-
Computer Methods and Programs in... Jun 2024The pancreas is a vital organ in digestive system which has significant health implications. It is imperative to evaluate and identify malignant pancreatic lesions... (Review)
Review
The pancreas is a vital organ in digestive system which has significant health implications. It is imperative to evaluate and identify malignant pancreatic lesions promptly in light of the high mortality rate linked to such malignancies. Endoscopic Ultrasound (EUS) is a non-invasive precise technique to detect pancreas disorders, but it is highly operator dependent. Artificial intelligence (AI), including traditional machine learning (ML) and deep learning (DL) techniques can play a pivotal role to enhancing the performance of EUS regardless of operator. AI performs a critical function in the detection, classification, and segmentation of medical images. The utilization of AI-assisted systems has improved the accuracy and productivity of pancreatic analysis, including the detection of diverse pancreatic disorders (e.g., pancreatitis, masses, and cysts) as well as landmarks and parenchyma. This systematic review examines the rapidly developing domain of AI-assisted system in EUS of the pancreas. Its objective is to present a thorough study of the present research status and developments in this area. This paper explores the significant challenges of AI-assisted system in pancreas EUS imaging, highlights the potential of AI techniques in addressing these challenges, and suggests the scope for future research in domain of AI-assisted EUS systems.
Topics: Humans; Endosonography; Artificial Intelligence; Pancreas; Machine Learning; Deep Learning; Pancreatic Neoplasms; Pancreatic Diseases; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted
PubMed: 38703435
DOI: 10.1016/j.cmpb.2024.108205 -
Pancreatology : Official Journal of the... Apr 2024Mucinous cystic neoplasms (MCN) of the pancreas express estrogen and progesterone receptors. Several case reports describe MCN increasing in size during gestation. The...
BACKGROUND
Mucinous cystic neoplasms (MCN) of the pancreas express estrogen and progesterone receptors. Several case reports describe MCN increasing in size during gestation. The aim of this study is to assess if pregnancy is a risk factor for malignant degeneration of MCN.
METHODS
All female patients who underwent pancreatic resection of a MCN between 2011 and 2021 were included. MCN resected or diagnosed within 12 months of gestation were defined perigestational. MCN with high grade dysplasia or an invasive component were classified in the high grade (HG) group. The primary outcome was defined as the correlation between exposure to gestation and peri-gestational MCN to development of HG-MCN.
RESULTS
The study includes 176 patients, 25 (14 %) forming the HG group, and 151 (86 %) forming the low grade (LG) group. LG and HG groups had a similar distribution of systemic contraceptives use (26 % vs. 16 %, p = 0.262), and perigestational MCN (7 % vs 16 %, p = 0.108). At univariate analysis cyst size ≥10 cm (OR 5.3, p < 0.001) was associated to HG degeneration. Peri gestational MCN positively correlated with cyst size (R = 0.18, p = 0.020). In the subgroup of 14 perigestational MCN patients 29 % had HG-MCN and 71 % experienced cyst growth during gestation with an average growth of 55.1 ± 18 mm.
CONCLUSIONS
Perigestational MCN are associated to increased cyst diameter, and in the subset of patients affected by MCN during gestation a high rate of growth was observed. Patients with a MCN and pregnancy desire should undergo multidisciplinary counselling.
PubMed: 38702207
DOI: 10.1016/j.pan.2024.04.009 -
Turkish Journal of Surgery Dec 2023Hydatid disease is a zoonotic parasitic disease which rarely involves pancreas primarily. Diagnosis of pancreatic hydatid cyst is a challenge and operative skills are...
Hydatid disease is a zoonotic parasitic disease which rarely involves pancreas primarily. Diagnosis of pancreatic hydatid cyst is a challenge and operative skills are important to avoid spillage of cyst's content. A 19-year-old male patient was admitted to hospital with recurrent abdominal pain which was on epigastrium and left upper quadrant of abdomen. Pain was not associated with nausea, vomiting or fever. An abdominal computed tomography (CT) scan was ordered. As a result of abdominal CT scan, there was a cystic area in tail of pancreas with a diameter of 5.6 cm which includes septa and there was calcification on borders of the cyst. Possible diagnosis were either pancreatic hydatid disease, pancreatic cyst adenoma or cystadenocarcinoma or pseudocyst of autoimmune pancreatitis. Whole body positron emission tomography (PET-CT) scan showed no other cyst or lesion other than pancreatic cyst. Hydatid disease indirect hemagglutination test has been studied and it was positive. Imaging studies and laboratory results were suggested hydatid disease and laparoscopic distal pancreatectomy has been applied. Primary pancreatic hydatid disease should be in differential diagnosis when newly appearing pancreatic cyst has been diagnosed, especially in endemic areas. Appropriate surgical technique has to be applied to avoid dissemination of cyst's content.
PubMed: 38694528
DOI: 10.47717/turkjsurg.2023.4768 -
Zhongguo Yi Xue Ke Xue Yuan Xue Bao.... Apr 2024As the detection rate of pancreatic cystic lesions(PCL)increases,artificial intelligence(AI)has made breakthroughs in the imaging workflow of PCL,including image... (Review)
Review
As the detection rate of pancreatic cystic lesions(PCL)increases,artificial intelligence(AI)has made breakthroughs in the imaging workflow of PCL,including image post-processing,lesion detection,segmentation,diagnosis and differential diagnosis.AI-based image post-processing can optimize the quality of medical images and AI-assisted models for lesion detection,segmentation,diagnosis and differential diagnosis significantly enhance the work efficiency of radiologists.This article reviews the application progress of AI in PCL imaging and provides prospects for future research directions.
Topics: Artificial Intelligence; Humans; Pancreatic Cyst; Diagnosis, Differential; Image Processing, Computer-Assisted; Pancreatic Neoplasms
PubMed: 38686726
DOI: 10.3881/j.issn.1000-503X.15633 -
Endoscopy International Open Apr 2024Rising prevalence of pancreatic cysts and inconsistent management guidelines necessitate innovative approaches. New features of large language models (LLMs), namely...
Rising prevalence of pancreatic cysts and inconsistent management guidelines necessitate innovative approaches. New features of large language models (LLMs), namely custom GPT creation, provided by ChatGPT can be utilized to integrate multiple guidelines and settle inconsistencies. A custom GPT was developed to provide guideline-based management advice for pancreatic cysts. Sixty clinical scenarios were evaluated by both the custom GPT and gastroenterology experts. A consensus was reached between experts and review of guidelines and the accuracy of recommendations provided by the custom GPT was evaluated and compared with experts. The custom GPT aligned with expert recommendations in 87% of scenarios. Initial expert recommendations were correct in 97% and 87% of cases, respectively. No significant difference was observed between the accuracy of custom GPT and the experts. Agreement analysis using Cohen's and Fleiss' Kappa coefficients indicated consistency among experts and the custom GPT. This proof-of-concept study shows the custom GPT's potential to provide accurate, guideline-based recommendations for pancreatic cyst management, comparable to expert opinions. The study highlights the role of advanced features of LLMs in enhancing clinical decision-making in fields with significant practice variability.
PubMed: 38681146
DOI: 10.1055/a-2289-9334 -
Journal of Medical Case Reports Apr 2024Non-pancreatic pseudocysts are rare lesions that typically form from the omentum and mesentery. These cysts have a thick fibrotic wall made up of fibrous tissue and may...
INTRODUCTION
Non-pancreatic pseudocysts are rare lesions that typically form from the omentum and mesentery. These cysts have a thick fibrotic wall made up of fibrous tissue and may show signs of calcifications and inflammatory changes. The fluid inside them can vary, ranging from hemorrhage and pus to serous or sometimes chylous content. In most cases, these cysts appear as a result of trauma, surgery, or infection.
CASE PRESENTATION
A 35-year-old male patient from Ethiopia presented with swelling in his lower abdomen that had been present for 2 years. Initially, the swelling was small but gradually increased in size. The patient experienced frequent urination but no pain or difficulty during urination, urgency, intermittent urination, or blood in the urine. The swelling was initially painless but became painful 2 months prior to his presentation. Abdominal computed tomography scans revealed a well-defined, lobulated peritoneal lesion measuring 16 × 12 × 10 cm, consisting primarily of fluid-filled cysts with a thick, enhancing wall and septa. Additionally, there was a large, heterogeneous enhancing soft tissue component measuring 8 × 6 cm. As a result, the cystic mass was surgically removed in its entirety with partial removal of the bladder wall, and the patient was discharged in an improved condition.
CONCLUSION
Primary non-pancreatic pseudocysts are extremely rare lesions that must be differentiated from other possible causes of cystic lesions within the peritoneal or retroperitoneal regions. Surgeons should be aware of the potential occurrence of these lesions, which may have an unknown origin.
Topics: Humans; Male; Adult; Tomography, X-Ray Computed; Cysts; Peritoneal Diseases; Treatment Outcome
PubMed: 38679699
DOI: 10.1186/s13256-024-04503-5 -
Annals of Surgical Oncology Jul 2024Presacral neuroendocrine neoplasms (PNENs) are rare tumors, with limited data on management and outcomes.
INTRODUCTION
Presacral neuroendocrine neoplasms (PNENs) are rare tumors, with limited data on management and outcomes.
METHODS
A retrospective review of institutional medical records was conducted to identify all patients with PNENs between 2008 and 2022. Data collection included demographics, symptoms, imaging, surgical approaches, pathology, complications, and long-term outcomes.
RESULTS
Twelve patients were identified; two-thirds were female, averaging 44.8 years of age, and, for the most part, presenting with back pain, constipation, and abdominal discomfort. Preoperative imaging included computed tomography scans and magnetic resonance images, with somatostatin receptor imaging and biopsies being common. Half of the patients had metastatic disease on presentation. Surgical approach varied, with anterior, posterior, and combined techniques used, often involving muscle transection and coccygectomy. Short-term complications affected one-quarter of patients. Pathologically, PNENs were mainly well-differentiated grade 2 tumors with positive synaptophysin and chromogranin A. Associated anomalies were common, with tail-gut cysts prevalent. Mean tumor diameter was 6.3 cm. Four patients received long-term adjuvant therapy. Disease progression necessitated additional interventions, including surgery and various chemotherapy regimens. Skeletal, liver, thyroid, lung, and pancreatic metastases occurred during follow-up, with no mortality reported. Kaplan-Meier analysis showed a 5-year local recurrence rate of 23.8%, disease progression rate of 14.3%, and de novo metastases rate of 30%.
CONCLUSION
The study underscores the complex management of PNENs and emphasizes the need for multicenter research to better understand and manage these tumors. It provides valuable insights into surgical outcomes, recurrence rates, and overall survival, guiding future treatment strategies for PNEN patients.
Topics: Humans; Female; Male; Retrospective Studies; Neuroendocrine Tumors; Middle Aged; Adult; Survival Rate; Follow-Up Studies; Aged; Prognosis; Sacrum; Neoplasm Recurrence, Local
PubMed: 38679679
DOI: 10.1245/s10434-024-15328-3 -
Medicina (Kaunas, Lithuania) Apr 2024Groove pancreatitis represents a chronic focal form of pancreatitis affecting the zone between the pancreatic head and the duodenal "C" loop, known as the groove area....
Groove pancreatitis represents a chronic focal form of pancreatitis affecting the zone between the pancreatic head and the duodenal "C" loop, known as the groove area. This is a rare condition that affects the pancreatic periampullary part, including the duodenum and the common bile duct, which is usually associated with long-term alcohol and tobacco misuse, and is more frequent in men than in women. The most common clinical symptoms of groove pancreatitis include weight loss, acute abdominal pain, nausea, and jaundice. This report is about a 66-year-old woman with a history of heavy smoking, presenting with weight loss, nausea, and upper abdominal pain. Contrast-enhanced computed tomography revealed the existence of chronic pancreatitis as well as the dilatation of the main pancreatic duct, a cyst of the pancreatic head, and enlargement of the biliary tract. Conservatory treatment was initiated but with no improvement of symptoms. Since endoscopic retrograde cholangiopancreatography was not possible due to the local changes, we decided to perform pancreatoduodenectomy, as surgery appears to be the single effective treatment.
Topics: Humans; Pancreaticoduodenectomy; Aged; Female; Tomography, X-Ray Computed; Pancreatitis, Chronic; Pancreatitis; Pancreas
PubMed: 38674272
DOI: 10.3390/medicina60040626 -
Familial Cancer Apr 2024Pancreatic surveillance can detect early-stage pancreatic cancer and achieve long-term survival, but currently involves annual endoscopic ultrasound and MRI/MRCP, and is... (Review)
Review
Pancreatic surveillance can detect early-stage pancreatic cancer and achieve long-term survival, but currently involves annual endoscopic ultrasound and MRI/MRCP, and is recommended only for individuals who meet familial/genetic risk criteria. To improve upon current approaches to pancreatic cancer early detection and to expand access, more accurate, inexpensive, and safe biomarkers are needed, but finding them has remained elusive. Newer approaches to early detection, such as using gene tests to personalize biomarker interpretation, and the increasing application of artificial intelligence approaches to integrate complex biomarker data, offer promise that clinically useful biomarkers for early pancreatic cancer detection are on the horizon.
PubMed: 38662265
DOI: 10.1007/s10689-024-00381-4