Fully Automated Tumor Bud Assessment in Hematoxylin and Eosin-Stained Whole Slide Images of Colorectal Cancer.

Tumor budding (TB), the presence of single cells or small clusters of up to 4 tumor cells at the invasive front of colorectal cancer (CRC), is a proven risk factor for adverse outcomes. International definitions are necessary to reduce interobserver variability. According to the current international guidelines, hotspots at the invasive front should be counted in hematoxylin and eosin (H&E)-stained slides. This is time-consuming and prone to interobserver variability; therefore, there is a need for computer-aided diagnosis solutions. In this study, we report an artificial intelligence-based method for detecting TB in H&E-stained whole slide images. We propose a fully automated pipeline to identify the tumor border, detect tumor buds, characterize them based on the number of tumor cells, and produce a TB density map to identify the TB hotspot. The method outputs the TB count in the hotspot as a computational biomarker. We show that the proposed automated TB detection workflow performs on par with a panel of 5 pathologists at detecting tumor buds and that the hotspot-based TB count is an independent prognosticator in both the univariate and the multivariate analysis, validated on a cohort of n = 981 patients with CRC. Computer-aided detection of tumor buds based on deep learning can perform on par with expert pathologists for the detection and quantification of tumor buds in H&E-stained CRC histopathology slides, strongly facilitating the introduction of budding as an independent prognosticator in clinical routine and clinical trials.

Do the Well Known Prognostic Parameters in Pancreatic Ductal Adenocarcinoma Really Reflect Survival?

OBJECTIVE: Pancreatic ductal adenocarcinoma is an aggressive tumor with short survival. In this study we aimed to investigate the effect of well-known prognostic parameters on survival in these tumors. MATERIAL AND METHOD: A total of 56 pancreatic ductal adenocarcinoma cases diagnosed between 2005 and 2014 were included in the study. Survival data were obtained and histopathological parameters were re-evaluated in each patient. RESULTS: Tumor size (p=0.029), mitotic count (p=0.030), lymph node metastasis (p=0.003), metastatic lymph node ratio (p < 0.001) and ampullary invasion (p=0.044) had a statistically significant relationship with survival. However, there was no relationship between survival and tumor grade, lymphovascular and perineural invasion, and peripancreatic soft tissue invasion. CONCLUSION: Our results showed that existent 2010 WHO pancreatic ductal adenocarcinoma grading parameters excluding mitotic count are subjective and not applicable. Considering that almost all of the tumors in our series were larger than 2 cm, we think that the 2 cm cut-off in tumor size is insufficient to make the tumor stage pT2. Peripancreatic soft tissue invasion, which is a common finding in pancreatic ductal adenocarcinoma, should also not be assessed like adjacent tissue invasion and make the tumor reach pT3 stage independent of tumor size. It is clear that the existent WHO tumor grading and pT staging parameters need to be revised and the mitotic count, which correlates with survival, should be presented in pathology reports.