IgG4-related autoimmune pancreatitis (AIP) is a rare inflammatory condition characterized by elevated IgG4-positive plasma cells and lymphoplasmacytic infiltration in the pancreas. This disease responds to steroid therapy but can be challenging to differentiate from pancreatic cancer. In this paper, we present two cases of IgG4-related AIP presenting as pancreatic masses. Our aim is to highlight the diagnostic complexities of this condition and emphasize the need for a multidisciplinary approach to avoid unnecessary surgical interventions and ensure appropriate treatment.

Small cell lung cancer (SCLC) is notorious for its aggressive behavior and propensity for metastasis. Although metastasis to the pancreas from SCLC is relatively rare, it warrants attention due to its overlapping symptomatology with primary pancreatic malignancies and other abdominal pathologies (such as those involving the liver or gallbladder). Despite recent advances, the mechanisms driving SCLC metastasis to the pancreas remain elusive, providing challenges in diagnosis and treatment. This case report details the presentation of a 59-year-old woman with SCLC metastasis to the pancreas, initially masquerading as primary pancreatic carcinoma, as highlighted by her presenting symptoms of jaundice, weight loss, and abdominal pain. Diagnostic workup, including imaging studies and tissue sampling, confirmed the unexpected presence of metastatic SCLC in the pancreas. The patient was ultimately transferred to a tertiary care facility for further workup. This case serves as a reminder to maintain a broad differential diagnosis, particularly in the face of such an unusual presentation. It also highlights the need for further research to elucidate the molecular and cellular mechanisms driving SCLC metastasis to the pancreas, with the ultimate goal of improving diagnostic accuracy and therapeutic outcomes for patients with this aggressive disease.

Fibroblast Activation Protein Inhibitor (FAPI) positron emission tomography (PET) imaging has emerged as a useful method for identifying pancreatic disorders, notably pancreatitis. Unlike Fluorine-18 fluorodeoxyglucose (FDG), FAPI uptake is directly proportional to the degree of fibrosis, making it very useful in separating pancreatic tumors from inflammation. Recent investigations have shown that FAPI positron emission tomography/computer tomography (PET/CT) can identify pancreatic inflammation with great sensitivity, providing vital diagnostic information. In this case study, a 52-year-old male with a history of Ewing sarcoma presented with epigastric pain. Pancreatitis was confirmed on a computer tomography (CT) scan showing mild fat stranding in the pancreatic body and tail, in addition to a significant increase in pancreatic head mass, necessitating further evaluation with FDG PET/CT and FAPI PET/CT, as the patient was known to have metastatic sarcoma. While FDG PET/CT revealed an avid infiltrative lesion in the duodenal/pancreatic head area, FAPI PET/CT showed diffuse uptake in the pancreatic body and tail, indicating fibroblast-mediated inflammation consistent with pancreatitis. This case demonstrates the usefulness of FAPI imaging in discriminating between pancreatic metastasis and pancreatitis, with FAPI PET/CT providing crucial diagnostic information when FDG uptake is ambiguous.

A 57-year-old man with a background of chronic pancreatitis presented with acutely worsening abdominal pain and vomiting. He previously had a pancreatic duct stent in situ which had been removed 1 year prior to presentation. Initially suspected to be acute-on-chronic pancreatitis, a computed tomography (CT) scan of the abdomen and pelvis revealed an atrophic pancreas and a new mass in the pancreatic head, raising the suspicion of pancreatic malignancy. An urgent endoscopic ultrasound (EUS)-guided fine needle biopsy of the pancreatic head mass surprisingly revealed the presence of actinomyces colonies on histological evaluation. Prompt initiation of a prolonged antibiotic course led to significant clinical and radiological improvement. This case highlights the rare presentation of pancreatic actinomycosis which can often masquerade as malignancy. Although a gut commensal, actinomyces can elicit pathogenic effects if allowed to enter tissues through a breach in the mucosal lining such as following abdominal surgery or pancreatic duct intervention as observed in this case. Early recognition and appropriate treatment with antibiotics can lead to clinical recovery and complete resolution of the infection.

Pancreatic masses are commonly encountered in clinical practice, with concern for the possibility of cancer. Tissue sampling or outright surgical resection may be offered in this setting. However, surgery has been unnecessarily performed in patients with pancreatic masses that proved to be benign. Less invasive options for pancreatic masses that may be benign like tuberculosis should thus be explored. Three adult Filipino patients less than 60 years old presented with symptomatic pancreatic masses suspected of cancer on abdominal imaging studies. Two were smokers without a history of prior tuberculosis. Without any tissue sampling, anti-tuberculosis treatment was eventually given to all three patients due to concomitant diagnoses of extrapancreatic tuberculosis. Endoscopic ultrasound documentation of post-treatment resolution of pancreatic masses was noted in all cases. In endemic regions, although clinical diagnosis of tuberculosis may be possible for pancreatic masses, empiric treatment should still be a last-line option in cases where tissue sampling cannot be done.

BACKGROUND: Endoscopic ultrasound (EUS)-guided tissue acquisition is the preferred modality for diagnosing pancreatic lesions and mediastinal and abdominal lymph nodes. Rapid on-site cytologic evaluation improves the diagnostic outcome of EUS-guided fine-needle aspiration (FNA) but is unavailable at many centers. Alternatively, macroscopic on-site evaluation (MOSE) may improve the diagnostic outcome of EUS-FNA, but data are limited. Hence, the present study was conducted to assess the efficacy of MOSE in improving adequacy and accuracy.
METHODS: We retrospectively analyzed data of consecutive patients with pancreatic or lymph nodal lesions undergoing EUS-guided FNA at a tertiary care center from December 2020 to December 2022. The study\'s primary outcomes were adequacy and diagnostic accuracy of the EUS-guided tissue acquisition, with secondary analysis of predictors of adequacy and accuracy.
RESULTS: Data from 124 patients (44.4% male, median age: 54 years) who underwent EUS-FNA were included in the present analysis. The presence of macroscopic visible core (MVC) on MOSE was reported in 93/124 (75%) cases. An adequate sample for histopathological or cytological examination was obtained in 110/124 (88.7%) cases, while the diagnostic accuracy was 85.5%. On multivariate analysis, the absence of MVC on MOSE was found to be the independent negative predictor of both adequacy (OR 0.092, 95% CI: 0.024-0.349) and accuracy (OR 0.175, 95% CI: 0.057-0.536).
CONCLUSIONS: The presence of MVC on MOSE can be an indicator of specimen adequacy and can improve the diagnostic yield of EUS-FNA.

Haematological diseases with pancreatic masses as the first symptom are clinically rare but should not be ignored. This case report describes a 60-year-old female patient with acute leukaemia that had a pancreatic mass as her first symptom. The patient was admitted and elastography combined with endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA) was used for diagnosis, treatment planning and determination of prognosis. The site selected for the EUS-FNA puncture was the caudal section of the pancreatic body and the posterior wall of the gastric body was used as the puncture point. The elastography view of the head of the pancreas was blue/green with predominant blue colour. A 19 G puncture needle with a slow-draw core and two stitches of micro-negative pressure were used. Cytology detected heterotypic cells, pancreatic puncture histopathology, the presence of pancreatic alveolar structures and heterotypic tumour cells in the interstitium. Immunohistochemistry of the pancreatic puncture tissue showed B-cell lymphoblast-derived tumours and bone marrow puncture indicated acute lymphoblastic leukaemia. The patient was diagnosed with acute lymphoblastic leukaemia invading the pancreas and was treated with chemotherapy. After treatment, her condition was stable. Follow-up is ongoing and there have been no signs of tumour recurrence or metastasis.

UNASSIGNED: Standard suction technique (SST), slow-pull technique (SPT), and wet suction technique (WEST) of EUS-FNA are designed to improve the diagnostic yields of solid and solid-cystic lesions. We conducted a multicenter, prospective, randomized crossover trial to compare SST, SPT, and WEST on specimen quality and diagnostic accuracy using a 22G needle.
UNASSIGNED: Patients with solid or solid-cystic lesions referred for EUS-FNA at four tertiary hospitals from December 2017 to August 2019 were considered eligible. All lesions were sampled using a 22G needle by the three techniques performed consecutively in a randomized order. The primary outcome was quality of the specimen acquired by each technique regarding blood contamination, tissue integrity and cellularity for diagnosis, graded on a predefined scale. The secondary outcomes were the diagnostic yield of EUS-FNA and the incidence of adverse events. ClinicalTrial. gov registration number: NCT03567863.
UNASSIGNED: A total of 300 patients (mean age, 60.6 years, 188 men) were enrolled. WEST was superior (mean score 4.02 ± 1.51) over SST (3.67 ± 1.57, P = 0.018), but comparable to SPT (3.83 ± 1.55, P = 0.370) in overall specimen quality evaluation. WEST produced better tissue integrity (1.42 ± 0.74) and higher cellularity (1.32 ± 0.80) than SST and SPT. SPT (1.43 ± 0.69) was superior to SST (1.27 ± 0.72, P = 0.004) and WEST (1.28 ± 0.71, P = 0.006) in avoiding blood contamination. WEST achieved a diagnostic accuracy of 74.7%, higher than SST (64.4%, P = 0.007) and SPT (65.0%, P = 0.012). One bleeding event occurred with a pancreatic lesion.
UNASSIGNED: WEST was comparable to SPT and superior to SST in the overall quality of the specimen and achieved highest diagnostic yield.

UNASSIGNED: Standard suction technique (SST), slow-pull technique (SPT), and wet suction technique (WEST) of EUS-FNA are designed to improve the diagnostic yields of solid and solid-cystic lesions. We conducted a multicenter, prospective, randomized crossover trial to compare SST, SPT, and WEST on specimen quality and diagnostic accuracy using a 22G needle.
UNASSIGNED: Patients with solid or solid-cystic lesions referred for EUS-FNA at four tertiary hospitals from December 2017 to August 2019 were considered eligible. All lesions were sampled using a 22G needle by the three techniques performed consecutively in a randomized order. The primary outcome was quality of the specimen acquired by each technique regarding blood contamination, tissue integrity and cellularity for diagnosis, graded on a predefined scale. The secondary outcomes were the diagnostic yield of EUS-FNA and the incidence of adverse events. ClinicalTrial. gov registration number: NCT03567863.
UNASSIGNED: A total of 300 patients (mean age, 60.6 years, 188 men) were enrolled. WEST was superior (mean score 4.02 ± 1.51) over SST (3.67 ± 1.57, P = 0.018), but comparable to SPT (3.83 ± 1.55, P = 0.370) in overall specimen quality evaluation. WEST produced better tissue integrity (1.42 ± 0.74) and higher cellularity (1.32 ± 0.80) than SST and SPT. SPT (1.43 ± 0.69) was superior to SST (1.27 ± 0.72, P = 0.004) and WEST (1.28 ± 0.71, P = 0.006) in avoiding blood contamination. WEST achieved a diagnostic accuracy of 74.7%, higher than SST (64.4%, P = 0.007) and SPT (65.0%, P = 0.012). One bleeding event occurred with a pancreatic lesion.
UNASSIGNED: WEST was comparable to SPT and superior to SST in the overall quality of the specimen and achieved highest diagnostic yield.

BACKGROUND: We aimed to develop a deep learning-based segmentation system for rapid on-site cytopathology evaluation (ROSE) to improve the diagnostic efficiency of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) biopsy.
METHODS: A retrospective, multicenter, diagnostic study was conducted using 5345 cytopathological slide images from 194 patients who underwent EUS-FNA. These patients were from Nanjing Drum Tower Hospital (109 patients), Wuxi People\'s Hospital (30 patients), Wuxi Second People\'s Hospital (25 patients), and The Second Affiliated Hospital of Soochow University (30 patients). A deep convolutional neural network (DCNN) system was developed to segment cell clusters and identify cancer cell clusters with cytopathological slide images. Internal testing, external testing, subgroup analysis, and human-machine competition were used to evaluate the performance of the system.
RESULTS: The DCNN system segmented stained cells from the background in cytopathological slides with an F1-score of 0·929 and 0·899-0·938 in internal and external testing, respectively. For cancer identification, the DCNN system identified images containing cancer clusters with AUCs of 0·958 and 0·948-0·976 in internal and external testing, respectively. The generalizable and robust performance of the DCNN system was validated in sensitivity analysis (AUC > 0·900) and was superior to that of trained endoscopists and comparable to cytopathologists on our testing datasets.
CONCLUSIONS: The DCNN system is feasible and robust for identifying sample adequacy and pancreatic cancer cell clusters. Prospective studies are warranted to evaluate the clinical significance of the system.
BACKGROUND: Jiangsu Natural Science Foundation; Nanjing Medical Science and Technology Development Funding; National Natural Science Foundation of China.