Prediction of overall survival in patients with pancreatic ductal adenocarcinoma: histogram analysis of ADC value and correlation with pathological intratumoral necrosis

End-to-end prognostication in pancreatic cancer by multimodal deep learning: a retrospective, multicenter study

OBJECTIVES

Pancreatic cancer treatment plans involving surgery and/or chemotherapy are highly dependent on disease stage. However, current staging systems are ineffective and poorly correlated with survival outcomes. We investigate how artificial intelligence (AI) can enhance prognostic accuracy in pancreatic cancer by integrating multiple data sources.

MATERIALS AND METHODS

Patients with histopathology and/or radiology/follow-up confirmed pancreatic ductal adenocarcinoma (PDAC) from a Dutch center (2004-2023) were included in the development cohort. Two additional PDAC cohorts from a Dutch and Spanish center were used for external validation. Prognostic models including clinical variables, contrast-enhanced CT images, and a combination of both were developed to predict high-risk short-term survival. All models were trained using five-fold cross-validation and assessed by the area under the time-dependent receiver operating characteristic curve (AUC).

RESULTS

The models were developed on 401 patients (203 females, 198 males, median survival (OS) = 347 days, IQR: 171-585), with 98 (24.4%) short-term survivors (OS < 230 days) and 303 (75.6%) long-term survivors. The external validation cohorts included 361 patients (165 females, 138 males, median OS = 404 days, IQR: 173-736), with 110 (30.5%) short-term survivors and 251 (69.5%) longer survivors. The best AUC for predicting short vs. long-term survival was achieved with the multi-modal model (AUC = 0.637 (95% CI: 0.500-0.774)) in the internal validation set. External validation showed AUCs of 0.571 (95% CI: 0.453-0.689) and 0.675 (95% CI: 0.593-0.757).

CONCLUSION

Multimodal AI can predict long vs. short-term survival in PDAC patients, showing potential as a prognostic tool in clinical decision-making.

KEY POINTS

Question Prognostic tools for pancreatic ductal adenocarcinoma (PDAC) remain limited, with TNM staging offering suboptimal accuracy in predicting patient survival outcomes. Findings The multimodal AI model demonstrated improved prognostic performance over TNM and unimodal models for predicting short- and long-term survival in PDAC patients. Clinical relevance Multimodal AI provides enhanced prognostic accuracy compared to current staging systems, potentially improving clinical decision-making and personalized management strategies for PDAC patients.

Mesothelin expression prediction in pancreatic cancer based on multimodal stochastic configuration networks

Predicting tumor biomarkers with high precision is essential for improving the diagnostic accuracy and developing more effective treatment strategies. This paper proposes a machine learning model that utilizes CT images and biopsy whole slide images (WSI) to classify mesothelin expression levels in pancreatic cancer. By combining multimodal learning and stochastic configuration networks, a radiopathomics mesothelin-prediction system named RPMSNet is developed. The system extracts radiomic and pathomic features from CT images and WSI, respectively, and sends them into stochastic configuration networks for the final prediction. Compared to traditional radiomics or pathomics, this system has the capability to capture more comprehensive image features, providing a multidimensional insight into tissue characteristics. The experiments and analyses demonstrate the accuracy and effectiveness of the system, with an area under the curve of 81.03%, an accuracy of 73.67%, a sensitivity of 71.54%, a precision of 76.78%, and a F1-score of 72.61%, surpassing both single-modality and dual-modality models. RPMSNet highlights its potential for early diagnosis and personalized treatment in precision medicine.

Prediction of overall survival in patients with locally advanced pancreatic cancer using longitudinal diffusion-weighted MRI

Background and purpose

Biomarkers for prediction of outcome in patients with pancreatic cancer are wanted in order to personalize the treatment. This study investigated the value of longitudinal diffusion-weighted magnetic resonance imaging (DWI) for prediction of overall survival (OS) in patients with locally advanced pancreatic cancer (LAPC) treated with stereotactic body radiotherapy (SBRT).

Materials and methods

The study included 45 patients with LAPC who received 5 fractions of 10 Gy on a 1.5T MRI-Linac. DWI was acquired prior to irradiation at each fraction. The analysis included baseline values and time-trends of the apparent diffusion coefficient (ADC) and DWI parameters obtained using a decomposition method. A multivariable Cox proportional hazards model for OS was made using best-subset selection, using cross-validation based on Bootstrap.

Results

The median OS from the first day of SBRT was 15.5 months (95% CI: 13.2-20.6), and the median potential follow-up time was 19.8 months. The best-performing multivariable model for OS included two decomposition-based DWI parameters: one baseline and one time-trend parameter. The C-Harrell index describing the model's discriminating power was 0.754. High baseline ADC values were associated with reduced OS, whereas no association between the ADC time-trend and OS was observed.

Conclusion

Decomposition-based DWI parameters indicated value in the prediction of OS in LAPC. A DWI time-trend parameter was included in the best-performing model, indicating a potential benefit of acquiring longitudinal DWI during the SBRT course. These findings support both baseline and longitudinal DWI as candidate prognostic biomarkers, which may become tools for personalization of the treatment of patients with LAPC.

Theranostic nanoparticles for detection and treatment of pancreatic cancer

Pancreatic ductal adenocarcinoma (PDAC) is one of the most recalcitrant cancers due to its late diagnosis, poor therapeutic response, and highly heterogeneous microenvironment. Nanotechnology has the potential to overcome some of the challenges to improve diagnostics and tumor-specific drug delivery but they have not been plausibly viable in clinical settings. The review focuses on active targeting strategies to enhance pancreatic tumor-specific uptake for nanoparticles. Additionally, this review highlights using actively targeted liposomes, micelles, gold nanoparticles, silica nanoparticles, and iron oxide nanoparticles to improve pancreatic tumor targeting. Active targeting of nanoparticles toward either differentially expressed receptors or PDAC tumor microenvironment (TME) using peptides, antibodies, small molecules, polysaccharides, and hormones has been presented. We focus on microenvironment-based hallmarks of PDAC and the potential for actively targeted nanoparticles to overcome the challenges presented in PDAC. It describes the use of nanoparticles as contrast agents for improved diagnosis and the delivery of chemotherapeutic agents that target various aspects within the TME of PDAC. Additionally, we review emerging nano-contrast agents detected using imaging-based technologies and the role of nanoparticles in energy-based treatments of PDAC. This article is categorized under: Implantable Materials and Surgical Technologies > Nanoscale Tools and Techniques in Surgery Therapeutic Approaches and Drug Discovery > Nanomedicine for Oncologic Disease Diagnostic Tools > In Vivo Nanodiagnostics and Imaging.

Pancreatic intraepithelial neoplasia detection and duct pathology grading using FT-IR imaging and machine learning

Pancreatic intraepithelial neoplasia (PanIN) is manifested by noninvasive lesions in the epithelium of smaller pancreatic ducts. Generally, cancer development risk from low-grade PanIN is minor, whereas, invasive pancreatic ductal adenocarcinoma (PDAC) development is highly related to high-grade PanINs. Therefore, in the case of high-grade PanIN detection, additional surgical resection may be recommended. However, even the low-grade PanINs can indicate possible progression to PDAC. The definition of PanIN is constantly changing and there is a need for new tools to better characterize and understand its behavior. We have recently developed a comprehensive pancreatic cancer classification model with biopsies collected from over 600 biopsies from 250 patients. Here, we take the next step and employ Infrared (IR) spectroscopy to build the first classification model for PanINs detection. Furthermore, we created a Partial Least Squares Regression (PLSR) model to characterize ducts from benign to cancerous. This model was then used to predict and grade PanINs accordingly to their malignancy level.

Significantly Elevated CA 19-9 after COVID-19 Vaccination and Literature Review of Non-Cancerous Cases with CA 19-9 > 1000 U/mL

BACKGROUND

CA 19-9 is a commonly assessed tumor marker, considered characteristic of pancreatic ductal adenocarcinoma (PDAC) and biliary tract cancers; however, the positive predictive value of CA 19.9 is too low, and the usage of CA 19.9 as a screening tool in the healthy population remains controversial.

METHODS

The presented case illustrates a reversed diagnosis of highly elevated serum CA 19-9 levels in a 54-year-old female complaining of pain in the epigastric region, shortly after COVID-19 vaccination. Laboratory tests showed a significantly elevated level of the CA 19-9 marker (>12,000 U/mL, reference value: <37 U/mL) with normal pancreatic enzyme activity. The patient underwent imaging examination, which showed no abnormalities, except for increased pancreatic dimension and areas of fluid signal in the pancreas in magnetic resonance imaging (MRI), which may correspond to autoimmune pancreatitis (AIP). The patient remains asymptomatic with a recommendation for a follow-up MRI in 12 months.

RESULTS

A literature review conducted revealed multi-causal CA 19-9 increases above 1000 U/mL, including non-cancerous diseases of the lung, pancreas, liver, ovary, kidney, and others. The median concentration of CA 19-9 regardless of the cause of disease was 2810 U/mL (IQR ± 6895). The median CA 19-9 values in men and women were 3500 (IQR ± 10,050) and 2455 (IQR ± 3927), respectively, and differ significantly between the compared groups (p < 0.05). There was no difference between CA 19-9 values and the categorized cause of the increase.

CONCLUSIONS

Conducting differential diagnosis, it should not be forgotten that most international guidelines recommend the use of CA 19-9 only in conjunction with pathology of pancreas in radiological imaging; however, even such a combination can point the diagnostic pathway in the wrong direction. A highly elevated CA 19-9 level, typically associated with PDAC, may be the result of benign disease including AIP related to COVID-19 vaccination.

Cysts or necrotic components in pancreatic ductal adenocarcinoma is associated with the risk of EUS-FNA/B complications including needle tract seeding

BACKGROUND

EUS-FNA/B for pancreatic ductal adenocarcinoma (PDAC) is generally considered to be safe; however, while the incidence is low, there are occurrences of complications. Among these complications, there are serious ones like needle tract seeding (NTS), and it is not known than which types of tumors have the risks of EUS-FNA/B complications. This study aimed to evaluate the risk of EUS-FNA/B complications in patients with PDAC, focusing on morphological features.

METHODS

Overall, 442 patients who underwent EUS-FNA/B for solid pancreatic masses between January 2018 and May 2022 in four institutions were retrospectively surveyed. Finally, 361 patients histopathologically diagnosed with PDAC were analyzed. Among these patients, 79 tumors with cysts or necrotic components were compared with 282 tumors without cysts or necrotic components. The incidence and risk of EUS-FNA/B complications including NTS were evaluated.

RESULTS

There were 9 (2.4 %) of total EUS-FNA/B complications and 3 (0.8 %) of NTS. The incidence of total complication rate and NTS in tumors with cysts or necrotic components were significantly higher than in those without cysts or necrotic components (total complication 6.3 % vs. 1.4 %, p = 0.026, NTS 3.7 % vs. 0 %, p = 0.01). The transgastric route of puncture (OR: 93.3, 95 % CI: 3.81-2284.23) and the existence of cysts or necrotic components (OR: 7.3, 95 % CI: 1.47-36.19) were risk factors for EUS-FNA/B complications identified by the multivariate analysis.

CONCLUSIONS

We should pay attention to the risks of EUS-FNA/B complications, including NTS, when the tumor has cysts or necrotic components.

Gemcitabine effects on tumor microenvironment of pancreatic ductal adenocarcinoma: Special focus on resistance mechanisms and metronomic therapies

Pancreatic ductal adenocarcinoma (PDAC) is considered one of the deadliest malignancies, with dismal survival rates and extremely prevalent chemoresistance. Gemcitabine is one of the primary treatments used in treating PDACs, but its benefits are limited due to chemoresistance, which could be attributed to interactions between the tumor microenvironment (TME) and intracellular processes. In preclinical models, certain schedules of administration of gemcitabine modulate the TME in a manner that does not promote resistance. Metronomic therapy constitutes a promising strategy to overcome some barriers associated with current PDAC treatments. This review will focus on gemcitabine's mechanism in treating PDAC, combination therapies, gemcitabine's interactions with the TME, and gemcitabine in metronomic therapies.

Pretreatment synthetic magnetic resonance imaging predicts disease progression in nonmetastatic nasopharyngeal carcinoma after intensity modulation radiation therapy

BACKGROUND

To investigate the potential of synthetic MRI (SyMRI) in the prognostic assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC), and the predictive value when combined with diffusion-weighted imaging (DWI) as well as clinical factors.

METHODS

Fifty-three NPC patients who underwent SyMRI were prospectively included. 10th Percentile, Mean, Kurtosis, and Skewness of T1, T2, and PD maps and ADC value were obtained from the primary tumor. Cox regression analysis was used for analyzing the association between SyMRI and DWI parameters and progression-free survival (PFS), and then age, sex, staging, and treatment as confounding factors were also included. C-index was obtained by bootstrap. Moreover, significant parameters were used to construct models in predicting 3-year disease progression. ROC curves and leave-one-out cross-validation were used to evaluate the performance and stability.

RESULTS

Disease progression occurred in 16 (30.2%) patients at a follow-up of 39.6 (3.5, 48.2) months. T1_Kurtosis, T1_Skewness, T2_10th, PD_Mean, and ADC were correlated with PFS, and T1_Kurtosis (HR: 1.093) and ADC (HR: 1.009) were independent predictors of PFS. The C-index of SyMRI and SyMRI + DWI + Clinic models was 0.687 and 0.779. Moreover, the SyMRI + DWI + Clinic model predicted 3-year disease progression better than DWI or Clinic model (p ≤ 0.008). Interestingly, there was no significant difference between the SyMRI model (AUC: 0.748) and SyMRI + DWI + Clinic model (AUC: 0.846, p = 0.092).

CONCLUSION

SyMRI combined with histogram analysis could predict disease progression in NPC patients, and SyMRI + DWI + Clinic model further improved the predictive performance.

Correlation between ADC Histogram-Derived Metrics and the Time to Metastases in Resectable Pancreatic Adenocarcinoma

Background: A non-invasive method to improve the prognostic stratification would be clinically beneficial in patients with resectable pancreatic adenocarcinoma (PDAC). The aim of this study was to correlate conventional magnetic resonance (MR) features and the metrics derived from the histogram analysis of apparent diffusion coefficient (ADC) maps, with the risk and the time to metastases (TTM) after surgery in patients with PDAC. Methods: pre-operative MR examinations of 120 patients were retrospectively analyzed. Patients were grouped according to the presence (M+) or absence (M−) of metastases during follow-up. Conventional MR features and histogram-derived metrics were compared between M+ and M− patients using the Fisher’s or Mann−Whitney tests; receiver operating characteristic (ROC) curves were constructed for the features that showed a significant difference between groups. A Cox regression analysis was performed to identify the features with a significant effect on the TTM, and Kaplan−Meier curves were constructed for significant features. Results: 68.3% patients developed metastases over a mean follow-up time of 29 months (range, 3−54 months). ADC skewness and kurtosis were significantly higher in M+ than in M− patients (p < 0.001). Skewness had a significant effect on the risk of metastases (hazard ratio—HR = 5.22, p < 0.001). Patients with an ADC skewness ≥0.23 had a significantly shorter TTM than those with a skewness <0.22 (11.7 vs. 30.8 months, p < 0.001). Conclusions: pre-operative histogram analysis of ADC maps provides parameters correlated to the metastatic potential of PDAC. Higher ADC skewness seems to be associated with a significantly shorter TTM in patients with resectable PDAC.

Impact of the tumor immune microenvironment on the outcome of pancreatic cancer: a retrospective study based on clinical pathological analysis

BACKGROUND

The cancerous microenvironment, characterized by the infiltration of CD4+ and CD8+ T cells, play a critical role in regulating the progression of cancer and treating efficiency of immunotherapy. However, the distribution of these cells and their associated cytokines in the tumor microenvironment of pancreatic cancer (PC) are not yet fully understood. Our study aims to analyze the contents of CD4+IL-17+ and CD8+ T cells in PC and their relationship with the clinicopathological features and survival outcomes of patients.

METHODS

PC tissues and adjacent tissues were retrospectively collected from 40 patients in our hospital. The expression of CD4, IL-17, and CD8 in histological samples was measured by immunohistochemistry. The correlation between CD4, IL-17, and CD8 expression and clinical characteristics was analyzed using Kaplan-Meier survival analysis. The risk factors affecting the outcome of PC were examined by the Cox proportional hazards model, then a nomogram predicting the survival of PC using these risk factors was established.

RESULTS

The content of CD4+IL-17+ T cells in PC tissues was significantly higher than that in adjacent normal tissues, while the number of CD8+ T cells was significantly lower than that in adjacent normal tissues (P<0.01). CD4+ T cells in PC tissues was significantly associated with TNM stage and lymph node metastasis (P<0.05). IL-17 and CD8 were significantly associated with histological grade, TNM stage, local infiltration, and lymph node metastasis (P<0.05). The median survival times (MSTs) of CD4 positive and negative patients were 13.2 and 21.4 months, respectively. The MSTs of IL-17 positive and negative patients were 10.4 and 24.8 months, respectively. The MSTs were 21.9 and 11.8 months for CD8 positive and negative patients, respectively (P<0.05). The Cox regression model demonstrated that TNM staging, lymph node metastasis, and CD4+IL-17+ and CD8+ T cells affected PC prognosis (P<0.05). The nomogram showed that the survival probability was reduced in patients with TNM stage III to IV, lymph node metastasis, high CD4+IL-17+ level, and low CD8+ expression.

CONCLUSIONS

CD4+IL-17+ and CD8+ T cells in PC tissues are associated with TNM staging, lymph node metastasis, and MST, and can be used as new prognostic indicators for PC.