The Diagnosis of Autoimmune Pancreatitis Using Endoscopic Ultrasonography

What Is the Latest in Autoimmune Pancreatitis

Autoimmune pancreatitis (AIP) is a steroid-responsive fibroinflammatory disorder with 2 clinically distinct subtypes known as type 1 autoimmune and type 2 autoimmune pancreatitis. Type 1 AIP is considered the pancreatic manifestation of immunoglobulin G4-related disease, a systemic disease often presenting with other organ involvement. Advances in understanding the unique clinical presentation, imaging findings, histopathology, and clinical course of this relatively uncommon disease have led to international consensus regarding diagnosis and treatment. While corticosteroids remain the mainstay of treatment, several emerging novel therapies have been explored primarily in the context or relapsing and refractory cases.

EUS-guided fine-needle biopsy versus fine-needle aspiration for histopathological evidence for type 1 autoimmune pancreatitis: A single-center retrospective study in China

Background and Objectives

EUS is recommended for guiding pancreatic tissue acquisition in suspected autoimmune pancreatitis (AIP) cases. However, there is a lack of comparative research on the effectiveness between EUS-guided fine-needle aspiration (EUS-FNA) and EUS-guided fine-needle biopsy (EUS-FNB) for diagnosing AIP in China. This study aimed to evaluate the diagnostic accuracy of EUS-guided tissue acquisition (EUS-TA) specifically for type 1 AIP.

Methods

Between 2010 and 2023, individuals with AIP who received EUS-TA at Changhai Hospital were included in the study.

Results

A total of 173 patients diagnosed with AIP who underwent EUS-TA were included in the final analysis. Of these, 104 patients (60.1%) received EUS-FNA, and 69 patients (39.9%) underwent EUS-FNB. Sufficient pancreatic tissue samples (>5 cells/high-power field) were obtained in 164 of 173 patients (94.8%), with success rates of 94.2% for EUS-FNA and 95.7% for EUS-FNB (P > 0.05). EUS-FNB exhibited higher rates of reliable level 1 histopathological findings (40.9% vs. 16.3%, P < 0.001) and reliable level 2 histopathological findings (33.3% vs. 12.2%, P < 0.001) compared with EUS-FNA. Furthermore, a higher occurrence of IgG4-positive plasma cell infiltration (>10 cells/high-power field) was observed with EUS-FNB compared with EUS-FNA (74.2% vs. 27.9%, P < 0.001). The multivariate logistic analysis also revealed that EUS-FNA was less effective in obtaining reliable evidence compared with EUS-FNB, as evident in both level 2 (P = 0.002; odds ratio, 0.21; 95% confidence interval, 0.08-0.56) and level 1 (P = 0.001; odds ratio, 0.19; 95% confidence interval, 0.08-0.49) histopathological evidence.

Conclusions

EUS-FNB demonstrates higher rates of level 1 and level 2 histopathological findings, as well as more abundant IgG4-positive plasma cell infiltration, compared with EUS-FNA.

The Role of Endoscopic Ultrasound and Ancillary Techniques in the Diagnosis of Autoimmune Pancreatitis: A Comprehensive Review

Autoimmune pancreatitis (AIP) is a unique form of chronic pancreatitis with a multifactorial pathogenesis. Historically, it has been classified as type 1 and type 2, according to its clinical and histological features. The diagnosis of AIP is challenging and relies on a combination of clinical, histopathologic, serologic, and imaging characteristics. In the available guidelines, the imaging hallmarks of AIP are based on cross-sectional imaging and cholangiopancreatography retrograde endoscopic findings. Endoscopic ultrasound (EUS) is generally used for pancreatic tissue acquisition to rule out pancreatic cancer and diagnose AIP with limited accuracy. Several papers reported the reliability of EUS for providing informative morphologic features of AIP. Nowadays, the improvement in the resolution of EUS conventional images and the development of new ancillary technologies have further increased the diagnostic yield of EUS: contrast-enhanced EUS and EUS elastography are non-invasive and real-time techniques that strongly support the diagnosis and management of pancreatic diseases. In this review article, we will present the role of conventional EUS and ancillary diagnostic techniques in the diagnosis of AIP to support clinicians and endosonographers in managing this condition.

Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning

Objectives

Localized autoimmune pancreatitis is difficult to differentiate from pancreatic ductal adenocarcinoma on endoscopic ultrasound images. In recent years, deep learning methods have improved the diagnosis of diseases. Hence, we developed a special cross-validation framework to search for effective methodologies of deep learning in distinguishing autoimmune pancreatitis from pancreatic ductal adenocarcinoma on endoscopic ultrasound images.

Methods

Data from 24 patients diagnosed with localized autoimmune pancreatitis (8751 images) and 61 patients diagnosed with pancreatic ductal adenocarcinoma (20,584 images) were collected from 2016 to 2022. We applied transfer learning to a convolutional neural network called ResNet152, together with our innovative imaging method contributing to data augmentation and temporal data process. We divided patients into five groups according to different factors for 5-fold cross-validation, where the ordered and balanced datasets were created for the performance evaluations.

Results

ResNet152 surpassed the endoscopists in all evaluation metrics with almost all datasets. Interestingly, when the dataset is balanced according to the factor of the endoscopists' diagnostic accuracy, the area under the receiver operating characteristic curve and accuracy were highest at 0.85 and 0.80, respectively.

Conclusions

It is deduced that image features useful for ResNet152 correlate with those used by endoscopists for their diagnoses. This finding may contribute to sample-efficient dataset preparation to train convolutional neural networks for endoscopic ultrasonography-imaging diagnosis.

Challenges for clinicians treating autoimmune pancreatitis: Current perspectives

Autoimmune pancreatitis (AIP) is a rare disease clinically characterized by obstructive jaundice, unintentional weight loss, acute pancreatitis, focal pancreatic mass, and diabetes. AIP is classified into two subtypes - type 1 and type 2 - according to pathological findings, clinical features, and serology test results, but some cases may be defined as type not otherwise in the absence of pathological findings and inflammatory bowel disease. To address the differences in diagnostic criteria by country, standard diagnostic criteria for AIP were proposed in 2011 by an international consensus of expert opinions. Differential diagnosis of AIP from pancreatic ductal adenocarcinoma is important but remains challenging for clinicians. Fortunately, all subtypes of AIP show dramatic response to steroid treatment. This review discusses the current perspectives on the diagnosis and management of AIP in clinical practice.

The Role of EUS-Guided FNA and FNB in Autoimmune Pancreatitis

Autoimmune pancreatitis (AIP) is an increasingly recognized disease classified into two different subtypes based on histology. According to the International Diagnostic Criteria (ICDC), the diagnosis is achieved using a combination of different criteria. In patients presenting with a typical imaging appearance, the diagnosis may be straightforward, and steroid treatment is recommended, even without histological confirmation. In patients with atypical imaging or mass-forming appearance, the differential diagnosis with pancreatic cancer is challenging and crucial for treatment strategy. Endoscopic ultrasound (EUS)-guided tissue acquisition has been proposed to achieve a histological diagnosis. Fine-needle aspiration (FNA) was first proposed to aspirate cells from pancreatic lesions. Despite excellent results in terms of sensitivity for pancreatic cancer, the data are disappointing regarding the diagnosis of AIP. The recent development of new needles allowing fine-needle biopsy (FNB) has been associated with improved diagnostic accuracy based on preserving the tissue architecture, which is necessary to detect the typical histological features of AIP. However, the published literature on the role of EUS-guided FNA and FNB is limited and mainly focused on type 1 AIP. The present study aimed to review the available literature on the role of EUS-guided FNA and FNB in the diagnosis of AIP.

Recent Advances in Endosonography-Elastography: Literature Review

Ultrasonographic elastography is a modality used to visualize the elastic properties of tissues. Technological advances in ultrasound equipment have supported the evaluation of elastography (EG) in endosonography (EUS). Currently, the usefulness of not only EUS-strain elastography (EUS-SE) but also EUS-shear wave elastography (EUS-SWE) has been reported. We reviewed the literature on the usefulness of EUS-EG for various diseases such as chronic pancreatitis, pancreatic solid lesion, autoimmune pancreatitis, lymph node, and gastrointestinal and subepithelial lesions. The importance of this new diagnostic parameter, "tissue elasticity" in clinical practice might be applied not only to the diagnosis of liver fibrosis but also to the elucidation of the pathogeneses of various gastrointestinal diseases, including pancreatic diseases, and to the evaluation of therapeutic effects. The most important feature of EUS-EG is that it is a non-invasive modality. This is an advantage not found in EUS-guided fine needle aspiration (EUS-FNA), which has made remarkable progress in the field of diagnostics in recent years. Further development of artificial intelligence (AI) is expected to improve the diagnostic performance of EUS-EG. Future research on EUS-EG is anticipated.

Interobserver Reliability of the Endoscopic Ultrasound Criteria for the Diagnosis of Early Chronic Pancreatitis: Comparison between the 2009 and 2019 Japanese Diagnostic Criteria

In 2009, diagnostic criteria for early chronic pancreatitis (DCECP2009) were proposed by the Japan Pancreas Society. This study aimed to evaluate the interobserver reliability (IOR) of endoscopic ultrasound (EUS) criteria for diagnosis of early chronic pancreatitis (ECP) between DCECP2009 and 2019 diagnostic criteria for ECP (DCECP2019) to assess the validity of the revision from the perspective of EUS findings. Among patients who underwent a detailed observation of the pancreas by EUS at our institution between January 2018 and March 2019, EUS images of 97 patients were extracted. Images were reviewed by 12 gastrointestinal endoscopy experts (eight pancreatologists, group A and four nonpancreatologists, group B). The overall kappa (K)-values for the IOR of the DCECP2009 EUS criteria were 0.424 and 0.563:0.231 for groups A:B, whereas the overall K-values for the DCECP2019 criteria were 0.618, and 0.733:0.442 for groups A:B. Regarding changes in the final diagnosis of ECP based on clinical features and EUS findings, 20 cases were definite ECP, 53 were probable ECP, and 24 were normal according to DCECP2009. In contrast, seven were definite ECP, 19 were probable ECP, and 71 were normal according to DECEP2019. IOR of DCECP2019 was higher than that of DCECP2009, which indicates an improvement in precision.