Background: Histologic examination of resected pancreatic cancer after neoadjuvant therapy (NAT) is used to assess the effect of NAT and may guide the choice for adjuvant treatment. However, evaluating residual tumor burden in pancreatic cancer is challenging given tumor response heterogeneity and challenging histomorphology. Artificial intelligence techniques may offer a more reproducible approach. Methods: From 64 patients, one H&E-stained slide of resected pancreatic cancer after NAT was digitized. Three separate classes were manually outlined in each slide (i.e., tumor, normal ducts, and remaining epithelium). Corresponding segmentation masks and patches were generated and distributed over training, validation, and test sets. Modified U-nets with varying encoders were trained, and F1 scores were obtained to express segmentation accuracy. Results: The highest mean segmentation accuracy was obtained using modified U-nets with a DenseNet161 encoder. Tumor tissue was segmented with a high mean F1 score of 0.86, while the overall multiclass average F1 score was 0.82. Conclusions: This study shows that artificial intelligence-based assessment of residual tumor burden is feasible given the promising obtained F1 scores for tumor segmentation. This model could be developed into a tool for the objective evaluation of the response to NAT and may potentially guide the choice for adjuvant treatment.
Objective: Examine the potential benefit of total pancreatectomy (TP) as an alternative to pancreatoduodenectomy (PD) in patients at high risk for postoperative pancreatic fistula (POPF). Summary Background Data: TP is mentioned as an alternative to PD in patients at high risk for POPF, but a systematic review is lacking. Methods: Systematic review and meta-analyses using Pubmed, Embase (Ovid), and Cochrane Library to identify studies published up to October 2022, comparing elective single-stage TP for any indication versus PD in patients at high risk for POPF. The primary endpoint was short-term mortality. Secondary endpoints were major morbidity (i.e., Clavien-Dindo grade ≥ IIIa) on the short-term and quality of life. Results: After screening 1212 unique records, five studies with 707 patients (334 TP and 373 high-risk PD) met the eligibility criteria, comprising one randomized controlled trial and four observational studies. The 90-day mortality after TP and PD did not differ (6.3% vs. 6.2%; RR = 1.04 ). Major morbidity rate was lower after TP compared to PD (26.7% vs. 38.3%; RR = 0.65 [95%CI 0.48-0.89]), but no significance was seen in matched/randomized studies (29.0% vs. 36.9%; RR = 0.73 [95%CI 0.48-1.10]). Two studies investigated quality of life (EORTC QLQ-C30) at a median of 30-52 months, demonstrating comparable global health status after TP and PD (77% [ ± 15] vs. 76% [ ± 20]; P = 0.857). Conclusions: This systematic review and meta-analysis found no reduction in short-term mortality and major morbidity after TP as compared to PD in patients at high risk for POPF. However, if TP is used as a bailout procedure, the comparable long-term quality of life is reassuring.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.