Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer.

OBJECTIVE: This study aimed to develop and evaluate an automatic model using artificial intelligence (AI) for quantifying vascular involvement and classifying tumor resectability stage in patients with pancreatic ductal adenocarcinoma (PDAC), primarily to support radiologists in referral centers. Resectability of PDAC is determined by the degree of vascular involvement on computed tomography scans (CTs), which is associated with considerable inter-observer variability. METHODS: We developed a semisupervised machine learning segmentation model to segment the PDAC and surrounding vasculature using 613 CTs of 467 patients with pancreatic tumors and 50 control patients. After segmenting the relevant structures, our model quantifies vascular involvement by measuring the degree of the vessel wall that is in contact with the tumor using AI-segmented CTs. Based on these measurements, the model classifies the resectability stage using the Dutch Pancreatic Cancer Group criteria as either resectable, borderline resectable, or locally advanced (LA). RESULTS: We evaluated the performance of the model using a test set containing 60 CTs from 60 patients, consisting of 20 resectable, 20 borderline resectable, and 20 locally advanced cases, by comparing the automated analysis obtained from the model to expert visual vascular involvement assessments. The model concurred with the radiologists on 227/300 (76%) vessels for determining vascular involvement. The model's resectability classification agreed with the radiologists on 17/20 (85%) resectable, 16/20 (80%) for borderline resectable, and 15/20 (75%) for locally advanced cases. CONCLUSIONS: This study demonstrates that an AI model may allow automatic quantification of vascular involvement and classification of resectability for PDAC. RELEVANCE STATEMENT: This AI model enables automated vascular involvement quantification and resectability classification for pancreatic cancer, aiding radiologists in treatment decisions, and potentially improving patient outcomes. KEY POINTS: • High inter-observer variability exists in determining vascular involvement and resectability for PDAC. • Artificial intelligence accurately quantifies vascular involvement and classifies resectability for PDAC. • Artificial intelligence can aid radiologists by automating vascular involvement and resectability assessments.

MR Elastography of the Pancreas: Bowel Preparation and Repeatability Assessment in Pancreatic Cancer Patients and Healthy Controls.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) stromal viscoelasticity can be measured using MR elastography (MRE). Bowel preparation regimens could affect MRE quality and knowledge on repeatability is crucial for clinical implementation. PURPOSE: To assess effects of four bowel preparation regimens on MRE quality and to evaluate repeatability and differentiate patients from healthy controls. STUDY TYPE: Prospective. POPULATION: 15 controls (41 ± 16 years; 47% female), 16 PDAC patients (one excluded, 66 ± 12 years; 40% female) with 15 age-/sex-matched controls (65 ± 11 years; 40% female). Final sample size was 25 controls and 15 PDAC. FIELD STRENGTH/SEQUENCE: 3-T, spin-echo echo-planar-imaging, turbo spin-echo, and fast field echo gradient-echo. ASSESSMENT: Four different regimens were used: fasting; scopolaminebutyl; drinking 0.5 L water; combination of 0.5 L water and scopolaminebutyl. MRE signal-to-noise ratio (SNR) was compared between all regimens. MRE repeatability (test-retest) and differences in shear wave speed (SWS) and phase angle (ϕ) were assessed in PDAC and controls. Regions-of-interest were defined for tumor, nontumorous (n = 8) tissue in PDAC, and whole pancreas in controls. Two radiologists delineated tumors twice for evaluation of intraobserver and interobserver variability. STATISTICAL TESTS: Repeated measures analysis of variance, coefficients of variation (CoVs), Bland-Altman analysis, (un)paired t-test, Mann-Whitney U-test, and Wilcoxon signed-rank test. P-value<0.05 was considered statistically significant. RESULTS: Preparation regimens did not significantly influence MRE-SNR. Therefore, the least burdensome preparation (fasting only) was continued. CoVs for tumor SWS were: intrasession (12.8%) and intersession (21.7%), and intraobserver (7.9%) and interobserver (10.3%) comparisons. For controls, CoVs were intrasession (4.6%) and intersession (6.4%). Average SWS for tumor, nontumor, and healthy tissue were: 1.74 ± 0.58, 1.38 ± 0.27, and 1.18 ± 0.16 m/sec (ϕ: 1.02 ± 0.17, 0.91 ± 0.07, and 0.85 ± 0.08 rad), respectively. Significant differences were found between all groups, except for ϕ between healthy-nontumor (P = 0.094). DATA CONCLUSION: The proposed bowel preparation regimens may not influence MRE quality. MRE may be able to differentiate between healthy tissue-tumor and tumor-nontumor. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.

Long-Term Outcome of Immediate Versus Postponed Intervention in Patients With Infected Necrotizing Pancreatitis (POINTER): Multicenter Randomized Trial.

OBJECTIVE: To compare the long-term outcomes of immediate drainage versus the postponed-drainage approach in patients with infected necrotizing pancreatitis. BACKGROUND: In the randomized POINTER trial, patients assigned to the postponed-drainage approach using antibiotic treatment required fewer interventions, as compared with immediate drainage, and over a third were treated without any intervention. METHODS: Clinical data of those patients alive after the initial 6-month follow-up were re-evaluated. The primary outcome was a composite of death and major complications. RESULTS: Out of 104 patients, 88 were re-evaluated with a median follow-up of 51 months. After the initial 6-month follow-up, the primary outcome occurred in 7 of 47 patients (15%) in the immediate-drainage group and 7 of 41 patients (17%) in the postponed-drainage group (RR 0.87, 95% CI 0.33-2.28; P =0.78). Additional drainage procedures were performed in 7 patients (15%) versus 3 patients (7%) (RR 2.03; 95% CI 0.56-7.37; P =0.34). The median number of additional interventions was 0 (IQR 0-0) in both groups ( P =0.028). In the total follow-up, the median number of interventions was higher in the immediate-drainage group than in the postponed-drainage group (4 vs. 1, P =0.001). Eventually, 14 of 15 patients (93%) in the postponed-drainage group who were successfully treated in the initial 6-month follow-up with antibiotics and without any intervention remained without intervention. At the end of follow-up, pancreatic function and quality of life were similar. CONCLUSIONS: Also, during long-term follow-up, a postponed-drainage approach using antibiotics in patients with infected necrotizing pancreatitis results in fewer interventions as compared with immediate drainage and should therefore be the preferred approach. TRIAL REGISTRATION: ISRCTN33682933.

Immediate versus Postponed Intervention for Infected Necrotizing Pancreatitis.

BACKGROUND: Infected necrotizing pancreatitis is a potentially lethal disease that is treated with the use of a step-up approach, with catheter drainage often delayed until the infected necrosis is encapsulated. Whether outcomes could be improved by earlier catheter drainage is unknown. METHODS: We conducted a multicenter, randomized superiority trial involving patients with infected necrotizing pancreatitis, in which we compared immediate drainage within 24 hours after randomization once infected necrosis was diagnosed with drainage that was postponed until the stage of walled-off necrosis was reached. The primary end point was the score on the Comprehensive Complication Index, which incorporates all complications over the course of 6 months of follow-up. RESULTS: A total of 104 patients were randomly assigned to immediate drainage (55 patients) or postponed drainage (49 patients). The mean score on the Comprehensive Complication Index (scores range from 0 to 100, with higher scores indicating more severe complications) was 57 in the immediate-drainage group and 58 in the postponed-drainage group (mean difference, -1; 95% confidence interval [CI], -12 to 10; P = 0.90). Mortality was 13% in the immediate-drainage group and 10% in the postponed-drainage group (relative risk, 1.25; 95% CI, 0.42 to 3.68). The mean number of interventions (catheter drainage and necrosectomy) was 4.4 in the immediate-drainage group and 2.6 in the postponed-drainage group (mean difference, 1.8; 95% CI, 0.6 to 3.0). In the postponed-drainage group, 19 patients (39%) were treated conservatively with antibiotics and did not require drainage; 17 of these patients survived. The incidence of adverse events was similar in the two groups. CONCLUSIONS: This trial did not show the superiority of immediate drainage over postponed drainage with regard to complications in patients with infected necrotizing pancreatitis. Patients randomly assigned to the postponed-drainage strategy received fewer invasive interventions. (Funded by Fonds NutsOhra and Amsterdam UMC; POINTER ISRCTN Registry number, ISRCTN33682933.).

Acute pancreatitis in COVID-19 patients: true risk?

BACKGROUND: A relation between coronavirus disease 2019 (COVID-19) and acute pancreatitis has been suggested. However, the incidence and clinical relevance of this relation remain unclear. OBJECTIVE: We aimed to investigate the incidence, severity and clinical impact of acute pancreatitis in patients with COVID-19. METHODS: This is a cross-sectional study of a prospective, observational cohort concerning all COVID-19 patients admitted to two Dutch university hospitals between 4 March 2020 and 26 May 2020. Primary outcome was acute pancreatitis potentially related to COVD-19 infection. Acute pancreatitis was defined according to the revised Atlanta Classification. Potential relation with COVID-19 was defined as the absence of a clear aetiology of acute pancreatitis. RESULTS: Among 433 patients with COVID-19, five (1.2%) had potentially related acute pancreatitis according to the revised Atlanta Classification. These five patients suffered from severe COVID-19 infection; all had (multiple) organ failure and 60% died. None of the patients developed necrotizing pancreatitis. Moreover, development of acute pancreatitis did not lead to major treatment consequences. CONCLUSIONS: In contrast with previous research, our study demonstrated that COVID-19 related acute pancreatitis is rare and of little clinical impact. It is therefore debatable if acute pancreatitis in COVID-19 patients requires specific screening. We hypothesize that acute pancreatitis occurs in patients with severe illness due to COVID-19 infection as a result of transient hypoperfusion and pancreatic ischemia, not as a direct result of the virus.

Locally advanced rectal cancer: 3D diffusion-prepared stimulated-echo turbo spin-echo versus 2D diffusion-weighted echo-planar imaging.

BACKGROUND: Diffusion-weighted imaging (DWI) has shown great value in rectal cancer imaging. However, traditional DWI with echo-planar imaging (DW-EPI) often suffers from geometrical distortions. We applied a three-dimensional diffusion-prepared stimulated-echo turbo spin-echo sequence (DPsti-TSE), allowing geometrically undistorted rectal DWI. We compared DPsti-TSE with DW-EPI for locally advanced rectal cancer DWI. METHODS: For 33 prior-to-treatment patients, DWI images of the rectum were acquired with DPsti-TSE and DW-EPI at 3 T using b-values of 200 and 1000 s/mm2. Two radiologists conducted a blinded scoring of the images considering nine aspects of image quality and anatomical quality. Tumour apparent diffusion coefficient (ADC) and distortions were compared quantitatively. RESULTS: DPsti-TSE scored significantly better than DW-EPI in rectum distortion (p = 0.005) and signal pileup (p = 0.001). DPsti-TSE had better tumour Dice similarity coefficient compared to DW-EPI (0.84 versus 0.80, p = 0.010). Tumour ADC values were higher for DPsti-TSE compared to DW-EPI (1.47 versus 0.86 × 10-3 mm2/s, p < 0.001). Radiologists scored DPsti-TSE significantly lower than DW-EPI on aspects of overall image quality (p = 0.001), sharpness (p < 0.001), quality of fat suppression (p < 0.001), tumour visibility (p = 0.009), tumour conspicuity (p = 0.010) and rectum wall visibility (p = 0.005). CONCLUSIONS: DPsti-TSE provided geometrically less distorted rectal cancer diffusion-weighted images. However, the image quality of DW-EPI over DPsti-TSE was referred on the basis of several image quality criteria. A significant bias in tumour ADC values from DPsti-TSE was present. Further improvements of DPsti-TSE are needed until it can replace DW-EPI.