This study aimed to compare the image quality and detection performance of pancreatic cystic lesions between computed tomography (CT) images reconstructed by deep learning reconstruction (DLR) and filtered back projection (FBP). This retrospective study included 54 patients (mean age: 67.7 ± 13.1) who underwent contrast-enhanced CT from May 2023 to August 2023. Among eligible patients, 30 and 24 were positive and negative for pancreatic cystic lesions, respectively. DLR and FBP were used to reconstruct portal venous phase images. Objective image quality analyses calculated quantitative image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) using regions of interest on the abdominal aorta, pancreatic lesion, and pancreatic parenchyma. Three blinded radiologists performed subjective image quality assessment and lesion detection tests. Lesion depiction, normal structure illustration, subjective image noise, and overall image quality were utilized as subjective image quality indicators. DLR significantly reduced quantitative image noise compared with FBP (p < 0.001). SNR and CNR were significantly improved in DLR compared with FBP (p < 0.001). Three radiologists rated significantly higher scores for DLR in all subjective image quality indicators (p ≤ 0.029). Performance of DLR and FBP were comparable in lesion detection, with no statistically significant differences in the area under the receiver operating characteristic curve, sensitivity, specificity and accuracy. DLR reduced image noise and improved image quality with a clearer depiction of pancreatic structures. These improvements may have a positive effect on evaluating pancreatic cystic lesions, which can contribute to appropriate management of these lesions.

OBJECTIVE: Intraductal papillary mucinous neoplasm (IPMN)-derived pancreatic ductal adenocarcinoma (PDAC) management is generally extrapolated from pancreatic intraepithelial neoplasia (PanIN)-derived PDAC guidelines. However, these are biologically divergent, and heterogeneity further exists between tubular and colloid subtypes.
METHODS: Consecutive upfront surgery patients with PanIN-derived and IPMN-derived PDAC were retrospectively identified from international centers (2000-2019). One-to-one propensity score matching for clinicopathologic factors generated three cohorts: IPMN-derived versus PanIN-derived PDAC, tubular IPMN-derived versus PanIN-derived PDAC, and tubular versus colloid IPMN-derived PDAC. Overall survival (OS) was compared using Kaplan-Meier and log-rank tests. Multivariable Cox regression determined corresponding hazard ratios (HR) and 95% confidence intervals (95% CI).
RESULTS: The median OS (mOS) in 2350 PanIN-derived and 700 IPMN-derived PDAC patients was 23.0 and 43.1 months (P < 0.001), respectively. PanIN-derived PDAC had worse T-stage, CA19-9, grade, and nodal status. Tubular subtype had worse T-stage, CA19-9, grade, nodal status, and R1 margins, with a mOS of 33.7 versus 94.1 months (P < 0.001) in colloid. Matched (n = 495), PanIN-derived and IPMN-derived PDAC had mOSs of 30.6 and 42.8 months (P < 0.001), respectively. In matched (n = 341) PanIN-derived and tubular IPMN-derived PDAC, mOS remained poorer (27.7 vs 37.4, P < 0.001). Matched tubular and colloid cancers (n = 112) had similar OS (P = 0.55). On multivariable Cox regression, PanIN-derived PDAC was associated with worse OS than IPMN-derived (HR: 1.66, 95% CI: 1.44-1.90) and tubular IPMN-derived (HR: 1.53, 95% CI: 1.32-1.77) PDAC. Colloid and tubular subtype was not associated with OS (P = 0.16).
CONCLUSIONS: PanIN-derived PDAC has worse survival than IPMN-derived PDAC supporting distinct outcomes. Although more indolent, colloid IPMN-derived PDAC has similar survival to tubular after risk adjustment.

BACKGROUND: Pancreatic cysts in autosomal dominant polycystic kidney disease (ADPKD) correlate with PKD2 mutations, which have a different phenotype than PKD1 mutations. However, pancreatic cysts are commonly overlooked by radiologists. Here, we automate the detection of pancreatic cysts on abdominal MRI in ADPKD.
METHODS: Eight nnU-Net-based segmentation models with 2D or 3D configuration and various loss functions were trained on positive-only or positive-and-negative datasets, comprising axial and coronal T2-weighted MR images from 254 scans on 146 ADPKD patients with pancreatic cysts labeled independently by two radiologists. Model performance was evaluated on test subjects unseen in training, comprising 40 internal, 40 external, and 23 test-retest reproducibility ADPKD patients.
RESULTS: Two radiologists agreed on 52% of cysts labeled on training data, and 33%/25% on internal/external test datasets. The 2D model with a loss of combined dice similarity coefficient and cross-entropy trained with the dataset with both positive and negative cases produced an optimal dice score of 0.7 ± 0.5/0.8 ± 0.4 at the voxel level on internal/external validation and was thus used as the best-performing model. In the test-retest, the optimal model showed superior reproducibility (83% agreement between scan A and B) in segmenting pancreatic cysts compared to six expert observers (77% agreement). In the internal/external validation, the optimal model showed high specificity of 94%/100% but limited sensitivity of 20%/24%.
CONCLUSIONS: Labeling pancreatic cysts on T2 images of the abdomen in patients with ADPKD is challenging, deep learning can help the automated detection of pancreatic cysts, and further image quality improvement is warranted.

BACKGROUND: Intraductal papillary mucinous neoplasm (IPMN)-derived pancreatic ductal adenocarcinoma (PDAC) is resected at smaller sizes compared to its biologically distinct counterpart, pancreatic intraepithelial neoplasia (PanIN)-derived PDAC. Thus, experts proposed T1 sub-staging for IPMN-derived PDAC. However, this has never been validated.
METHODS: Consecutive upfront surgery patients with IPMN-derived PDAC from five international high-volume centers were classified by the proposed T1 sub-staging classification (T1a ≤ 0.5, T1b > 0.5 and ≤1.0, and T1c >1.0 and ≤2.0 cm) using the invasive component size. Kaplan-Meier and log-rank tests were utilized to compare overall survival (OS). A multivariable Cox-regression was used to determine hazard ratios (HR) with confidence intervals (95%CI).
RESULTS: Among 747 patients, 69 (9.2%), 50 (6.7%), 99 (13.0%), and 531 patients (71.1%), comprised the T1a, T1b, T1c, and T2-4 subgroups, respectively. Increasing T-stage was associated with elevated CA19-9, poorer grade, nodal positivity, R1-margin, and tubular subtype. Median OS for T1a, T1b, T1c, and T2-4 were 159.0 (95%CI:126.0-NR), 128.8 (98.3-NR), 77.6 (48.3-108.2), and 31.4 (27.5-37.7) months, respectively (p < .001). OS decreased with increasing T-stage for all pairwise comparisons (all p < .05). After risk-adjustment, age > 65, elevated CA19-9, T1b [HR : 2.55 (1.22-5.32)], T1c [HR : 3.04 (1.60-5.76)], and T2-4 [HR : 3.41 (1.89-6.17)] compared to T1a, nodal positivity, R1-margin, and no adjuvant chemotherapy were associated with worse OS. Disease recurrence was more common in T2-4 tumors (56.4%) compared to T1a (18.2%), T1b (23.9%), and T1c (36.1%, p < .001).
CONCLUSIONS: T1 sub-staging of IPMN-derived PDAC is valid and has significant prognostic value. Advancing T1 sub-stage is associated with worse histopathology, survival, and recurrence. T1 sub-staging is recommended for future guidelines.

UNASSIGNED: In cystic lesions of the pancreas, hydatid cyst should be considered in the differential diagnoses and its presence should be ruled out before any invasive interventions. Serological tests along with imaging studies related to hydatid cyst diagnostic indicators should be performed in people who live in Echinococcus granulosus endemic areas and suffer from cystic lesions of the gastrointestinal tract.
UNASSIGNED: Primary pancreatic hydatid cysts, caused by the tapeworm Echinococcus granulosus, represent a rare occurrence often challenging to diagnose due to their similarity to other pancreatic conditions. This case report outlines a 67-year-old male presenting with jaundice and cholestasis but lacking typical symptoms associated with pancreatic hydatid cysts. Laboratory findings revealed elevated bilirubin levels, liver enzyme abnormalities, and tumor markers, prompting imaging studies that indicated a cystic mass near the pancreatic head. Misdiagnosed initially as a mucinous cystic neoplasm, the patient underwent Whipple surgery, unveiling a large cystic lesion upon examination.

Pancreatic cystic lesions (PCLs) have increased in prevalence due to the increased usage and advancements in cross-sectional abdominal imaging. Current diagnostic techniques cannot distinguish between PCLs requiring surgery, close surveillance, or expectant management. This has increased the morbidity and healthcare costs from inappropriately aggressive and conservative management strategies. Endoscopic ultrasound (EUS) needle-based confocal laser endomicroscopy (nCLE) allows for microscopic examination and delineation of the surface epithelium of PCLs. Landmark studies have identified characteristics distinguishing various types of PCLs, confirmed the high diagnostic yield of EUS-nCLE (especially for PCLs with an equivocal diagnosis), and shown that EUS-nCLE helps to change management and reduce healthcare costs. Refining procedure technique and reducing procedure length have improved the safety of EUS-nCLE. The utilization of artificial intelligence and its combination with other EUS-based advanced diagnostic techniques would further improve the results of EUS-based PCL diagnosis. A structured training program and device improvements to allow more complete mapping of the pancreas cyst epithelium will be crucial for the widespread adoption of this promising technology.

A serous cystic tumor is a rare entity that has a benign course. Its imaging characteristics, such as the presence of multiple cysts with or without nodular enhancement, can simulate other cystic or solid lesions of the pancreas. Identification of the enhancing scar with punctate calcifications on computed tomography (CT) or magnetic resonance imaging (MRI) may be a distinctive finding suggesting this diagnosis. Neuroendocrine tumors of the pancreas are a different and also rare entity. In images, they have early arterial enhancement. In MRI, they are hyperintense on T2 and hypointense on T1, with avid contrast enhancement. A case of a patient with two focal lesions in the pancreas is presented and the importance of integrating clinical findings, semiology in diagnostic images and, if applicable, the histopathological result for the optimal management of pancreatic tumors is illustrated, highlighting the crucial role of a radiologist in this process.

BACKGROUND: A chronic expanding hematoma is an uncommon entity described as an organized blood collection that increases in size after the initial hemorrhagic event without histological neoplastic features. The standard treatment is complete resection. To our knowledge, this is the first report of a chronic expanding hematoma mimicking a pancreatic cystic tumor that has been successfully resected utilizing a laparoscopic approach.
METHODS: We report the case of a 32-year-old man with a 10-cm chronic expanding hematoma that was preoperatively diagnosed as a cystic pancreatic tumor. Dynamic computed tomography revealed a cyst at the inferior part of the uncinate process of the pancreas without contrast enhancement. His blood biochemical data were within normal limits. The operation initially utilized a laparoscopic approach; however, the procedure was converted to hand-assisted laparoscopic surgery due to capsule adherence to surrounding organs and finally, enucleation of the tumor was performed. Pathological findings revealed a chronic expanding hematoma in the retroperitoneal space.
CONCLUSIONS: Chronic expanding hematoma in the retroperitoneal space is so rare and sometimes adheres to the surrounding tissue. It is difficult to distinguish hematoma attaching pancreas and pancreatic cyst preoperatively. In rare cases such as this, hand-assisted laparoscopic surgery is a feasible, less invasive procedure for facilitating complete resection and preventing recurrence.

暂无摘要。

UNASSIGNED: The guidelines regarding the management of intraductal papillary mucinous neoplasms (IPMNs) all have slightly different surgical indications for high-risk lesions. We aim to retrospectively compare the accuracy of four guidelines in recommending surgery for high-risk IPMNs, and assess the accuracy of elevated CA-19-9 levels and imaging characteristics of IPMNs considered high-risk in predicting malignancy or high-grade dysplasia (HGD).
UNASSIGNED: The final histopathological diagnosis of surgically resected high-risk IPMNs during 2013-2020 were compared to preoperative surgical indications, as enumerated in four guidelines: the 2015 American Gastroenterological Association (AGA), 2017 International Consensus, 2018 European Study Group, and 2018 American College of Gastroenterology (ACG). Surgery was considered \"justified\" if histopathology of the surgical specimen showed HGD/malignancy, or there was postoperative symptomatic improvement.
UNASSIGNED: Surgery was postoperatively justified in 26/65 (40.0%) cases. All IPMNs with HGD/malignancy were detected by the 2018 ACG and the combined (absolute and relative criteria) 2018 European guidelines. The combined (\"high-risk stigmata\" and \"worrisome features\") 2017 International guideline missed 1/19 (5.3%) IPMNs with HGD/malignancy. The 2015 AGA guideline missed the most cases (11/19, 57.9%) of IPMNs with HGD/malignancy. We found the features most-associated with HGD/malignancy were pancreatic ductal dilation, and elevated CA-19-9 levels.
UNASSIGNED: Following the 2015 AGA guideline results in the highest rate of missed HGD/malignancy, but the lowest rate of operating on IPMNs without these features; meanwhile, the 2018 ACG and the combined (absolute and relative criteria) 2018 European guidelines result in more operations for IPMNs without HGD/malignancy, but the lowest rates of missed HGD/malignancy in IPMNs.