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

Abstract

Rationale: 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. Methods: 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. Results: 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] vs. 0.78 [95% CI, 0.72-0.84]; P = 0.03), validation (0.81 [95% CI, 0.72-0.89] vs. 0.76 [95% CI, 0.66-0.84], P = 0.05) and test (0.89 [95% CI, 0.79-0.96] vs. 0.73 [95% CI, 0.61-0.83], P < 0.001) cohorts. Especially in the challenging patients of intermediate risk (FRS: 3-6), the DLS showed significantly higher accuracy (training: 79.9% vs. 61.5% [ P = 0.005]; validation: 70.3% vs. 56.3% [ P = 0.04]; test: 92.1% vs. 65.8% [ P = 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 (r 2 = 0.512, P < 0.001). The user satisfaction score in the test cohort was 4 out of 5. Conclusions: 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.

Hyperpolarized Magnetic Resonance and Artificial Intelligence: Frontiers of Imaging in Pancreatic Cancer

“…For the prediction of clinically relevant postoperative pancreatic fistula using CT images, Mu et al [ 96 ] utilized a Resnet18 model with fewer filters on 513 patients imaged between 2006 and 2019. All patients underwent pancreatico-enteric anastomosis after the diagnosis of pancreas disease at three institutions.…”

The prediction of surgical complications using artificial intelligence in patients undergoing major abdominal surgery: A systematic review

“…15,17,18,21,22 In the majority of the machine learning models tested, sensitivity was lower than specificity. 14,16,19,20,23,24,26 The lowest sensitivity was found in the study of Cao et al 19 with a value of 0.06 with a convolutional neural network. In the studies of Azimi et al, 14 Cao et al, 19 Grass et al, 16 and Nudel et al 20 sensitivities were below 0.50.…”

“…12,15,16,18,19,21e23,25,26 Two articles used bootstrap resampling 14,17 to internally validate their data, and in 2 studies a training and validation split of the data was used without cross-validation. 20,24 The article of Adams et al 13 did not specify the type of internal validation. External validation of the data set was described in 10 studies.…”

“…These test data can be created either by splitting the original data into a training and test set, as done by 6 studies, 12,14,18e20,25 or by externally testing it on a prospective cohort, as done in 2 studies. 13,24 Shi et al 26 externally validated their model, without stating which method was used. In the article by Chen et al 15 it was not reported whether external validation of their machine learning model was performed.…”

Recent advances in artificial intelligence for pancreatic ductal adenocarcinoma

“…In the pancreatic fields, the availability of AI in surgery is still very limited. An AI-based risk prediction model of postoperative complication has been reported[ 71 , 72 ]. Postoperative pancreatic fistula (POPF) is a serious complication after pancreatoduodenectomy (PD).…”