection on H&E images using weakly supervised learning

Tumor budding (TB) is defined as a cluster of one to four tumor cells at the tumor invasive front. Though promising as a prognostic factor for colorectal cancer, its routine clinical use is hampered by high inter- and intra- observer disagreement on routine H&E staining. Pan-cytokeratin immunohistochemical staining increases agreement but is costly, non-routine, and may yield false tumor buds (false positives). This makes the development of automatic algorithms to identify TB difficult. Therefore, we propose a weakly-supervised method that does not require strictly accurate tissue-level annotations and is resilient to false positives. Our database consists of 29 H&E whole slide images. TB and non-tumor ROIs were generated by cropping 512x512 regions around annotated tumor buds and within annotated non-tumor regions, respectively. Attention-based multiple instance learning was applied to identify ROIs containing tumor buds. This resulted in a precision of 0.9477 ± 0.0516, recall of 0.9131 ± 0.0568, and AUC of 0.9482 ± 0.0679 on an external dataset. These results provide preliminary evidence for the feasibility of our method to identify tumor buds accurately.