Development of pancreatic cancer is predictable well in advance using contrast-enhanced CT: a case-cohort study

Radiologists' Expectations of Artificial Intelligence in Pancreatic Cancer Imaging: How Good Is Good Enough?

BACKGROUND

Existing (artificial intelligence [AI]) tools in radiology are modeled without necessarily considering the expectations and experience of the end user-the radiologist. The literature is scarce on the tangible parameters that AI capabilities need to meet for radiologists to consider them useful tools.

OBJECTIVE

The purpose of this study is to explore radiologists' attitudes toward AI tools in pancreatic cancer imaging and to quantitatively assess their expectations of these tools.

METHODS

A link to the survey was posted on the www.ctisus.com website, advertised in the www.ctisus.com email newsletter, and publicized on LinkedIn, Facebook, and Twitter accounts. This survey asked participants about their demographics, practice, and current attitudes toward AI. They were also asked about their expectations of what constitutes a clinically useful AI tool. The survey consisted of 17 questions, which included 9 multiple choice questions, 2 Likert scale questions, 4 binary (yes/no) questions, 1 rank order question, and 1 free text question.

RESULTS

A total of 161 respondents completed the survey, yielding a response rate of 46.3% of the total 348 clicks on the survey link. The minimum acceptable sensitivity of an AI program for the detection of pancreatic cancer chosen by most respondents was either 90% or 95% at a specificity of 95%. The minimum size of pancreatic cancer that most respondents would find an AI useful at detecting was 5 mm. Respondents preferred AI tools that demonstrated greater sensitivity over those with greater specificity. Over half of respondents anticipated incorporating AI tools into their clinical practice within the next 5 years.

CONCLUSION

Radiologists are open to the idea of integrating AI-based tools and have high expectations regarding the performance of these tools. Consideration of radiologists' input is important to contextualize expectations and optimize clinical adoption of existing and future AI tools.

Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning

OBJECTIVES

This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans.

MATERIALS AND METHODS

A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics.

RESULTS

The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97-0.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92-0.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87-0.98) and 0.95 (53 of 56, 95% CI, 0.87-1.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91-0.97), 1.0 (95% CI, 0.98-1.0), 0.96 (95% CI, 0.97-1.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96-0.98).

CONCLUSIONS

The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.

A primer on artificial intelligence in pancreatic imaging

Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication. This article reviews the current status of artificial intelligence in pancreatic imaging and critically appraises the quality of existing evidence using the radiomics quality score.

Proteomics-Driven Biomarkers in Pancreatic Cancer

Pancreatic cancer is a devastating disease that has a grim prognosis, highlighting the need for improved screening, diagnosis, and treatment strategies. Currently, the sole biomarker for pancreatic ductal adenocarcinoma (PDAC) authorized by the U.S. Food and Drug Administration is CA 19-9, which proves to be the most beneficial in tracking treatment response rather than in early detection. In recent years, proteomics has emerged as a powerful tool for advancing our understanding of pancreatic cancer biology and identifying potential biomarkers and therapeutic targets. This review aims to offer a comprehensive survey of proteomics' current status in pancreatic cancer research, specifically accentuating its applications and its potential to drastically enhance screening, diagnosis, and treatment response. With respect to screening and diagnostic precision, proteomics carries the capacity to augment the sensitivity and specificity of extant screening and diagnostic methodologies. Nonetheless, more research is imperative for validating potential biomarkers and establishing standard procedures for sample preparation and data analysis. Furthermore, proteomics presents opportunities for unveiling new biomarkers and therapeutic targets, as well as fostering the development of personalized treatment strategies based on protein expression patterns associated with treatment response. In conclusion, proteomics holds great promise for advancing our understanding of pancreatic cancer biology and improving patient outcomes. It is essential to maintain momentum in investment and innovation in this arena to unearth more groundbreaking discoveries and transmute them into practical diagnostic and therapeutic strategies in the clinical context.

Pancreatic duct imaging during aging

As part of the aging process, fibrotic changes, fatty infiltration, and parenchymal atrophy develop in the pancreas. The pancreatic duct also becomes wider with age. This article provides an overview of the diameter of the pancreatic duct in different age groups and different examination methods. Knowledge of these data is useful to avoid misinterpretations regarding the differential diagnosis of chronic pancreatitis, obstructive tumors, and intraductal papillary mucinous neoplasia (IPMN).

Artificial intelligence in pancreatic cancer: diagnosis, limitations, and the future prospects-a narrative review

PURPOSE

This review aims to explore the role of AI in the application of pancreatic cancer management and make recommendations to minimize the impact of the limitations to provide further benefits from AI use in the future.

METHODS

A comprehensive review of the literature was conducted using a combination of MeSH keywords, including "Artificial intelligence", "Pancreatic cancer", "Diagnosis", and "Limitations".

RESULTS

The beneficial implications of AI in the detection of biomarkers, diagnosis, and prognosis of pancreatic cancer have been explored. In addition, current drawbacks of AI use have been divided into subcategories encompassing statistical, training, and knowledge limitations; data handling, ethical and medicolegal aspects; and clinical integration and implementation.

CONCLUSION

Artificial intelligence (AI) refers to computational machine systems that accomplish a set of given tasks by imitating human intelligence in an exponential learning pattern. AI in gastrointestinal oncology has continued to provide significant advancements in the clinical, molecular, and radiological diagnosis and intervention techniques required to improve the prognosis of many gastrointestinal cancer types, particularly pancreatic cancer.

Patients with Chronic Liver Disease under Surveillance for Hepatocellular Carcinoma Have a Favorable Long-Term Outcome for Pancreatic Cancer Due to Early Diagnosis and High Resection Rate

Patients with viral hepatitis-related chronic liver disease (CLD) under surveillance for hepatocellular carcinoma (HCC) are often diagnosed with pancreatic cancer (PC) at an early stage. However, the long-term outcomes of these patients are unclear. We aimed to clarify the long-term outcomes of patients with PC with viral hepatitis-related CLD using a chart review. Data collection included the Union for International Cancer Control (UICC) stage at PC diagnosis, hepatitis B virus and hepatitis C virus status, and long-term outcomes. The distribution of the entire cohort (N = 552) was as follows: early stage (UICC 0-IB; n = 52, 9.5%) and non-early stages (UICC IIA-IV; n = 500, 90.5%). At diagnosis, the HCC surveillance group (n = 18) had more patients in the early stages than the non-surveillance group (n = 534) (50% vs. 8.0%), leading to a higher indication rate for surgical resection (72.2% vs. 29.8%) and a longer median survival time (19.0 months vs. 9.9 months). We confirmed that patients with viral hepatitis-related CLD under HCC surveillance were diagnosed with PC at an early stage. Because of the higher indication rate for surgical resection in these patients, they had favorable long-term outcomes for PC.

A retrospective preliminary study of intrapancreatic late enhancement as a noteworthy imaging finding in the early stages of pancreatic adenocarcinoma

OBJECTIVE

To characterize intrapancreatic late enhancement (ILE) observed in the early stages of pancreatic adenocarcinoma (PAC).

METHODS

Among 203 patients pathologically diagnosed with PAC between October 2011 and February 2021, 32 patients with pre-diagnostic abdominal contrast-enhanced CT performed from 6 months to 5 years before the diagnosis were enrolled in this study. Indirect findings (IFs) on pre-diagnostic CT, including ILE, were evaluated and examined for various clinical data and time intervals to diagnosis (TIDs). The detected ILE was quantitatively evaluated, and the effect of ILE awareness on lesion detection by two radiologists and their interobserver agreement were assessed.

RESULTS

Among the 32 patients, 23 showed IFs. ILE was observed in 14 patients (63%), with a median TID of 17 months (interquartile ratio [IQR]: 9.3-42.3). ILE alone was observed in eight patients (35%), ILE with focal pancreatic parenchymal atrophy (FPPA) was observed in five patients (22%), and ILE with main pancreatic duct abnormalities (MPDA) was observed in one patient (4%). Pancreatic head lesions were significantly more frequent in patients with ILE alone than in patients with FPPA or MPDA (p = 0.026). The median long-axis diameters of the region with ILE and ILE-to-pancreas contrast were 10 (IQR: 5-11) mm and 24 (IQR: 17-33) HU, respectively. Awareness of ILE led observers to detect two or three more pancreatic head lesions, and interobserver agreement increased from poor agreement (k = 0.17) to moderate agreement (k = 0.55).

CONCLUSION

ILE is a significant IF for early PAC detection.

KEY POINTS

• Intrapancreatic late enhancement (ILE) is a significant indirect finding in the early detection of pancreatic adenocarcinoma. • ILE without other indirect findings is expected to help detect pancreatic head lesions. • Image evaluation focusing on ILE can increase lesion detection and improve the interobserver agreement.

Focal pancreatic parenchyma atrophy is a harbinger of pancreatic cancer and a clue to the intraductal spreading subtype

BACKGROUND/OBJECTIVES

Radiological evidence of focal pancreatic parenchymal atrophy (FPPA) may presage early pancreatic ductal adenocarcinoma (PDAC) development. We aimed to clarify the incidence of FPPA and the clinicopathological features of PDAC with FPPA before diagnosis.

METHODS

Data on endoscopic ultrasound-guided fine-needle biopsies and surgical samples from 170 patients with pancreatic cancer histologically diagnosed between 2014 and 2019 were extracted from the pathology database of Komagome Hospital and Juntendo University hospital and retrospectively evaluated together with 51 patients without PDAC.

RESULTS

FPPA was identified in 47/170 (28%) patients before PDAC diagnosis and in 2/51 (4%) patients in the control group (P < 0.01). The median duration from FPPA detection to diagnosis was 35 (interquartile range [IQR]:16-63) months. In 24/47 (51%) patients with FPPA, the atrophic area resolved. The lesion was in the head and body/tail in 7/40 and 67/56 of the patients with (n = 47) and without FPPA (n = 123), respectively (P < 0.001). Histopathologically confirmed non-invasive lesions in the main pancreatic duct and a positive surgical margin in the resected specimens occurred in 53% vs. 21% (P = 0.078) and 29% vs. 3% (P = 0.001) of the groups, respectively. The PDAC patients with FPPA accompanied by a malignant pancreatic resection margin had high-grade pancreatic intraepithelial neoplasia.

CONCLUSIONS

FPPA occurred in 28% of the PDAC group at 35 months prediagnosis. The FPPA area resolved before PDAC onset. Benchmarking previous images of the pancreas with the focus on FPPA may enable prediction of PDAC. PDAC with FPPA involves widespread high-grade pancreatic intraepithelial neoplasia requiring a wide surgical margin for surgical excision.

Transabdominal ultrasound of pancreatic ductal adenocarcinoma: A multi-centered population-based study in sensitivity, associated diagnostic intervals, and survival

OBJECTIVES

To determine the sensitivity of ultrasound (US) in detecting pancreatic ductal adenocarcinoma in our region, to identify factors associated with US test result, and assess the impact on the diagnostic interval and survival.

METHODS

Patients diagnosed between January 1, 2014 and December 31, 2015 in Nova Scotia, Canada were identified by a cancer registry. US performed prior to diagnosis were retrospectively graded as true positive (TP), indeterminate or false negative (FN). Amongst US results, differences in age, weight and tumor size were assessed [one-way analysis of variance (ANOVA)]. Associations between result and sex, tumor location (proximal/distal), clinical suspicion of malignancy, and visualization of the pancreas, tumor, secondary signs and liver metastases were assessed (Chi-square). Mean follow-up imaging, diagnostic, and survival intervals were assessed (one-way ANOVA).

RESULTS

One hundred thirteen US of 107 patients (54 women; mean 70 ± 13 years) were graded as follows: 48/113 (42.5%) TPs; 42/113 (37.2%) indeterminates; and 23/113 (20.4%) FNs. Sensitivity was 48/71(67.6%). There was no difference in age, weight or tumor size amongst US result (P > 0.5). FNs had proportionally more men (P = 0.011) and lacked clinical suspicion of malignancy (P = 0.0006); TPs had proportionally more proximal tumors (P = 0.017). US result was associated with visualization of the pancreas, tumor, secondary signs and liver metastases (P < 0.005). FNs had longer mean follow-up imaging (P < 0.0001) and diagnostic (P = 0.0007) intervals, and worse mean survival (P = 0.034).

CONCLUSIONS

In our region, the sensitivity of US in detecting pancreatic ductal adenocarcinoma is 67.6%. A false negative US is associated with delayed diagnostic work-up and worse mean survival.

Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case-control study

PURPOSE

To characterize the prevalence of missed pancreatic masses and pancreatic ductal adenocarcinoma (PDAC)-related findings on CT and MRI between pre-diagnostic patients and healthy individuals.

MATERIALS AND METHODS

Patients diagnosed with PDAC (2010-2016) were retrospectively reviewed for abdominal CT- or MRI-examinations 1 month-3 years prior to their diagnosis, and subsequently matched to controls in a 1:4 ratio. Two blinded radiologists scored each imaging exam on the presence of a pancreatic mass and secondary features of PDAC. Additionally, original radiology reports were graded based on the revised RADPEER criteria.

RESULTS

The cohort of 595 PDAC patients contained 60 patients with a pre-diagnostic CT and 27 with an MRI. A pancreatic mass was suspected in hindsight on CT in 51.7% and 50% of cases and in 1.3% and 0.9% of controls by reviewer 1 (p < .001) and reviewer 2 (p < .001), respectively. On MRI, a mass was suspected in 70.4% and 55.6% of cases and 2.9% and 0% of the controls by reviewer 1 (p < .001) and reviewer 2 (p < .001), respectively. Pancreatic duct dilation, duct interruption, focal atrophy, and features of acute pancreatitis is strongly associated with PDAC (p < .001). In cases, a RADPEER-score of 2 or 3 was assigned to 56.3% of the CT-reports and 71.4% of MRI-reports.

CONCLUSION

Radiological features as pancreatic duct dilation and interruption, and focal atrophy are common first signs of PDAC and are often missed or unrecognized. Further investigation with dedicated pancreas imaging is warranted in patients with PDAC-related radiological findings.

Application of artificial intelligence to pancreatic adenocarcinoma

BACKGROUND AND OBJECTIVES

Pancreatic cancer (PC) is one of the deadliest cancers worldwide although substantial advancement has been made in its comprehensive treatment. The development of artificial intelligence (AI) technology has allowed its clinical applications to expand remarkably in recent years. Diverse methods and algorithms are employed by AI to extrapolate new data from clinical records to aid in the treatment of PC. In this review, we will summarize AI's use in several aspects of PC diagnosis and therapy, as well as its limits and potential future research avenues.

METHODS

We examine the most recent research on the use of AI in PC. The articles are categorized and examined according to the medical task of their algorithm. Two search engines, PubMed and Google Scholar, were used to screen the articles.

RESULTS

Overall, 66 papers published in 2001 and after were selected. Of the four medical tasks (risk assessment, diagnosis, treatment, and prognosis prediction), diagnosis was the most frequently researched, and retrospective single-center studies were the most prevalent. We found that the different medical tasks and algorithms included in the reviewed studies caused the performance of their models to vary greatly. Deep learning algorithms, on the other hand, produced excellent results in all of the subdivisions studied.

CONCLUSIONS

AI is a promising tool for helping PC patients and may contribute to improved patient outcomes. The integration of humans and AI in clinical medicine is still in its infancy and requires the in-depth cooperation of multidisciplinary personnel.

Recent advances in artificial intelligence for pancreatic ductal adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) remains the most lethal type of cancer. The 5-year survival rate for patients with early-stage diagnosis can be as high as 20%, suggesting that early diagnosis plays a pivotal role in the prognostic improvement of PDAC cases. In the medical field, the broad availability of biomedical data has led to the advent of the "big data" era. To overcome this deadly disease, how to fully exploit big data is a new challenge in the era of precision medicine. Artificial intelligence (AI) is the ability of a machine to learn and display intelligence to solve problems. AI can help to transform big data into clinically actionable insights more efficiently, reduce inevitable errors to improve diagnostic accuracy, and make real-time predictions. AI-based omics analyses will become the next alterative approach to overcome this poor-prognostic disease by discovering biomarkers for early detection, providing molecular/genomic subtyping, offering treatment guidance, and predicting recurrence and survival. Advances in AI may therefore improve PDAC survival outcomes in the near future. The present review mainly focuses on recent advances of AI in PDAC for clinicians. We believe that breakthroughs will soon emerge to fight this deadly disease using AI-navigated precision medicine.

Analysis of Progression Time in Pancreatic Cancer including Carcinoma In Situ Based on Magnetic Resonance Cholangiopancreatography Findings

BACKGROUND

Pancreatic cancer (PC) exhibits extremely rapid growth; however, it remains largely unknown whether the early stages of PC also exhibit rapid growth speed equivalent to advanced PC. This study aimed to investigate the natural history of early PCs through retrospectively assessing pre-diagnostic images.

METHODS

We examined the data of nine patients, including three patients with carcinoma in situ (CIS), who had undergone magnetic resonance cholangiopancreatography (MRCP) to detect solitary main pancreatic duct (MPD) stenosis >1 year before definitive PC diagnosis. We retrospectively analyzed the time to diagnosis and first-time tumor detection from the estimated time point of first-time MPD stenosis detection without tumor lesion.

RESULTS

The median tumor size at diagnosis and the first-time tumor detection size were 14 and 7.5 mm, respectively. The median time to diagnosis and first-time tumor detection were 26 and 49 months, respectively.

CONCLUSIONS

No studies have investigated the PC history, especially that of early PCs, including CIS, based on the initial detection of MPD stenosis using MRCP. Assessment of a small number of patients showed that the time to progression can take several years in the early PC stages. Understanding this natural history is very important in the clinical setting.

CT Abnormalities of the Pancreas Associated With the Subsequent Diagnosis of Clinical Stage I Pancreatic Ductal Adenocarcinoma More Than One Year Later: A Case-Control Study

Background: Pancreatic ductal adenocarcinoma (PDAC) is highly lethal, partly due to challenges in early diagnosis. However, the prognosis for earlier stages (carcinoma in situ or stage T1a invasive carcinoma) is relatively favorable. Objective: To investigate findings of an earlier diagnosis of PDAC on pre-diagnostic CT examinations performed at least one year before the diagnosis of clinical stage I PDAC. Methods: This retrospective study included 103 patients with clinical stage I PDAC and a pre-diagnostic CT at least one year before the CT that detected PDAC, as well as 103 control patients without PDAC on CT examinations separated by at least 10 years. The frequency and temporal characteristics of focal pancreatic abnormalities (pancreatic mass, main pancreatic duct (MPD) change, parenchymal atrophy, faint parenchymal enhancement, cyst, and parenchymal calcification) on pre-diagnostic CT examinations were determined. Results: A focal pancreatic abnormality was present on the most recent pre-diagnostic CT in 55/103 (53.4%) patients with PDAC versus 21/103 (20.4%) control patients (p<.001). In patients with PDAC, the most common focal abnormalities on pre-diagnostic CT were atrophy (39/103, 37.9%), faint enhancement (17/65, 26.2%), and MPD change (14/103, 13.6%), which were all more frequent in patients with PDAC than in control patients (p<.05). In 54/55 (98.2%) patients with PDAC, the PDAC corresponded with the site of a focal abnormality (exact location or the abnormality's upstream or downstream edge) on pre-diagnostic CT. Frequency of focal abnormalities decreased with increasing time before the CT that detected PDAC (1-2 years before diagnosis, 64.9%; 2-3 years, 49.2%; 3-5 years, 41.8%; 5-7 years, 29.7%; 7-10 years, 18.5%; over 10 years, 0%). Mean duration from the finding's initial appearance to diagnosis of PDAC was 4.6 years for atrophy, 3.3 years for faint enhancement, and 1.1 years for MPD change. Conclusion: Most patients with clinical stage I PDAC demonstrated focal pancreatic abnormalities on pre-diagnostic CT obtained at least one year before diagnosis. Focal MPD change exhibited the shortest duration from its development to subsequent diagnosis, where atrophy and faint enhancement exhibited a relatively prolonged course. Clinical impact: These findings could facilitate earlier PDAC diagnosis and thus improve prognosis.

AdipoRon: A Novel Insulin Sensitizer in Various Complications and the Underlying Mechanisms: A Review

BACKGROUND

AdipoRon is the first synthetic analog of endogenous adiponectin, an adipose tissue-derived hormone. AdipoRon possesses pharmacological properties similar to adiponectin and its ability to bind and activate the adipoR1 and adipoR2 receptors makes it a suitable candidate for the treatment of a multitude of disorders.

OBJECTIVE

In the present review, an attempt was made to compile and discuss the efficacy of adipoRon against various disorders.

RESULTS

AdipoRon is a drug that acts not only in metabolic diseases but in other conditions unrelated to energy metabolism. It is well- reported that adipoRon exhibits strong anti-obesity, anti-diabetic, anticancer, anti-depressant, anti-ischemic, anti-hypertrophic properties and also improves conditions like post-traumatic stress disorder, anxiety, and systemic sclerosis.

CONCLUSION

A lot is known about its effects in experimental systems, but the translation of this knowledge to the clinic requires studies which, for many of the potential target conditions, have yet to be carried out. The beneficial effects of AdipoRon in novel clinical conditions will suggest an underlying pathophysiological role of adiponectin and its receptors in previously unsuspected settings.

Computed tomography findings for predicting the future occurrence of pancreatic cancer: value of pancreatic volumetry

BACKGROUND

The features of pancreatic parenchyma that tend to progress towards pancreatic cancer (PC) are unknown. We performed volumetry of the pancreas in PC patients using computed tomography (CT) scans acquired before detection of PC, and investigated whether CT findings of pancreatic parenchyma could predict the future occurrence of PC.

METHODS

Between April 2009 and March 2017, a total of 3769 patients underwent abdominal contrast-enhanced CT, the scans of which were archived as digital images. Among them, 15 PC patients underwent abdominal CT 6-120 months before diagnosis of PC. This retrospective study compared the 15 PC patients (PC group) with 15 propensity score-matched subjects without PC (non-PC group). Pancreatic volumetry and radiological findings were compared between the two groups.

RESULTS

There were significant differences between the PC and non-PC groups in the volume of the main pancreatic duct (MPD) plus any cystic lesion (P = 0.007), volume of the MPD plus any cystic lesion/body surface area (BSA; P = 0.009), MPD diameter (P = 0.011), and MPD diameter/BSA (P = 0.013). Univariate analysis revealed volume of MPD plus any cystic lesion/BSA ≥ 0.53 mL/m² (odds ratio [OR] 38.50, P = 0.002), volume of pancreatic parenchyma/BSA < 27.0 mL/m² (OR 12.25, P = 0.030), and MPD diameter/BSA ≥ 1.0 mm/m² (OR 13.00, P = 0.006) as significant risk factors for PC.

CONCLUSIONS

Quantification of the volume of MPD plus any cystic lesion/BSA, volume of pancreatic parenchyma/BSA, and MPD diameter/BSA on pre-diagnosis CT were useful for predicting the future occurrence of PC.

Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset

PURPOSE

To develop a two-stage three-dimensional (3D) convolutional neural networks (CNNs) for fully automated volumetric segmentation of pancreas on computed tomography (CT) and to further evaluate its performance in the context of intra-reader and inter-reader reliability at full dose and reduced radiation dose CTs on a public dataset.

METHODS

A dataset of 1994 abdomen CT scans (portal venous phase, slice thickness ≤ 3.75-mm, multiple CT vendors) was curated by two radiologists (R1 and R2) to exclude cases with pancreatic pathology, suboptimal image quality, and image artifacts (n = 77). Remaining 1917 CTs were equally allocated between R1 and R2 for volumetric pancreas segmentation [ground truth (GT)]. This internal dataset was randomly divided into training (n = 1380), validation (n = 248), and test (n = 289) sets for the development of a two-stage 3D CNN model based on a modified U-net architecture for automated volumetric pancreas segmentation. Model's performance for pancreas segmentation and the differences in model-predicted pancreatic volumes vs GT volumes were compared on the test set. Subsequently, an external dataset from The Cancer Imaging Archive (TCIA) that had CT scans acquired at standard radiation dose and same scans reconstructed at a simulated 25% radiation dose was curated (n = 41). Volumetric pancreas segmentation was done on this TCIA dataset by R1 and R2 independently on the full dose and then at the reduced radiation dose CT images. Intra-reader and inter-reader reliability, model's segmentation performance, and reliability between model-predicted pancreatic volumes at full vs reduced dose were measured. Finally, model's performance was tested on the benchmarking National Institute of Health (NIH)-Pancreas CT (PCT) dataset.

RESULTS

Three-dimensional CNN had mean (SD) Dice similarity coefficient (DSC): 0.91 (0.03) and average Hausdorff distance of 0.15 (0.09) mm on the test set. Model's performance was equivalent between males and females (P = 0.08) and across different CT slice thicknesses (P > 0.05) based on noninferiority statistical testing. There was no difference in model-predicted and GT pancreatic volumes [mean predicted volume 99 cc (31cc); GT volume 101 cc (33 cc), P = 0.33]. Mean pancreatic volume difference was -2.7 cc (percent difference: -2.4% of GT volume) with excellent correlation between model-predicted and GT volumes [concordance correlation coefficient (CCC)=0.97]. In the external TCIA dataset, the model had higher reliability than R1 and R2 on full vs reduced dose CT scans [model mean (SD) DSC: 0.96 (0.02), CCC = 0.995 vs R1 DSC: 0.83 (0.07), CCC = 0.89, and R2 DSC:0.87 (0.04), CCC = 0.97]. The DSC and volume concordance correlations for R1 vs R2 (inter-reader reliability) were 0.85 (0.07), CCC = 0.90 at full dose and 0.83 (0.07), CCC = 0.96 at reduced dose datasets. There was good reliability between model and R1 at both full and reduced dose CT [full dose: DSC: 0.81 (0.07), CCC = 0.83 and reduced dose DSC:0.81 (0.08), CCC = 0.87]. Likewise, there was good reliability between model and R2 at both full and reduced dose CT [full dose: DSC: 0.84 (0.05), CCC = 0.89 and reduced dose DSC:0.83(0.06), CCC = 0.89]. There was no difference in model-predicted and GT pancreatic volume in TCIA dataset (mean predicted volume 96 cc (33); GT pancreatic volume 89 cc (30), p = 0.31). Model had mean (SD) DSC: 0.89 (0.04) (minimum-maximum DSC: 0.79 -0.96) on the NIH-PCT dataset.

CONCLUSION

A 3D CNN developed on the largest dataset of CTs is accurate for fully automated volumetric pancreas segmentation and is generalizable across a wide range of CT slice thicknesses, radiation dose, and patient gender. This 3D CNN offers a scalable tool to leverage biomarkers from pancreas morphometrics and radiomics for pancreatic diseases including for early pancreatic cancer detection.

Pre-Operative Imaging and Pathological Diagnosis of Localized High-Grade Pancreatic Intra-Epithelial Neoplasia without Invasive Carcinoma

Pancreatic ductal adenocarcinoma (PDAC) arises from precursor lesions, such as pancreatic intra-epithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasm (IPMN). The prognosis of high-grade precancerous lesions, including high-grade PanIN and high-grade IPMN, without invasive carcinoma is good, despite the overall poor prognosis of PDAC. High-grade PanIN, as a lesion preceding invasive PDAC, is therefore a primary target for intervention. However, detection of localized high-grade PanIN is difficult when using standard radiological approaches. Therefore, most studies of high-grade PanIN have been conducted using specimens that harbor invasive PDAC. Recently, imaging characteristics of high-grade PanIN have been revealed. Obstruction of the pancreatic duct due to high-grade PanIN may induce a loss of acinar cells replaced by fibrosis and lobular parenchymal atrophy. These changes and additional inflammation around the branch pancreatic ducts (BPDs) result in main pancreatic duct (MPD) stenosis, dilation, retention cysts (BPD dilation), focal pancreatic parenchymal atrophy, and/or hypoechoic changes around the MPD. These indirect imaging findings have become important clues for localized, high-grade PanIN detection. To obtain pre-operative histopathological confirmation of suspected cases, serial pancreatic-juice aspiration cytologic examination is effective. In this review, we outline current knowledge on imaging characteristics of high-grade PanIN.

Application of Radiomics Analysis Based on CT Combined With Machine Learning in Diagnostic of Pancreatic Neuroendocrine Tumors Patient's Pathological Grades

Purpose

To evaluate the value of multiple machine learning methods in classifying pathological grades (G1,G2, and G3), and to provide the best machine learning method for the identification of pathological grades of pancreatic neuroendocrine tumors (PNETs) based on radiomics.

Materials and Methods

A retrospective study was conducted on 82 patients with Pancreatic Neuroendocrine tumors. All patients had definite pathological diagnosis and grading results. Using Lifex software to extract the radiomics features from CT images manually. The sensitivity, specificity, area under the curve (AUC) and accuracy were used to evaluate the performance of the classification model.

Result

Our analysis shows that the CT based radiomics features combined with multi algorithm machine learning method has a strong ability to identify the pathological grades of pancreatic neuroendocrine tumors. DC + AdaBoost, DC + GBDT, and Xgboost+RF were very valuable for the differential diagnosis of three pathological grades of PNET. They showed a strong ability to identify the pathological grade of pancreatic neuroendocrine tumors. The validation set AUC of DC + AdaBoost is 0.82 (G1 vs G2), 0.70 (G2 vs G3), and 0.85 (G1 vs G3), respectively.

Conclusion

In conclusion, based on enhanced CT radiomics features could differentiate between different pathological grades of pancreatic neuroendocrine tumors. Feature selection method Distance Correlation + classifier method Adaptive Boosting show a good application prospect.

Computerized tomography scan in pre-diagnostic pancreatic ductal adenocarcinoma: Stages of progression and potential benefits of early intervention: A retrospective study

BACKGROUND

The frequency, nature and timeline of changes on thin-slice (≤3 mm) multi-detector computerized tomography (CT) scans in the pre-diagnostic phase of pancreatic ductal adenocarcinoma (PDAC) are unknown. It is unclear if identifying imaging changes in this phase will improve PDAC survival beyond lead time.

METHODS

From a cohort of 128 subjects (Cohort A) with CT scans done 3-36 months before diagnosis of PDAC we developed a CTgram defining CT Stages (CTS) I through IV in the radiological progression of pre-diagnostic PDAC. We constructed Cohort B of PDAC resected at CTS I and II and compared survival in CTS I and II in Cohort A (n = 22 each; control natural history cohort) vs Cohort B (n = 33 and 72, respectively; early interception cohort).

RESULTS

CTs were abnormal in 16% and 85% at 24-36 and 3-6 months respectively, before PDAC diagnosis. The PDAC CTgram stages, findings and median lead times (months) to clinical diagnosis were: CTS I: Abrupt duct cut-off/duct dilatation (-12.8); CTS II: Low density mass confined to pancreas (-9.5), CTS III: Peri-pancreatic infiltration (-5.8), CTS IV: Distant metastases (only at diagnosis). PDAC survival was better in cohort B than in cohort A despite inclusion of lead time in Cohort A: CTS I (36 vs 17.2 months, p = 0.03), CTS II (35.2 vs 15.3 months, p = 0.04).

CONCLUSION

Starting 12-18 months before PDAC diagnosis, progressive and increasingly frequent changes occur on CT scans. Resection of PDAC at the time of pre-diagnostic CT changes is likely to provide survival benefit beyond lead time.

Pancreatic Cancer Imaging: A New Look at an Old Problem

Computed tomography is the most commonly used imaging modality to detect and stage pancreatic cancer. Previous advances in pancreatic cancer imaging have focused on optimizing image acquisition parameters and reporting standards. However, current state-of-the-art imaging approaches still misdiagnose some potentially curable pancreatic cancers and do not provide prognostic information or inform optimal management strategies beyond stage. Several recent developments in pancreatic cancer imaging, including artificial intelligence and advanced visualization techniques, are rapidly changing the field. The purpose of this article is to review how these recent advances have the potential to revolutionize pancreatic cancer imaging.

The implications of missed or misinterpreted cases of pancreatic ductal adenocarcinoma on imaging: a multi-centered population-based study

OBJECTIVES

To assess the proportion of missed/misinterpreted imaging examinations of pancreatic ductal adenocarcinoma (PDAC), and their association with the diagnostic interval and survival.

METHODS

Two hundred fifty-seven patients (mean age, 71.8 years) diagnosed with PDAC in 2014-2015 were identified from the Nova Scotia Cancer Registry. Demographics, stage, tumor location, and dates of initial presentation, diagnosis, and, if applicable, surgery and death were recorded. US, CT, and MRI examinations during the diagnostic interval were independently graded by two radiologists using the RADPEER system; discordance was resolved in consensus. Mean diagnostic interval and survival were compared amongst RADPEER groups (one-way ANOVA). Kaplan-Meier analysis was performed for age (< 65, 65-79, ≥ 80), sex, tumor location (proximal/distal), stage (I-IV), surgery (yes/no), chemotherapy (yes/no), and RADPEER score (1-3). Association between these covariates and survival was assessed (multivariate Cox proportion hazards model).

RESULTS

RADPEER 1-3 scores were assigned to 191, 27, and 39 patients, respectively. Mean diagnostic intervals were 53, 86, and 192 days, respectively (p = 0.018). There were only 3/257 (1.2%) survivors. Mean survival was not different between groups (p = 0.43). Kaplan-Meier analysis showed worse survival in RADPEER 1-2 (p = 0.007), older age (p < 0.001), distal PDAC (p = 0.016), stage (p < 0.0001), and no surgery (p < 0.001); survival was not different with sex (p = 0.083). Cox analysis showed better survival in RADPEER 3 (p = 0.005), women (p = 0.002), surgical patients (p < 0.001), and chemotherapy (p < 0.001), and worse survival in stage IV (p = 0.006).

CONCLUSION

Imaging-related delays occurred in one-fourth of patients and were associated with longer diagnostic intervals but not worse survival, potentially due to overall poor survival in the cohort.

KEY POINTS

• One-fourth of patients (66/257, 25.7%) with pancreatic ductal adenocarcinoma (PDAC) underwent imaging examinations that demonstrated manifestations of the disease, but findings were either missed or misinterpreted; RADPEER 2 and 3 scores were assigned to 10.5% and 15.2% of patients, respectively. • Patients with imaging examinations assigned RADPEER 3 scores were associated with significantly longer diagnostic intervals (192 ± 323 days) than RADPEER 1 (53 ± 86 days) and RADPEER 2 (86 ± 120 days) (p < 0.001). • Imaging-related diagnostic delays were not associated with worse survival; however, this may have been confounded by the overall poor survival in our cohort (only 3/257 (1.2%) survivors).

Partial Pancreatic Parenchymal Atrophy Is a New Specific Finding to Diagnose Small Pancreatic Cancer (≤10 mm) Including Carcinoma in Situ: Comparison with Localized Benign Main Pancreatic Duct Stenosis Patients

BACKGROUND

This study aimed to evaluate and identify the specific CT findings by focusing on abnormalities in the main pancreatic duct (MPD) and pancreatic parenchyma in patients with small pancreatic cancer (PC) including carcinoma in situ (CIS).

METHODS

Nine CT findings indicating abnormalities of MPD and pancreatic parenchyma were selected as candidate findings for the presence of small PC ≤ 10 mm. The proportions of patients positive for each finding were compared between small PC and benign MPD stenosis groups. Interobserver agreement between two independent image reviewers was evaluated using kappa statistics.

RESULTS

The final analysis included 24 patients with small PC (including 11 CIS patients) and 28 patients with benign MPD stenosis. The proportion of patients exhibiting partial pancreatic parenchymal atrophy (PPA) corresponding to the distribution of MPD stenosis (45.8% vs. 7.1%, p < 0.01), upstream PPA arising from the site of MPD stenosis (33.3% vs. 3.6%, p = 0.01), and MPD abrupt stenosis (45.8% vs. 14.3%, p = 0.03) was significantly higher in the small PC group than in the benign MPD stenosis group.

CONCLUSIONS

The presence of partial PPA, upstream PPA, and MPD abrupt stenosis on a CT image was highly suggestive of the presence of small PCs including CIS.

Pancreatic Fat Infiltration Is Associated with a Higher Risk of Pancreatic Ductal Adenocarcinoma

Background

Pancreatic ductal adenocarcinoma (PDAC) has a poor survival rate, partly due to delayed diagnosis. Identifying high-risk individuals could lead to early detection and improve survival. A number of risk factors such as alcohol consumption and metabolic syndrome are associated with fatty infiltration of the pancreas. Experimental models show that a fatty pancreas promotes tissue inflammation and fibrosis, which could promote PDAC.

Methods

We conducted a case-control study in a single-university tertiary hospital. Sixty-eight PDAC cases with recent non-contrast computed tomography (CT) and 235 controls were studied. The controls had no history of malignancy and underwent CT colonography for cancer screening in the same period. Pancreatic fat was estimated by calculating pancreatic (P) attenuation, corrected to splenic (S) attenuation, measured in three 1.0-cm² regions of the pancreas. The P.S100 value calculated was used to estimate fatty infiltration of the pancreas (FIP), with a lower P.S100 representing a higher FIP.

Results

The PDAC patients had a lower BMI and a higher rate of type 2 diabetes mellitus. The P.S100 was lower in cases than in controls (86.452 vs. 92.414, p = 4.016e-06), suggesting that FIP is higher with PDAC. The risk of developing PDAC steadily increased significantly for the quartiles with a higher FIP compared to the low FIP quartile. No correlation between BMI and FIP (r = -0.1031179; 95% confidence interval [CI] -0.22267106 to 0.01949092) was found. Adjusting for confounders (age, sex, BMI, and DM), the risk of developing PDAC according to the FIP was estimated to be 3.75 (95% CI 1.9234408-7.993337; p = 0.000171). FIP was stable before and after the diagnosis of PDAC in 9 cases with prior CT scans when no pancreatic tumor was identifiable.

Conclusion

Fatty pancreas is associated with an increased risk of pancreatic cancer. Once confirmed in larger-scale studies, these findings could help to identify at-risk individuals, particularly in high-risk groups such as chronic alcohol consumers.

Diagnostic accuracy of unenhanced CT texture analysis to differentiate mass-forming pancreatitis from pancreatic ductal adenocarcinoma

PURPOSE

To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC).

METHODS

A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDAC patients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded.

RESULTS

We applied 200% of SMOTE to MFP and PDAC patients, resulting in 90 MFP patients compared with 120 PDAC patients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model.

CONCLUSIONS

Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.

Incidentally detected pancreatic adenocarcinomas on computed tomography obtained during the follow-up for other diseases

PURPOSE

To determine imaging findings of pancreatic adenocarcinomas incidentally detected on contrast-enhanced multiphasic dynamic computed tomography (CT) obtained during the follow-up for other diseases.

METHODS

From January 2007 to December 2018, 14 patients with pancreatic adenocarcinomas incidentally detected on CT obtained during the follow-up for other diseases (incidental group) and 105 patients with pancreatic adenocarcinomas symptomatically detected on ultrasound or CT (non-incidental group) were included. Imaging characteristics of the tumor were compared between the two groups. Additionally, imaging findings prior to the detection of a tumor on previous CT images in the incidental group were also assessed.

RESULTS

In cancers of the pancreas body/tail, there was a significantly smaller tumor size (median, 17 mm vs. 42 mm, p < 0.001), a significantly lower incidence of loss of fatty marbling (p = 0.025), vascular involvement (p < 0.001), lymph node metastasis (p = 0.046) and distant metastasis (p = 0.017), and a significantly higher incidence of preserved lobulation (p < 0.001) in the incidental group than in the non-incidental group. Regarding the cancers of the pancreas head, there were no significant differences in the radiological findings between the two groups. On previous CT images, small pancreatic nodules, secondary signs, and loss of fatty marbling tended to be the preceding findings of incidental pancreatic adenocarcinomas.

CONCLUSION

Incidentally detected pancreatic adenocarcinomas in the pancreas body/tail were characterized by an earlier tumor stage than in cases of symptomatically detected pancreatic adenocarcinoma. Several CT findings prior to the detection of a tumor may be useful for the early detection of pancreatic adenocarcinoma during the follow-up for other diseases.

Pitfalls in the MDCT of pancreatic cancer: strategies for minimizing errors

Multidetector computed tomography (MDCT) is a widely used cross-sectional imaging modality for initial evaluation of patients with suspected pancreatic ductal adenocarcinoma (PDAC). However, diagnosis of PDAC can be challenging due to numerous pitfalls associated with image acquisition and interpretation, including technical factors, imaging features, and cognitive errors. Accurate diagnosis requires familiarity with these pitfalls, as these can be minimized using systematic strategies. Suboptimal acquisition protocols and other technical errors such as motion artifacts and incomplete anatomical coverage increase the risk of misdiagnosis. Interpretation of images can be challenging due to intrinsic tumor features (including small and isoenhancing masses, exophytic masses, subtle pancreatic duct irregularities, and diffuse tumor infiltration), presence of coexisting pathology (including chronic pancreatitis and intraductal papillary mucinous neoplasm), mimickers of PDAC (including focal fatty infiltration and focal pancreatitis), distracting findings, and satisfaction of search. Awareness of pitfalls associated with the diagnosis of PDAC along with the strategies to avoid them will help radiologists to minimize technical and interpretation errors. Cognizance and mitigation of these errors can lead to earlier PDAC diagnosis and ultimately improve patient prognosis.

Development of pancreatic cancer during observation for hepatocellular carcinoma: A retrospective cohort study

BACKGROUND/AIMS

We aimed to investigate incidence, characteristics, and possible risk factors of pancreatic cancer in patients under observation for hepatocellular carcinoma (HCC) because the association of hepatitis virus B infection and pancreatic cancer has been reported.

PATIENTS AND METHODS

We performed a retrospective cohort study in the Gastroenterology Department of a University Hospital in Japan between 2004 and 2012. A total of 1848 patients who underwent treatment for HCC were included at the initiation of treatment for HCC (mean follow-up period, 33.6 months). The patients received trimonthly radiological follow-ups. Newly developed cases of pancreatic cancer during follow-up for HCC were compared with that of an age- and sex-matched theoretical cohort from national statistics. Possible predisposing factors for pancreatic cancer related to HCC were assessed. Cumulative probabilities of developing a pancreatic cancer were compared using log-rank test.

RESULTS

About 13 of 1848 patients developed pancreatic cancer (mean follow-up period, 45.2 months). The risk ratio for all patients was 3.02 (log-rank test: P =0.01). Statistical analyses showed no effects of the following factors on the development of pancreatic cancer: age, sex, follow-up period, alcohol intake, laboratory data, presence of hepatitis virus, characteristics of HCC, type of treatment, number of radiological examinations, and cumulative effective dose.

CONCLUSIONS

Increased incidence of pancreatic cancer was found in patients under observation for HCC in a relatively small cohort. HCC or other common underlying conditions might be a risk factor for development of pancreatic cancer.

Use of Precision Imaging in the Evaluation of Pancreas Cancer

Pancreas cancer is an aggressive and fatal disease that will become one of the leading causes of cancer mortality by 2030. An all-out effort is underway to better understand the basic biologic mechanisms of this disease ranging from early development to metastatic disease. In order to change the course of this disease, diagnostic radiology imaging may play a vital role in providing a precise, noninvasive method for early diagnosis and assessment of treatment response. Recent progress in combining medical imaging, advanced image analysis and artificial intelligence, termed radiomics, can offer an innovate approach in detecting the earliest changes of tumor development as well as a rapid method for the detection of response. In this chapter, we introduce the principles of radiomics and demonstrate how it can provide additional information into tumor biology, early detection, and response assessments advancing the goals of precision imaging to deliver the right treatment to the right person at the right time.

Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue

OBJECTIVE. The objective of our study was to determine the utility of radiomics features in differentiating CT cases of pancreatic ductal adenocarcinoma (PDAC) from normal pancreas. MATERIALS AND METHODS. In this retrospective case-control study, 190 patients with PDAC (97 men, 93 women; mean age ± SD, 66 ± 9 years) from 2012 to 2017 and 190 healthy potential renal donors (96 men, 94 women; mean age ± SD, 52 ± 8 years) without known pancreatic disease from 2005 to 2009 were identified from radiology and pathology databases. The 3D volume of the pancreas was manually segmented from the preoperative CT scans by four trained researchers and verified by three abdominal radiologists. Four hundred seventy-eight radiomics features were extracted to express the phenotype of the pancreas. Forty features were selected for analysis because of redundancy of computed features. The dataset was divided into 255 training cases (125 normal control cases and 130 PDAC cases) and 125 validation cases (65 normal control cases and 60 PDAC cases). A random forest classifier was used for binary classification of PDAC versus normal pancreas of control cases. Accuracy, sensitivity, and specificity were calculated. RESULTS. Mean tumor size was 4.1 ± 1.7 (SD) cm. The overall accuracy of the random forest binary classification was 99.2% (124/125), and AUC was 99.9%. All PDAC cases (60/60) were correctly classified. One case from a renal donor was misclassified as PDAC (1/65). The sensitivity was 100%, and specificity was 98.5%. CONCLUSION. Radiomics features extracted from whole pancreas can be used to differentiate between CT cases from patients with PDAC and healthy control subjects with normal pancreas.