Abstract Library

#4586 Base on neuroendocrine tumour classification in CT imaging using pretrained vision transformers and data augmentation

Introduction: Neuroendocrine tumours (NETs) are a group of cancers that can be difficult to distinguish from other malignancies in CT imaging. Their diverse appearance often leads to diagnostic challenges, requiring advanced techniques to improve classification accuracy. Pretrained Vision Transformers (ViTs) have shown promise in medical image analysis, but additional methods are needed to enhance model robustness, particularly when dealing with complex and heterogeneous tumour characteristics.

Conference:

Presenting Author:

Authors: Li H, Tang Z, Ding Z, Chen Y, Li H,

Keywords: Vision transformers, Cancer Detection, Transfer Learning, Medical Image Analysis,

#4487 Fast pancreatic cancer diagnosis using lightweight Mamba framework

Introduction: Pancreatic cancer is a deadly malignancy often diagnosed too late for effective treatment. Fast and precise identification of pathological regions in histopathology images is essential but limited by current slow methods. We present a framework to accelerate this process and enhance diagnostic support.

Conference:

Presenting Author:

Authors: Shengzhe Y, Yan K,

Keywords: Pancreatic Cancer, Lightweight Mamba Architecture, Pathology Region Classification and Recognition,

#3857 The use of quantitative contrast-enhanced endoscopic ultrasound in the evaluation of pancreatic neuroendocrine tumors – Can we move from quality to quantity? A proof-of-concept study

Introduction: Contrast-enhanced EUS (CE-EUS) is a helpful tool for the diagnosis of pancreatic focal lesions, as pancreatic cancer (PC) and pancreatic neuroendocrine tumor (pNEN). The enhancement of the lesion after contrast medium injection is usually assessed qualitatively and arbitrarily by the endosonographer. Dedicated software has recently been developed to obtain an unbiased quantitative assessment using perfusion parameters.

Conference:

Presenting Author: Tacelli M

Authors: Tacelli M, Bina N, Capurso G, Zaccari P, Petrone M,

Keywords: CE-EUS, pNEN, artificial intelligence, pancreatic cancer, prediction,

#3789 Comparison of postoperative textbook outcome between pancreatic neuroendocrine tumor and pancreatic ductal adenocarcinoma – A nationwide retrospective cohort study

Introduction: Pancreatic neuroendocrine tumors (pNET) represent only 6% of pancreatic tumors, compared to 93% for pancreatic ductal adenocarcinoma (PDAC). Textbook outcome (TO) is a composite outcome measure that reflects a hospital’s surgical performance as well as quality of current practice.

Conference:

Presenting Author: Chen J

Authors: Chen J, Augustinus S, Engelsman A, Bonsing B, Groot Koerkamp B,

Keywords: pNET, PDAC, Dutch Pancreatic Cancer Audit, Textbook Outcome, Postoperative results,

#3604 Preoperative acute pancreatitis and hyperenzymemia are associated with poor prognosis in patients with non-functional pancreatic neuroendocrine tumors

Introduction: Acute pancreatitis (AP) and hyperenzymemia have been studied regarding their incidences and potential prognostic value in pancreatic cancer and intraductal papillary mucinous neoplasm. However, currently, the knowledge of the relationship between AP/ hyperenzymemia and pancreatic neuroendocrine tumors (PNETs) is from few cases reports or series.

Conference:

Presenting Author: Tan Q

Authors: Tan Q, Song H, Cao D, Wang X, Liu X,

Keywords: Acute pancreatitis, amylase, lipase, pancreatic neuroendocrine tumor, prognosis,