Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. The authors aimed to develop and validate a computed tomography (CT)-based deep learning-based radiomics (DLR) model to identify OPM in PDAC before treatment.

This retrospective, bicentric study included 302 patients with PDAC (training: n =167, OPM-positive, n =22; internal test: n =72, OPM-positive, n =9: external test, n =63, OPM-positive, n =9) who had undergone baseline CT examinations between January 2012 and October 2022. Handcrafted radiomics (HCR) and DLR features of the tumor and HCR features of peritoneum were extracted from CT images. Mutual information and least absolute shrinkage and selection operator algorithms were used for feature selection. A combined model, which incorporated the selected clinical-radiological, HCR, and DLR features, was developed using a logistic regression classifier using data from the training cohort and validated in the test cohorts.

Three clinical-radiological characteristics (carcinoembryonic antigen 19-9 and CT-based T and N stages), nine HCR features of the tumor, 14 DLR features of the tumor, and three HCR features of the peritoneum were retained after feature selection. The combined model yielded satisfactory predictive performance, with an area under the curve (AUC) of 0.853 (95% CI: 0.790-0.903), 0.845 (95% CI: 0.740-0.919), and 0.852 (95% CI: 0.740-0.929) in the training, internal test, and external test cohorts, respectively (all P <0.05). The combined model showed better discrimination than the clinical-radiological model in the training (AUC=0.853 vs. 0.612, P <0.001) and the total test (AUC=0.842 vs. 0.638, P <0.05) cohorts. The decision curves revealed that the combined model had greater clinical applicability than the clinical-radiological model.

The model combining CT-based DLR and clinical-radiological features showed satisfactory performance for predicting OPM in patients with PDAC.

One of the primary reasons for the dismal survival rates in pancreatic ductal adenocarcinoma (PDAC) is that most patients are usually diagnosed at late stages. There is an urgent unmet clinical need to identify and develop diagnostic methods that could precisely detect PDAC at its earliest stages.

To evaluate the potential value of radiomics analysis in the differentiation of early-stage PDAC from late-stage PDAC.

A total of 71 patients with pathologically proved PDAC based on surgical resection who underwent contrast-enhanced computed tomography (CT) within 30 d prior to surgery were included in the study. Tumor staging was performed in accordance with the 8th edition of the American Joint Committee on Cancer staging system. Radiomics features were extracted from the region of interest (ROI) for each patient using Analysis Kit software. The most important and predictive radiomics features were selected using Mann-Whitney U test, univariate logistic regression analysis, and minimum redundancy maximum relevance (MRMR) method. Random forest (RF) method was used to construct the radiomics model, and 10-times leave group out cross-validation (LGOCV) method was used to validate the robustness and reproducibility of the model.

A total of 792 radiomics features (396 from late arterial phase and 396 from portal venous phase) were extracted from the ROI for each patient using Analysis Kit software. Nine most important and predictive features were selected using Mann-Whitney U test, univariate logistic regression analysis, and MRMR method. RF method was used to construct the radiomics model with the nine most predictive radiomics features, which showed a high discriminative ability with 97.7% accuracy, 97.6% sensitivity, 97.8% specificity, 98.4% positive predictive value, and 96.8% negative predictive value. The radiomics model was proved to be robust and reproducible using 10-times LGOCV method with an average area under the curve of 0.75 by the average performance of the 10 newly built models.

The radiomics model based on CT could serve as a promising non-invasive method in differential diagnosis between early and late stage PDAC.

To identify the radiological features and clinical biomarkers that could predict the occult metastasis (OM) of pancreatic ductal adenocarcinoma (PDAC).

This retrospective study included PDAC patients who were radiologically diagnosed resectable (R) or borderline resectable (BR) and underwent surgical exploration from January 2018 to December 2021. Depending on whether distant metastases were found during the exploration, patients were divided into OM and non-OM groups. Univariate and multivariable logistic regression analyses were performed to determine the radiological and clinical predictive factors for occult metastasis. Model performance was determined by discrimination and calibration.

A total of 502 patients (median age, 64 years; interquartile range, 57-70 years; 294 men) were enrolled, among which 68 (13.5%) patients were found with distant metastases, with 45 liver-only, 19 peritoneal-only, four patients had both liver and peritoneal metastases. Rim enhancement and peripancreatic fat stranding were more frequent in the OM group than in the non-OM group. Tumor size (p = 0.028), tumor resectability (p = 0.031), rim enhancement (p < 0.001), peripancreatic fat stranding (p < 0.001) and level of CA125 (p = 0.021) were independent predictors of occult metastasis according to the multivariable analyses, and the areas under the curve (AUCs) of these characteristics were 0.703, 0.594, 0.638, 0.655, 0.631, respectively. The combined model showed the highest AUC of 0.823.

Rim enhancement, peripancreatic fat stranding, tumor size, tumor resectability and level of CA125 are risk factors for OM of PDAC. The combined model of radiological and clinical features may help the preoperative prediction of OM in PDAC.

To identify prognostic CT features that predict recurrence in patients with resectable pancreatic body/tail adenocarcinoma (PBTA) and construct a CT-based nomogram for preoperative risk stratification.

A total of 258 patients with resectable PBTA who underwent upfront surgery were retrospectively enrolled (development cohort, n = 172; validation cohort, n = 86), and their clinical and CT features were analyzed. Stepwise Cox proportional hazard analysis was performed to identify prognostic features and construct a predictive nomogram for recurrence-free survival (RFS). The prognostic performance of the CT-based nomogram was validated and compared to the 8th American Joint Committee on Cancer (AJCC) pathological staging system.

In the development cohort, the following five CT features for predicting recurrence were identified to construct the nomogram: tumor density in the venous phase, tumor necrosis, adjacent organ invasion, splenic vein invasion, and superior mesenteric vein/portal vein abutment. In the validation cohort, the CT-based nomogram showed a concordance index of 0.65 (95% confidence interval: 0.58-0.73), which was higher than the 8th AJCC staging system. The area under the curves of the nomogram for predicting recurrence at 0.5, 1, and 2 years were 0.66, 0.71, and 0.72, respectively. Patients were categorized into high- and low-risk groups with 1-year recurrence probabilities of 0.73 and 0.43, respectively.

The proposed nomogram provided accurate recurrence risk stratification for patients with resectable PBTA in a preoperative setting and may be used to facilitate clinical decision-making.

The proposed CT-based nomogram, based on easily available CT features, may serve as an effective and convenient tool for stratifying further the recurrence risk of patients with pancreatic body/tail adenocarcinoma.

• The CT-based nomogram, incorporating five commonly used CT features, successfully preoperatively stratified patients with resectable PBTA into distinct prognosis groups. • Tumor density in the venous phase, tumor necrosis, splenic vein invasion, adjacent organ invasion, and superior mesenteric vein/portal vein abutment were associated with RFS in patients with resectable PBTA. • The CT-based nomogram exhibited better predictive performance for recurrence than the 8th AJCC staging system.

To explore the potential of the joint radiomics analysis of positron-emission tomography (PET) and magnetic resonance imaging (MRI) of primary tumours for predicting the risk of synchronous distant metastasis (SDM) in patients with pancreatic ductal adenocarcinoma (PDAC).

18F-FDG PET and MRI images of PDAC patients from January 2011 to December 2020 were collected retrospectively. Patients (n=66) who received 18F-FDG PET/CT and MRI were included in a development group. Patients (n=25) scanned with hybrid PET/MRI were incorporated in an external test group. A radiomics signature was constructed using the least absolute shrinkage and selection operator algorithm to select PET-MRI radiomics features of primary PDAC tumours. A radiomics nomogram was developed by combining the radiomics signature and important clinical indicators using univariate and multivariate analysis to assess patients' metastasis risk. The nomogram was verified with the employment of an external test group.

Regarding the development cohort, the radiomics nomogram was found to be better for predicting the risk of distant metastasis (area under the curve [AUC]: 0.93, sensitivity: 87%, specificity: 85%) than the clinical model (AUC: 0.70, p<0.001; sensitivity:70%, specificity: 65%) and the radiomics signature (AUC: 0.89, p>0.05; sensitivity: 65%, specificity:100%). Concerning the external test cohort, the radiomics nomogram yielded an AUC of 0.85.

PET-MRI based radiomics analysis exhibited effective prediction of the risk of SDM for preoperative PDAC patients and may offer complementary information and provide hints for cancer staging.

The relationship between postoperative CA125 level changes and early recurrence after curative resection of resectable PDAC is still unclear.

The electronic medical records and follow-up data of patients with resectable pancreatic cancer were evaluated. Dynamic CA125 detection was used to identify the rules for postoperative CA125 level change and its prognostic value in patients with resectable pancreatic cancer.

The study included a total of 118 patients with resectable pancreatic cancer who underwent curative resection. Early postoperative CA125 levels were significantly higher than those before surgery (P < 0.05). It decreased gradually in the group without early recurrence (P < 0.05) but not in the early recurrence group (P>0.05). There was no correlation between early postoperative CA125 levels and early recurrence (P > 0.05). CA125 levels three months after surgery were associated with an increased risk of early recurrence (P = 0.038, 95% CI (1.001-1.025)). The cutoff CA125 level at 3 months after surgery for predicting early recurrence was 22.035. Patients with CA125 levels < 22.035 three months postoperatively had similar DFS and OS, regardless of whether the value was exceeded in the early postoperative period, but these values were significantly better than those of patients with CA125 levels > 22.035 at 3 months postoperatively (p < 0.05).

Patients with different prognoses have different patterns of CA125 level changes. Elevations in CA125 levels > 3 months postoperatively, rather than early postoperative elevation, were associated with a poor prognosis.

The prognostic impact of positive peritoneal lavage cytology on pancreatic cancer is unclear. Therefore, this study aimed to evaluate its impact in resectable pancreatic body and tail cancer.

Between January 2006 and December 2019, 97 patients with pancreatic body and tail cancer underwent peritoneal lavage cytology and curative resection at our institution. We analyzed the impact of positive peritoneal lavage cytology on clinicopathological factors and on the prognosis of pancreatic body and tail cancer.

Malignant cells were detected in 14 patients (14.4%) using peritoneal lavage cytology. In these patients, the tumor diameter was significantly larger (p < 0.001) and anterior serosal invasion (p = 0.034), splenic artery invasion (p = 0.013), lympho-vessel invasion (p = 0.025), and perineural invasion (p = 0.008) were significantly more frequent. The R1 resection rate was also significantly higher in patients with positive peritoneal lavage cytology than in negative patients (p = 0.015). Positive peritoneal lavage cytology had a significantly poor impact on overall survival (p = 0.001) and recurrence-free survival (p < 0.001). This cytology was also an independent poor prognostic factor for recurrence (p = 0.022) and was associated with peritoneal dissemination and liver metastasis.

Positive peritoneal lavage cytology is considered to be indicative of more systemic disease in patients with resectable pancreatic body and tail cancer than in patients with negative peritoneal lavage cytology. Early detection of pancreatic cancer before it develops micrometastases is important to improve prognosis, and CY+ patients require more intensive multimodality treatment than standard treatment for resectable pancreatic cancer.

The value of extended lymphadenectomy in pancreatoduodenectomy (PD) has been discussed by five randomized controlled studies. However, the limitations in the studies made their conclusions not sufficiently reliable.

This multi-center randomized controlled study was designed to clarify the efficacy of extended lymphadenectomy in PD for pancreatic ductal adenocarcinoma (PDAC).

From December 2016 to October 2018, 170 consecutive patients undergoing PD were enrolled and randomized to standard or extended lymphadenectomy for the treatment of PDAC from three high-volume institutions in China. Demographic, pathological characteristics and survival data of these patients were collected and analyzed. No neoadjuvant treatment was performed. The primary endpoint was the 3-year overall survival.

For all patients, the 3-year survival rate was 25.88%. There was no between-group difference in 3-year survival rate (27.16% vs 24.72% p=0.717). The median survival time for the standard group was 18 months, while for the extended group it was 15 months. The demographic and pathological characteristics were similar between groups. More positive lymph nodes could be found in the extended group (2.34 ± 3.46 vs 1.41 ± 2.12, p=0.035), which led to nodule stage migration. All patients received chemotherapy. But patients in extended group were more likely to fail in completion of all-cycles chemotherapy before recurrence (31.46% vs 17.28%, p=0.032). Incomplete chemotherapy before recurrence, higher N status and abnormal CA125 were independent risk factors for 1-year survival (p<0.001, 95% CI 0.076-0.368; p=0.017, 95% CI 1.113-3.021; p=0.021, 95% CI 1.136-4.960, respectively), which was higher in the standard group (75.31% vs 58.43%, p=0.020).

The extended lymphadenectomy in PD did not improve the long-term survival in patients with PDAC. Patients with extended lymphadenectomy had a worse 1-year overall survival. However, the nodule stage migration facilitated by the extended lymphadenectomy contributed to the precise tumor staging.

Pathological diagnosis plays a critical role in the treatment of locally advanced pancreatic cancer (LAPC). However, the commonly used biopsy methods still have a number of shortcomings, such as a relatively low diagnostic accuracy and a high incidence of complications.

A retrospective review was conducted to compare 76 patients with laparoscopic biopsy and staging and 11 patients with CT-guided pancreatic biopsy for LAPC between January 2017 and October 2020. Logistic regression with univariate and multivariate analyses was performed to identify preoperative predictors of occult metastasis.

The diagnostic accuracy of laparoscopic biopsy and staging for pancreatic cancer was 100%. Sixty-two patients were confirmed to have LAPC, 59 patients by pancreatic biopsy and three patients by regional lymph node biopsy. Fourteen patients were diagnosed with distant occult metastasis, three patients by liver biopsy and 11 patients by peritoneum biopsy. Nine patients with severe obstructive manifestations underwent a simultaneous bypass procedure. No postoperative hemorrhage, pancreatic fistula, intra-abdominal infection, or trocar site metastasis was observed. Laparoscopic biopsy and staging had a higher diagnostic accuracy (100% vs. 81.8%, p=0.0147) and a shorter duration to chemotherapy (3 days vs. 9 days, p=0.035) than CT-guided biopsy. Elevated CA125 levels (≥35 U/ml) were a significant preoperative predictor of occult metastasis (OR 6.482, 95% CI 1.624-25.874, p=0.008).

Laparoscopic biopsy and staging are safe and effective methods to obtain rapid pathology and precise staging for LAPC patients, especially for patients with elevated CA125 levels.