Serous Cystic Neoplasms Research Articles

Pancreatic cystic neoplasms

Pancreatic cystic lesions represent achallenging heterogeneous entity with a potential risk of malignant transformation. The diagnostics include in particular medical history taking with collection of relevant clinical information and high-resolution imaging, preferably using magnetic resonance imaging (MRI) with MR cholangiopancreatography (MRCP) and/or endoscopic ultrasonography. A differentiation between different cystic entities and identification of risk factors are crucial for making appropriate treatment decisions. Only a small proportion of pancreatic cystic neoplasms require surgery. Pancreatic cystic lesions with a relevant risk of malignancy, such as main duct intraductal papillary mucinous neoplasms (IPMN), mucinous cystic neoplasms (MCN), solid pseudopapillary neoplasms (SPN) and general cystic pancreatic lesions with risk factors regardless of the entity, should be resected, whereas an individualized approach is required for branch duct IPMN and serous cystic neoplasms (SCN) and dysontogenetic cysts require no treatment. Parenchyma-sparing and minimally invasive resection techniques should be preferred whenever possible for resecting pancreatic cystic tumors. Approximately 10% of patients develop recurrences over time.

Imaging of pancreatic serous cystadenoma and common imitators.

Pancreatic cystic neoplasms are lesions comprised of cystic components that show different biological behaviors, epidemiology, clinical manifestations, imaging features, and malignant potential and management. Benign cystic neoplasms include serous cystic neoplasms (SCAs). Other pancreatic cystic lesions have malignant potential, such as intraductal papillary mucinous neoplasms and mucinous cystic neoplasms. SCAs can be divided into microcystic (classic appearance), honeycomb, oligocystic/macrocystic, and solid patterns based on imaging appearance. They are usually solitary but may be multiple in von Hippel-Lindau disease, which may depict disseminated involvement. The variable appearances of SCAs can mimic other types of pancreatic cystic lesions, and cross-sectional imaging plays an important role in their differential diagnosis. Endoscopic ultrasonography has helped in improving diagnostic accuracy of pancreatic cystic lesions by guiding tissue sampling (biopsy) or cyst fluid analysis. Immunohistochemistry and newer techniques such as radiomics have shown improved performance for preoperatively discriminating SCAs and their mimickers.

A case of preoperative embolization for a giant hypervascular pancreatic serous cystic neoplasm in pancreaticoduodenectomy

BackgroundPreoperative vascular embolization is an effective strategy for managing meningiomas, neck paragangliomas, renal cell carcinomas, and bone metastasis by reducing the intraoperative bleeding volume and operation time. Although hypervascular tumors also occur in the pancreas, preoperative embolization for these tumors is not commonly practiced. We herein present a case of a giant serous cystic neoplasm (SCN) of the pancreas with significant arterial vascularity that was managed with preoperative interventional radiology and subsequently resected via pancreaticoduodenectomy.Case presentationA 60-year-old man presented with an 8-cm hypervascular tumor located at the head of the pancreas, identified as an SCN on pathologic examination. The tumor had increased by 13 mm over 5 years, necessitating surgical intervention. Computed tomography revealed a substantial blood supply to the tumor from the dorsal pancreatic artery and gastroduodenal artery, both branches of the superior mesenteric artery. To mitigate the risk of severe intraoperative bleeding from this giant hypervascular tumor, branches of the dorsal pancreatic artery and gastroduodenal artery were embolized using metallic coils and further secured using a gelatin sponge 1 day prior to pancreatectomy. During the laparotomy, the tumor appeared to have decreased in size, likely because of reduced distension and congestion. Despite significant adhesions to surrounding tissues secondary to prolonged compression and inflammation, the pancreaticoduodenectomy was completed successfully in 5 h and 15 min with blood loss of 763 mL. The patient was discharged on postoperative day 15 without complications.ConclusionsPreoperative arterial embolization for hypervascular pancreatic tumors might control the risk of massive intraoperative bleeding, contributing to a favorable postoperative outcome. Utilizing interventional radiology for preoperative inflow control is one of the beneficial strategies for pancreatectomy in patients with a giant SCN.

Epigenetic silencing of BEND4, a novel DNA damage repair gene, is a synthetic lethal marker for ATM inhibitor in pancreatic cancer.

Synthetic lethality is a novel model for cancer therapy. To understand the function and mechanism of BEN domain-containing protein 4 (BEND4) in pancreatic cancer, eight cell lines and a total of 492 cases of pancreatic neoplasia samples were included in this study. Methylation-specific polymerase chain reaction, CRISPR/Cas9, immunoprecipitation assay, comet assay, and xenograft mouse model were used. BEND4 is a new member of the BEN domain family. The expression of BEND4 is regulated by promoter region methylation. It is methylated in 58.1% (176/303) of pancreatic ductal adenocarcinoma (PDAC), 33.3% (14/42) of intraductal papillary mucinous neoplasm, 31.0% (13/42) of pancreatic neuroendocrine tumor, 14.3% (3/21) of mucinous cystic neoplasm, 4.3% (2/47) of solid pseudopapillary neoplasm, and 2.7% (1/37) of serous cystic neoplasm. BEND4 methylation is significantly associated with late-onset PDAC (> 50 years, P < 0.01) and tumor differentiation (P < 0.0001), and methylation of BEND4 is an independent poor prognostic marker (P < 0.01) in PDAC. Furthermore, BEND4 plays tumor-suppressive roles in vitro and in vivo. Mechanistically, BEND4 involves non-homologous end joining signaling by interacting with Ku80 and promotes DNA damage repair. Loss of BEND4 increased the sensitivity of PDAC cells to ATM inhibitor. Collectively, the present study revealed an uncharacterized tumor suppressor BEND4 and indicated that methylation of BEND4 may serve as a potential synthetic lethal marker for ATM inhibitor in PDAC treatment.

Reassessment of EUS features in preoperative diagnosis of pancreatic serous cystic neoplasm: Lessons to avoid misdiagnosis.

Pancreatic serous cystic neoplasm (SCN) is a benign cystic neoplasm that is likely to be surgically resected due to preoperative misdiagnosis or tentative diagnosis even using endoscopic ultrasonography (EUS). We aimed to analyze EUS findings of SCN associated with misdiagnosis. Between January 2012 and September 2023, histologically confirmed pancreatic SCN were included and EUS features were reviewed. Overall, 294 patients with 300 surgically resected SCNs were included. The median age of the patients was 51 years and 75.9% were females. The lesions were predominantly located in the body/neck/tail of the pancreas (63.0%). The overall preoperative diagnostic rate of SCN was 36.3%, with the most common misdiagnosis being intraductal papillary mucinous neoplasm (IPMN) (31.3%), while 16.3% remained undefined. The preoperative diagnostic rate of SCN varied across different endosonographic morphologies, with oligocystic, macrocystic, microcystic, and solid patterns yielding rates of 12.8%, 37.9%, 76.5%, and 19.2%, respectively. Notably, the presence of central scar and vascularity improved the diagnostic accuracy and correctly identified 41.4% and 52.3% of thelesions. While mucus or pancreatic duct (PD) communication significantly increased the likelihood of misdiagnosis, particularly as IPMN. Multivariate analysis revealed a morphological pattern, mucin-producing signs, wall thickening, vascularity, and PD communication were independent factors related to preoperative misdiagnosis, with an overall accuracy of 82.3%. Preoperative diagnosis of SCN remains challenging. The microcystic pattern emerged as a reliable feature, while mucin-producing signs, including mural nodules, mucus, and PD communication, pose diagnostic pitfalls despite the presence of typical central scar or vascularity commonly in SCN.

A case of macrocystic type pancreatic serous cystic neoplasm with recurrent pancreatitis

A case of macrocystic type pancreatic serous cystic neoplasm with recurrent pancreatitis

Fine-needle aspiration technique under endoscopic ultrasound guidance: A technical approach for RNA profiling of pancreatic neoplasms.

Early diagnosis of pancreatic ductal adenocarcinoma (PDAC) has been a longstanding challenge. The prognosis of patients with PDAC depends on the stage at diagnosis. It is necessary to identify biomarkers for the detection and differentiation of pancreatic tumors and optimize PDAC sample preparation procedures for DNA and RNA analysis. Most molecular studies are done using paraffin-embedded blocks; however, the integrity of DNA and RNA is often compromised in this format. Moreover, RNA isolated from human pancreatic tissue samples is generally of low quality, in part, because of the high concentration of endogenous pancreatic RNAse activity present. To assess the potential of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) to obtain specimens from pancreatic neoplasms for subsequent RNA molecular profiling, including next-generation sequencing (NGS). Thirty-four EUS-FNA samples were included in this study: PDAC (n = 15), chronic pancreatitis (n = 5), pancreatic cysts (n = 14), mucinous cysts (mucinous cystic neoplasia/intraductal papillary mucinous neoplasia) n = 7, serous cystic neoplasms n = 5, and pseudocysts n = 2. Cyst material consisted of cyst fluid and cyst wall samples obtained by through-the-needle biopsy (TTNB). Samples were stored at -80 °C until analysis. RNA purity (A260/230, A260/280 ratios), concentration, and integrity (RIN) were assessed. Real-time polymerase chain reaction was conducted on all samples, and small RNA libraries were prepared from solid mass samples. RNA was successfully extracted from 29/34 (85%) EUS-FNA samples: 100% pancreatic adenocarcinoma samples, 100% chronic pancreatitis samples, 70% pancreatic fluid cyst samples, and 50% TTNB samples. The relative expression of GAPDH and HPRT were obtained for all successfully extracted RNA samples (n = 29) including low-quality RNA specimens. Low concentration and nonoptimal RIN values (no less than 3) of RNA extracted from EUS-FNA samples did not prevent NGS library preparation. The suitability of cyst fluid samples for RNA profiling varied. The quality of RNA extracted from mucinous cyst fluid had a median RIN of 7.7 (5.0-8.2), which was compatible with that from solid neoplasms [6.2 (0-7.8)], whereas the quality of the RNA extracted from all fluids of serous cystic neoplasms and TTNB samples had a RIN of 0. The results demonstrate the high potential of EUS-FNA material for RNA profiling of various pancreatic lesions, including low-quality RNA specimens.

Fragmentomics of cell-free DNA as a sensitive biomarker for early detection of pancreatic cancer.

4173 Background: Pancreatic ductal adenocarcinoma (PDAC) is one for the most lethal types of cancer. Nearly 80% of the PDAC patients are diagnosed at advanced unresectable stages. Therefore, an accurate early diagnosis assay is urgently needed for reducing PDAC related mortalities. In this study, we aim to utilize cfDNA fragmentomics and machine learning techniques for sensitively detecting PDAC patients. Methods: Total647 cases were prospectively enrolled in this study. Plasma samples were collected from each participant for shallow WGS (~5X). After quality control process, 166 PDAC patients and 167 healthy controls were enrolled as a training cohort. Additional 112 PDAC patients and 111 healthy controls were included as an independent validation cohort. Additional 67 cases with pancreatic benign cystic tumors were also enrolled for model validation including IPMN (Intraductal papillary mucinous neoplasms), MCN (Mucinous cystic neoplasms) and SCN (Serous cystic neoplasms). Four fragmentomics profiles, including copy number variation, fragment size, mutation signatures, and FRAGmentomics-based Methylation Analysis (FRAGMA) were utilized by a machine learning algorithm for developing a predictive model. Results: The predictive model showed an exceptional performance to distinguish PDAC patients from healthy controls, yielding Area Under the Curve (AUC) of 0.993 in the training cohort (5-fold cross validation) and 0.990 in the validation cohort. In the training cohort, our model was capable of detecting PDAC patients at sensitivity of 95.8% and specificity of 95.2% while using 0.49 as cutoff. The validation cohort achieved 99.1% sensitivity at 91.0% specificity while applying the same cutoff. Conclusions: Our model was able to accurately detect PDAC at early stages, by incorporating fragmentomics features through machine learning. It can potentially be used for PDAC early screening, and therefore reducing PDAC related mortalities.

A unique case of a typical pancreatic ductal adenocarcinoma that initially presented with a cystic component but underwent morphological changes.

A 66-year-old man was initially suspected of having a microcystic serous cystic neoplasm based on magnetic resonance imaging findings of a multifocal mass measuring 46mm in the pancreatic head, with a cystic component showing a high signal on T2-weighted images. The tumor marker levels were within normal limits. However, contrast-enhanced computed tomography revealed thick cyst walls with delayed staining, which was atypical for serous cystic neoplasms; therefore, the patient was followed up closely. Twenty-two months later, the delayed contrast area was enlarged, carbohydrate antigen 19-9 levels were elevated, and 18 F-fluorodeoxyglucose-positron emission tomography revealed increased accumulation, indicating a potentially malignant lesion. Pancreatoduodenectomy was performed and histopathological examination confirmed the diagnosis of normal-type pancreatic carcinoma with predominantly poorly differentiated cells. Based on the pathological findings and a literature review, it is highly likely that this case represents pancreatic ductal adenocarcinoma with a cystic structure from the beginning. While distinguishing pancreatic ductal adenocarcinoma from other pancreatic cystic tumors, such as serous cystic neoplasms, is critical owing to differing treatments and prognoses, caution is warranted as they may exhibit similar imaging features, as observed in our patient.

Natural history and growth prediction model of pancreatic serous cystic neoplasms

ObjectiveSerous cystic neoplasms (SCN) are benign pancreatic cystic neoplasms that may require resection based on local complications and rate of growth. We aimed to develop a predictive model for the growth curve of SCNs to aid in the clinical decision making of determining need for surgical resection. MethodsUtilizing a prospectively maintained pancreatic cyst database from a single institution, patients with SCNs were identified. Diagnosis confirmation included imaging, cyst aspiration, pathology, or expert opinion. Cyst size diameter was measured by radiology or surgery. Patients with interval imaging ≥3 months from diagnosis were included. Flexible restricted cubic splines were utilized for modeling of non-linearities in time and previous measurements. Model fitting and analysis were performed using R (V3.50, Vienna, Austria) with the rms package. ResultsAmong 203 eligible patients from 1998 to 2021, the mean initial cyst size was 31 mm (range 5–160 mm), with a mean follow-up of 72 months (range 3–266 months). The model effectively captured the non-linear relationship between cyst size and time, with both time and previous cyst size (not initial cyst size) significantly predicting current cyst growth (p < 0.01). The root mean square error for overall prediction was 10.74. Validation through bootstrapping demonstrated consistent performance, particularly for shorter follow-up intervals. ConclusionSCNs typically have a similar growth rate regardless of initial size. An accurate predictive model can be used to identify rapidly growing outliers that may warrant surgical intervention, and this free model (https://riskcalc.org/SerousCystadenomaSize/) can be incorporated in the electronic medical record.

Sixteen cases of laparoscopic central pancreatectomy for benign or low-grade malignant tumours in the pancreatic neck and proximal body.

The purpose of this study is to examine and analyse the outcomes and patient experiences associated with laparoscopic central pancreatectomy. The perioperative data of 16 patients who underwent laparoscopic central pancreatectomy were retrospectively analysed at Ningbo Medical Center Lihuili Hospital (Xingning Branch and Eastern Branch) from September 2017 to July 2023. All surgical procedures were completed without the need for intraoperative conversion to open surgery. In two cases, intraoperative cholangiography was performed, while in four cases, intraoperative fluoroscopic laparoscopic assistance was utilized. The duration of the operations varied from 160 to 360 min, with an average of 281.75 min. The estimated volume of intraoperative bleeding ranged from 50 to 300 mL, with an average of 113.75 mL. The postoperative pathology results revealed that there were two cases of intraductal papillary mucinous neoplasm, six cases of serous cystic neoplasms, one case of mucinous cystic neoplasm, five cases of solid pseudopapillary neoplasms, and two cases of neuroendocrine tumours. The maximum diameter of the tumours ranged from 3.0 to 5.0 cm, with an average of 3.67 cm. There were no instances of postoperative common bile duct stenosis or biliary leakage. Among the cases, five did not exhibit pancreatic fistula, six experienced biochemical leakage, three had grade B pancreatic fistula, and two had grade C pancreatic fistula. Laparoscopic central pancreatectomy, as a method to preserve pancreatic function, entails specific surgical risks and a notable likelihood of postoperative pancreatic fistula, necessitating the expertise of seasoned surgeons for its execution.

MiR-200b categorizes patients into pancreas cystic lesion subgroups with different malignant potential

Extracellular vesicles (EV) carry their cargo in a membrane protected form, however, their value in early diagnostics is not well known. Although pancreatic cysts are heterogeneous, they can be clustered into the larger groups of pseudocysts (PC), and serous and mucinous pancreatic cystic neoplasms (S-PCN and M-PCN, respectively). In contrast to PCs and S-PCNs, M-PCNs may progress to malignant pancreatic cancers. Since current diagnostic tools do not meet the criteria of high sensitivity and specificity, novel methods are urgently needed to differentiate M-PCNs from other cysts. We show that cyst fluid is a rich source of EVs that are positive and negative for the EV markers CD63 and CD81, respectively. Whereas we found no difference in the EV number when comparing M-PCN with other pancreatic cysts, our EV-based biomarker identification showed that EVs from M-PCNs had a higher level of miR-200b. We also prove that not only EV-derived, but also total cyst fluid miR-200b discriminates patients with M-PCN from other pancreatic cysts with a higher sensitivity and specificity compared to other diagnostic methods, providing the possibility for clinical applications. Our results show that measuring miR-200b in cyst fluid-derived EVs or from cyst fluid may be clinically important in categorizing patients.

Application of a pyramid pooling Unet model with integrated attention mechanism and Inception module in pancreatic tumor segmentation.

The segmentation and recognition of pancreatic tumors are crucial tasks in the diagnosis and treatment of pancreatic diseases. However, due to the relatively small proportion of the pancreas in the abdomen and significant shape and size variations, pancreatic tumor segmentation poses considerable challenges. To construct a network model that combines a pyramid pooling module with Inception architecture and SE attention mechanism (PIS-Unet), and observe its effectiveness in pancreatic tumor images segmentation, thereby providing supportive recommendations for clinical practitioners. A total of 303 patients with histologically confirmed pancreatic cystic neoplasm (PCN), including serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN), from Shanghai Changhai Hospital between March 2011 and November 2021 were included. A total of 1792 T2-weighted imaging (T2WI) slices were used to build a CNN model. The model employed a pyramid pooling Inception module with a fused attention mechanism. The attention mechanism enhanced the network's focus on local features, while the Inception module and pyramid pooling allowed the network to extract features at different scales and improve the utilization efficiency of global information, thereby effectively enhancing network performance. Using three-fold cross-validation, the model constructed by us achieved a dice score of 85.49±2.02 for SCN images segmentation, and a dice score of 87.90±4.19 for MCN images segmentation. This study demonstrates that using deep learning networks for the segmentation of PCNs yields favorable results. Applying this network as an aid to physicians in PCN diagnosis shows potential for clinical applications.

Giant pancreatic serous cystic neoplasm requiring percutaneous variceal embolization due to repeated bleeding from gastric varices after unsuccessful endoscopic treatment:

Giant pancreatic serous cystic neoplasm requiring percutaneous variceal embolization due to repeated bleeding from gastric varices after unsuccessful endoscopic treatment:

Pancreatic serous cystadenoma case report of conservative approach

There are multiples pancreatic tumors, some of them being benign some being malignant, some more frequent than others, such as pancreatic pseudocyst and serous cystic neoplasm, in this case it’s about the last one witch is the most common cystic neoplasm of the pancreas about 30%, the initial approach to this type of tumors its either CT scan or MRI, which will show the honeycomb-like pattern, which is pathognomonic of this neoplasm, and the treatment options depend on the symptoms that produce.

Preoperative differentiation of pancreatic cystic neoplasm subtypes on computed tomography radiomics.

Serous cystic neoplasm (SCN), mucinous cystic neoplasm (MCN), and intraductal papillary mucinous neoplasm (IPMN) comprise a large proportion of pancreatic cystic neoplasms (PCNs). Patients with MCN and IPMN require surgery due to the potential of malignant transformation, whereas those with SCN require periodic surveillance. However, the differential diagnosis of patients with PCNs before treatment remains a great challenge for all surgeons. Therefore, the establishment of a reliable diagnostic tool is urgently required for the improvement of precision diagnostics. Between February 2015 and December 2020, 143 consecutive patients with PCNs who were confirmed by postoperative pathology were retrospectively included in the study cohort, then randomized into development and test cohorts at a ratio of 7:3. The predictors of preoperative clinical-radiologic parameters were evaluated by univariate and multivariable logistic regression analyses. A total of 1,218 radiomics features were computationally extracted from the enhanced computed tomography (CT) scans of the tumor region, and a radiomics signature was established by the random forest algorithm. In the development cohort, multi- and binary-class radiomics models integrating preoperative variables and radiomics features were constructed to distinguish between the 3 types of PCNs. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the predictive efficiency of the model. An independent internal test cohort was applied to validate the classification models. All preoperative prediction models were built by integrating the radiomics signature with 13 diagnosis-related radiomics features and 3 important clinical-radiologic parameters: age, sex, and tumor diameter. The multiclass prediction model presented an overall accuracy of 0.804 in the development cohort and 0.707 in the test cohort. The binary-class prediction models displayed higher overall accuracies of 0.853, 0.866, and 0.928 in the development dataset and 0.750, 0.839, and 0.889 in the test dataset. In the test cohort, the binary-class radiomics models showed better predictive performances {AUC =0.914 [95% confidence interval (CI): 0.786 to 1.000], 0.863 (95% CI: 0.714 to 0.941), and 0.926 (95% CI: 0.824 to 1.000)} than the multiclass radiomics model [AUC =0.850 (95% CI: 0.696 to 1.000)], with a large net benefit in the decision curve analysis (DCA). The radiomics-based nomogram provided the correct predicted probability for the diagnosis of PCNs. The proposed radiomics models with clinical-radiologic parameters and radiomics features help to predict the accurate diagnosis among PCNs to advance personalized medicine.

Study on the application value of fluorescent laparoscopy in pancreatic tumor surgery.

Fluorescent laparoscopy is rarely used in pancreatic surgery. The aim of this study was to investigate the value of fluorescent laparoscopy in pancreatic tumor surgery. A total of 19 patients with pancreatic tumors who were treated in the Department of Hepatobiliary Surgery at the First Affiliated Hospital of Wannan Medical College from January 2021 to August 2022 were selected. Fluorescent laparoscopy was used intraoperatively, and the imaging characteristics of different tumors were recorded and analyzed. Among the 19 participants, postoperative pathology confirmed 12 cases of pancreatic cancer (8 cases of moderately differentiated adenocarcinoma, 3 cases of moderately-poorly differentiated adenocarcinoma, and 1 case of acinar cell carcinoma), 4 cases of pancreatic cystic tumors (1 case of microcystic serous cystadenoma, 1 case of serous cystadenoma, 1 case of solid pseudopapillary tumor, and 1 case of solid-cystic pseudopapillary tumor), 1 case of pancreatic neuroendocrine tumor (G1 stage), and 2 cases of inflammatory lesions. There were 8 cases of pancreaticoduodenectomy, 6 cases of distal pancreatectomy, 3 cases of middle pancreatectomy, 1 case of local pancreatectomy, and 1 case of duodenum-preserving pancreatic head resection. One minute after intravenous injection of indocyanine green (ICG), 10 of the 12 patients with pancreatic cancer showed tumor peritumor imaging; 2 cases of pancreatic serous cystic tumors did not show imaging; 2 cases of solid pseudopapillary tumors had tumor body imaging; 1 case of neuroendocrine tumor had tumor body imaging, with complete fluorescence imaging after specimen dissection; there were 2 cases pathologically confirmed as inflammatory lesions, 1 case with tumor body imaging, and 1 case with capsule imaging. By reasonably controlling the administration time and dose of ICG during surgery, some pancreatic tumors can be fluorescently imaged, which is beneficial for intraoperative tumor localization and margin determination.

Pancreatic cystic neoplasms: Still high rates of preoperative misdiagnosis in the guidelines and endoscopic ultrasound era

BackgroundA wrong diagnosis of nature is common in pancreatic cystic neoplasms. The aim of the current study is to reappraise the diagnostic errors for presumed pancreatic cystic neoplasms in patients undergoing surgery. MethodsAll pancreatic resections for presumed pancreatic cystic neoplasms following international guidelines between 2011 and 2020 were analyzed. Misdiagnosis was defined as the discrepancy between preoperative diagnosis of nature and final pathology. Mismatch was defined as the discrepancy between the preoperative suspect of malignancy (or its absence) and final pathology. ResultsA total of 601 patients were included. Endoscopic ultrasound was performed in 301 (50%) patients. Overall misdiagnosis and mismatch were 19% and 34%, respectively, with no significant benefit for those patients who underwent endoscopic ultrasound. The highest rate of misdiagnosis was reached for cystic neuroendocrine tumors (61%) and the lowest for solid pseudopapillary tumors (6%). Several diagnostic errors had clinical relevance, including 7 (13%) presumed serous cystic neoplasms eventually found to be other malignant entities, 50 (24%) intraductal papillary mucinous neoplasms with high-risk stigmata revealed to be non-malignant, and 38 (33%) intraductal papillary mucinous neoplasms without high-risk stigmata revealed to be malignant at final pathology. A preoperative presumption of malignant mucinous cystic neoplasm was correct in only 20 (16%) patients. ConclusionsDespite not always being clinically relevant, diagnostic errors are still common among resected pancreatic cystic neoplasms when applying international guidelines. New diagnostic tools beyond endoscopic ultrasound are needed to refine the diagnosis of those lesions at higher risk for unnecessary surgery or accidentally observed, nevertheless being malignant.

Automated diagnosis of pancreatic mucinous and serous cystic neoplasms with modality-fusion deep neural network using multi-modality MRIs.

Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential. MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs. A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality. The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN. Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.

EUS-guided fine needle aspiration-based clues to mistaken or uncertain identity: serous pancreatic cysts

Background/ObjectivesPancreatic serous cystic neoplasms (SCN) present a diagnostic challenge given their increasing frequency of detection and benign nature yet relatively high rate of misdiagnosis. Here, imaging and analyses associated with EUS-guided fine-needle aspiration (EUS-FNA) are evaluated for their ability to provide a correct preoperative diagnosis of SCN. MethodsA surgical cohort with confirmed pathological diagnosis of SCN (n = 62) and a surveillance cohort with likely SCN (n = 31) were assessed for imaging (CT/MRI/EUS) and EUS-FNA-based analyses (cytology/DNA analysis for Von Hippel-Lindau [VHL] gene alterations/biomarkers). ResultsIn the surgical cohort, CT/MRI and EUS respectively predicted SCN in 4 of 58(7%) and 19 of 62(31%). Cyst fluid cytology and VHL alterations predicted SCN in 1 of 51(2%) and 5 of 21(24%), respectively. High specificity cyst fluid biomarkers (vascular endothelial growth factor [VEGF]/glucose/carcinoembryonic antigen [CEA]/amylase) correctly identified SCN in 25 of 27(93%). In the surveillance cohort, cyst fluid biomarkers predicted SCN in 12 of 12(100%) while VHL alterations identified SCN 3 of 10(30%). ConclusionHigh specificity cyst fluid biomarkers provided the most sensitive means of diagnosing SCN preoperatively. To obtain a preoperative diagnosis of SCN at the highest level of certainty, a multidisciplinary approach should be taken to inform appropriate SCN management.