Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography

Abstract

<b>Rationale:</b> Clinically relevant postoperative pancreatic fistula (CR-POPF) is among the most formidable complications after pancreatoduodenectomy (PD), heightening morbidity/mortality rates. Fistula Risk Score (FRS) is a well-developed predictor, but it is an intraoperative predictor and quantifies >50% patients as intermediate risk. Therefore, an accurate and easy-to-use preoperative index is desired. Herein, we test the hypothesis that quantitative analysis of contrast-enhanced computed tomography (CE-CT) with deep learning could predict CR-POPFs. <b>Methods:</b> A group of 513 patients underwent pancreatico-enteric anastomosis after PD at three institutions between 2006 and 2019 was retrospectively collected, and formed a training (70%) and a validation dataset (30%) randomly. A convolutional neural network was trained and generated a deep-learning score (DLS) to identify the patients with higher risk of CR-POPF preoperatively using CE-CT images, which was further externally tested in a prospective cohort collected from August 2018 to June 2019 at the fourth institution. The biological underpinnings of DLS were assessed using histomorphological data by multivariate linear regression analysis. <b>Results:</b> CR-POPFs developed in 95 patients (16.3%) in total. Compared to FRS, the DLS offered significantly greater predictability in training (AUC:0.85 [95% CI, 0.80-0.90] <i>vs.</i> 0.78 [95% CI, 0.72-0.84]; <i>P</i> = 0.03), validation (0.81 [95% CI, 0.72-0.89] <i>vs.</i> 0.76 [95% CI, 0.66-0.84], <i>P</i> = 0.05) and test (0.89 [95% CI, 0.79-0.96] <i>vs.</i> 0.73 [95% CI, 0.61-0.83], <i>P</i> < 0.001) cohorts. Especially in the challenging patients of intermediate risk (FRS: 3-6), the DLS showed significantly higher accuracy (training: 79.9% <i>vs.</i> 61.5% [<i>P</i> = 0.005]; validation: 70.3% <i>vs.</i> 56.3% [<i>P</i> = 0.04]; test: 92.1% <i>vs.</i> 65.8% [<i>P</i> = 0.013]). Additionally, DLS was independently associated with pancreatic fibrosis (coefficients: -0.167), main pancreatic duct (coefficients: -0.445) and remnant volume (coefficients: 0.138) in multivariate linear regression analysis (r² = 0.512, <i>P</i> < 0.001). The user satisfaction score in the test cohort was 4 out of 5. <b>Conclusions:</b> Preoperative CT based deep-learning model provides a promising novel method for predicting CR-POPF occurrences after PD, especially at intermediate FRS risk level. This has a potential to be integrated into radiologic reporting system or incorporated into surgical planning software to accommodate the preferences of surgeons to optimize preoperative strategies, intraoperative decision-making, and even postoperative care.