Differentiating benign from malignant pancreatic cysts on computed tomography

A model for predicting degree of malignancy in patients with intraductal papillary mucinous neoplasm

Background/Objectives

There is no predictive model available to address early stage malignant intraductal papillary mucinous neoplasm (IPMN) including high grade dysplasia (HGD) and pT1a (invasive component≤0.5 cm). The aim of this study was to establish an objective and sufficient model to predict the degree of malignancy in patients with IPMN, which can be easily applied in daily practice and adopted for any type of lesion.

Methods

A retrospective cohort study of 309 patients who underwent surgical resection for IPMN was performed. Members of the cohort were randomly allocated to the training or testing set. A detection tree model and random forest model were used for a 3-class classification to distinguish low grade dysplasia (LGD), HGD/pT1a IPMN, and invasive intraductal papillary mucinous cancer (I-IPMC) beyond pT1a.

Results

Of the 309 patients, 54 (17.4%) had early stage malignancy (19 HGD, 35 pT1a), 49 (15.9%) had I-IPMC beyond pT1a, and 206 (66.7%) had LGD IPMN. We proposed a 3-class classification model using a random forest algorithm, and the model had an accuracy of 99.5% with the training set, and displayed an accuracy of 96.0% with the testing set. We used SHAP for interpretation of the model and showed the top five factors (mural nodule size, main pancreatic duct diameter, CA19-9 levels, lesion edge and common bile duct dilation) were most likely to influence the 3-class classification results in terms of interpretation of the random forest model.

Conclusions

This predictive model will help assess an individual's risk for different stages of IPMN malignancy and may help identify patients with IPMN who require surgery.

Giant Pseudocyst of the Pancreas: A Case Report

Pancreatic cysts are usually asymptomatic over 70% of the time. They can be benign or malignant. Enhanced imaging modalities and increased usage of routine imaging have increased the identification of pancreatic cysts. If symptomatic, abdominal pain or back pain, unexplained weight loss, jaundice, steatorrhea or palpable mass are usually the presenting complaints. Pancreatic cysts are typically assessed by cross-sectional computed tomography (CT) and magnetic resonance imaging (MRI). In this article, we present a case of a 33-year-old female with a recurrent large pancreatic pseudocyst, initially measured 15.8 cm x 14 cm x 14 cm, who was subsequently admitted to our unit and managed successfully. After undergoing diagnostic laparoscopy, exploratory laparotomy, and pancreatic cystogastrostomy, the pseudocyst shrunk to 8 cm x 6 cm over 13 weeks. It is rare to come across a pseudocyst of such large dimensions. Despite its large size, the patient presented with vague abdominal pain as the only chief complaint. The unusual presentation of symptoms and the enormous size of the pseudocyst make this a unique case. Managing giant pancreatic pseudocysts can be complex, as seen in this scenario by the multiple approaches attempted to treat the pseudocyst.

Basic pancreatic lesions: Radiologic-pathologic correlation

The basic pancreatic lesions include location, size, shape, number, capsule, calcification/calculi, hemorrhage, cystic degeneration, fibrosis, pancreatic duct alterations, and microvessel. One or more basic lesions form a kind of pancreatic disease. As recognizing the characteristic imaging features of pancreatic basic lesions and their relationships with pathology aids in differentiating the variety of pancreatic diseases. The purpose of this study is to review the pathological and imaging features of the basic pancreatic lesions.