Endoscopic ultrasonography evaluation for pancreatic cysts: Necessity or overkill?

Application of artificial intelligence in pancreas endoscopic ultrasound imaging- A systematic 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.

Cystic pancreatic lesions, the endless dilemma

Cystic pancreatic lesions involve a wide variety of pathological entities that include neoplastic and non-neoplastic lesions. The proper diagnosis, differentiation, and staging of these cystic lesions are considered a crucial issue in planning further management. There are great challenges for their diagnostic models. In our time, new emerging methods for this diagnosis have been discovered. Endoscopic ultrasonography-guided fine-needle aspiration cytology with chemical and molecular analysis of cyst fluid and EUS-guided fine needle-based confocal laser endomicroscopy, through the needle microforceps biopsy, and single-operator cholangioscopy/pancreatoscopy are promising methods that have been used in the diagnosis of cystic pancreatic lesions. Hereby we discuss the diagnosis of cystic pancreatic lesions and the benefits of various diagnostic models.

Long-term Risk of Malignancy in Branch-Duct Intraductal Papillary Mucinous Neoplasms

BACKGROUND & AIMS

Long-term outcomes of patients with branch-duct intraductal papillary mucinous neoplasms (IPMNs), particularly those after 5 years of surveillance, have not been fully evaluated in large studies. We analyzed incidences of IPMN-derived carcinoma and concomitant ductal adenocarcinoma (pancreatic ductal adenocarcinoma [PDAC]) over 20 years in a large population of patients.

METHODS

We identified 1404 consecutive patients (52% women; mean age, 67.5 years) with a diagnosis of branch-duct IPMN, from 1994 through 2017, at the University of Tokyo in Japan. Using a competing risk analysis, we estimated cumulative incidence of pancreatic carcinoma, overall and by carcinoma type. We used competing risks proportional hazards models to estimate subdistribution hazard ratios (SHRs) for incidences of carcinomas. To differentiate IPMN-derived and concomitant carcinomas, we collected genomic DNA from available paired samples of IPMNs and carcinomas and detected mutations in GNAS and KRAS by polymerase chain reaction and pyrosequencing.

RESULTS

During 9231 person-years of follow-up, we identified 68 patients with pancreatic carcinomas (38 patients with IPMN-derived carcinomas and 30 patients with concomitant PDACs); the overall incidence rates were 3.3%, 6.6%, and 15.0% at 5, 10, and 15 years, respectively. Among 804 patients followed more than 5 years, overall cumulative incidence rates of pancreatic carcinoma were 3.5% at 10 years and 12.0% at 15 years from the initial diagnosis. The size of the IPMN and the diameter of the main pancreatic duct associated with incidence of IPMN-derived carcinoma (SHR 1.85; 95% confidence interval 1.38-2.48 for a 10-mm increase in the IPMN size and SHR 1.56; 95% confidence interval 1.33-1.83 for a 1-mm increase in the main pancreatic duct diameter) but not with incidence of concomitant PDAC.

CONCLUSIONS

In a large long-term study of patients with branch-duct IPMNs, we found the 5-year incidence rate of pancreatic malignancy to be 3.3%, reaching 15.0% at 15 years after IPMN diagnosis. We observed heterogeneous risk factor profiles between IPMN-derived and concomitant carcinomas.

Utility of endoscopic ultrasound and endoscopic ultrasound-guided fine-needle aspiration for the diagnosis and management of pancreatic cystic lesions: Differences between the guidelines

Recent advances and frequent use of cross-sectional imaging studies have increased opportunities for incidental diagnoses of pancreatic cystic lesions (PCL). In the management of PCL, distinguishing between mucinous versus non-mucinous and malignant versus benign cysts is important to diagnose pancreatic cancer in its early stage. For this reason, there have been several guidelines to manage PCL. Endoscopic ultrasound (EUS) and EUS-guided fine-needle aspiration (FNA) play important roles in the guidelines, although there are some differences in their roles. In this review, we aimed to evaluate the current status of EUS and EUS-FNA in the management of PCL and the status of these procedures in the guidelines.

Single-session esophagogastroduodenoscopy and endoscopic ultrasound using a forward-viewing radial scan ultrasonic endoscope

BACKGROUND

Endoscopic ultrasound is useful for obtaining high-resolution images of pancreaticobiliary diseases, but is not readily available for physical checkups. In this study, we evaluated the safety and efficacy of single-session esophagogastroduodenoscopy and endoscopic ultrasound in the detection of upper-gastrointestinal and pancreaticobiliary diseases using a forward-viewing radial scan ultrasonic endoscope.

METHODS

A total of 148 patients who were scheduled for upper-gastrointestinal screening using an endoscope were prospectively included. All patients were examined by EUS in combination with EGD using a forward-viewing radial scan ultrasonic endoscope. The primary endpoint was the safety of the procedures. The secondary endpoints were the prevalence of diseases, the basal imaging capability of EUS, the procedure time, total dose of propofol, and the correlation between background factors and the prevalence of pancreatic disease. The imaging capability at each region was scored as 0 (invisible) to 2 (sufficient visualization to evaluate the organs).

RESULTS

Intraoperative hypotension occurred as an adverse event of intravenous anesthesia in one patient. There were 82 pancreaticobiliary findings and 165 upper-gastrointestinal findings (malignancy not included). Follicular lymphoma of the intra-abdominal lymph nodes was detected in one patient. The mean imaging scores of each section were 1.95 (pancreatic head and papilla), 2.0 (pancreatic body), 1.99 (pancreatic tail), and 1.89 (common bile duct and gallbladder). Age, history of diabetes mellitus, and smoking history were significantly associated with the prevalence of pancreatic diseases.

CONCLUSION

The simultaneous performance of EGD and EUS using a new ultrasonic endoscope is tolerable and safe for upper-gastrointestinal and pancreaticobiliary screening.

Interobserver agreement among expert pathologists on through-the-needle microforceps biopsy samples for evaluation of pancreatic cystic lesions

BACKGROUND AND AIMS

The recent development of microforceps for EUS through-the-needle biopsy (TTNB) sampling of the wall of pancreatic cystic lesions (PCLs) allows the collection of histologic specimens never handled and evaluated before by pathologists. We aimed to estimate the interobserver agreement among pathologists in evaluating such samples.

METHODS

TTNB specimen slides from 40 PCLs with worrisome features were retrieved and independently evaluated for specimen adequacy, presence of lining epithelium, grade of epithelial dysplasia, presence of ovarian type stroma, and specific diagnosis by 6 expert pathologists from 6 different tertiary care centers. The Gwet's AC1 was used to assess interobserver agreement.

RESULTS

An almost perfect agreement was observed for specimen adequacy (AC1, .82; 95% confidence interval [CI], .79-.98), presence of lesional epithelium (AC1, .90; 95% CI, .86-.92), epithelial dysplasia (AC1, .97; 95% CI, .95-.99), and ovarian-like stroma (AC1, .90; 95% CI, .86-.93). When considering all diagnoses separately, a moderate to substantial agreement was observed (AC1, .62; 95% CI, .57-.67), similarly to mucinous cysts versus serous adenoma versus other diagnoses (AC1, .65; 95% CI, .59-.70) and for mucinous cysts versus all other diagnoses (AC1,.74; 95% CI, .68-.84). The agreement for diagnosis of mucinous cystic neoplasm versus intraductal mucinous papillary neoplasm was almost perfect (AC1, .88; 95% CI, .81-.95).

CONCLUSIONS

Interobserver agreement between expert pathologists in the evaluation of TTNB samples from PCLs with worrisome features was close to perfection for all evaluated parameters, except definitive diagnosis. When mucinous cystic lesions were compared versus all other diagnoses, the agreement became substantial, thus indicating that TTNB specimens can provide important information for PCL management decisions.

Endoscopic ultrasonography for the evaluation of pancreatic cystic neoplasms

Endoscopic ultrasonography (EUS) is a modality with high spatial resolution that enables comprehensive observation of the entire pancreas and plays an important role in the diagnosis of pancreatic lesions. Recent advances in diagnostic imaging methods such as ultrasound, computed tomography, and magnetic resonance imaging have increased the incidental detection of pancreatic cystic lesions (PCLs). EUS has been recognized as an essential diagnostic method for the detection and evaluation of PCLs. EUS has two important roles: as a detailed (high-resolution) imaging diagnostic method and as an approach for collecting cyst fluid content by EUS-guided fine needle aspiration for pathological diagnosis or biomarker evaluation. Furthermore, in recent years, the usefulness of contrast-enhanced EUS for the differential diagnosis of PCLs or evaluation of grade of malignancy, and a novel imaging technique called needle-based confocal laser endomicroscopy to observe intraductal structures through a needle, has been reported. An understanding of the morphological characteristics of PCLs depicted by ultrasound imaging and of the benefits and limitations of EUS diagnosis in daily practice is needed.

Endoscopic diagnosis of cystic lesions of the pancreas

Endoscopic methods are increasingly used in the diagnosis of cystic lesions of the pancreas. The two major endoscopic approaches are endoscopic ultrasonography (EUS) and transpapillary diagnosis. EUS-guided fine-needle aspiration cytology and EUS-guided fine needle-based confocal laser endomicroscopy have been used in the differential diagnosis of mucinous and non-mucinous pancreatic cysts. EUS is the most sensitive modality for detecting mural nodules (MN) in intraductal papillary mucinous neoplasms (IPMN). Contrast-enhanced harmonic EUS (CH-EUS), as an add-on to EUS, is useful for identifying and characterizing MN. Recent studies show that CH-EUS has a sensitivity of 60-100% and a specificity of 75-92.9% for diagnosing malignant cysts. Intraductal ultrasonography and peroral pancreatoscopy are especially useful for detecting MN and IPMN. A recent meta-analysis showed that cytological assessment of pancreatic juice using a transpapillary approach had a pooled sensitivity, specificity, and accuracy of 35.1%, 97.2%, and 92.9%, respectively, for diagnosing malignant IPMN. Further studies are warranted to determine the indications for each of these novel techniques in assessing cystic lesions of the pancreas.

Endoscopic ultrasound-through-the-needle biopsy in pancreatic cystic lesions: A multicenter study

BACKGROUND AND AIM

Tissue acquisition in pancreatic cystic lesions (PCL) is the ideal method for diagnosis and risk stratification for malignancy of these lesions. Direct sampling from the walls of PCL with different devices has shown better results than cytology from cystic fluid. We carried out a retrospective, multicenter study to evaluate the feasibility, safety, and diagnostic yield of a micro-forceps, specifically designed to be used through a 19-gauge needle after endoscopic ultrasonography (EUS)-guided puncture of PCL.

METHODS

We retrospectively collected data from patients who underwent EUS-through-the-needle biopsy (EUS-TTNB) in PCL at six referral centers.

RESULTS

The sampling procedure was carried out in 56 patients (mean age 57.5 ± 13.1 years, M:F 17:39), and was technically successful in all of them (100%; 95% confidence interval [CI], 94-100%). Adverse events occurred in 9/56 (16.1%; 95% CI, 8-28%) patients, with self-limited intracystic hemorrhage the most common (7/56, 12.5%; 95% CI, 5-24%). All adverse events were mild, and resolved without any specific intervention. Specimens were considered adequate for histological diagnosis in 47/56 (83.9%; 95% CI, 72-92%). In two of these patients, despite the histological adequacy, a diagnosis could not be reached. In two other cases, a specimen sufficient for a cytological diagnosis was obtained. Overall diagnostic yield by combining cytological and histological samples was 47/56 (83.9%; 95% CI, 72-92%).

CONCLUSION

EUS-TTNB with micro-forceps in PCL is feasible, safe, and has a high diagnostic yield. Future prospective studies are needed to better assess the clinical impact of EUS-TTNB on the management of PCL.

Patients with pancreatic cystic neoplasms can benefit from management of multidisciplinary team: Experience from a Chinese academic center

BACKGROUND

Pancreatic cystic neoplasms (PCNs) are a spectrum of neoplasms that can be benign or malignant. The accuracy of diagnosis is critical for this disease since different types of PCNs are treated differently using various modalities. The use of a multidisciplinary team (MDT) has been shown to improve the management and outcomes of various diseases. We aimed to determine the performance of MDT in the management of PCNs.

METHODS

We retrospectively reviewed 167 pathologically-proven PCN patients and divided them among three groups according to their surgical data and treatment modalities: 1) historical control group (HC group); 2) concurrent control group (CC group); and 3) MDT group. The composition of subtypes of PCNs, preoperative diagnostic accuracy, postoperative complications, and postoperative hospital stay were compared among the three groups.

RESULTS

The incidence of SCN reduced in the MDT group, while the incidence of IPMN was much higher (P < 0.05). MDT management significantly improved the accuracy of preoperative diagnosis (71.7%) and also increased the individual diagnostic accuracies of ultrasound, CT, and MRI/MRCP. Postoperative pancreatic fistula was significantly reduced in the MDT group (28.3%; P < 0.001). Furthermore, the mean hospital stay after surgery in the MDT group (10.37 days) was shorter than those of the other two groups (27.35 days in HC group, and 19.28 days in CC group; P < 0.05).

CONCLUSION

For patients with PCN, MDT management was associated with an improvement in the overall accuracy of preoperative diagnosis, a lower incidence postoperative morbidity, and decreased length of hospital stay.

Endoscopic Ultrasound Imaging for Differential Diagnosis of Pancreatic Neoplasms: A 7-Year Study in a Chinese Population

Background

Currently, non-invasive methods for screening pancreatic cancer are lacking. There is little information regarding whether endoscopic ultrasound (EUS) imaging has a discriminatory ability for detecting benign and malignant pancreatic neoplasms. In this study, we retrospectively analyzed the demographic, clinicopathologic, and EUS features and follow-up information.

Material/Methods

A total of 58 patients with pancreatic neoplasms who underwent endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) over a 7-year period (2009–2016) at our Department of Digestive Diseases were enrolled in our study.

Results

Of the 58 patients, 38 (65.5%) were diagnosed with malignant pancreatic neoplasms and 20 (34.5%) were benign ones. Of all the EUS findings, size of neoplasm (P=0.037) and regularity of margin (P=0.011) were significantly different between malignant and benign pancreatic neoplasms. However, age, sex, location, echo pattern, and dilation of main pancreatic duct did not show any significant difference (P>0.05). Size combined with regularity to detect malignant pancreatic neoplasms showed the following diagnostic values: sensitivity, 73.68%; specificity, 90%; positive predictive value, 76.60%; negative predictive value 81.82%; and area under the receiver operating characteristic curve, 0.887 (95% CI: 0.777–0.955, P<0.0001).

Conclusions

Our results showed the high value of EUS for differentiating malignant pancreatic neoplasms from benign ones. Due to this and its non-invasive nature, EUS should be the first-line method for detection of neoplastic pancreatic lesions.