Multiple solid pancreatic lesions: Prevalence and features of non-malignancies on dynamic enhanced CT

Diffuse-Type Pancreatic Ductal Adenocarcinoma Mimicking Autoimmune Pancreatitis

Pancreatic ductal adenocarcinoma (PDAC) classically presents as a solitary mass on cross-sectional imaging. Diffuse-type PDAC is an unusual variant that accounts for 1%-5% of PDACs. Owing to its rarity, there are no established radiographic or endosonographic definitions. We report a unique case of diffuse-type PDAC presenting with imaging findings of 2 distinct masses in the pancreatic head and tail and with endoscopic ultrasound findings of diffuse gland enlargement mimicking autoimmune pancreatitis. The case illustrates the importance of sampling several areas of the pancreas when diffuse enlargement is present on endoscopic ultrasound and multiple masses are seen on cross-sectional imaging.

Synchronous Pancreatic Masses

Any mass lesion in the pancreas usually raises the possibility of undiagnosed pancreatic cancer. With the advancement of imaging modalities, we are seeing an increasing number of incidental findings, some of which may be clinically significant. When dealing with incidental pancreatic findings, it is critical to keep a broad differential in mind in addition to ruling out pancreatic malignancy. We present 3 rare cases of patients with 2 or more synchronous solid masses in the pancreas caused by pancreatic cancer, type 1 autoimmune pancreatitis, and sarcoidosis.

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

A Comparison of Etiologies and Characteristics of Solitary Versus Synchronous Pancreatic Masses Undergoing Endoscopic Ultrasound-Guided Biopsy

OBJECTIVES

Pancreatic mass lesions are often solitary, although rarely synchronous pancreatic masses are encountered. No study has compared synchronous lesions with solitary lesions in the same population. The aim of the present study was to determine the prevalence, clinical, radiographic, and histologic findings of multiple pancreatic masses on consecutive patients undergoing endoscopic ultrasound (EUS) for pancreatic mass lesion.

METHODS

All patients undergoing EUS for pancreatic mass lesions with histologic sampling over a 5-year span were identified. Charts were abstracted for demographics, medical history, radiographic findings, EUS findings, and histology and were reviewed.

RESULTS

A total of 646 patients were identified, of which 27 patients (4.18%) had more than 1 pancreatic mass on EUS or cross-sectional imaging. The 2 groups were comparable with each other in terms of demographic factors and medical history. The 2 cohorts were comparable in location of the largest pancreas lesion and EUS characteristics. Patients with synchronous mass lesions were more likely to have metastatic lesions (P = 0.01). No other differences in histology were noted between the 2 groups.

CONCLUSIONS

Patients with multiple pancreatic mass lesions were more likely to have metastatic lesions compared with patients with solitary lesions.

Multifocal autoimmune pancreatitis: A retrospective study in a single tertiary center of 26 patients with a 20-year literature review

BACKGROUND

Multifocal-type autoimmune pancreatitis (AIP), sometimes forming multiple pancreatic masses, is frequently misdiagnosed as pancreatic malignancy in routine clinical practice. It is critical to know the imaging features of multifocal-type AIP to prevent misdiagnosis and unnecessary surgery. To the best of our knowledge, there have been no studies evaluating the value of diffusionweighted imaging (DWI), axial fat-suppressed T1 weighted image (T1WI), and dynamic contrast enhanced-computed tomography (DCE-CT) in detecting the lesions of multifocal-type AIP.

AIM

To clarify the exact prevalence and radiological findings of multifocal AIP in our cohorts and compare the sensitivity of DWI, axial fat-suppressed T1WI, and DCE-CT for detecting AIP lesions. We also compared radiological features between multifocal AIP and pancreatic ductal adenocarcinoma with several key imaging landmarks.

METHODS

Twenty-six patients with proven multifocal AIP were retrospectively included. Two blinded independent radiologists rated their confidence level in detecting the lesions on a 5-point scale and assessed the diagnostic performance of DWI, axial fat-suppressed T1WI, and DCE-CT. CT and magnetic resonance imaging of multifocal AIP were systematically reviewed for typical imaging findings and compared with the key imaging features of pancreatic ductal adenocarcinoma.

RESULTS

Among 118 patients with AIP, 26 (22.0%) had multiple lesions (56 lesions). Ulcerative colitis was associated with multifocal AIP in 7.7% (2/26) of patients, and Crohn’s disease was present in 15.3% (4/26) of patients. In multifocal AIP, multiple lesions, delayed homogeneous enhancement, multifocal strictures of the main pancreatic duct, capsule-like rim, lower apparent diffusion coefficient values, and elevated serum Ig4 level were observed significantly more frequently than pancreatic ductal adenocarcinoma, whereas the presence of capsule-like rim in multifocal-type AIP was lower in frequency than total AIP. Of these lesions of multifocal AIP, DWI detected 89.3% (50/56) and 82.1% (46/56) by the senior and junior radiologist, respectively.

CONCLUSION

Multifocal AIP is not as rare as previously thought and was seen in 22.0% of our patients. The diagnostic performance of DWI for detecting multifocal AIP was best followed by axial fat-suppressed T1WI and DCE-CT.

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.

Exploring prior diseases associated with pancreatic cancer

Background Pancreatic cancer (PC) is among the most deadly forms of cancer; however, the risk factors of PC have yet to be sufficiently identified. In the present study, we sought to screen all prior diseases associated with PC incidence concurrently and construct pathways for the diseases. Materials and methods This total population-based case-control study used data collected from Taiwan's National Health Insurance Research Database for the period covering 1997-2013. The case group included 3726 patients newly diagnosed with PC, who were precisely matched to 3726 controls based on gender, age, residence, and insurance premiums. Stepwise multivariate logistic regression was used to screen previous diseases in windows of 1, 2 …, 9 years prior to the first diagnosis of PC. Path analysis was used to construct the pathways between relevant prior diseases and PC. Results Within 1 year prior to PC diagnosis, a total of 11 diseases were significantly correlated with PC, included 9 positive and 2 negative associations. Path analysis identified diabetes, pancreatitis as diseases with direct positive pathways to PC incidence, and dementia with direct negative pathways. Conclusions It appears that diabetes, peptic ulcer, and digestive conditions were the prior diseases associated with PC incidence.

Application of artificial intelligence in pancreaticobiliary diseases

The role of artificial intelligence and its applications has been increasing at a rapid pace in the field of gastroenterology. The application of artificial intelligence in gastroenterology ranges from colon cancer screening and characterization of dysplastic and neoplastic polyps to the endoscopic ultrasonographic evaluation of pancreatic diseases. Artificial intelligence has been found to be useful in the evaluation and enhancement of the quality measure for endoscopic retrograde cholangiopancreatography. Similarly, artificial intelligence techniques like artificial neural networks and faster region-based convolution network are showing promising results in early and accurate diagnosis of pancreatic cancer and its differentiation from chronic pancreatitis. Other artificial intelligence techniques like radiomics-based computer-aided diagnosis systems could help to differentiate between various types of cystic pancreatic lesions. Artificial intelligence and computer-aided systems also showing promising results in the diagnosis of cholangiocarcinoma and the prediction of choledocholithiasis. In this review, we discuss the role of artificial intelligence in establishing diagnosis, prognosis, predicting response to treatment, and guiding therapeutics in the pancreaticobiliary system.

Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network

BACKGROUND

Early diagnosis and accurate staging are important to improve the cure rate and prognosis for pancreatic cancer. This study was performed to develop an automatic and accurate imaging processing technique system, allowing this system to read computed tomography (CT) images correctly and make diagnosis of pancreatic cancer faster.

METHODS

The establishment of the artificial intelligence (AI) system for pancreatic cancer diagnosis based on sequential contrast-enhanced CT images were composed of two processes: training and verification. During training process, our study used all 4385 CT images from 238 pancreatic cancer patients in the database as the training data set. Additionally, we used VGG16, which was pre-trained in ImageNet and contained 13 convolutional layers and three fully connected layers, to initialize the feature extraction network. In the verification experiment, we used sequential clinical CT images from 238 pancreatic cancer patients as our experimental data and input these data into the faster region-based convolution network (Faster R-CNN) model that had completed training. Totally, 1699 images from 100 pancreatic cancer patients were included for clinical verification.

RESULTS

A total of 338 patients with pancreatic cancer were included in the study. The clinical characteristics (sex, age, tumor location, differentiation grade, and tumor-node-metastasis stage) between the two training and verification groups were insignificant. The mean average precision was 0.7664, indicating a good training effect of the Faster R-CNN. Sequential contrast-enhanced CT images of 100 pancreatic cancer patients were used for clinical verification. The area under the receiver operating characteristic curve calculated according to the trapezoidal rule was 0.9632. It took approximately 0.2 s for the Faster R-CNN AI to automatically process one CT image, which is much faster than the time required for diagnosis by an imaging specialist.

CONCLUSIONS

Faster R-CNN AI is an effective and objective method with high accuracy for the diagnosis of pancreatic cancer.

TRIAL REGISTRATION

ChiCTR1800017542; http://www.chictr.org.cn.