Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach

The automatic segmentation of the pancreatic cyst lesion (PCL) is essential for the automated diagnosis of pancreatic cyst lesions on endoscopic ultrasonography (EUS) images. In this study, we proposed a deep-learning approach for PCL segmentation on EUS images. We employed the Attention U-Net model for automatic PCL segmentation. The Attention U-Net was compared with the Basic U-Net, Residual U-Net, and U-Net++ models. The Attention U-Net showed a better dice similarity coefficient (DSC) and intersection over union (IoU) scores than the other models on the internal test. Although the Basic U-Net showed a higher DSC and IoU scores on the external test than the Attention U-Net, there was no statistically significant difference. On the internal test of the cross-over study, the Attention U-Net showed the highest DSC and IoU scores. However, there was no significant difference between the Attention U-Net and Residual U-Net or between the Attention U-Net and U-Net++. On the external test of the cross-over study, all models showed no significant difference from each other. To the best of our knowledge, this is the first study implementing segmentation of PCL on EUS images using a deep-learning approach. Our experimental results show that a deep-learning approach can be applied successfully for PCL segmentation on EUS images.

PSUEDOPANCREATIC CYST INVASION INTO PSOAS MUSCLE: CASE REPORT OF UNUSUAL LOCATION OF PSEUDO- PANCREATIC CYST

A 53 year old female patient presented in emergency with heaviness and pain in left hypogastrium and lumber region. On detailed history, patient revealed getting admitted for acute abdomen approximately 3 months back where she was diagnosed with gall stone induced pancreatitis. She was managed conservatively.

Co-analysis of pancreatic cyst fluid carcinoembryonic antigen and glucose with novel cut-off levels better distinguishes between mucinous and non-mucinous neoplastic pancreatic cystic lesions

Background Pancreatic cyst fluid analysis plays an important role in distinguishing between mucinous and non-mucinous cyst lesions. We aimed to compare the diagnostic performances of cyst fluid carcinoembryonic antigen (CEA), CA 19-9, and glucose in differentiating mucinous from non-mucinous neoplastic pancreatic cystic lesions (PCLs) and determine the best cut-off levels. Methods Patients’ data were evaluated retrospectively. 102 patients’ PCLs were grouped as non-neoplastic ( n = 25), non-mucinous neoplastic ( n = 20), mucinous neoplastic ( n = 47) and pancreatic adenocarcinomas with cystic degeneration ( n = 10); and CEA, CA 19-9, and glucose levels were compared. Receiver-operating characteristic analysis was performed, and the ideal cut-off values were determined. Results Cyst fluid CEA and CA 19-9, levels were significantly higher ( P < 0.001, P < 0.001, respectively) and glucose levels were significantly lower ( P = 0.001) in mucinous than in non-mucinous neoplastic PCLs. Area under curve with 95% confidence interval of CEA, glucose and CEA and glucose test combination was 0.939 (95% CI = 0.885–0.993, P = 0.001), 0.809 (95% CI = 0.695–0.924, P < 0.001) and 0.937 (95% CI = 0.879–0.995), respectively. CEA cut-offs to rule-in and rule-out mucinous neoplastic were 135.1 ng/mL (sensitivity = 62%, specificity = 94.7%) and 6.12 ng/mL (sensitivity = 94.1%, specificity = 80.4%), respectively. Glucose cut-off of 2.8 mmol/L was chosen both to rule-in and rule-out mucinous neoplastic PCLs (sensitivity = 78%, specificity = 80%). Co-analysis of CEA and glucose to distinguish mucinous from non-mucinous neoplastic PCLs had sensitivity = 87.8%, specificity = 93.3%, and diagnostic accuracy = 89.3%. Conclusions We concluded that co-analysis of cyst fluid CEA (cut-off = 135.1 ng/mL) and glucose (cut-off = 2.8 mmol/L) at novel cut-offs had the best testing performance to rule-in mucinous neoplastic PCLs. To rule-out mucinous PCLs co-analysis of CEA (cut-off = 6.12 ng/mL) and glucose (cut-off = 2.8 mmol/L) added value to prediction.

Pancreatic cyst surgery

Pancreatic cysts are rare. In the domestic literature from 1885 to 1958, only 295 such observations were published. The disease can occur at any age, but more often from 20 to 40 years, and somewhat more often in women.

Gastric antral duplication cyst: A case report

Alimentary tract duplications may be symptomatic or may be discovered incidentally. They are named for the organ with which they are associated.1 Congenital gastrointestinal (GI) tract duplication cysts are commonly located in the ileum (53%), mediastinum (18%), colon (13%), stomach (7%), duodenum (6%), rectum (4%), or oesophagus (2%)2. A single theory is insufficient to explain all types of duplications.3 Children may present with symptoms like vomiting, abdominal pain, lumps, or weight loss.4 The presence of ectopic gastric mucosa and the potential for malignancy remain matters of concern.2 Surgical management is essential for these rare cysts.5 We encountered a Bangladeshi boy with a gastric duplication cyst (GDC) that was pre-operatively diagnosed as a pancreatic cyst. A variety of imaging modalities failed to indicate GDC before the operation. Here we present the clinical course of the case and discuss the difficulties and problems in diagnosing GDC.